Over the years, the need for autonomous systems such as drones, also known as unmanned aerial vehicles (UAVs), has significantly increased in popularity across several industries, including the military. The Internet of Battlefield Things (IoBT) represents a modern technological advancement that significantly enhances the operational efficacy of defense systems. It establishes an integrated military force by connecting individuals to intelligent technology in drones, radios, equipment, antennas and ground stations. This is achieved through the utilization of cloud and edge computing, sensors, mobile devices, embedded systems, and IoT-based systems. However, IoBT security is significantly compromised by enemies that exploit the vulnerabilities and malicious intrusions that specifically target the external environment or to obtain sensitive data. In addition, a comprehensive understanding of cyberattacks and countermeasures is essential for assuring the security of IoBT. On the other hand, as cyber threats get more complicated, trust becomes increasingly important for the security of digital systems. Within this context, the zero trust architecture contends that the security of a complex network is inherently vulnerable to internal and external threats. In defense, UAV security system applications, for example, the primary purpose of the zero trust architecture is to limit the vulnerability of military UAV systems to cyberattacks, hence reducing the possibility of data breaches and illegal entry. This study conducts a systematic review aimed at identifying different aspects of cybersecurity strategies for protecting UAV systems within the IoBT domain. Furthermore, zero trust architecture is presented in the study as an effective prospective solution to the security issues that develop in defense UAV systems.

Pipeline conflicts arising from data dependencies are a common issue encountered in the hardware implementation of layered QC-LDPC decoders. This paper proposes an efficient layered decoding architecture to reduce pipeline conflicts without introducing stall cycles, by reordering the processing order offline and using the patch method based on variable-to-check message. The experimental results on the LDPC code of the IEEE802.16 standard in the OFDM-PON system demonstrate that the proposed architecture has a sensitivity improvement of 0.125 dBm and 0.375 dBm, respectively, compared with our previous work and the method described in the other work.

The widespread availability of tools to collect and share spatial data enables us to produce a large amount of geographic information on a daily basis. This enormous production of spatial data requires scalable data management systems. Geospatial architectures have changed from clusters to cloud architectures and more parallel and distributed processing platforms to be able to tackle these challenges. Peer-to-peer (P2P) systems as a backbone of distributed systems have been established in several application areas such as web3, blockchains, and crypto-currencies. Unlike centralized systems, data storage in P2P networks is distributed across network nodes, providing scalability and no single point of failure. However, managing and processing queries on these networks has always been challenging. In this work, we propose a spatio-temporal indexing data structure, DSTree. DSTree does not require additional Distributed Hash Trees (DHT) to perform multi-dimensional range queries. Inserting a piece of new geographic information updates only a portion of the tree structure and does not impact the entire graph of the data. For example, for time-series data, such as storing sensor data, the DSTree performs better. Despite the advantages of our proposed framework, challenges remain. We conclude that more significant research effort from GIScience and related fields in developing decentralized applications is needed. The need for the standardization of different geographic information when sharing data on the IPFS network is one of the requirements.

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these type of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand, and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

In this work, several random Boolean networks (RBN) are generated and analyzed from two characteristics: their time evolution diagram and their transition diagram. To do this, its randomness is estimated using three metrics, of which algorithmic complexity is the only one capable of revealing both transitions towards the chaotic regime and the algorithmic contribution of certain states to the transition diagram and their relationship with the order they occupy in the temporal evolution of the respective RBN.

A global event such as the COVID-19 crisis presents new, often unexpected responses that are fascinating to investigate from both, scientific and social standpoints. Despite several documented similarities, the Coronavirus pandemic is clearly distinct from the 1918 flu pandemic in terms of our exponentially increased, almost instantaneous ability to access/share information, offering an unprecedented opportunity to visualise rippling effects of global events across space and time. Personal devices provide “big data” on people’s movement, the environment and economic trends, while access to the unprecedented flurry in scientific publications and media posts provides a measure of the response of the educated world to the crisis. Most bibliometric (co-authorship, co-citation, or bibliographic coupling) analyses ignore the time dimension, but COVID-19 has made it possible to perform a detailed temporal investigation into the pandemic. Here, we report a comprehensive network analysis based on more than 20000 published documents on viral epidemics, authored by over 75,000 individuals from 140 nations in the past one year of the crisis. In contrast to the 1918 flu pandemic, access to published data over the past two decades enabled a comparison of publishing trends between the ongoing COVID-19 pandemic and those of the 2003 SARS epidemic, to study changes in thematic foci and societal pressures dictating research over the course of a crisis.

This paper draws upon the theory of turbulence in physics to explore the similarities and differences between volatility in financial markets and turbulent phenomena at a statistical physics level. By analogizing the dynamics of financial markets with fluid turbulence, we have developed an innovative analytical framework aimed at deepening the understanding of the complexity inherent in financial markets. Our research methodology includes a comparative analysis of simulated time series data for the Standard & Poor's 500 Index and fully developed turbulent velocity time series. We focus on the similarities in key statistical physical properties, including probability distributions, correlation structures, and power spectral densities. Furthermore, we have established a model of capital flow in financial markets and proposed corresponding solutions. Through computational simulations and data analysis, we find that while financial market volatility shares some statistical characteristics with turbulent phenomena, significant differences exist in the shapes of probability distributions and the temporal scales of correlations. This suggests that although financial markets exhibit patterns akin to turbulence, the behavior of this complex, multi-variable driven system does not completely correspond to natural turbulence, highlighting the limitations of directly applying turbulence theory to financial market analysis. Our study offers a new perspective for the theories of financial markets and the field of econophysics, providing fresh insights into the complexity of financial markets and contributing to the prevention and management of financial risk.

The chiral optical Tamm state (COTS) is a special localized state at the interface of a handedness-preserving mirror and a structurally chiral medium such as a cholesteric liquid crystal or a chiral sculptured thin film. The spectral behavior of COTS, observed as reflection resonances, is described by the temporal coupled-mode theory. Mode coupling is different for two circular light polarizations because COTS has a helix structure replicating that of the cholesteric. The mode coupling for co-handed circularly polarized light exponentially attenuates with the cholesteric layer thickness since the COTS frequency falls into the stop band. Cross-handed circularly polarized light freely goes through the cholesteric layer and can excite COTS when reflected from the handedness-preserving mirror. The coupling in this case is proportional to anisotropy of the cholesteric and theoretically it is only anisotropy of magnetic permittivity that can ultimately cancel this coupling. These two couplings being equal results in a polarization crossover (the Kopp--Genack effect) for which a linear polarization is optimal to excite COTS. The corresponding cholesteric thickness and scattering matrix for COTS are generally described by simple expressions.

The adapted Posner spatial cue-target paradigm was used to explore the relationship between exogenous temporal attention caused by rhythm and endogenous and exogenous spatial attention. The study was divided into two experiments. In Experiment 1, 33 participants used arrow cues to orient endogenous spatial attention and rhythm to orient exogenous temporal attention. In Experiment 2, with 29 participants, exogenous spatial attention was directed by highlighting the cue box. Exogenous temporal attention was directed by rhythm. Experiment 1 indicated that RTs were faster for attended targets than the unattended. The main effect of temporal attention was significant, with RTs being faster for synchrony and late compared to early. RTs were faster for late compared to synchrony. The main effect of stimulus repetition was significant, with faster RTs for targets when the rhythmic cue consisted of five compared to four. The interaction between spatial attention and temporal attention was not significant. Experiment 2 demonstrated that exogenous spatial attention only exhibited IOR under early four stimulus repetitions. The main effect of temporal attention was significant, with RTs being faster for synchrony and late compared to early. The main effect of stimulus repetition was significant, with faster RTs for targets when the rhythmic cue consisted of five compared to four. The interaction between spatial attention and temporal attention was significant. The results indicated that rhythmic temporal attention supported foreperiod effects. Exogenous temporal attention and endogenous spatial attention independently affect behavior, while exogenous temporal attention and exogenous spatial attention mutually influenced behavior.

In this article, the evolution in space and in time of the coronavirus pandemic is studied by utilizing a neural network with a self-organizing nature for the spatial analysis of data, and a fuzzy fractal method for capturing the temporal trends of the time series of the countries. Self-organizing neural networks possess the capability for clustering countries in the space domain based on their similar characteristics with respect to their coronavirus cases. In this form enabling finding the countries that are having similar behavior and thus can benefit from utilizing the same methods in fighting the virus propagation. To validate the approach, publicly available datasets of coronavirus cases worldwide have been used. In addition, a fuzzy fractal approach is utilized for the temporal analysis of time series of the countries. Then, a hybrid combination of both the self-organizing maps and the fuzzy fractal approach is proposed for efficient COVID-19 forecasting of the countries. Relevant conclusions have emerged from this study, that may be of great help in putting forward the best possible strategies in fighting the virus pandemic. A lot of the existing works concerned with the Coronavirus have look at the problem mostly from the temporal viewpoint that is of course relevant, but we strongly believe that the combination of both aspects of the problem is relevant to improve the forecasting ability. The most relevant contribution of this article is the proposal of combining neural networks with a self-organizing nature for clustering countries with high similarity and the fuzzy fractal approach for being able to forecast the times series and help in planning control actions for the Coronavirus pandemic.

A model of a single-server queuing-inventory system (QIS) with catastrophes and a finite waiting room for consumer customers (c-customers) has been developed. When a catastrophe occurs, all inventory in the system's warehouse is destroyed, but c-customers in the system are still waiting for restocking. In addition to c-customers, negative customers (n-customers) are also taken into account, which displaces one c-customers (if any). The policy (?, ?) is used to replenish stocks. If upon arrival of the c-customer the inventory level is zero, then according to Bernoulli’s scheme this c-customer is either lost or joining the queue. The mathematical model of the studied QIS is constructed in the form of a two-dimensional continuous-time Markov chain (2D CTMC). Exact and approximate methods for calculating the steady-state probabilities of constructed 2D CTMCs are developed and closed-form expressions are derived for calculating the performance measures. The results of numerical experiments are presented, demonstrating the high accuracy of the developed approximate formulas, as well as the behavior of performance indicators depending on the reorder point. In addition, an optimization problem is solved to obtain the optimal reorder point to minimize the expected total cost.

The performance of the presurgical test (preSurg) for temporal lobe epilepsy (TLE) was evaluated via video-electroencephalography (VEEG), electroencephalography (EEG), 99mTc-HmPAO single-photon emission tomography (SPECT) and 1.5 T magnetic resonance imaging (MRI) in a group of 112 men (37.0 ± 1.1 years) and 106 women (39.7 ± 1.1 years) operated on for TLE. The epileptic zone (EZ) was adequately identified to determine whether the patient reached an Engel I grade (EI) at least one year postop. Accuracy was evaluated by the coefficient α, ranging from 3 (when result = EZ) to 2 (result in the same hemisphere as the EZ), 1 (noninformative result) or 0 (EZ in the contralateral hemisphere). The simplicity of diagnosis was defined as the number of preSurg surgeries needed to identify the EZ. EI was obtained in 85.8% of patients even though 42.2% of patients had noninformative MRI results. For preSurg α was (mean ± SEM) = VEEG (2.83 ± 0.04) > MRI (2.14 ± 0.08) > EEG (1.87 ± 0.09) > SPECT (1.71 ± 0.09). The accuracy (combination of sensitivity and specificity) was calculated as follows: VEEG (0.797) > MRI (0.518) > EEG (0.446) > SPECT (0.360). The likelihood positive ratio was greater, and the likelihood negative ratio was lower for VEEG. The most relevant factor for the regression model was VEEG (3.106) > MRI (2.558) > EEG (1.905), and the factors were not significantly related to SPECT. EZs in EI patients with low simplicity were identified mainly by VEEG. A very good postoperative outcome can be obtained even in TLE patients with no lesions on MRI. The VEEG is the most reliable preSurg test and may be the only reliable test for patients with very low simplicity (i.e., difficult).single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: Place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: briefly describe the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions.

The main objective of this work is to investigate the temporal variation of PM10 concentrations within the urban area of Athens during the years 2001-2015. For this purpose, the time series of the particulate matter with aerodynamic diameter less than 10μm (PM10) is recorded for a 15-year period (2001-2015) in two different monitoring stations located in the urban area of Athens. The results show a totally different behavior of PM10 concentrations between the Athens city center and the suburban areas. It seems that in the city center the main sources of PM10 are traffic and heating systems especially during the cold period of the year. Furthermore, in the city center a significant seasonal variation was found with high concentrations during the cold period of the year and lower concentrations during the warm period of the year. Moreover, it was found that during the weekends, there is a decrease in PM10 concentrations probably due to the fact that majority of people do not use their vehicles. Finally, for both locations a significant temporal decreasing trend of the mean annual PM10 concentrations was found which indicates that during the last years, there have been improvements towards a better air quality.

The Active Distribution Networks (ADNs) are Multi-Input Multi-Output (MIMO) systems with coupled dynamics which cause interactions among the control loops of the Distributed Energy Resources (DERs). This undesired effect lead to performance degradation in the voltage control. To mitigate the effects of these unavoidable coupling, the present paper proposes a systematic design procedure based on the analysis of the interaction's sources. In details, each DER is equipped with a double loop PI to control the active and reactive powers output by the Voltage Source Converter (VSC) which connects the DER to the network's node. Furthermore, to guarantee Ancillary Services (ASs), the two loops are coupled by a simple mechanism of cooperation of the active power to voltage regulation realized by a filtered droop law. To achieve voltage regulation with reduced loop interactions, the PI parameters and the filter's pulse are designed according to a two sequential steps procedure based on the (Internal Model Control) IMC technique. Simulation studies are finally presented to demonstrate that the proposed design method achieves both reduction of the loop interaction and robust voltage control in presence of model parameter uncertainty in the MIMO model.

Proteomics research has become one of the most important topics in the fields of life science and natural science. At present, research on protein–protein interaction networks (PPINs) mainly focuses on detecting protein complexes or function modules. However, existing approaches are either ineffective or incomplete. In this paper, we investigate function module detection mechanisms in PPIN, including open databases, existing detection algorithms and recent solutions. After that, we describe the proposed solution based on simplified swarm optimization (SSO) algorithm and gene ontology knowledge. The proposed solution implements SSO algorithm for clustering proteins with similar function, and imports biological gene ontology knowledge for further identifying function complexes and improving detection accuracy. Furthermore, we use four different categories of species dataset for experiment: Fruitfly, Mouse, Scere, and Human. The testing and analysis result show that the proposed solution is feasible, efficient and could achieve a higher accuracy of prediction than existing approaches.

Image stitching is a crucial aspect of image processing. However, factors like perspective and environment often lead to irregular shapes in stitched images. Cropping or completion methods typically result in substantial loss of information. This paper proposes a method for rectifying irregularly images into rectangles using deformable meshes and residual networks. The method utilizes a convolutional neural network to quantify rigid structures of images. Choosing the most suitable mesh structure based on the extraction results, offering options such as triangular, rectangular, and hexagonal. Subsequently, the irregularly image, predefined mesh structure, and predicted mesh structure are input into a wide residual neural network for regression. The loss function comprises local and global, aimed at minimizing the loss of image information within the mesh and global target. This method not only significantly reduces information loss during rectification but also adapting to different images with various rigid structures. Validation on the DIR-D dataset shows this method outperforms state-of-the-art methods in image rectification.

The Upper Hunter Valley is a major coal mining area containing approximately 40% of the currently identified total coal reserves in New South Wales (NSW), Australia. Due to the ongoing increase of mining activities, PM10 (air-borne particle with an aerodynamic diameter less than 10 micrometres) pollution has become a major air quality concern in local communities. This paper summarises the spatial and temporal variability modes of PM10 pollution in the region, based on long-term multi-site monitoring data and the application of the rotated principal component analysis (RPCA) and wavelet analysis techniques. RPCA identified two distinct air quality clusters/subregions in the valley, one in the west/northwest, the other in the southeast. Wavelet analysis revealed the annual cycle to be most persistent temporal mode of PM10 variability in both subregions, with intermittent signals observed at time scales of around 120, 30~90 and under 30 days. How these variation modes are related to the effects of local PM10 emissions and the influence of meteorology at different time scales deserves further attention in future work. The findings will be used in air quality reporting and forecasting in NSW. The methodology and results can also be useful for air quality research in similar regions elsewhere.

This paper proposed an optimal tracking control scheme through adaptive dynamic programming(ADP) for a class of partially unknown discrete-time nonlinear systems based on radial basis function neural network(RBF-NN). In order to acquire the unknown system dynamics, we use two RBF-NNs, the one is used to construct the identifier, and the another is used to directly approximate the steady-state control input, where a novel adaptive law is proposed to update neural network weights. While the optimal feedback control and the cost function are derived via feedforward neural networks approximating, it is proposed to regulate the tracking error, the critic network and the actor network are then trained online to obtain the solution of the associated Hamilton–Jacobi–Bellman (HJB) equation being built under the ADP framework. Simulations verify the effectiveness of the optimal tracking control technique using the neural networks.

With the integrated development of the Internet, wireless sensor technology, cloud computing, and mobile Internet, there has been a lot of attention given to research about and applications of the Internet of Things. A Wireless Sensor Network (WSN) is one of the important information technologies in the Internet of Things; it integrates multi-technology to detect and gather information in a network environment by mutual cooperation, using a variety of methods to process and analyze data, implement awareness, and perform tests. This paper mainly researches the localization algorithm of sensor nodes in a wireless sensor network. Firstly, a multi-granularity region partition is proposed to divide the location region. In the range-based method, the RSSI (Received Signal Strength indicator, RSSI) is used to estimate distance. The optimal RSSI value is computed by the Gaussian fitting method. Furthermore, a Voronoi diagram is characterized by the use of dividing region. Rach anchor node is regarded as the center of each region; the whole position region is divided into several regions and the sub-region of neighboring nodes is combined into triangles while the unknown node is locked in the ultimate area. Secondly, the multi-granularity regional division and Lagrange multiplier method are used to calculate the final coordinates. Because nodes are influenced by many factors in the practical application, two kinds of positioning methods are designed: the unknown node is in the positioning unit or not. When the unknown node is on the side of the positioning unit, we use the method of vector similarity. Moreover, we use the centroid algorithm to calculate the ultimate coordinates of unknown node. When the unknown node is not on the side of the positioning unit, we establish a Lagrange equation containing the constraint condition to calculate the first coordinates. Furthermore, we use the Taylor expansion formula to correct the coordinates of the unknown node. In addition, this localization method has been validated by establishing the real environment.

The study of the concentrations and effects of fine particulate matter in urban areas have been of great interest to researchers in recent times. This is due to the acknowledgment of the far-reaching impacts of fine particulate matter on public health. Remote sensing data have been used to monitor the trend of concentrations of particulate matter by deriving aerosol optical depth (AOD) from satellite images. The Center for International Earth Science Information Network (CIESIN) has released the second version of its global PM_2.5 data with improvement in spatial resolution. This paper revisits the study of spatial and temporal variations in particulate matter in Saudi Arabia by exploring the cluster analysis of the new data. Cluster analysis of the PM_2.5 values of Saudi cities is performed by using Anselin local Moran’s I statistic. Also, the analysis is carried out at the regional level by using self-organizing map (SOM). The results show an increasing trend in the concentrations of particulate matter in Saudi Arabia, especially in some selected urban areas. The eastern and south-western parts of the Kingdom have significantly clustering high values. Some of the PM2.5 values have passed the threshold indicated by the World Health Organization (WHO) standard and targets posing health risks to Saudi urban population.

A phenotype is the composite of an observable expression of a genome for traits in a given environment. The trajectories of phenotypes computed from an image sequence and timing of important events in a plant’s life cycle can be viewed as temporal phenotypes and indicative of the plant’s growth pattern and vigor. In this paper, we introduce a novel method called FlowerPhenoNet which uses deep neural networks for detecting flowers from multiview image sequences for high throughput temporal plant phenotyping analysis. Following flower detection, a set of novel flower-based phenotypes are computed, e.g., the day of emergence of the first flower in a plant’s life cycle, the total number of flowers present in the plant at a given time, the highest number of flowers bloomed in the plant, growth trajectory of a flower and the blooming trajectory of a plant. To develop a new algorithm and facilitate performance evaluation based on experimental analysis, a benchmark dataset is indispensable. Thus, we introduce a benchmark dataset called FlowerPheno which comprises image sequences of three flowering plant species, e.g., sunflower, coleus, and canna, captured by a visible light camera in a high throughput plant phenotyping platform from multiple view angles. The experimental analyses on the FlowerPheno dataset demonstrate the efficacy of the FlowerPhenoNet.

Designing motion representations for the problem of 3D human action recognition from skeleton sequences is an important yet challenging task. An effective representation should be robust to noise, invariant to viewpoint changes and result in a good performance with low-computational demand. Two main challenges in this task include how to efficiently represent spatio-temporal patterns of skeletal movements and how to learn their discriminative features for classification task. This paper presents a novel skeleton-based representation and a deep learning framework for 3D action recognition using RGB-D sensors. We propose to build an action map called SPMF (Skeleton Posture-Motion Feature), which is a compact image representation built from skeleton poses and their motions. An Adaptive Histogram Equalization (AHE) algorithm is then applied on the SPMF to enhance their local patterns and form an enhanced action map, namely Enhanced-SPMF. For learning and classification tasks, we exploit Deep Convolutional Neural Networks based on the DenseNet architecture to learn directly an end-to-end mapping between input skeleton sequences and their action labels via the Enhanced-SPMFs. The proposed method is evaluated on four challenging benchmark datasets, including both individual actions, interactions, multiview and large-scale datasets. The experimental results demonstrate that the proposed method outperforms previous state-of-the-art approaches on all benchmark tasks, whilst requiring low computational time for training and inference.

Underwater Sensor Networks (UWSNs) can enable a broad range of applications such as resource monitoring, disaster prevention, and navigation-assisted. It is especially relevant for sensor nodes location in UWSNs. Global Positioning System (GPS) is not suitable for using in UWSNs because of the underwater propagation problems. Hence some localization algorithms based on the precise time synchronization between sensor nodes have been proposed which are not feasible for UWSNs. In this paper, we propose a localization algorithm called Two-Phase Time Synchronization-Free Localization Algorithm (TP-TSFLA). TP-TSFLA contains two phases, namely, range-based estimation phase and range-free evaluation phase. In the first phase, we address a time synchronization-free localization scheme base on the Particle Swarm Optimization (PSO) algorithm to decrease the localization error. In the second phase, we propose a Circle-based Range-Free Localization Algorithm (CRFLA) to locate the unlocalized sensor nodes which cannot obtain the location information through the first phase. In the second phase, sensor nodes which are localized in the first phase act as the new anchor nodes to help realize localization. Hence in this algorithm, we use a small number of mobile beacons to help achieve location without any other anchor nodes. Besides, to improve the precision of the range-free method, an extension of CRFLA by designing a coordinate adjustment scheme is updated. The simulation results show that TP-TSFLA can achieve a relative high localization ratio without time synchronization.

Nowadays the dynamism induced by the constant change of strategic decisions on the markets produces an extra difficulty in the management of an organization. The strategic decisions made by managers can become obsolete in a short period of time. One of the major difficulties in managing a commercial organization is to predict, with some precision degree, the impact some strategic decisions have on the financial results. Business Intelligence (BI) is an area widely used to help managers to make strategic decisions. But the methods used, behind the scenes, to achieve the conclusions are kept secret by BI company-based services. Modelling the environment can be a good option to study the impact of an action, provided by a strategic decision, in a real environment. A good model should give an approximate result of an action applied to a previous state of the environment. Artificial Neural Networks (ANNs) are proven to be excellent in modeling environments with some level of data noise. The same strategic action can have different results in different organizations. A tool that allows an evaluation of a strategic action applied to an environment should have a major importance in the management scope. Modeling the environment should save time and money for the organization to improve the performance of the strategic plan. If one evaluates the state of the environment after a strategic action being applied, it can be possible to mitigate the risk of failure of the strategic plan. As we will be able to verify, it is possible to use ANNs to model strategic environments that should allow the prediction of sales and operating results by the used strategies with some precision, although the level of success will be directly related with the user’s necessity.

Xinjiang, as a climate-sensitive region in northwest China, holds significant importance in studying extreme weather events for agricultural production and socioeconomic development. Based on data from 52 meteorological stations and 23 extreme climate indicators in Xinjiang from 1960 to 2021, the 5a moving average, linear trend estimation, climate tendency rate, and GIS spatial analysis methods are used to analyze the distribution and change characteristics of extreme climate. The results revealed that from 1960 to 2021, TXx, TNx, TXn, TNn, FD, ID, TN10p, TX10p, and WSDI showed a significant upward trend, while SU, TR, TN90p, TX90p, and CSDI showed a significant downward trend. What is more, the range of changes in the extreme temperature indexes from 1990 to 2021 is higher than that of 1960 to 1989. The high-value areas of extreme indexes are primarily concentrated in the northern part, while the high-value areas of cold event indexes are mainly distributed in the southern part. The upward/downward trends all accounting for over 80.00% of the entire region. The Rx1day, Rx5day, PRCPTOT, R95p, R99p, R10, R20, and R25 showed a significant growth trend from 1960 to 2021, and the range of change in the extreme precipitation indexes from 1990 to 2021 was lower than that from 1960 to 1989. Moreover, their high-value areas and high climate tendency areas are mainly concentrated in the northern and western parts of Xinjiang, with upward trends all accounting for over 71.00% of the entire region. The research results provide theoretical foundations for formulating climate risk strategies in the northwest region of China.

Amid escalating urbanization, devising rational commercial space layouts is a critical challenge. Leveraging machine learning, this study uses a Back-propagation (BP) neural network to optimize commercial spaces in Weinan City's central urban area. The results indicate an increased number of commercial facilities with a trend of multi-centered agglomeration and outward expansion. Based on these findings, we propose a strategic framework for rational commercial space development emphasizing aggregation centers, development axes, and spatial guidelines. This strategy provides valuable insights for urban planners in small and medium-sized cities in the Yellow River Basin and metropolitan areas, ultimately showcasing the power of machine learning in enhancing urban planning.

One of the industries with the fastest rate of growth is healthcare, and this industry's enormous data requires extensive cloud storage. The cloud may offer some protection, but there is no assurance that data owners can rely on it for refuge and privacy amenities. Therefore, it is essential to offer security and privacy protection. Increased customer satisfaction with security and privacy preservation is crucial since healthcare big data and its sources are stored in the cloud and contain increasingly private and sensitive information. However, maintaining privacy and security in an untrusted green cloud environment is difficult, thus the data owner should have complete data control. A new work SecPri-BGMPOP(security and privacy of Boost graph Convolutional Network -Pinpointing-Optimization Performance) is suggested that can offer a solution that involves several different steps in order to handle the numerous problems relating to security and protecting privacy. Initially Boost Graph Convolutional Network Clustering (BGCNC) algorithm, which reduces computational complexity in terms of time and memory measurements, is first applied to the input dataset to begin the clustering process. Second, enlarge by employing a piece of the magnifying bit string to generate a safe key, pinpointing based encryption avoids amplify leakage even if a rival or attacker decrypts the key or asymmetric encryption. Finally, to determine the accuracy of the method, an optimal key was created using a meta-heuristic algorithmic framework called Hybrid fragment horde bland lobo Optimization (HFHBLO). Our proposed method currently kept in a cloud environment, allowing analytics users to utilize it without risking their privacy or security.

Remote sensing has considerable potential to contribute to the identification and reconstruction of lost hydrological systems and networks. Remote sensing-based reconstructions of palaeo-river networks have commonly employed single or limited time-span imagery, which limits their capacity to identify features in complex and varied landscape contexts. This paper presents a seasonal multi-temporal approach to the detection of palaeo-rivers over large areas based on long-term vegetation dynamics and spectral decomposition techniques. The use of multi-temporal data has allowed the overcoming of seasonal cultivation patterns and long-term visibility issues related to crop selection, large-scale irrigation and land use patterns. The application of this approach on the Sutlej-Yamuna interfluve (northwest India), a core area for the Bronze Age Indus Civilisation, has enabled the reconstruction of an unsuspectedly complex palaeo-river network comprising more than 8000 kms of palaeo-channels. It has also enabled the definition of the morphology of these relict courses, which provides insights into the environmental conditions in which they operated. These new data will contribute to a better understanding of the settlement distribution and environmental settings in which this, often considered riverine, civilisation operated.

This paper is motivated by spatio-temporal pattern in the occurrence of Leishmaniasis in Afghanistan and the relatively high number of zero counts. We hold the view that correlations that arise from spatial and temporal sources are inherently distinct. Our method decouples these two sources of correlations, there are at least two advantages in taking this approach. First, it circumvents the need to inverting a large correlation matrix, which is a commonly encountered problem in spatio-temporal analyses. Second, it simplifies the modelling of complex relationships such as anisotropy, which would have been extremely difficult or impossible if spatio-temporal correlations were simultaneously considered. We identify three challenges in the modelling of a spatio-temporal process: (1) accommodation of covariances that arise from spatial and temporal sources; (2) choosing the correct covariance structure and (3) extending to situations where a covariance is not the natural measure of association. Moreover, because the data covers a period that overlaps with the US invasion of Afghanistan, the high number of zero counts may be the result of no disease incidence or lapse of data collection. To resolve this issue, a model truncated at zero built on a foundation of the generalized estimating equations was proposed.

Previous high throughput screening studies indicated trans-eQTLs tend to be tissue specific. In this study, I probed if this feature can be used to identify tissue-specific gene regulatory networks. eQTL data (P<5e-8) for 16,259 genes were identified and their summary association statistics were obtained from the eQTLGene database. Next, eQTLs that display both cis and trans regulatory effects were selected and the association between their corresponding genes were examined using Mendelian randomization. A total of 169 genes that exerted trans-regulatory impacts on 692 genes were identified. 90% of the genes (N=749) aggregated into a gene regulatory network significantly enriched in hemo-immune processes. The robustness of finding was confirmed through simulation. The identified network displayed the scale-free topology. This provided the reason to examine the association of the network’s hub genes with the phenome. The outcome of analyses revealed GSDMB and ORMDL3 impact several disorders of immune origin and ALDH2 overexpression contributes to obesity. This study reports trans-eQTLs can be used to identify tissue-specific gene regulatory networks and describes a workflow to achieve this purpose. The network identified in this study showed scale-free topology indicating the hub genes of a GRN could be targeted to prevent disease outcomes.

In a recent paper, Nicolas Gisin suggests that by conducting physics with intuitionistic rather than classical mathematics, rich temporality - that is, passage and tense, and specifically, the future’s openness - can be incorporated into physics. Physics based on classical mathematics is tenseless and deterministic, and that, so he holds, renders it incongruent with experience. According to Gisin, physics ought to represent the indeterminate nature of reality, and he proposes that intuitionistic mathematics is the key to succeeding in doing so. While I share his insistence on the reality of passage and tense, and on the future being real and open, I argue that the amendment he offers does not work. I show that, its attunement to time notwithstanding, intuitionistic mathematics is as tenseless as classical mathematics, and that physics is bound to remain tenseless regardless of the math it employs. There is much to learn about tensed time, but the task belongs to phenomenology and not to physics.

System-of-systems (SoS) evolution is a complex and unpredictable process. Although various principles to facilitate collaborative SoS evolution have been proposed, there is a lack of experimental data validating their effectiveness. To address these issues, we present an Agent-Based Model (ABM) for SoS evolution in the Internet of Vehicles (IoV) , serving as a quantitative analysis tool for SoS research. By integrating multiple complex and rational behaviors of individuals, we aim to simulate real-world scenarios as accurately as possible. To simulate the SoS evolution process, our model employs multiple agents with autonomous interactions and incorporates external environmental variables. Furthermore, we propose three evaluation metrics: evolutionary time, degree of variation, and evolutionary cost, to assess the performance of SoS evolution. Our study demonstrates that enhanced information transparency significantly improves the evolutionary performance of distributed SoS. Conversely, the adoption of uniform standards only brings limited performance enhancement to distributed SoSs. Although our proposed model has limitations, it stands out from other approaches that utilize Agent-Based Modeling to analyze SoS theories. Our model focuses on realistic problem contexts and simulates realistic interaction behaviors. This study enhances the comprehension of SoS evolution processes and provides valuable insights for the formulation of effective evolutionary strategies.

Green spaces take part a vital role in reducing the harmful effects occurred through the process of rapid urbanization. This study focuses on evaluating the change of green space and per capita green space in Colombo District, Sri Lanka in between 2008 and 2015 using Landsat images. The NDVI differencing method and classification method were used to detect the change of land cover. According to the results, a gradual decline of green space from 629.1km2 to 591.16km2 with a rate of 6.03% can be depicted. The change is considerable in Kaduwela, Moratuwa and Maharagama DSDs and quite better in the areas such as Avissawella, Homagama and Padukka. The per capita green space has been decreased from 272.361 m2 to 248.811 m2. Though these rates are very well higher than the UN, EU and WHO standards for the district, Colombo DSD do not comply with UN and EU standards. The case would turn into worst in 2025, as the predictions with current rates. Therefore, the study recommends taking immediate actions to make a greener city. Further, a tax system is proposed to get the attraction of the general public.

Stream chemistry effectively integrates watershed ecosystem processes on both spatial and temporal scales. Streams of coastal areas integrate a more homogeneous, flat topography wherein there can be interactions between the stream and the body of water into which it drains, especially where tidal fluxes occur. The present study assessed water quality of Thompson Bayou, which comes to the campus of the University of West Florida in a wetland after flowing through 4 km of commercial and private property with associated impacts on water quality. Sampling was carried out for one year at eight discrete sites along Thompson Bayou from the UWF campus to the Escambia River. We used a portable field meter to measure temperature, pH, dissolved O2 (DO), and specific conductivity (SC). Except for temperature, all variables exhibited a spatial pattern of significant variation with distance, with consistent increases in DO and SC as the stream approached the river. These variables also exhibited a temporal pattern of significant seasonal variation, including—and especially—temperature. Data suggest that spatial and temporal patterns of water quality of Thompson Bayou are determined by (1) processing of water by the wetland, (2) interactions of the stream channel with upland forest stands, and (3) the tidal hydrology of the Escambia River.

Parkinson’s Disease (PD) is a neurodegenerative and progressive disease that impacts the nerve cells in the brain and varies from person to person. The exact cause of PD is still unknown, and the diagnosis of PD does not include a specific objective test with certainty. Although deep learning has made great progress in medical neuroimaging analysis, these methods are very susceptible to biases present in neuroimaging datasets. An innovative decorrelated deep learning technique is introduced to mitigate class bias and scanner bias while simultaneously focusing on finding distinguishing characteristics in resting-state functional MRI (rs-fMRI) data, which assist in recognizing the PD with good accuracy. The decorrelation function reduces the non-linear correlation between features and bias in order to learn bias-invariant features. The Parkinson’s Progression Markers Initiative (PPMI) dataset, referred to as a single scanner imbalanced dataset in this study used to validate our method. The imbalanced dataset problem affects the performance of the deep learning framework by overfitting to the majority class. To resolve this problem, we propose a new Decorrelated Convolutional Neural Networks (DcCNN) framework by applying decorrelation-based optimization to Convolutional Neural Networks(CNN). An analysis of evaluation metrics comparisons shows that integrating the decorrelation function boosts the performance of PD recognition by removing class bias. Specifically, our DcCNN model performs significantly better than existing traditional approaches to tackle the imbalance problem. Finally, the same framework can be extended to create scanner invariant features without significantly impacting the performance of a model. The obtained dataset is a multi-scanner dataset which leads to scanner bias due to the differences in acquisition protocols and scanners. The multi-scanner dataset is a combination of two datasets, namely PPMI and FTLDNI - frontotemporal lobar degeneration neuroimaging initiative (NIFD) dataset. The results of t-distributed stochastic neighbor embedding (t-SNE) and scanner classification accuracy of our proposed Feature Extraction-DcCNN (FE-DcCNN) model validated the effective removal of scanner bias. Our method achieves an average accuracy of 77.80% on a multi-scanner dataset for differentiating PD from healthy control, which is superior to the DcCNN model trained on a single scanner imbalanced dataset.

Multivariate statistical approaches (MSA), such as principal components analysis and multidimensional scaling, seek to uncover meaningful patterns within datasets by considering multiple response variables in a concerted fashion. Although these techniques are readily used by ecologists to visualize and explain differences between study sites, they could theoretically be employed to differentiate organisms within an experimental framework while simultaneously identifying response variables that drive documented experimental differences. Therefore, MSA were used herein to attempt to understand the response of the common, Indo-Pacific reef coral Seriatopora hystrix to temperature changes using data from laboratory-based temperature challenge studies performed in Southern Taiwan. Gene expression and physiological data partitioned experimental specimens by time of sampling, treatment temperature, and site of origin upon employing MSA, signifying that S. hystrix and its dinoflagellate endosymbionts display physiological and molecular signatures that are characteristic of sampling time, site of colony origin, and/or temperature regime. These findings promote the utility of MSA for documenting biologically meaningful shifts in the physiological and/or sub-cellular response of marine invertebrates exposed to environmental change.

Wireless Powered Communication Networks (WPCN), which has attracted much attention of researchers, also been recently recommended in 5^th generation (5G) wireless networks. With the help of the WPCN, the reliability and battery life of wireless low-power devices can be improved. In this paper, we investigate throughput and ergodic capacity in WPCN-assisted amplify-and-forward (AF) relaying system, considering two transmission modes including delay-tolerant and delay-limited. As important achievement, we propose symmetric energy harvesting protocol, namely time power switching relaying (TPSR) in order to find maximal throughput. In particular, both time switching and power switching coefficients in this schemes are considered. Unlike most of the previous works, we further focus on impact of outdated channel state information (CSI) in this WPCN. In order to evaluate information processing efficiency, the performance can be substantially improved by optimally harvesting time and power coefficients of the received signal at relay node for energy and information extraction, and by deploying several scenarios. By deploying Monte Carlo simulation, it is confirmed that the system performance is more sensitive to CSI estimation error, noise variance, signal-to-noise ratio (SNR) and resulting in other reasonable computations of TPSR need be deployed to obtain QoS requirement.

The intense motion of a ship can greatly impacts the comfort of crew members and the safety of the vessel. Therefore, accurately estimating and predicting ship attitudes has become an important issue. This paper introduces the latest development in functional deep learning model called DeepOnet. It takes wave height as input and ship motion as output, using a cause-to-result prediction approach. The modeling data used in this study is sourced from publicly available experimental data from the Iowa Institute of Hydraulic Research. Firstly, parameters system tuning was conducted for the neural network's hyperparameters to determine the appropriate combination of parameters. Secondly, the DeepOnet model for wave height and multi-degree-of-freedom motion was established, and the influence of increasing time steps on prediction accuracy was examined. Finally, a comparison was made between the DeepOnet model and the classical time series model LSTM. It was found that the DeepOnet model had a 10-fold improvement in accuracy for roll and heave attitudes. Moreover, as the forecast duration increased, the advantage of DeepOnet showed a trend of strengthening. As a functional prediction model, DeepOnet provides a new promising tool for very short-term prediction of ship motion.

Antimony (Sb) has gained significance as a critical raw material (CRM) within the European Union (EU) due to its strategic importance in various industrial sectors, particularly in the textile industry for flame retardants and as a component of Sb-based semiconductor materials. Moreover, Sb is emerging as a potential alternative for anodes used in lithium-ion batteries, a key element in the Energy transition. This study focused on exploring the feasibility of identifying and quantifying Sb mineralizations through the spectral signature of soils using reflectance spectroscopy, a non-invasive remote sensing technique, and by employing deep learning algorithms such as Convolutional Neural Networks (CNNs). Common signal preprocessing techniques were applied to the spectral data, and the soils were analyzed by Inductively Coupled Plasma Mass Spectrometry (ICP-MS). Despite achieving high R-squared values, the study faces a significant challenge of generalization of the model to new data. Despite the limitations, this study provides valuable insights into potential strategies for future research in this field.

Day by day, the share of renewable energy-based power plants such as offshore wind farms and photovoltaic power plants, in the present-day power systems is escalating. Nevertheless, most of these power-producing facilities have been located quite far away from the load centers. At this stage, HVDC power systems provide satisfactory options due to qualities such as reduced line losses, substantial controllability, and environmental advantages. Nevertheless, unique converter designs are required to combine asynchronous HVDC networks with each other and with already existing high voltage alternating current (HVAC) networks. In this study, based on the above special cases, a unique DC-DC modular multilevel converter (MMC) architecture is presented that provides an excellent solution for both integrating modern asynchronous HVDC networks and integrating these modern HVDC power systems with existing asynchronous HVAC power systems. The mathematical analysis of the recommended DC-DC MMC design has been examined in detail and the power transfer between two asynchronous power grids has been realized in a simulation environment. Efficient bilateral power transmission has been made achievable by the control system. The recommended DC-DC MMC topology has shown to be a highly successful approach, in the interconnection of HVDC power systems, according to the simulation results.

One of the central criteria for free will is “Could I have done otherwise?” But because of a temporal asymmetry in human choice, the question makes no sense. The question is backward-looking, while human choices are forward-looking. At the time when any choice is actually made, there is as of yet no action to do otherwise. Expectation is the only thing to contradict (do other than). So the ability to do something not expected by the ultimate expecter, Laplace’s demon, is a better criterion for free will. If human action is fundamentally unpredictable, then we have free will. Scientists have studied a form of fundamental unpredictability, known as undecidability. The features that make a system capable of undecidable dynamics have been identified: program-data duality; potential to access an infinite computational medium; and the ability to implement negation. Humans have all three of these features, so we very likely are fundamentally unpredictable, so we have free will.

Background: Evaluating muscle mass and function among stroke patients is important. However, evaluating muscle volume and function is not easy due to the disturbance of consciousness and paresis. Temporal muscle thickness (TMT) has been introduced as a novel surrogate marker for muscle mass, function, and nutritional status. We herein performed a narrative literature review on temporal muscle and stroke to understand the current meaning of the TMT in the clinical stroke practice. Methods: The search was performed in PubMed, last updated in October 2021. Report on temporal muscle morphomics and stroke-related diseases or clinical entities were collected. Results: Four studies reported on TMT and subarachnoid hemorrhage, 2 intracerebral hemorrhage, 2 ischemic stroke, 2 standard TMT values, and 2 nutritional status. TMT was reported as a prognostic factor for several diseases, surrogate markers for skeletal muscle mass, and an indicator of nutritional status. Computed tomography, magnetic resonance imaging, and ultrasonography were used to measure TMT. Conclusions: TMT is gradually used as a prognostic factor of stroke or surrogate marker for skeletal muscle mass and nutritional status. Establishing standard methods to measure TMT and large prospective studies to investigate the further relationship between TMT and diseases are needed.

Human activities (e.g., exploitation, utilization, and conservation) exert substantial impact on forest ecological functions (FEF). The human influence on FEF significantly varies across developmental stages, which are attributed to the temporal and spatial in nature. This study evaluates some notable FEF indices (FEFI) in the 448 counties within the Yellow River basin (YRB) using panel data from the Seventh to Ninth National Forest Inventory. Data analysis involves employing the residual trends, geographical and temporal weighted regression. Results indicate that, firstly, the overall forest ecological function in the YRB is moderate to inferior, with superior FEF in counties endowed with more natural forest resources. Afforestation demonstrates a short-term improvement, but its effectiveness diminishes over time. Secondly, the positive spatial correlation is stronger among counties, characterized by both high-high and low-low agglomeration effects. Scattered planting, simple stand structure, and concentrated harvesting of forests at the identical stand ages hinder the formation of complex and large-scale FEF agglomerations. Thirdly, significant spatial-temporal differences exist in the impact of human activities on FEF. In the upper reaches of the basin, increased vegetation coverage through agricultural and forestry production benefited FEF, however, some over-exploitation of forests and grasslands is observed there. In the middle reaches, the economic development, expanding population and the greening activities help to improve FEF effectively, but excessive water using in agricultural production brought more difficulties to FEF improvement. In the lower reaches of the basin, improved wastelands and forest protection positively influence FEF. This study recommends that county governments should prioritize forest management with multi-species and multi-layered complex forests. Each county should define its position in regional development and ecological protection, considering the potential impacts on neighboring regions. This holistic approach promotes more effective integrated regional management.

Oxidative stress toxicity (OSTOX), as well as lowered antioxidant defenses (ANTIOX), play a role in temporal lobe epilepsy (TLE). Nevertheless, the associations between OSTOX/ANTIOX and psychiatric comorbidities in TLE are largely unknown.Thus, this study examines plasma malondialdehyde (MDA), lipid hydroperoxides (LOOH), advanced oxidation protein products (AOPP), nitric oxide metabolites (NOx), total radical trapping antioxidant parameter (TRAP) and sulfhydryl (-SH) groups in Depression due to TLE (n=25); Anxiety Disorders due to TLE (n=27); Psychotic Disorder due to TLE (n=25); “pure TLE” (n=27); and healthy controls (n=40).TLE and mesial temporal sclerosis (MTS) were characterized by significant increases in OSTOX (MDA, AOPP, LOOH) and lowered ANTIOX (-SH groups, TRAP). The discrimination of pure TLE from controls yielded a significant area under the ROC curve for MDA (0.999), AOPP (0.851), -SH groups (0.899) and the OSTOX/ANTIOX ratio (0.996). Seizure frequency is significantly associated with increased MDA and lowered LOOH and NOx levels. Increased MDA was associated with the severity of depressive and physiosomatic symptoms, whilst increased AOPP levels predicted suicidal ideation. Depression and anxiety disorders co-occurring with TLE showed significantly lower MDA levels than TLE without any comorbidities. The psychotic and negative symptoms of TLE are associated with increased MDA levels and excitation with increased LOOH and lowered TRAP levels.These results indicate that oxidative stress toxicity especially protein oxidation and aldehyde formation coupled with lowered -SH groups play a key role in the pathophysiology of TLE/MTS. Increased aldehyde formation also impacts psychopathology, psychosis, as well as negative and depressive symptoms.

This article reports new measurements of laser-induced plasma hypersonic expansion measurements of diatomic molecular cyanide (CN). Focused, high-peak power 1064-nm Q-switched radiation of the order of 1 TW/cm² generates optical breakdown plasma in a cell containing a 1:1 molar gas mixture of N₂ and CO₂ at a fixed pressure of 1.1 × 10⁵ Pascal and in a 100 ml/min flow of the mixture. Line-of-sight (LOS) analysis of recorded molecular spectra indicate the outgoing shockwave at expansion speeds well in excess of Mach number 5. Spectra of atomic carbon confirm an increased electron density near the shock wave, and equally, molecular CN spectra reveal higher excitation temperature near the shockwave. The results are consistent with corresponding high-speed shadow graphs obtained by visualization with an effective shutter speed of five n anosecond. In addition, LOS analysis and application of integral inversion techniques allow inferences about the spatio-temporal distribution of the plasma.

Optical artificial neural networks (ONNs) — analog computing hardware tailored for machine learning [1,2] — have significant potential for ultra-high computing speed and energy efficiency [3]. We propose a new approach to architectures for ONNs based on integrated Kerr micro-comb sources [4] that is programmable, highly scalable and capable of reaching ultra-high speeds. We experimentally demonstrate the building block of the ONN — a single neuron perceptron — by mapping synapses onto 49 wavelengths of a micro-comb to achieve a high single-unit throughput of 11.9 Giga-FLOPS at 8 bits per FLOP, corresponding to 95.2 Gbps. We test the perceptron on simple standard benchmark datasets — handwritten-digit recognition and cancer-cell detection — achieving over 90% and 85% accuracy, respectively. This performance is a direct result of the record small wavelength spacing (49GHz) for a coherent integrated microcomb source, which results in an unprecedented number of wavelengths for neuromorphic optics. Finally, we propose an approach to scaling the perceptron to a deep learning network using the same single micro-comb device and standard off-the-shelf telecommunications technology, for high-throughput operation involving full matrix multiplication for applications such as real-time massive data processing for unmanned vehicle and aircraft tracking.

Landscape changes based on spectral responses allow showing plant cover changes through diversity, composition, and ecological connectivity. The spatial and temporal vegetation dynamics of the Bijagual Massif from 1986 to 2021 were analyzed as a measure of ecological integrity, conservation, and territory. The covers identified were high open forest (Hof), dense grassland of non-wooded mainland (Dgnm), a mosaic of pastures and crops (Mpc), lagoons (Lag), and bare and degraded lands (Bdl). The Bijagual Massif has 8,574.1 ha. In 1986, Dgnm occupied 42.6% of the total area, followed by Mpc (32.8%) and Hof (24.5%); by 2000, Mpc and Hof increased (43.7 and 28.1%, respectively), while Dgnm decreased (28%); by 2021, Dgnm was restricted to the northeastern zone and continued to decrease (25.2%), Mpc occupied 52.9%, Hof 21.7% and Bdl 0.1%. Of the three fractions of the connectivity probability index, only dPCintra and dPCflux contribute to ecological connectivity. Hof and Dgnm show patches with biota habitat quality and availability. Between 1986 and 2021, Dgnm lost 1,489 ha (41%) and Hof 239.5 ha (11%). Mpc replaced various covers (1,722.2 ha; 38%) in 2021. Bijagual has a valuable biodiversity potential limited by Mpc. Territorial planning and sustainable agroecological and ecotourism proposals are required due to the context of the ecosystems.

Background: Temporal lobe epilepsy (TLE) is the most common focal epilepsy subtype in adults and is frequently accompanied by depression, anxiety and psychosis. Aberrations in total paraoxonase (PON)1 status may occur in TLE and those psychiatric conditions. Methods: We examined paraoxonase (PON)1 status, namely Q192R PON1 genotypes and PON1 enzymatic activities, in 40 normal controls and 104 TLE patients, 27 without comorbidities, and 77 with comorbidities including mood disorders (n=25), anxiety disorders (n=27) and psychosis (n=25). Outcomes: CMPAase and arylesterase activities were significantly lower in TLE and mesial temporal sclerosis (MTS) with and without psychiatric comorbidities than in normal controls. The areas under the ROC curve of CMPAase were 0.893 (0.037) for TLE and 0.895 (±0.037) for MTS. Partial Least Squares (PLS) path analysis showed that there were specific indirect effects of PON1 genotype on TLE severity (p<0.0001) and psychopathology (p<0.0001), which were both mediated by lowered CMPAase activity, while arylesterase activity was not significant. The severity of TLE was significantly associated with psychopathology scores. Furthermore, PON1 CMPAase activity was inversely associated with Mini Mental State Examination scores. Interpretation: The severity of TLE and comorbidities are to a large extent explained by lowered PON1 enzyme activities and by effects of the Q192R genotype which are mediated by lowered CMPAase activity. Total PON1 status plays a key role in the pathophysiology of TLE, MTS and psychiatric comorbidities by increasing the risk of oxidative toxicity. PON1 enzyme activities are new drug targets in TLE to treat seizure frequency and psychiatric comorbidities.

The massive amount of human biological, imaging and clinical data produced by multiple and diverse sources, necessitates integrative modeling approaches able to summarize all this information into answers to specific clinical questions. In this paper, we present a hypermodeling scheme able to combine models of diverse cancer aspects regardless of their underlying method or scale. Describing tissue-scale cancer cell proliferation, biomechanical tumor growth, nutrient transport, genomic-scale aberrant cancer cell metabolism, and cell signaling pathways that regulate the cellular response to therapy, the hypermodel integrates mutation, miRNA expression, imaging, and clinical data. The constituting hypomodels as well as their orchestration and links are described. Two specific cancer types, Wilms tumor (nephroblastoma) and non-small cell lung cancer, are addressed as proof of concept study cases. Personalized simulations over the actual anatomy of a patient have been carried out. The hypermodel has also applied to predict tumor control after radiotherapy and the relationship between tumor proliferative activity and response to neoadjuvant chemotherapy. Our innovative hypermodel holds promise as a digital twin based clinical decision support system and the core of future in silico trial platforms, although additional retrospective adaptation and validation is necessary.

Under optimal conditions, just 3–6 ms of visual stimulation suffices for humans to see motion. Motion perception on this time scale implies that the visual system under these conditions reliably encodes, transmits, and processes neural signals with near-millisecond precision. Motivated by in vitro evidence for high temporal precision of motion signals in the primate retina, we investigated how neuronal and perceptual limits of motion encoding relate. Specifically, we examined the correspondence between the time scale at which cat retinal ganglion cells in vivo represent motion information and temporal thresholds for human motion discrimination. The time scale for motion encoding by ganglion cells ranged from 4.6–91 ms, depended nonlinearly on temporal frequency but not on contrast. Human psychophysics revealed that minimal stimulus durations required for perceiving motion direction were similarly brief, 5.6–65 ms, similarly depended on temporal frequency but, above ~10%, not on contrast. Notably, physiological and psychophysical measurements corresponded closely throughout (r = 0.99), despite more than a 20-fold variation in both human thresholds and optimal time scales for motion encoding in the retina. These results demonstrate that neural circuits for motion vision in cortex can maintain and make use of the high temporal fidelity of the retinal output signals.

Change Detection (CD) of aerial images refers to identifying and analyzing changes between two or more aerial images of the same location taken at different times. The CD is a highly challenging task due to the need to distinguish relevant changes, such as urban expansion, deforestation, or post-disaster damage assessment, from irrelevant ones, such as light conditions, shadows, and seasonal variations. Many CD papers have recently been published, where most of the papers that proposed a new model contained a comparison between their proposed and state-of-the-art (SOTA) models. While many recent studies propose new deep learning (DL) models for improving CD performance, their comparative analyses are often restricted, lacking comprehensive insights into the proposed models' real-world generalizability, robustness, and performance trade-offs across diverse change characteristics. This paper presents a novel generic framework to systematically benchmark and assess DL-based CD models through three parallel pipelines: 1) cross-testing models on diverse benchmark datasets to evaluate generalization, 2) robustness analysis against different image corruptions, and 3) multi-faceted contour-level analytics evaluating detection sensitivity to change size/complexity. The framework is applied to comparatively evaluate five state-of-the-art DL-based CD models - Changeformer, BIT, Tiny, SNUNet, and CSA-CDGAN. Extensive experiments unveil each model's strengths, limitations and biases, highlighting their relative proficiencies in generalizing across data distributions, resilience to noise corruption, and discriminative capabilities for changes of varying characteristics. The proposed benchmarking framework demonstrates significant potential for guiding the selection of suitable CD models tailored to specific application requirements by comprehensively evaluating their generalizability, robustness, and detection capabilities across diverse real-world scenarios. This systematic evaluation approach can drive future research into developing more robust and versatile CD solutions aligned with practical needs.

Superpixels are a representation of still images as pixel grids because of their more meaningful information compared with atomic pixels. However, their usefulness for video classification has been given little attention. In this paper, rather than using spatial RGB values as low-level features, we use optical flows mapped into hue-saturation-value (HSV) space to capture rich motion features over time. We introduce motion superpixels, which are superpixels generated from flow fields. After mapping flow fields into HSV space, independent superpixels are formed by iteration of seeded regions. Every grid of a motion superpixel is tracked over time using nearest neighbors in the histogram of flow (HOF) for consecutive flow fields. To define the temporal representation, the evolution of three features within the superpixel region, namely the HOF, HOG, and the center of superpixel mass are used as descriptors. The bag of features algorithm is used to quantify final features, and generalized histogram-kernel support vector machines are used as learning algorithms. We evaluate the proposed superpixel tracking on first-person videos and action sports videos.

Event-based vision is an emerging field of computer vision that offers unique properties such as asynchronous visual output, high temporal resolutions, and dependence on brightness changes to generate data. These properties can enable robust high-temporal-resolution object detection and tracking when combined with frame-based vision. In this paper, we present a hybrid, high-temporal-resolution, object detection and tracking approach, that combines learned and classical methods using synchronized images and event data. Off-the-shelf frame-based object detectors are used for initial object detection and classification. Then, event masks, generated per each detection, are used to enable inter-frame tracking at varying temporal resolutions using the event data. Detections are associated across time using a simple low-cost association metric. Moreover, we collect and label a traffic dataset using the hybrid sensor DAVIS 240c. This dataset is utilized for quantitative evaluation using state-of-the-art detection and tracking metrics. We provide ground truth bounding boxes and object IDs for each vehicle annotation. Further, we generate high-temporal-resolution ground truth data to analyze the tracking performance at different temporal rates. Our approach shows promising results with minimal performance deterioration at higher temporal resolutions (48 – 384 Hz) when compared with the baseline frame-based performance at 24 Hz.

Optical networks offer a wide range of benefits to the telecommunication sector world- wide with its provision of higher bandwidth which leads to faster data speed, longer transmission distance, and improved latency. Currently, the complexity associated with advancements in optical networks poses problems to network flexibility, reliability, and quality of service. Over the years, many reviews and proposals have been implemented by several literatures to provide solutions for optical networks using software-defined networks and network service orchestrators. This paper reviews the significant challenges in current optical network applications, the various solutions rendered by software-defined networks as well as network service orchestration, the impediments, and gaps in these software – defined networks. This paper will go a step further to look into the various improvements and implementations of software-defined networks tailored to solve specific optical network problems. This paper further proposes a flexible orchestration architecture for software-defined networks for solving flexibility and scalability problems in optical networks. This proposal uses Open Network System (ONOS) SDN controller, leveraging on dockerisation as well as kubernetes clusterisation and orchestration. This solution presents a more flexible, reliable, customable, and higher quality of service which is an improvement upon current solutions in literature.

It was observed that a cluster of ordered genes (Hox1, Hox2, Hox3,…) in the genome are activated in the ontogenetic units (1, 2, 3,…) of an embryo along the Anterior/Posterior axis following the same order of the Hox genes. This Spatial Collinearity (SC) is very strange since it correlates events of very different spatial dimensions. It was later observed in vertebrates, that, in the above ordering, first is Hox1expressed in ontogenetic unit 1, followed later by Hox2 in unit 2, and even later Hox3 in unit 3….This temporal collinearity (TC) is an enigma and even to-day is explored in depth. In 1999 T. Kondo and D. Duboule, after posterior upstream extended DNA excisions , concluded that the Hox cluster behaves ‘as if’ TC disappears. Here the consideration of TC really disappearing is taken face value and its repercussions are analyzed. Furthermore, an experiment is proposed to test TC disappearance. An outcome of this experiment could be the reappearance (partial or total) of TC.

Surface temperature influences human health directly and alters the biodiversity and productivity of the environment. While previous research has identified that the composition of urban landscapes influences the physical properties of the environment such as surface temperature, a generalizable and flexible framework is needed that can be used to compare cities across time and space. This study employs the Structure of Urban Landscapes (STURLA) classification combined with remote sensing of New York City’s (NYC) surface temperature. These are then linked using machine learning and statistical modeling to identify how greenspace and the built environment influence urban surface temperature. It was observed that areas with urban units composed of largely the built environment hosted the hottest temperatures while those with vegetation and water were coolest. Likewise, this is reinforced by borough-level spatial differences in both urban structure and heat. Comparison of these relationships over the period between2008 and 2017 identified changes in surface temperature that are likely due to the changes in prevalence in water, lowrise buildings, and pavement across the city. This research reinforces how human alteration of the environment changes ecosystem function and offers units of analysis that can be used for research and urban planning.

The main purpose of this article is to identify brain diseases such as Alzheimer's and Parkinson's in an intelligent way using Python software and processing the function of neurons in the neural network areas of the brain, which are classified into different components, and the data is based on the information obtained from FMRI images using algorithms artificial intelligence can intelligently diagnose the type of disease. Therefore, by using spatial clustering based on the deep learning method with noise algorithm (DBSCAN), fMRI brain image and fMRI brain surface complexity are classified, and then image preprocessing will be applied to fMRI images by using artificial intelligence neural networks (ANN) algorithm. became. Then, by using the ANN algorithm and Deep CNN topology of the brain neural network, the type of disease in the brain can be diagnosed by simulating the performance of an artificial neural network (ANN) in Python software. Deep machine learning-based methods, especially algorithms based on neural networks, have shown great success in medical image analysis for various tasks including brain tumor detection, segmentation, and classification, and Alzheimer's and epilepsy. In this research, we propose an integrated model based on a convolutional neural network for simultaneous recognition and classification of brain diseases for intelligent diagnosis of tumors and epilepsy. The average accuracy obtained from our proposed model is 97.89 percent accuracy and 91.66 percent specificity.

With the widespread use of new equipment such as distributed photovoltaics, distributed energy storage, electric vehicles, and distributed wind power, the control of low-voltage distribution networks (LVDNs) has become increasingly complex. Acquiring the most recent topological structure is essential for conducting accurate analysis and real-time control of LVDNs. The signal-injection-based topology identification algorithm is favored for its speed and efficiency. This study proposes a new signal-injection-based topology identification algorithm aimed at solving the issues of reduced completeness and correctness of identification caused by missing feature signal records (FSRs). By analyzing the correlations between FSRs of different positions, the algorithm employs vertical and horizontal completion methods to effectively address missing data, combined with inclusion detection algorithms, to identify the topology of LVDNs. Based on the study of actual LVDN data, the results indicate that the algorithm not only significantly improves the completeness and correctness of topology identification for LVDNs but can also increase the number of devices in operation by evaluating the status of topological equipment, further enhancing the topology identification performance.

Social networks have captured the attention of many people worldwide. However, these services have also attracted a considerable number of malicious users whose purpose is to compromise digital assets of other members by using messages as an attack vector to execute different variants of cyberattacks against them. Therefore, this work presents an approach based on Natural Language Processing tools and a Convolutional Neural Network architecture to detect and classify, on social network messages, four types of cyberattacks, such as malware, phishing, spam, and even one whose purpose is deceiving the user into spreading malicious messages to other users, which in this work is identified as bot attacks. One notable feature of this work is that it analyzes textual content without depending on any characteristics from a specific social network, making its analysis independent from particular data sources. Finally, this work was tested on real data, demonstrating its results in two stages. The first detects the existence of any of the four cyberattacks within the message, obtaining an accuracy value of 0.91. After detecting a message as a cyberattack, the next stage is to classify it into one of the four types of cyberattack, achieving an accuracy value of 0.82.

Spatio-Temporal Dynamic Mode Decomposition (STDMD) is an extension of Dynamic Mode Decomposition (DMD) designed to handle spatio-temporal datasets. It extends the framework so that it can analyze data that has both spatial and temporal variations, allowing for the extraction of spatial structures and their temporal evolution. The STDMD method extracts temporal and spatial development information simultaneously, including wavenumber, frequencies and growth rates, which is essential in complex dynamic systems. We provide a comprehensive mathematical framework for sequential and parallel STDMD approaches. We also introduce delay coordinates generalization to the presented algorithms to extend the scope of their application. The extension, labeled delay embedding STDMD allows the use of delayed data, which can be both time-delayed and space-delayed. An explicit expression of the presented algorithms in matrix form is also provided, which facilitates theoretical analysis and provides a solid foundation for further research and development. The novel approach is demonstrated using some illustrative model dynamics.

The rhizosphere fungal community can play an important role in determining plant growth and health. In this study, using high-throughput sequencing, we investigated the fungal diversity and community composition in the roots and rhizosphere soil of 21 potato (Solanum tuberosum L.) cultivars. The samples were collected at three different sampling points. Furthermore, we assessed the differences in both diversity and composition of pathogen and saprotroph communities. In soil and roots, the fungal richness and relative abundance of pathogens and saprotrophs were mainly affected by sampling time. However, root fungal communities were also significantly affected by cultivar. The most substantial effect of cultivar was on root pathogen diversity. Moreover, the occurrence of most pathogens strongly varied among cultivars. Soil fungal community composition was primarily determined by sampling time; whereas in roots, the primary determinant was cultivar. Our results demonstrate changes in fungal communities over the potato growing season, as well as highlight the importance of potato cultivar on root fungal communities, and emphasise their importance in plant breeding.

Ocean circulation serve as the primary channels for transporting material and energy flows throughout the entire ocean system, which plays a crucial role in shaping Earth’s climate, weather patterns, and marine ecosystems. The ocean movements have far-reaching impacts on both the environment and human life. An effective method for semantically modeling the ocean circulation is urgently required to be established. To achieve a unified description of ocean circulation at the semantic level, this paper introduces the theory and methodology of ocean ontology, which is developed through an analysis of domain knowledge in ocean circulation. We focus on analyzing the concepts, temporal relationships, and spatial relationships of ocean circulation. By defining classes, properties, relationships, instances, and constraint conditions within the logical structure of an ontology, it is feasible to formalize the expression of conceptual elements and their relationships. Additionally, semantic inference rules are established to finalize the construction of the ocean circulation ontology. The effectiveness of ontology construction has been verified through practical examples. Furthermore, a specialized knowledge base framework has been developed upon the ontology description of ocean circulation. Some examples of knowledge base queries have been articulated and verified. The results demonstrate that this ontology can effectively represent the relevant knowledge in the domain of ocean circulation and provide a meaningful strategy for investigating semantic integration and knowledge sharing in this field.

This paper applies a new artificial intelligence architecture, the Temporal Fusion Transformer (TFT), for the joint GDP forecasting of 25 OECD countries at different time horizons. This new attention-based architecture offers significant advantages over other deep learning methods. First, results are interpretable since the impact of each explanatory variable on each forecast can be calculated. Second, it allows to visualize persistent temporal patterns and to identify significant events and different regimes. Third, it provides quantile regressions and permits to train the model on multiple time series from different distributions. Results suggest that TFTs outperform regression models, especially in periods of turbulence such as the COVID-19 shock. Interesting economic interpretations are obtained depending on whether the country is domestic demand-led or export-led growth. In essence, TFT is revealed as a new tool that artificial intelligence provides to economists and policy makers, with enormous prospects for the future.

So-called ‘zero’ or ‘null’ tenses have often been characterized as functionally deficient forms, deprived of any inherent content. In this paper, we will focus on the semantics of a morpho-phonologically null inflectional verbal paradigm in Anindilyakwa (Groote Eylandt, N.T., Australia, which is both temporally and aspectually underspecified. Through a quantitative corpus study conducted in the paper, we establish that ‘zero inflection’ in this language, contra prior works on such tenses in general (e.g. Bybee 1990) and in Anindilyakwa in particular (Bednall 2019), presents various degrees of sensitivity to traditional Vendlerian aspectual parameters. We show that while telicity is not a significant predictor for the temporal interpretation of zero-inflected Anindilyakwa verbs, and dynamicity is a good but not very good predictor, only a very broad opposition between change-of-state (including qua boundedness) and non-change-of-state, or perfective/imperfective, gives very significant biases towards past vs. present anchoring. We also show that atomic telicity is the only categorical Aktionsart predictor for temporal anchoring in this context correctly predict the temporal anchoring of such verbs, and stativity is not biased towards present interpretations, thereby questioning currently received typological theories of the semantics of so-called ‘zero-tenses’ / aspectuo-temporally underspecified tenses.

The effective management of Fusarium wilt of bananas (FW) depends on the knowledge of the disease dynamics in time and space. The objectives of this work were: To estimate disease intensity and impact, and to investigate the spatial and temporal dynamic of FW. Fields planted with Silk (n = 10), Pome (n = 17) or Cavendish (n = 3) banana subgroups were surveyed in Brazil, totaling 95 ha. In each field, all plants were visually assessed and diseased plants were georeferenced. The incidence of FW and the impact of the disease on yield on a regional scale were estimated. Spatial patterns were analyzed using quadrat- and distance-based methods. FW incidence ranged from 0.09 to 41.42%, being higher in Silk fields (median = 14.26%). Impacts of epidemics on yield ranged from 18.4 to 8,192.5 kg.ha-1.year-1, with a median of 935.2 kg.ha-1.year-1. The higher economic impact of the disease was observed on Silk cultivar with a median loss of US$ 910.5 ha-1.year-1. Overall, estimated losses increased on average by US$ 109.8 ha-1.year-1 at each 1% of incidence. Aggregation of FW was detected by all analytical methods in 13 fields (1 of Cavendish, 11 of Pome and 1 of Silk). In the other 17 fields, at least one analytical method did not reject the null hypothesis of randomness. One field (5 ha), composed of six plots, was selected for spatial and temporal studies during two years with bi-monthly assessments. A sigmoidal curve represented the FW progress and the Gompertz model best fitted disease progress. The level of aggregation varied over time, and evidence of secondary infection to neighboring and distant plants were detected. FW is a widespread problem in Brazil and yield losses can be of high magnitude. Epidemiology-based management strategies can now be better established.

Background: As the opioid epidemic continues, understanding the geospatial, temporal and demand patterns is important for policymakers to assign resources and interdict individual, organization, and country-level bad actors. Methods: GIS geospatial-temporal analysis and extreme-gradient boosted random forests evaluate ICD-10 F11 opioid-related admissions and admission rates using geospatial analysis, demand analysis, and explanatory models, respectively. The period of analysis was January 2016 through September 2018. Results: The analysis shows existing high opioid admissions in Chicago and New Jersey with emerging areas in Atlanta, Salt Lake City, Phoenix, and Las Vegas. High rates of admission (claims per 10,000 population) exist in the Appalachian area and on the Northeastern seaboard. Explanatory models suggest that hospital overall workload and financial variables might be used for allocating opioid-related treatment funds effectively. Gradient-boosted random forest models accounted for 87.8% of the variability of claims on blinded 20% test data. Conclusions: Based on the GIS analysis, opioid admissions appear to have spread geographically, while higher frequency rates are still found in some regions. Interdiction efforts require demand-analysis such as that provided in this study to allocate scarce resources for supply-side and demand-side interdiction: prevention, treatment, and enforcement. Based on GIS analysis, the opioid epidemic is likely to spread or diffuse through the country, and interdiction efforts require demand-analysis such as that provided in this study to allocate scarce resources for supply-side and demand-side interdiction: prevention, treatment, and enforcement.

The detection of seismic events at regional and teleseismic distances is critical to Nuclear Treaty Monitoring. Traditionally, detecting regional and teleseismic events has required the use of an expensive multi-instrument seismic array; however in this work, we present DeepPick, a novel seismic detection algorithm capable of array-like performance from a single trace. We achieve this directly, by training our single-trace detector against labeled events from an array catalog, and by utilizing a deep temporal convolutional neural network. The training data consists of all arrivals in the International Seismological Centre Catalog for seven seismic arrays over a five year window from 1 Jan 2010 to 1 Jan 2015, yielding a total training set of 608,362 detections. The test set consists of the same seven arrays over a one year window from 1 Jan 2015 to 1 Jan 2016. We report our results by training the algorithm on six of the arrays and testing it on the seventh, so as to demonstrate the transportability and generalization of the technique to new stations. Detection performance against this test set is outstanding. Fixing a type-I error rate of 1%, the algorithm achieves an overall recall rate of 73% on the 141,095 array beam picks in the test set, yielding 102,394 correct detections. This is more than 4 times the 23,259 detections found in the analyst-reviewed single-trace catalogs over the same period, and represents an 8dB improvement in detector sensitivity over current methods. These results demonstrate the potential of our algorithm to significantly enhance the effectiveness of the global treaty monitoring network.

In this paper we derive a unified perspective for Optimal Transport (OT) theory and Mean Field Control (MFC) theory to analyse the learning process for Neural Networks algorithms in a high-dimensional framework. We consider Mean Field Neural Networks in the context of MFC theory, specifically the mean field formulation of OT theory that allows the development of highly efficient algorithms while providing a powerful tool in the context of explainable Artificial Intelligence.

The human microbiome is an extremely complex ecosystem considering the amount of bacterial species, their interactions, and its variability over time. Here we untangle the complexity of the human microbiome for the Irritable Bowel Syndrome (IBS) that is the most prevalent functional gastrointestinal disorder in human populations. Based on a novel information theoretic network inference model we detect species interaction networks that are functionally and structurally different for healthy and unhealthy individuals. Healthy networks are characterized by a neutral symmetrical pattern of species interactions and scale-free topology versus random unhealthy networks. We detect an inverse scaling relationship between species total outgoing information flow, meaningful of node interactivity, and relative species abundance (RSA). The top ten interacting species are also the least relatively abundant for the healthy microbiome and the most detrimental. These findings support the idea about the diminishing role of network hubs and hubs should be defined considering the total outgoing information flow rather than the node degree. Macroecologically, the healthy microbiome is characterized by the highest total species diversity growth rate, the lowest species turnover, and the smallest variability of RSA for all species. This result challenges current views that posit a universal association between healthy states and the highest absolute species diversity in ecosystems. Additionally, we show how the transitory microbiome is unstable and microbiome criticality is not at the phase transition between healthy and unhealthy states. We stress out the importance of considering interacting pairs versus single node dynamics when characterizing the microbiome and of ranking these pairs in terms of their dynamics. Interactions (i.e. species collective behavior) shape transition from healthy to unhealthy states.\\ The macroecological characterization of the microbiome is useful for diagnostic purposes and disease etiognosis, while species-specific analyses can detect species that are more beneficial leading to personalized design of pre- and pro-biotic treatments and microbiome engineering.

In this paper, we examine two strategies for boosting the performance of ensembles of Siamese networks (SNNs) for image classification using two loss functions (Triplet and Binary Cross Entropy) and two methods for building the dissimilarity spaces (FULLY and DEEPER). With FULLY, the distance between a pattern and a prototype is calculated by comparing two images using the fully connected layer of the Siamese network. With DEEPER, each pattern is described using a deeper layer combined with dimensionality reduction. The basic design of the SNNs takes advantage of supervised k-means clustering for building the dissimilarity spaces that train a set of support vector machines, which are then combined by sum rule for a final decision. The robustness and versatility of this approach are demonstrated on several cross-domain image data sets, including a portrait data set, two bioimage and two animal vocalization data sets. Results show that the strategies employed in this work to increase the performance of dissimilarity image classification using SNN is closing the gap with standalone CNNs. Moreover, when our best system is combined with an ensemble of CNNs, the resulting performance is superior to an ensemble of CNNs, demonstrating that our new strategy is extracting additional information.

Substances that can modify the androgen receptor pathway in humans and animals are entering the environment and food chain with the proven ability to disrupt hormonal systems and leading to toxicity and adverse effects on reproduction, brain development, and prostate cancer, among others. State-of-the-art databases with experimental data of human, chimp, and rat effects by chemicals have been used to build machine learning classifiers and regressors and evaluate these on independent sets. Different featurizations, algorithms, and protein structures lead to dif- ferent results, with deep neural networks (DNNs) on user-defined physicochemically-relevant features developed for this work outperforming graph convolutional, random forest, and large featurizations. The results show that these user-provided structure-, ligand-, and statistically-based features and specific DNNs provided the best results as determined by AUC (0.87), MCC (0.47), and other metrics and by their interpretability and chemical meaning of the descriptors/features. In addition, the same features in the DNN method performed better than in a multivariate logistic model: validation MCC = 0.468 and training MCC = 0.868 for the present work compared to evalu- ation set MCC = 0.2036 and training set MCC = 0.5364 for the multivariate logistic regression on the full, unbalanced set. Techniques of this type may improve AR and toxicity description and predic- tion, improving assessment and design of compounds. Source code and data are available at https://github.com/AlfonsoTGarcia-Sosa/ML

This paper extends our seminal paper on KnoBAB for efficient Conformance Checking computations performed on top of a customised relational model. After defining our proposed temporal algebra for temporal queries (xtLTLf ), we show that this can express existing temporal languages over finite and non-empty traces such as LTLf . This paper also proposes a parallelisation strategy for such queries thus reducing conformance checking into an embarrassingly parallel problem leading to super-linear speed up. This paper also presents how a single xtLTLf operator (or even entire sub-expressions) might be efficiently implemented via different algorithms thus paving the way to future algorithmic improvements. Finally, our benchmarks remark that our proposed implementation of xtLTLf (KnoBAB) outperforms state-of-the-art conformance checking software running on LTLf logic, be it data or dateless.

The reality of people’s lives has shifted from rural to urban areas, where an ever-increasing proportion of the world’s population lives. Providing infrastructure to serve these areas, especially in the Global South, is a key task of sustainable development. A deep understanding of the spatial arrangement and scales of these urban structures and their temporal evolution can help to develop innovative solutions to issues of energy, water, or transportation infrastructures. For this purpose, in this work we study the temporal evolution of urban built-up structures (Global Artificial Impervious Area) and population distributions (Global Human Settlement Population) in four regions of the Global South (Argentina, India, Egypt, and Nigeria). We qualitatively analyze regularity through the pair correlation function and subsequently identify typical scales within the different interurban systems. In doing so, we identify that especially the large settlement objects arrange themselves in a regular way and thus typical scales exist in urban systems. Thus, settlement objects are usually located about 20 to 40 km apart from each other. This information can be used to develop sustainable infrastructure concepts, for example for passenger transport between settlements.

Recently, the triple-network convergence system (TNCS) has emerged from the deep integration of the power grid, transportation network, and information network. Fault recovery research in the TNCS is important since this system's complexity and interactivity can expand the faults scale and increase faults impact. Currently, fault recovery focuses primarily on single power grids and cyber-physical systems, but there are certain shortcomings, such as ignoring uncertainties including generator start-up failures and the occurrence of new faults during recovery, energy supply-demand imbalances leading to system security issues and communication delay caused by network attacks. In this study, we propose a recovery method based on the improved TD3 algorithm, factoring in shortcomings of the existing research. Specifically, we establish a TNCS model to analyze interaction mechanisms and design a state matrix to represent the uncertainty changes in the TNCS, a negative reward to reflect the impact of unit start-up failures, a special reward to reflect the impact of communication delay and an improved Actor network update mechanism. Experimental results show that our method obtains the optimal recovery decisions, maximizes restoration benefit in power grid failure scenarios and demonstrates a strong resilience against communication delay caused by DoS attacks.

The real-time Railway Traffic Management Problem (rtRTMP) is discussed in the field of railway transportation. In this paper, rtRTMP is considered for planning shunting routes based on the use of routing methods on a spatial-temporal graph. An approach and algorithm of Spatial-Temporal Graph formation for rail yard transportation network is proposed. The idea is to construct an undirected loop-free Double Vertex Graph for determining optimal shunting routes consisting of several half-runs for several trains shunting under draw-out tracks capacity constraints. Experimental results on the rail yard simulation model are presented.

The spatial and temporal changes in social vulnerability to natural hazards in Mexico are analyzed. To this end, using census data from 2000, 2010, and 2020 and a statistical method, different indices were computed, and with a GIS-based approach, patterns of social vulnerability are examined. In addition, a risk assessment test for severe weather (thunderstorms, hailstorms, and tornadoes) is made out. The results show different common social vulnerability driving factors in the three analyzed years, with root causes that have not been addressed since the beginning of the century. Likewise, a wider gap between Mexico's most and least vulnerable populations is identified. The changes in spatial patterns respond to different historical situations, such as migration, urbanization, and increased population. Also, poverty, ethnicity, and marginalization factors located in very particular regions in Mexico have remained relatively the same in the last few years. These situations have strongly influenced the spatial-temporal distribution of vulnerability in the country. The role of social vulnerability in the disaster risk to extreme events such as thunderstorms, hailstorms, and tornadoes in Mexico is fundamental to understanding changes in disaster distribution at the national level, and it is the first step to generating improvements in integrated risk management.

Humans learn from a lot of information sources to make decisions. Once this information is learned in the brain, spatio-temporal associations are made, connecting all these sources (variables) in space and time represented as brain connectivity. In reality, to make a decision, we usually have only part of the infor-mation, either as a limited number of variables, or limited time to make the decision, or both. The brain functions as spatio-temporal associative memory. Inspired by the ability of the human brain, a brain-inspired spatio-temporal associative memory was proposed earlier, that utilizes the NeuCube brain-inspired spiking neural network framework. Here we apply the STAM framework to develop STAM for neuroimaging data, on the cases of EEG and fMRI, resulting in STAM-EEG and STAM-fMRI. The paper shows that once a NeuCube STAM classification model is trained on a complete spatio-temporal EEG or fMRI data, it can be recalled using only part of the time series, or/and only part of the used variables. We evaluate accordingly the temporal association accuracy and spatial association accuracy. This is a pilot study that opens the field for the development of multimodal classification systems on other multimodal neuroimaging data, such as the also shown longitudinal MRI data, trained on complete data, but recalled on partial data collected across different settings, in different labs and clinics, that may vary in terms of variables, time of data collection, and other parameters. The proposed methods will allow also for brain diagnostic/prognostic marker discovery using spatio-temporal neuroimaging data.

Crop type and field boundary mapping enable cost-efficient crop management on the field scale and serve as the basis for yield forecasts. Our study uses a data set with crop types and corresponding field borders from the federal state of Bavaria, Germany, as documented by farmers from 2016 to 2018. The study classified corn, winter wheat, barley, sugar beet, potato, and rapeseed as the main crops grown in Upper Bavaria. Corresponding Sentinel-2 data sets include the normalised difference vegetation index (NDVI) and raw band data from 2016 to 2018 for each selected field. The influences of clouds, raw bands, and NDVI on crop type classification are analysed, and the classification algorithms, i.e., support vector machine (SVM) and random forest (RF), are compared. Field boundary detection and extraction are based on non-iterative clustering and a newly developed procedure based on Canny edge detection. The results emphasise the application of Sentinel’s raw bands (B1–B12) and RF, which outperforms SVM with an accuracy of up to 94%. Furthermore, we forecast data for an unknown year, which slightly reduces the classification accuracy. The results demonstrate the usefulness of the proof-of-concept and its readiness for use in real applications.

Forest healing effects are increasingly valued for their contribution to human psychological and physiological health, motivating further advances aimed at improving the knowledge of the relevant forest resources. Biogenic volatile organic compounds, emitted by the plants and accumulating in the forest atmosphere, are essential contributors to the forest healing effects, and represent the focus of this study. Using a photoionization detector, we investigated the high frequency variability, in time and space, of the concentration of total volatile organic compounds, on a hilly site, as well as along forest paths and long hiking trails on Italian northern Apennines. The scale of concentration variability was found to be comparable to absolute concentration levels, within time scales of less than one hour, and spatial scales of several hundred meters. During daylight hours, the concentration peaked from noon to early afternoon, followed by early morning, with lowest levels in late afternoon. Based on a conceptual model, these results were related to meteorological variables, including the atmospheric vertical stability profile. Moreover, preliminary evidence pointed to higher concentration of volatile organic compounds in forests dominated by conifer trees, in comparison with pure beech forests.

Communication between devices has transitioned from wired to unwired. Wireless networks have been in use widely around the globe since the advent of smartphones, IoT devices and other technologies that are compatible with wireless mode of communication. At the same time security issues have also increased in such communication methods. The aim of this paper is to propose security and privacy issues of the wireless networks and present them through comprehensive surveys. In context of security issues, there are 2 typical DDoS attacks - HTTP flood and SYN flood. Other than DDoS attacks, there are several other threats to wireless networks. One of the most prevalent include security issues in Internet of Things. In terms of privacy issues in a wireless network, location-based applications, individual data, cellular network and V2G (Vehicle to Grid) network are surveyed. The survey is hosted using questionnaire and responses of 70 participants is recorded. It is observed from the survey results that many groups of people lack the knowledge of security and privacy of wireless technologies and networks despite their increased use, however, students are relatively more aware and have strong knowledge of those issues. It is concluded from the results that an effective solution to these problems can be hosting campaigns for spreading the security and privacy laws to help the groups of people who are lagging behind in this domain of knowledge become more aware. A unique solution is also presented to overcome the security issues which include implementation of detection and mitigation techniques, implementing Blockchain in the IoT devices and implementing fog computing solutions. The unique solutions to overcome the privacy issues are proposed in the form of a privacy approach from the LBS server between pairs of users to increase the implementation of DSPM and blockchain as a solution.

This study addresses the prediction of recurring failures in water supply networks, a complex and costly task, but essential for the effective maintenance of these vital infrastructures. Using historical failure data provided by Companhia de Água e Esgotos da Paraíba (CAGEPA), the research focuses on predicting the time until the next failure at specific points in the network. The authors divided the failures into two categories: Occurrences of New Faults (ONF) and Recurrences of Faults (RF). To make the predictions, they used predictive models based on Machine Learning, more specifically on MLP (Multi Layer Perceptron) neural networks. The study revealed that, by analyzing data from past failures and considering factors such as altitude, number of failures on the same street and days between failures, it is possible to achieve an accuracy greater than 80% in predicting failures within a 90-day interval. This demonstrates the feasibility of using fault history to predict future water supply outages with significant accuracy. These forecasts allow water utilities to plan and optimize their maintenance, minimizing inconvenience and losses. The article contributes to the field of water infrastructure management by suggesting that the data-driven approach can be applied in other cities or in networks of different types, such as energy or communication networks. The conclusions highlight the importance of data collection and analysis in preventing failures and optimizing water utilities’ resources.

We present a formalism to assess the safety of the COVID19 vaccines and infer a causal relation between vaccine administration and adverse effects, in particular death. We use data on adverse effects from VAERS covering the time interval [01-10-2020, 31-12-2021] (downloaded on 1 Feb 2022). We measure a vaccine fatality rate of order 0.01 for all vaccine manufacturers and identify a strong heterogeneity in the vaccine toxicity across vaccine lots, spanning up to four orders of magnitude. We compute the correlation between vaccination dates and death dates, and produce an estimate of the time lag that maximises the correlation, finding that the onset of adverse effects happened statistically (i.e. 32-41 percentiles) within one day after the vaccine administration and that death happened statistically (i.e. 22-50 percentiles) within about two weeks after the vaccine administration. These results provide data-based insights that can guide public health measures and health insurance policies.

Research on spatio-temporal geostatistical modelling remains a critical challenge in numerous scientific and engineering disciplines. This work introduces a novel extension of the dual kriging the spatio-temporal dual kriging (ST-DK) whose drift functions with fixed and adaptive coefficients are established. The approach appears to be effective in modelling complex spatio-temporal dynamics, particularly when relevant auxiliary variables exert substantial influence on the target variable. To illustrate its performance, we compare the ST-DK model with the classical spatio-temporal regression kriging (ST-RK) method for estimating temperature and air pressure data across Thailand in 2018. Our findings demonstrate that both ST-DK and ST-RK models, when utilizing adaptive coefficients, outperform their constant coefficient counterparts. Furthermore, the ST-DK method consistently exhibits superior performance compared to the ST-RK model.

In the context of reinforcement learning (RL), ensuring both safety and performance is crucial, especially in real-world scenarios where mistakes can lead to severe consequences. This study aims to address this challenge by integrating temporal logic constraints into RL algorithms, thereby providing a formal mechanism for safety verification. We employ a combination of theoretical and empirical methods, including the use of temporal logic for formal verification and extensive simulations to validate our approach. Our results demonstrate that the proposed method not only maintains high levels of safety but also achieves comparable performance to traditional RL algorithms. Importantly, our approach fills a critical gap in existing literature by offering a solution that is both mathematically rigorous and empirically validated. The study concludes that the integration of temporal logic into RL offers a promising avenue for developing algorithms that are both safe and efficient. This work lays the foundation for future research aimed at generalizing this approach to various complex systems and applications.

Kondo and collaborators recently reported the absence of Hox temporal collinearity in Xenopus tropicalis. They found none in the initiation of accumulation of Hox transcripts (detected via RNA seq). And none in the initial expression sequence of primary unprorocessed transcripts (Identified by using qRT-PCR against introns or intron-exon boundaries). Nor in the initial acquisition by Hox gene DNA of a mark for active chromatin. These findings are in conflict with the idea that temporal collinearity has to do with the initiation of Hox gene transcription or with the opening of and a progression from repressed to active states in Hox chromatin. But collinear acquisition of the same active chromatin mark has been shown by others in murine 5’ Hoxd cluster genes.The reason for this difference is unknown . This careful study thus indicated that the initiation phase of Hox expression shows no temporal collinearity in X. tropicalis. A previous study in X. laevis from the same group also showed that the sequence of times for reaching (normalised) half maximal Hox expression showed no temporal collinearity. These conclusions are likely to be correct. These authors do however also conclude that “experimental evidence for the temporal collinearity hypothesis is not strong” There is however strong evidence that Hox temporal collinearity does occur in early vertebrate embryos. Below. I present and discuss 3 lines of evidence to resolve the present conflict I argue that Hox temporal collinearity actually does exist and that it is part of a central mechanism in early development.

With the increasing adoption of building integrated photovoltaics (BIPV), concerns arise about potential glare. While recommended criteria to assess glare exist, it is challenging to apply these in the spatial and temporal domains and communicate the complex data to planning authorities and clients. This paper presents a new computational workflow using annual daylight simulation, material modelling using bi-directional scattering distribution functions (BSDFs) and image-based postprocessing to obtain 3-dimensional renderings of cumulative annual irradiance and glare duration on the built environment. The annual daylight simulation considers relevant sun positions in high temporal resolution (15-minute timesteps) and measured BSDFs to model different PV materials. The postprocessing includes a relative irradiance visualisation comparing the impact of a proposed PV proportional to a reference material. It also includes a new spatio-temporal workflow to assess the glare duration based on recommended thresholds. This workflow is demonstrated with a case study of a proposed PV roof for a church, assessing the glare potential of two different PV materials. The visualisations indicate glare durations well below the thresholds with satinated PVs, and in noncritical zones outside observer positions with standard PVs. Thus the proposed PV roof does not cause any disturbing glare.

Multivariate Time Series Classification (MTSC) is one of most important tasks in time series analysis, aiding in activities such as human motion recognition and medical diagnostics. Existing methods for MTSC do not explicitly model temporal differences and generalize the idea of temporal difference into a efficient temporal module. Additionally, existing methods are not yet able to capture cross-variable relationships well during network training. As a result, they are unable to achieve convincing feature representation, leading to suboptimal classification accuracy. In this paper, we propose a novel MTSC model called Temporal Difference and Cross-variate Fusion Network (TDCFN), which integrates a two-stream differential LSTM network and a cross-variate feature extraction network to enhance feature representation. TDCFN achieves superior classification accuracy by capturing dynamic temporal evolution and inter-variable relationships. The experimental results show that TDCFN can achieve competitive performance with state-of-the-art multivariate time series classification approaches.

This study investigates the spatial and temporal distribution of litter at 7 beach sectors in Cadiz Bay, Southwest Spain. Two ten-day surveys carried out in autumn 2022 and spring 2023 revealed a total of 4,199 and 4,634 items, respectively, with plastic being the predominant material (71.13% in autumn, 88.39% in spring). Litter quantities varied significantly among beaches, La Puntilla showing the highest abundance with 0.48 ± 0.25 items m-1 in autumn and 1.34 ± 0.61 items m-1 in spring. The lowest abundance was recorded at sector 1 of Valdelagrana beach (0.08 ± 0.06 items m-1) during autumn and at El Castillito beach (0.08 ± 0.04 items m-1) during spring. Statistical analyses did not reveal significant differences in litter quantities between autumn and spring, however high significant interaction was shown considering both season and beach lo-cation. Seasonal differences were also observed in litter composition. Litter categories increased from 90 in autumn to 107 in spring. The top 10 litter categories varied between seasons and included cigarette butts, plastic fragments and plastic packaging. Cigarette butts were principally abundant in autumn because re-lated to summer beach users and wet wipes were particularly observed in spring because linked to wastewaters and river discharges especially relevant in winter months. Hydrodynamic and wind conditions were analyzed, revealing complex relationships with litter abundance.

As the globe becomes more urban, the question how much natural biodiversity can subsist in cities becomes increasingly urgent to answer, and also how is urban diversity structured? To contribute to an answer, we studied the metacommunity of bees in a North European metropolitan area. The system consisted of 13 sites in the city of Aarhus, Denmark, censused from April to September during one year. Bees were sampled monthly in pan traps and a set of traits was related to their presence. In total, 40 species were collected–29 solitary species (40% of all sampled individuals), ten Bombus species (28%), and Apis mellifera (32%). Most sampled bees were soil-nesting, pollen generalists, and relatively common. Habitat diversity within a set of concentric circles with trap as centre and radius from 50 m to 1000 m was related to bee a diversity per site (total bee spp. with and without honeybee, solitary bees, and bumblebees). The relationship was only significant within the 1,000 m circle, and solitary bee diversity did not even correlate with habitat diversity at this large spatial scale level. The bee-site (space) and bee-month (time) networks were analyzed with respect to nestedness, modularity, and spatio-temporal b diversity. The two networks were weakly nested and strongly modular, being composed of five and six modules of tightly linked bees. Total b diversity, b_TOTAL, is the sum of species turnover, b_TURN, and species loss/gain or nestedness, b_NEST; and for both space and time, b_TURN was more important than b_NEST. Furthermore, b_TOTAL was higher than season b_TOTAL. Thus, the urban bee metacommunity was well-structured in both space and time and the high b_TURN indicated, that the network was strongly modular. We suggest the main reason is the high spatio-temporal patchiness of habitats, sustaining many unique species.

The factors influencing hepatitis E virus (HEV) circulation remain largely unexplored. We investigated HEV seroprevalence in humans and the prevalence of infection in farm pigs and rabbits in different regions of the Russian Federation, as well as the genetic diversity and population dynamics of HEV. Anti-HEV IgG antibody detection rates in the general population increase significantly with age, from 1.5% in children and adolescents under 20 years old to 4.8% in adults aged between 20 and 59 years old, to 16.7% in people aged 60 years and older. HEV seroprevalence varies between regions, with the highest rate observed in Belgorod Region (16.4% compared with the national average of 4.6%), which also has the country’s highest pig population. When compared with the archival data, both increases and declines in HEV seroprevalence have been observed within the last 10 years, depending on the study region. Virus shedding has been detected in 19 out of the 21 pig farms surveyed. On one farm, circulation of the same viral strain for five years was documented. All human and animal strains belonged to the HEV-3 genotype, with its clade 2 sequences being predominant in pigs. Sequences from patients, pigs, and sewage from pig farms clustered together, suggesting a zoonotic infection in humans and possible environmental contamination. The HEV-3 population size predicted using SkyGrid reconstruction demonstrated exponential growth in the 1970s–1990s, with a subsequent decline followed by a short rise around the year 2010, the pattern being similar to the dynamics of the pig population in the country. The HEV-3 reproduction number (Re) predicted using Birth-Death Skyline analysis has fluctuated around 1 over the past 20 years in Russia, but is 10 times higher in Belgorod Region. In conclusion, HEV-3 circulation varies both geographically and temporally, even within a single country. The possible factors contributing to this variability are largely related to the circulation of the virus among farm pigs.

Achieving eco-efficiency in agriculture production at low environmental costs is key to sustainable agriculture. Using the DEA-SBM model, this study evaluated the agricultural eco-efficiency of the 77 counties and districts in China’s Jiangsu province from 1999 to 2018 and analyzed its spatio-temporal evolution pattern and influencing factors. The mains conclusions were as follows: (1) The overall agricultural eco-efficiency and its decomposition terms, pure technology efficiency and scale efficiency, exhibited a fluctuating downward trend. The regional inequality in agricultural eco-efficiency had been widening and exhibited a strong positive spatial association. (2) The agricultural eco-efficiency in Jiangsu province presented a “high south and low north” spatial pattern. High-level agricultural eco-efficiency areas were in the Taihu Plain in Sunan, while low-level agricultural eco-efficiency zones are distributed across Subei City. The High-High-type spatial association pattern is concentrated in the Suzhou-Wuxi-Changzhou region, while the Low-Low areas are mainly in the coastal regions of Subei and Suzhong. (3) The spatial pattern of PTE and SE generally exhibited a “high south and low north” distribution. Areas with positive growth in agricultural eco-efficiency, PTE, and SE, were situated in Xuzhou, Nanjing city, and the bordering regions between Yangzhou and Huai’an, and Changzhou and Wuxi. (4) The excessive redundant use and application of pesticides, chemical fertilizer, agricultural diesel, labor, land, and agricultural carbon emission have been the primary factor affecting Jiangsu's agricultural eco-efficiency. Irrigation had also signficantly impacted agricultural eco-efficiency, while mechanical power and agricultural film had minimal effect. The majority of counties and districts in Subei, Suzhong, and Ningzhen Yang Hilly region have issues regarding their excessive usage of chemical fertilizer, pesticide, chemical fertilizer, agricultural diesel, labor, and land. The findings of this study can contribute towards a better understanding of agricultural eco-efficiency and spatial association effect and can help policymakers increase agricultural eco-efficiency.

Long-term, high-accuracy mapping of built-up land dynamics is essential for understanding urbanization and its consequences for the environment. Despite advances in remote sensing and classification algorithms, built-up land mapping using early satellite imagery (e.g., from the 2000s and earlier) remains prone to uncertainty. We mapped the extent of built-up land in the North China Plain, one of China’s most important agricultural regions, from 1990 to 2019 at three-year intervals. Using dense time-stack Landsat data, we applied discrete Fourier transformation to create temporal predictors and reduce mapping uncertainties for early years. We improved overall accuracy by 8% compared to using spectral and indices predictors alone. We implemented a temporal correction algorithm to remove inconsistent pixel classifications, further improving accuracy to a consistently high level (>94%) across years. A cross-product comparison showed that our study achieved the highest levels of accuracy across years. Total built-up land in the North China Plain increased from 37,941 km² in 1990–1992 to 131,578 km² in 2017–2019. Consistent, high-accuracy built-up land mapping provides a reliable basis for policy planning in one of the most rapidly urbanizing regions of the planet.

In recent years, graph neural networks (GNNs) have become a promising method for analyzing data structured in graph format. By considering connections between entities in a graph, GNNs are able to extract valuable insights. One notable variation of GNN is the graph attention network (GAT), which employs the attention mechanism and has demonstrated promising performance in various applications. However, its ability to incorporate feature information from nodes beyond the immediate neighborhood is limited, leading to degraded performance on heterophilic data. To address this limitation, this thesis proposes a novel attention-based model, namely the Directional Graph Attention Network (DGAT). This model combines the feature-based attention with the global directional information extracted from the graph topology, as inspired by the Directional Graph Network (DGN). A new class of Laplacian matrices is proposed and an existing theoretical result on DGN is extended. This extension bridges a gap in the literature. The experimental results presented in the thesis, based on nine real-world benchmarks and ten synthetic data sets, demonstrate the superiority of the proposed DGAT model compared to the GAT baseline model. Particularly on heterophilic data sets, DGAT showed a notable average increase of approximately 35% in node classification tasks across all heterophilic real-world data sets. In addition, DGAT outperforms GAT by an average margin of around 51% in all ten synthetic data sets with various levels of heterophily

We explored the statistics of filtering of simple patterns on a number of deterministic and random graphs as a tractable simple example of information processing in complex systems. In this problem, multiple inputs map to the same output, and the statistics of filtering is represented by the distribution of this degeneracy. For a few simple filter patterns on a ring we obtained an exact solution of the problem and described numerically more difficult filter setups. For each of the filter patterns and networks we found a few numbers essentially describing the statistics of filtering and compared them for different networks. Our results for networks with diverse architectures appear to be essentially determined by two factors: whether the graphs structure is deterministic or random, and the vertex degree. We find that filtering in random graphs produces a much richer statistics than in deterministic graphs. This statistical richness is reduced by increasing the graph’s degree.

This work has its origin in intuitive physical and statistical considerations. The problem of optimizing an artificial neural network is treated as a physical system, composed of a conservative vector force field. The derived scalar potential is a measure of the potential energy of the network, a function of the distance between predictions and targets. Starting from some analogies with wave mechanics, the description of the sys-tem is justified with an eigenvalue equation that is a variant of the Schr˜odinger equation, in which the potential is defined by the mutual information between inputs and targets. The weights and parameters of the network, as well as those of the state function, are varied so as to minimize energy, using an equivalent of the variational theorem of wave mechanics. The minimum energy thus obtained implies the principle of minimum mutual information (MinMI). We also propose a definition of the potential work produced by the force field to bring a network from an arbitrary probability distribution to the potential-constrained system, which allows to establish a measure of the complexity of the system. At the end of the discussion we expose a recursive procedure that allows to refine the state function and bypass some initial assumptions, as well as a discussion of some topics in quantum mechanics applied to the formalism, such as the uncertainty principle and the temporal evolution of the system. Results demonstrate how the minimization of energy effectively leads to a decrease in the average error between network predictions and targets.

The recent COVID-19 pandemic has showcased the implications of using virtual private networks (VPNs) as home-working is now common. Establishing the current state of knowledge on VPNs and their processes is vital. This corroborates an up to date understanding on the fundamentals of VPNs and their usage in today’s society; it informs on how to better use VPNs too. Insight into the security issues VPNs face and possible solutions to these allows for the identification of gaps for potential future research. Addressing these gaps would then indicate how to further improve VPNs, making sure VPNs are indeed beneficial to users.

The phenomenon of dissipative self-organization is studied on the example of time-crystal networks. Particular attention was given to transient processes, attractor topologies, phase transitions, and asymptotic stability. New concepts were introduced, including topological phases, spinorial states, and bond flavors. Concepts such as ground states, chemical potentials, elastic forces, temperature, and statistical distributions were endowed with a new meaning associated with asymptotic stability. Phenomena usually attributed exclusively to quantum physics have been shown to occur in this essentially classical environment. They coexist with, and in some cases, such as charge quantization, are related to the phenomenon of time dilation. The approach was applied to model vacuum self-organization. We have shown that under the ac-tion of competing forces, such as gravity and antigravity, a cascade of phase transitions can transform an unorganized vacuum into phases in which interactions, fields and waves resemble electromagnetic, weak, and strong, and their elements can be used as building blocks for prototype particles. In addition, some interrelation field parameters and probabilities of particle transmutations were calculated, which are not predicted by the standard model. The results are consistent with the experiment. The presented material and methodology may be of interest for studying self-organization in different environments.

Over the past decade, research in the field of Deep Learning has brought about novel improvements in image generation and feature learning; one such example being a Generative Adversarial Network. However, these improvements have been coupled with an increasing demand on mathematical literacy and previous knowledge in the field. Therefore, in this literature review, I seek to introduce Generative Adversarial Networks (GANs) to a broader audience by explaining their background and intuition at a more foundational level. I begin by discussing the mathematical background of this architecture, specifically topics in linear algebra and probability theory. I then proceed to introduce GANs in a more theoretical framework, along with some of the literature on GANs, including their architectural improvements and image-generation capabilities. Finally, I cover state-of-the-art image generation through style-based methods, as well as their implications on society.

Background: The circadian system, a vital temporal regulator influencing physiological processes, has implications for cancer development and treatment response. Our study assesses circadian timing's impact on whole-brain radiotherapy outcomes in brain metastases for personalized cancer therapy insights. Aim: Evaluate circadian influence on radiation treatment timing and its correlation with clinical outcomes. Identify patient populations benefiting from interventions synchronizing circadian rhythms, considering subgroup differences and potential disparities related to social determinants of health (SDoH). Design: IRB-approved retrospective analysis of 237 patients undergoing whole-brain radiotherapy for brain metastases (2017–2021), receiving over 80% of treatments in the morning or afternoon. Survival analyses utilized Kaplan–Meier curves. Setting/Participants: Single-institution study involving patients receiving whole-brain radiotherapy. Collected demographic, disease, and socioeconomic parameters from electronic medical records. Results: Morning treatment (n=158) showed a trend towards improved overall survival vs. afternoon (n=79), median survival 158 vs. 79 days (p=0.20, HR=0.84, CI95% 0.84–0.91). Subgroup benefits for morning treatment in females (p=0.04) and trends in controlled primary disease (p=0.11) and breast cancer metastases (p=0.08). SDoH-based disparities observed, with Black and lower-income patients exhibiting diminished circadian influence. Conclusions: Emphasizes chronobiological factors' relevance in brain metastases radiation therapy. Morning treatment correlates with improved survival, particularly in specific subgroups. Identifies potential circadian influence disparities based on SDoH, laying a foundation for personalized cancer therapy and interventions synchronizing circadian rhythms for enhanced treatment efficacy.

Understanding the spatiotemporal characteristics of merging behavior is crucial for the ad-vancement of autonomous driving technology. This study aims to analyze on-ramp vehicle merg-ing patterns, and investigate how various factors, such as merging scenarios and vehicle types, in-fluence driving behavior. Initially, a framework based on High-Definition (HD) Map is devel-oped to extract trajectory information in a meticulous manner. Subsequently, eight distinct merg-ing patterns (Pattern A to H) are identified, with a thorough examination of their behavioral characteristics from both temporal and spatial perspectives. Merging behaviors are examined temporally, encompassing the sequence of events from approaching the on-ramp to completing the merge. This study specifically analyzes the target lane's spatial characteristics, evaluates the merging distance (ratio), investigates merging speed distributions, compares merging patterns and identifying high-risk situations. Our novel findings reveal that Patterns C and F, with Time-to-Collision (TTC) values less than 2.5 seconds, pose a significantly higher risk than other patterns. In traffic simulations, Patterns B and E can be integrated, as they show negligible differences in speed, distance traveled, and duration. Additionally, the practice of truck platooning has a signif-icant impact on vehicle merging behavior. This study enhances the understanding of merging be-havior, facilitating autonomous vehicles' ability to comprehend and adapt to merging scenarios. Furthermore, this research is significant in improving driving safety, optimizing traffic manage-ment, and enabling the effective integration of autonomous driving systems with human drivers.