Graph Neural Networks (GNNs) are powerful models capable of managing intricate connections in non-Euclidean data, such as social networks, physical systems, chemical structures, and communication networks. Despite their effectiveness, the large-scale and complex nature of graph data demands substantial computational resources and high performance during both training and inference stages, presenting significant challenges, particularly in the context of embedded systems. Recent studies on GNNs have investigated both software and hardware solutions to enhance computational efficiency. Earlier studies on Deep Neural Networks (DNNs) have indicated that methods like reconfigurable hardware and quantization are beneficial in addressing these issues. Unlike DNN research, studies on efficient computational methods for GNNs are less developed and require more exploration. This survey reviews the latest developments in quantization and FPGA-based acceleration for GNNs, showcasing the capabilities of reconfigurable systems (often FPGAs) to offer customized solutions in environments marked by significant sparsity and the necessity for dynamic load management. It also emphasizes the role of quantization in reducing both computational and memory demands through the use of fixed-point arithmetic and streamlined vector formats. This paper concentrates on low-power, resource-limited devices over general hardware accelerators and reviews research applicable to embedded systems. Additionally, it provides a detailed discussion of potential research gaps, foundational knowledge, obstacles, and prospective future directions.

Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces. Transfer learning has proven extremely successful for traditional deep learning problems: resulting in faster training and improved performance. Despite the increasing interest in GNNs and their use cases, there is little research on their transferability. This research demonstrates that transfer learning is effective with GNNs, and describes how source tasks and the choice of GNN impact the ability to learn generalisable knowledge. We perform experiments using real-world and synthetic data within the contexts of node classification and graph classification. To this end, we also provide a general methodology for transfer learning experimentation and present a novel algorithm for generating synthetic graph classification tasks. We compare the performance of GCN, GraphSAGE and GIN across both the synthetic and real-world datasets. Our results demonstrate empirically that GNNs with inductive operations yield statistically significantly improved transfer. Further we show that similarity in community structure between source and target tasks support statistically significant improvements in transfer over and above the use of only the node attributes.

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 report gives a comprehensive summary of two problems about graph convolutional networks (GCNs): over-smoothing and heterophily challenges, and outlines future directions to explore.

Finite element discretizations of problems in computational physics often rely on hand-generated initial mesh and adaptive mesh refinement (AMR) to preferentially resolve regions containing important features during simulation. We propose Adaptnet, a Graph Neural Networks (GNNs) framework for learning mesh generation and adaptation. The model is composed of two GNNs: the first one, Meshnet, learns mesh parameters commonly used in open-source mesh generators, to generate an initial mesh from a Computer Aid Design (CAD) file; while the second one, Graphnet, learns mesh-based simulations to predict the components of an Hessian-based metric to perform anisotropic mesh adaptation. Our approach is tested on structural (Deforming plate - Linear elasticity) and fluid mechanics (Flow around cylinders - steady-state Stokes) problems. Our results show it can accurately predict the dynamics of the system and adapt the mesh accordingly. The adaptivity of the model supports learning resolution-independent dynamics and can scale to more complex state spaces at test time.

The accurate prediction of molecular properties such as lipophilicity and aqueous solubility are of great importance and pose challenges in several stages of the drug discovery pipeline. Machine learning methods like graph-based neural networks (GNNs) have shown exceptionally good performance in predicting these properties. In this work, we introduce a novel GNN architecture, called directed edge graph isomorphism network (D-GIN). It is composed of two distinct sub-architectures (D-MPNN, GIN) and achieves an improvement in accuracy over its sub-architectures employing various learning, and featurization strategies. We argue that combining models with different key aspects help make graph neural networks deeper and simultaneously increase their predictive power. Furthermore, we address current limitations in assessment of deep-learning models, namely, comparison of single training run performance metrics, and offer a more robust solution.

Identifying fake news on the media has been an important issue. This is especially true considering the wide spread of rumors on the popular social networks such as Twitter. Various kinds of techniques have been proposed for automatic rumor detection. In this work, we study the application of graph neural networks for rumor classification at a lower level, instead of applying existing neural network architectures to detect rumors. The responses to true rumors and false rumors display distinct characteristics. This suggests that it is essential to capture such interactions in an effective manner for a deep learning network to achieve better rumor detection performance. To this end we present a simplified aggregation graph neural network architecture. Experiments on publicly available Twitter datasets demonstrate that the proposed network has performance on a par with or even better than that of state-of-the-art graph convolutional networks, while significantly reducing the computational complexity.

Next-generation cancer and oncology research needs to take full advantage of the multi-modal structured, or graph, information, with the graph datatypes ranging from molecular structures to spatially resolved imaging and digital pathology to biological networks to knowledge graphs. Graph Neural Networks (GNNs) efficiently combine the graph structure representations with the high predictive performance of deep learning, especially on the large multi-modal datasets. In this review article, we survey the landscape of recent (2020-present) GNN applications in the context of cancer and oncology research, and delineate six currently predominant research areas. Subsequently, we identify the most promising directions for future research. We compare GNNs with graphical models and "non-structured" deep learning, and devise the guidelines for cancer and oncology researchers or physician-scientists asking the question of whether they should adopt the GNN methodology in their research pipelines.

This paper investigates the use of Physics-Informed Neural Networks (PINNs) in active learning cycles. We defined two scenarios: one semi-supervised and the other fully supervised. PINNs emphasize the integration of physical laws into neural networks to improve the predictive performance of vanilla neural networks and to enhance the efficiency of traditional methods for solving partial differential equations (PDEs). Key contributions include adapting existing computational frameworks to enable the use of Graph Neural Networks for solving problems that require the calculation of gradients on unstructured triangle meshes, a query strategy focusing on the physical loss, and a comparative analysis of this strategy against random sampling across both defined scenarios. This work establishes a foundation for future research aimed at expanding the application of Physics-Informed Graph Neural Networks (PIGNN) using active learning and addressing real-world problems in fluid dynamics and electrodynamics.

This paper presents the use of Graph Neural Networks (GNNs) to predict the tensile strength of Fused Deposition Modeling (FDM) specimens. In the present work, there are four main input parameters i.e. Infill percentage, Layer height, Print speed and Extrusion temperature while the Tensile Strength is an output parameter were considered. This study includes use of central composite design based response surface methodology to finalize the experimental layout. 3D printed specimen were manufactured as per the ASTM E8 standard on FDM printer using Polylactic Acid (PLA) as filament. Micro-tensile test were performed on the printed specimen as per ASTM E8 standard. The GNN algorithm was trained on a dataset of FDM specimens, achieving a mean squared error (MSE) of 2.47, mean absolute error (MAE) of 1.14, and R-squared value of 0.78. An adjacency matrix, which shows the connections between nodes in a graph. The obtained plot for nodes and weights in a GNN provide valuable information about the model and its performance. The results show the potential of using GNNs in predicting the mechanical properties of additively manufactured specimens and provide a promising direction for further research in this field.

Recommender systems as an effective information filtering system can be used to obtain information through the user's explicit or implicit behavior. On the one hand finding items that may be of interest to the user. On the other hand, the recommendation facilitates the interaction between the user and the item to increase the revenue. Recommender systems have been widely used in various fields, such as e-commerce, travel recommendation, online books and movies, social networks, etc, which can satisfy the intrinsic implicit needs of users through personalized services. In recent years, the development of deep learning has further improved the performance of recommendation systems. Although these methods improve the performance of the recommendation system, when the number of users and products increases, the recommendation system may face sparsity and cold start problems, and thus cannot achieve personalized recommendations. Knowledge graphs, which are structured data, have become the choice of many algorithms due to the high quality and wide scale of the data, and therefore many recommendation algorithms combined with knowledge graphs have emerged as a popular new direction in recommendation systems. These algorithms are able to preserve the rich connections between different entities. Moreover, when constructing the features of an entity, the entities that are far away from the central entity can also be utilized. Entities are no longer only directly connected to each other. To address the shortcomings of existing recommendation algorithms, this paper designs the recommendation algorithm GPRE using graph neural networks. GPRE focuses on expressing the user's features. The graph neural network provides GPRE with a strong generalization capability for modeling, which can provide long-range semantics between users and entities, as well as selective entity selection in the auxiliary graph neural network. Explicit semantic links are established between remote and central nodes to reduce the introduction of noise. In this paper, experiments are conducted on real-world datasets and the results are compared with baselines. The experimental results show that GPRE performs well on the experimental dataset.

Refractoriness to antiseizure medications is still a major concern in the pharmacotherapy of epilepsy. For this reason, we decided to evaluate the combination of levetiracetam and cannabidiol, administered at a subthreshold dose, to limit the possible adverse effects of this phytocannabinoid. We administered levetiracetam (300 mg/kg/day, via osmotic minipumps), cannabidiol (120 mg/kg/day, injected once a day subcutaneously), or their combination for one week in epileptic rats. Saline-treated epileptic rats were the control group. Animals were monitored with video electroencephalography the week before and after the treatment. No changes were found in the controls. Levetiracetam did not significantly reduce the total seizure number or the overall seizure duration. Still, the overall number of seizures (p<0.001, Duncan’s new multiple range test) and their total duration (p<0.01) increased in the week following treatment withdrawal. Cannabidiol did not change seizures when administered as a single drug. Instead, levetiracetam combined with cannabidiol resulted in a significant reduction in the overall number and duration of seizures (p<0.05), when comparing values measured during treatment with both pre- and post-treatment values. These findings depended on changes in convulsive seizures, while non-convulsive seizures were stable. These results suggest cannabidiol determined a remarkable potentiation of levetiracetam antiseizure effects at a subthreshold dose.

The paper illustrates a general framework in which a neural network application can be easily integrated and proposes a traffic forecasting approach that uses neural networks based on graphs. The method minimizes the communication network (between vehicles and the database servers) load and represents a reasonable trade-off between communication network load and forecasting accuracy. Traffic prediction leads to the choice of less congested routes and therefore to the reduction of energy consumption. The traffic is forecasting using a LTSM neural network with a regression layer. The inputs of the neural network are sequences - obtained from graph that represent the road network - at specific moments of time that are read from traffic sensors or the outputs of neural network (forecasting sequences). The input sequences can be filtered to improve the forecasting accuracy. This general framework is based on Contiki IoT operating system that ensure support for wireless communication and efficient implementation of processes in a resource constrained system and it is particularized to implement a graph neural network. Two cases are studied: one case in which the traffic sensors are periodically read and the other case in which the traffic sensors are read when their values changes are detected. A comparison between the cases is made and the influence of filtering is evaluated. The obtained accuracy is very good, very close to the accuracy obtained in infinite precision simulation, and the computation time is low enough and the system can work in real time.

In this paper, we present a groundbreaking methodology in the realm of aspect-level sentiment analysis, which capitalizes on the advanced capabilities of graph-based neural networks. Our approach, distinguished as the Aspect Correlation Graph Network (ACGN), represents a significant departure from conventional models. These traditional models often analyze aspects in isolation, failing to capture the intricate web of sentiment relationships that may exist within a single sentence. ACGN, however, is designed to address this gap by employing a sophisticated bidirectional attention mechanism, integrated with positional encoding. This unique combination not only enhances the model's ability to focus on relevant parts of the sentence but also aids in constructing detailed, aspect-focused representations. These representations are particularly crucial for understanding the nuanced interplay of sentiments associated with different aspects. Central to our model's architecture is the incorporation of a graph convolutional network. This network serves as a pivotal component in mapping and analyzing the complex network of sentiment correlations that can exist among various aspects within sentences. Through this integration, ACGN is able to unearth and interpret the subtle and often overlooked sentiment dynamics that traditional models might miss. Our comprehensive evaluations of the Aspect Correlation Graph Network, conducted using the SemEval 2014 datasets, have yielded promising results. These findings demonstrate a clear and significant advancement over the capabilities of existing models. Particularly, the results underscore the critical importance and utility of recognizing and understanding the connections between sentiments of different aspects in text analysis. This insight opens new avenues in the field of sentiment analysis, suggesting a broader application potential of ACGN in various contexts where understanding nuanced sentiment relationships is key. Overall, our study not only introduces a novel approach in aspect-level sentiment analysis but also sets a new standard for future research in this area. By highlighting the integral role of inter-aspect sentiment connections, ACGN paves the way for more sophisticated and accurate sentiment analysis tools, capable of handling the complexities of natural language with greater finesse and precision.

Sign Language Recognition (SLR) aims to bridge speech-impaired and general communities by recognizing signs from given videos. Researchers still face challenges developing efficient SLR systems because of the video’s complex background, light illumination, and subject structures. Recently many researchers developed a skeleton-based sign language recognition system to overcome the subject and background variation of hand gesture signs. However, skeleton-based SLR is still under exploration due to the lack of information and annotations on hand key points. More recently, researchers included body and face information with the hand gesture for the SLR, but their performance and efficiency are unsatisfactory. We proposed a Multi-Stream Graph-based Deep Neural Network (SL-GDN) for a skeleton-based SLR system to overcome the problems. The main purpose of the proposed SL-GDN approach is to improve the efficiency and performance of the SLR system with a low computational cost based on the human body pose in the form of 2D landmark locations. In the procedure, firstly, we constructed a skeleton graph based on the selected 27 whole-body key points among 67 key points to solve the inefficiency problems. Then we proposed multi-stream SL-GDN to extract features from the whole-body skeleton graph for four streams. Finally, we concatenated the four different features and applied a classification module to refine the feature and recognize corresponding sign classes. Our data-driven and graph construction method increases the system’s flexibility and brings high generability to adapt various data samples. We used three large-scale benchmark SLR datasets to evaluate the proposed model: WLASL, AUTSL and CSL. The demonstrated performance accuracy table proved the superiority of the proposed model, and we believe this will be considered a great invention in the SLR domain.

In considering knowledge graphs in a diverse range of domains of interest, graph neural networks have demonstrated significant improvements in node classification and prediction when applied to graph representation with learning node embedding to effectively represent hierarchical properties of graphs. DiffPool is a deep-learning approach using a differentiable graph pooling technique that generates hierarchical representations of graphs. In operation DiffPool is a differentiable graph pooling technique that generates hierarchical representations of graphs. DiffPool learns a differentiable soft cluster assignment for nodes at each layer of a deep graph neural network with nodes mapped sets of clusters. However, control of the learning process is difficult given the complexity and large number of parameters on an `end-to-end’ model. To address this difficulty we propose an novel approach termed FPool which is predicated on the basic approach adopted in DiffPool (where pooling is applied directly to node representations). Methods designed to enhance data classification have been developed and evaluated using a number popular and publicly available sensor data sets. Experimental results for FPool demonstrate improved classification and prediction performance when compared to alternative methods. Moreover, FPool shows an important reduction in the training time over the basic DiffPool framework.

In this research, we present a comprehensive methodology to categorize perfumes based on their fragrance profiles and subsequently aid in creating innovative odoriferous molecules using advanced neural networks. Drawing from data on Parfumo and the Good Scents Company webpage (Parfumo, 2008; The Good Scents Company, 2021), the study employs sophisticated web scraping techniques to gather diverse perfume attributes. Following this, a k-means algorithm is applied for perfume clustering, paving the way for recommending similar scents to consumers. The process then bridges customer preferences to molecular design by incorporating their feedback into generating new molecules via graph neural networks (GNNs). Through converting the Simple Molecular Input Line Entry System (SMILES) representation into graph structures, the GNN facilitates the creation of new molecular designs attuned to consumer desires. The proposed approach offers promising avenues for consumers to pinpoint similar perfume choices, incorporating feedback, and for manufacturers to conceptualize new fragrant molecules with a high likelihood of market resonance.

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

In the rapidly evolving field of real estate economics, the prediction of house prices continues to be a complex challenge, intricately tied to a multitude of socio-economic factors. However, traditional predictive models have often overlooked the spatial interdependencies that play a vital role in shaping housing prices. This study applies Graph Neural Networks (GNNs) on Open Statistics Knowledge Graphs to model spatial dependencies and predict house prices across Scotland’s 2011 data zones. To this end, integrated statistical indicators are retrieved from the official Scottish Open Government Data portal. The three representative GNN algorithms employed - ChebNet, GCN, and GraphSAGE - demonstrate higher prediction accuracy than traditional models, including the tabular-based XGBoost and a simple Multi-Layer Perceptron (MLP). In addition, local and global explainability are employed to increase transparency and trust in the predictions made by the most accurate GNN - GraphSAGE. The global feature importance is determined by a logistic regression surrogate model while the local, region-level understanding of the GNN predictions is achieved through the use of GNNExplainer. Explainaibility results are compared with those from a previous work that applied the XGBoost machine learning algorithm and the SHapley Additive exPlanations (SHAP) explainability framework on the same dataset. Interestingly, both global surrogate model and the SHAP approach underscored the Comparative Illness Factor, a health indicator, and the ratio of detached dwellings as the most crucial features in the global explainability. In the case of local explanations, while both methods showed similar results, the GNN approach provided a richer, more comprehensive understanding of the predictions for two specific data zones.

Selecting road networks in cartographic generalization has consistently posed formidable challenges, driving research towards the application of intelligent models. Despite previous efforts, the accuracy and connectivity preservation in these studies, particularly when dealing with road types of similar sample sizes, still warrant improvement. To address these shortcomings, we introduce a Heterogeneous Graph Attention Network (HAN) for road selection, where feature masking method is initially utilized to assess the significance of road features. Concentrating on the most relevant features, two meta-paths are introduced within the HAN framework: one for aggregating features of the same road type within the first-order neighborhood, emphasizing local connectivity, and another extending this aggregation to the second-order neighborhood, capturing a broader spatial context. For a comprehensive evaluation, we introduce a set of metrics considering both quantitative and qualitative aspects of the road network. Compared to traditional neural networks, our HAN model demonstrates superior accuracy and F1-score, particularly for road types with comparable samples. Additionally, it enhances the overall connectivity of the selected network. In summary, our HAN-based method provides an advanced solution for road network selection, surpassing previous approaches in terms of accuracy and connectivity preservation.

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.

: Biological networks such as protein interaction networks, gene regulation networks and metabolic pathways are examples of complex networks which are large graphs with small-world and scale-free properties. Analysis of these networks has a profound effect on our understanding the origins of life, health and disease states of organisms, and diagnose diseases to aid the search for remedial processes. In this review, we describe main analysis methods of biological networks using graph theory by first defining main parameters such as clustering coefficient, modularity and centrality. We then survey fundamental graph clustering methods and algorithms followed by the network motif search algorithms with the aim of finding repeating subgraphs in a biological network graph. A frequently appearing subgraph usually conveys a basic function carried out by that small network and discovering such a function provides an insight to the overall function of the organism. Lastly, we review network alignment algorithms that achieve to find similarities between two or more graphs representing biological networks. A conserved subgraph between the biological networks of organisms may mean a common ancestor and finding such relationship may help researchers derive ancestral relationships and predict the future evolution of organisms to enable designing new drugs. We conclude by the current challenging areas of biological network analysis using graph theory and parallel processing for high performance analysis

This paper investigates the integration of Graph Neural Networks (GNNs) and incremental learning for blockchain applications, with a focus on fraud detection, anomaly detection, and smart contract verification. By leveraging graph structure exploitation, GNNs can propagate information across nodes, reducing label dependency. Incremental learning enhances the model's adaptability to evolving blockchain networks, allowing continual learning without full retraining. Together, these technologies provide a scalable, efficient solution for improving security, performance, and adaptability in decentralized financial systems and smart contract environments.

The discovery of the quantum tunnelling effect---the transmission of particles through a high potential barrier---was one of the most impressive achievements of quantum mechanics made in the 1920s. Responding to the contemporary challenges, I introduce a novel deep neural network (DNN) architecture that processes information using the effect of quantum tunnelling. I demonstrate the ability of the quantum tunnelling DNN (QT-DNN) to recognise optical illusions like a human. Hardware implementation of QT-DNN is expected to result in an inexpensive and energy-efficient neuromorphic chip suitable for applications in autonomous vehicles. The optical illusions recognition tests developed in this paper should lay foundations for cognitive benchmarking tasks for AI systems of the future, benefiting the fields of sociophysics and behavioural science.

This paper explores innovative approaches to determining eigenvalues and eigenvectors through the combination of neural networks and traditional numerical methods. Traditional methods like the Newton-Raphson and Durand-Kerner algorithms are proven effective but often require good initial approximations and can be sensitive to the choice of starting points. In this study, we propose a hybrid approach that uses neural networks to generate better initial approximations, which are then iteratively refined using traditional methods. By combining the pattern recognition power of neural networks with the adaptability of traditional numerical methods, we demonstrate faster convergence and higher accuracy in determining eigenvalues and eigenvectors. Experimental results on various polynomials of different degrees and characteristics show that our hybrid approach outperforms individual methods, providing a more robust and efficient solution.

Nowadays, inquiries are one of the most important tasks to be executed in order to get valued information. When an inquiry is done to gather information about a human behavior there are some problems inherent to it. One of the main problems is how the information about many different persons can be processed to give good information about their environment. Most of the information gathered by these inquiries is used to analyze the behavior of the respondents. It can be used to estimate the success of a certain product on the market or just to validate the satisfaction of current costumers. The veracity of this information can be critical to model environments with some acceptable level of precision. Modelling environments through Artificial Neural Networks (ANN) is highly common because ANN’s are excellent to model predictable environments using a set of data. ANN’s are good in deal with sets of data with some noise, but they are fundamentally surjective mathematical functions and they aren’t able to give different results for the same input. So if an ANN is trained using data where the same input has different images which can be the case of survey data, this can be a problem for the success of modelling the environment. Therefore is necessary to process the data in order to adjust and eliminate invalid data.

Hyperspectral small target detection (HSTD) is a promising pixel-level detection task. However, due to the low contrast and imbalance number between the target and background spatially and high dimensions spectrally, it is a challenging one. To address these issues, this work proposes a representation learning-based graph and generative network for hyperspectral small target detection. The model builds a fusion network through frequency representation for HSTD, where the novel architecture incorporates irregular topological data and the spatial-spectral feature to improve its representation ability. Firstly, a graph convolutional network (GCN) module better models the non-local topological relationship between samples to represent the hyperspectral scene’s underlying data structure. The mini-batch-training pattern of the GCN decreases the high computational cost of building an adjacency matrix for high-dimensional data sets. In parallel, the generative model enhances the differentiation reconstruction and the deep feature representation ability with respect to the target spectral signature. Finally, a fusion module compensates for the extracted different types of HS features and integrates their complementary merits for hyperspectral data interpretation while increasing detection and background suppression capabilities. Experiments on different hyperspectral data sets demonstrate the advantages of the proposed architecture.

As modern systems are becoming more complex their control strategy cannot longer relay only on measurement information that usually comes from probes but also from mathematical models. Those systems models can lead to unbearable computation times due to their own complexity, turning the control process non-viable, which leads to the implementation of surrogate models that enable to achieve estimates within acceptable time to take decisions. A control trained with Deep Reinforcement Learning algorithm, using a Physics-Informed Neural Network to obtain the temperature map on the following time step, replaces the need of running Direct Numerical Simulations. On this work we considered an 1D heat conduction problem, which temperature distribution feeds a control system to activate a heat source aiming to obtain a constant, previously defined, temperature value. With this approach, control training becomes much faster without the need of performing numerical simulations or laboratory measurements, as well the control is taken based on Neural Network enabling its implementation on simple processors to edge computing.

Deep convolutional neural networks (CNNs) have revolutionised computer vision technology by automatically learning hierarchical representations of image data, leading to state-of-the-art performance in visual recognition tasks. This article presents a comprehensive review of deep CNNs, from their evolution and architectures to the current state-of-the-art research. The review also provides the core concepts and building blocks of CNNs and their concise mathematical representations. Furthermore, it explores applications of deep CNNs in three popular domains, including medical diagnosis, remote sensing, and facial recognition. This review will benefit researchers and practitioners in computer vision and artificial intelligence, as well as industry professionals seeking to leverage the latest advancements in deep learning technologies.

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.

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.

In this paper we study a class of impulsive delayed neural networks with parameter uncertainties and reaction-diffusion terms. Using the properties of M-matrices and some inequality techniques, some sufficient conditions are derived to guarantee the global exponential stability of the given system. The results obtained are presented by simple algebraic inequalities, which are certainly more concise than previous methods. Finally, the validity and usefulness of our results are illustrated by arithmetic examples.

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.

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.

There are various modeling techniques adopted for predicting the labor productivity that incorporate the influence of various factors, but neural networks are found to have strong pattern recognition and higher accuracy to get reliable estimates. To develop a construction labor productivity (CLP) model for concreting activities, data were collected through a questionnaire. The most critical influencing parameters were ranked according to their relative importance index (RII). Then the strength of the relationship between CLP and influencing parameters was analyzed using correlation coefficient results generated in Python program. Finally, the CLP model which represents the output of the crew within a certain factor was successfully developed using artificial neural networks (ANNs). Five objectives and six subjective critical influencing parameters were selected using RII. Crew experience, age of workers, and placement technique are the top three influencing parameters that have a strong relation with CLP with correlation coefficient values of 0.5681, 0.5349, and 0.5227 respectively. The developed model within these influencing parameters has a higher capability to predict the output of labor with a 92% coefficient of determination (R2) and a mean squared error of 0.316%. Therefore, the application of such a model for the accurate estimation of labor productivity is recommended.

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.

This paper presents an enhanced Fully Connected Neural Network (FCNN) framework that incorporates manifold learning and Renormalization Group (RG) methods. By integrating Christoffel symbols, the model adapts to the curvature and topology of the data manifold, improving learning from geometrically complex data. Additionally, RG methods enable effective multi-scale data processing. We demonstrate the enhanced model’s performance on synthetic and real-world datasets, showing improved accuracy compared to standard FCNNs, particularly in complex systems simulation.

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.

Traditional computer vision techniques aim to extract meaningful information from images but often depend on manual feature engineering, making it difficult to handle complex real-world scenarios. Fractional Calculus (FC), which extends derivatives to non-integer orders, provides a flexible way to model systems with memory effects and long-term dependencies, making it a powerful tool for capturing fractional rates of variation. Recently, Neural Networks (NNs) have demonstrated remarkable capabilities in learning complex patterns directly from raw data, automating computer vision tasks and enhancing performance. Therefore, the use of fractional calculus in neural network-based computer vision is a powerful method to address existing challenges by effectively capturing complex spatial and temporal relationships in images and videos. This paper presents a survey of Fractional Calculus Neural Network-based (FC NN-based) computer vision techniques for denoising, enhancement, object detection, segmentation, restoration, and NN compression. The survey compiles existing FFC NN-based approaches, elucidates underlying concepts, and identifies open questions and research directions. By leveraging FC's properties, FC NN-based approaches offer a novel way to improve the robustness and efficiency of computer vision systems.

In this study, a novel method is proposed to estimate surface-spectral reflectance from camera responses that combines model-based and training-based approaches. An imaging system is modeled using the spectral sensitivity functions of an RGB camera, spectral power distributions of multiple light sources, unknown surface-spectral reflectance, additive noise, and a gain parameter. The estimation procedure comprises two main stages: (1) selecting the local optimal reflectance dataset from a reflectance database and (2) determining the best estimate by applying a neural network to the local optimal dataset only. In stage (1), the camera responses are predicted for the respective reflectances in the database, and the optimal candidates are selected in the order of lowest prediction error. In stage (2), most reflectance training data are obtained by a convex linear combination of local optimal data using weighting coefficients based on random numbers. A feed-forward neural network with one hidden layer is used to map the observation space onto the spectral reflectance space. In addition, the reflectance estimation is repeated by generating multiple sets of random numbers, and the median of a set of estimated reflectances is determined as the final estimate of the reflectance. Experimental results show that the estimation accuracies exceed those of other methods.

Paraphrase generation is an important yet challenging task in NLP. Neural network-based approaches have achieved remarkable success in sequence-to-sequence(seq2seq) learning. Previous paraphrase generation work generally ignores syntactic information regardless of its availability, with the assumption that neural nets could learn such linguistic knowledge implicitly. In this work we make an endeavor to probe into the efficacy of explicit syntactic information for the task of paraphrase generation. Syntactic information can appear in the form of dependency trees which could be easily acquired from off-the-shelf syntactic parsers. Such tree structures could be conveniently encoded via graph convolutional networks(GCNs) to obtain more meaningful sentence representations, which could improve generated paraphrases. Through extensive experiments on four paraphrase datasets with different sizes and genres, we demonstrate the utility of syntactic information in neural paraphrase generation under the framework of seq2seq modeling. Specifically, our GCN-enhanced models consistently outperform their syntax-agnostic counterparts in multiple evaluation metrics.

Fire is a serious security threat that can lead to casualties, property damage, and environmental damage. However, despite the availability of object detection algorithms, challenges persist in detecting fires and smoke. These challenges include slow convergence speed, poor performance in detecting small targets, and high computational cost limiting deployments. In this paper, Fire smoke and human detection based on ConvNeXt and Mixed encoder (FCM-DETR), an end-to-end object detection algorithm based on Deformable DETR, is proposed. Firstly, we introduce ConvNeXt to take the place of Resnet, which greatly reduces the amount of computation and improves the ability to extract irregular flame features. Secondly, to effectively process multi-scale features, the original encoder is decoupled into two modules. Then Mixed encoder, an innovative encoder structure, is proposed, resulting in excellent performance of multi-scale fire and smoke features fusion. What can’t be overlooked is that the encoder block is compatible with any DETR-based models. Finally, the convergence speed is accelerated and the mean of average precision is improved by applying a novel loss function called Powerful IoU v2. The experimental results indicate that our model achieves the best detection accuracy compared to other models, with mAP reaching 66.7%, mAPs and Accuracyfire achieving impressive 50.2% and 98.05%, respectively.

This paper explores how smart cities can cope with land subsidence and liquefaction in the context of rapid urbanization in Japan. Since the 1960s, liquefaction has become an important topic in geotechnical engineering, and great efforts have been made to evaluate the resistance of soil to liquefaction. There is currently a lack of machine learning applications specifically for smart cities in areas such as geological hazards. This study uses two machine learning techniques, artificial neural networks and ensemble learning, to obtain a prediction model with high performance in predicting the bearing layer depth to improve the accuracy of geo-engineering surveys. The model was developed by analyzing actual survey data from 433 locations in Setegaya, Tokyo, by using artificial neural networks (ANNs) and bagging, respectively. The results show that machine learning has great advantages in predicting the bearing layer depth. In addition, compared with a single model such as artificial neural networks, the prediction performance of ensemble learning can be improved by about 20%. Both interdisciplinary approaches can help predict address risks and thus promote sustainable urban development, highlighting the potential of smart cities in the future.

Alzheimer's disease (AD) is a progressive and evolving neurodegenerative disease with an insidious onset that can lead to memory loss and cognitive impairment. There is no effective treatment for this disease. However, early diagnosis plays an important role in treatment planning to slow down its progression, as treatment has the greatest impact in the early stages of the disease. Neurological images obtained through different imaging techniques provide powerful information and help diagnose the disease. With the wide application of deep learning techniques in disease diagnosis, especially the prominence of Convolutional Neural Networks (CNNs) in computer vision and image processing, more and more studies are proposing the use of this algorithm for the diagnosis of AD. In this paper, we first systematically introduce the impact of AD on people, detailing the biomarkers, early clinical symptoms, and risk factors of this disease. Secondly, it goes on to detail the development of CNNs, their form, and methods to help diagnose AD. It is proposed that CNNs can help diagnose AD by analyzing medical imaging data, particularly structural brain scans such as magnetic resonance imaging (MRI) and functional scans such as positron emission tomography (PET). Finally, it is concluded that CNNs are of great importance for the diagnosis of AD and that they are likely to play an increasingly important role in the early detection of the disease, the understanding of disease mechanisms, and ultimately, in the development of effective AD therapies and interventions. CNNs are playing an increasingly important role in the Their potential impact on healthcare emphasizes the importance of continued research and innovation in neural networks and medical imaging.

Image denoising has been one of the important problems in the field of computer vision, and it has a wide range of practical value in many applications, such as medical image processing, image enhancement, and computational photography. Traditional image denoising methods are usually based on hand-designed features and filters, but these methods perform poorly under complex noise and image structures. In recent years, the rapid development of neural network technology has revolutionized the image-denoising task. This paper introduces the knowledge about neural networks and image denoising, explores the impact of neural networks on image denoising, and how is it possible to denoise images by neural networks. It also summarises other image-denoising methods and finally points out the challenges and problems faced by image-denoising at present. Some possible new development directions are proposed to provide new solutions for image-denoising researchers and to promote the development of the field.

Numerous approaches address over-fitting in neural networks: by imposing a penalty on the parameters of the network (L1, L2, etc); by changing the network stochastically (drop-out, Gaussian noise, etc.); or by transforming the input data (batch normalization, etc.). In contrast, we aim to ensure that a minimum amount of supporting evidence is present when fitting the model parameters to the training data. This, at the single neuron level, is equivalent to ensuring that both sides of the separating hyperplane (for a standard artificial neuron) have a minimum number of data points — noting that these points need not belong to the same class for the inner layers. We firstly benchmark the results of this approach on the standard Fashion-MINST dataset, comparing it to various regularization techniques. Interestingly, we note that by nudging each neuron to divide, at least in part, its input data, the resulting networks make use of each neuron, avoiding a hyperplane completely on one side of its input data (which is equivalent to a constant into the next layers). To illustrate this point, we study the prevalence of saturated nodes throughout training, showing that neurons are activated more frequently and earlier in training when using this regularization approach. A direct consequence of the improved neuron activation is that deep networks are now easier to train. This is crucially important when the network topology is not known a priori and fitting often remains stuck in a suboptimal local minima. We demonstrate this property by training a network of increasing depth (and constant width): most regularization approaches will result in increasingly frequent training failures (over different random seeds) whilst the proposed evidence-based regularization significantly outperforms in its ability to train deep networks.

Activation Functions are crucial parts of the Deep Learning Artificial Neural Networks. From the Biological point of view, a neuron is just a node with many inputs and one output. A neural network consists of many interconnected neurons. It is a “simple” device that receives data at the input and provides a response. The function of neurons is to process and transmit information; the neuron is the basic unit in the nervous system. Carly Vandergriendt (2018) stated the human brain at birth consists of an estimated 100 billion Neurons. The ability of a machine to mimic human intelligence is called Machine Learning. Deep Learning Artificial Neural Networks was designed to work like a human brain with the aid of arbitrary choice of Non-linear Activation Functions. Currently, there is no rule of thumb on the choice of Activation Functions, “Try out different things and see what combinations lead to the best performance”, however, sincerely; the choice of Activation Functions should not be Trial and error. Jamilu (2019) proposed that Activation Functions shall be emanated from AI-ML-Purified Data Set and its choice shall satisfy Jameel’s ANNAF Stochastic and or Deterministic Criterion. The objectives of this paper are to propose instances where Deep Learning Artificial Neural Networks are SUPERINTELLIGENT. Using Jameel’s ANNAF Stochastic and or Deterministic Criterion, the paper proposed four classes where Deep Learning Artificial Neural Networks are Superintelligent namely; Stochastic Superintelligent, Deterministic Superintelligent, and Stochastic-Deterministic 1^st and 2^nd Levels Superintelligence. Also, a Normal Probabilistic-Deterministic case was proposed.

Convolutional neural networks (CNN) have attracted much attention as a commonly used method for hyperspectral image (HSI) classification in recent years, however, CNNs can only be applied to Euclidean data and have limitations in dealing with relationships due to the limitations of local feature extraction. However, each pixel of a hyperspectral image contains a set of spectral bands that are correlated and interact with each other, and the methods used to process Euclidean data cannot effectively obtain these correlations. In contrast, the graph convolutional network (GCN) can be used in non-Euclidean data, but usually leads to oversmoothing and ignoring local detail features due to the need for superpixel segmentation processing to reduce computational effort. To overcome the above problems, we constructed a network a fusion network based on GCN and CNN, which contains two branches: a graph convolutional network based on superpixel segmentation and a convolutional network with added attention mechanism. The graph convolu-tional branch can extract the structural features and capture the relationships between the nodes, and the convolutional branch can extract the detailed features in the local fine region. Owing to the fact that the features extracted from the two branches are different, the classification performance can be improved by fusing the complementary features extracted from the two branches. To vali-date the proposed algorithm, experiments were conducted on three widely used datasets, namely Indian Pines, Pavia University, and Salinas, and the overall accuracy of 98.78% was obtained in the Indian Pines dataset, and the overall accuracy of 98.99% and 98.69% was obtained in the other two datasets. The results showed that the proposed fusion network can obtain richer features and achieve high classification accuracy.

With the rapid development of the Internet industry, the problem of information overload has arisen due to the abundance of information available online. Recommendation algorithms, as the core of recommendation systems, have been attracting much attention and are a hot topic of research for many experts and scholars. The classical recommendation algorithms are mainly divided into three major categories: collaborative filtering recommendation algorithms, content-based recommendation algorithms, and hybrid-based recommendation algorithms. Although these algorithms are widely used in various fields, with the proliferation of information, these traditional recommendation algorithms are no longer able to meet the needs of the times. To address this issue, recommendation systems have been developed to provide users with personalized and relevant information or products. Despite the wide use of recommendation algorithms, such as collaborative filtering, content-based filtering, and hybrid approaches, traditional recommendation algorithms have limitations and are no longer suitable for meeting the demands of the times. This paper proposes a new recommendation algorithm, SFRRG, that fuses structure and feature information in graph neural networks to improve the performance of the recommendation system in rating prediction. The effectiveness of the proposed algorithm is demonstrated through experiments on various data sets and compared with existing recommendation algorithms.

To address the challenge of recognizing ship states accurately amidst the complexities of marine environments, this study proposes a novel ship state recognition approach leveraging a graph convolutional neural network (GCNN). Initially, the method extracts canonical and efficient ship motion trajectories from AIS data. Subsequently, a state recognition network tailored for ship motion trajectories is devised and implemented employing graph convolution. Notably, the accuracy of this model is enhanced through the introduction of novel weights and optimization of the Adj parameter. Experimental evaluations conducted on a ship state dataset demonstrate significant performance improvements. Specifically, the proposed recognition network achieves a recognition accuracy of 98.3% for regulated ship trajectories, marking an impressive 8.4% enhancement over traditional convolutional neural networks. This advancement holds promise for enhancing ship state recognition accuracy across diverse maritime applications including maritime supervision, navigation safety, and ship management.

Mechanical equipment is composed of several parts, the interaction between the parts exists throughout whole life cycle leads to the widespread phenomenon of fault coupling and the diagnosis of independent faults cannot meet the requirements of the health management of mechanical equipment under actual working conditions. In this paper, the topological structure of graph neural network is used to describe the correlation of coupling faults and multiple fault types are regarded as network nodes respectively. The fault features are fused and extracted by graph convolution to achieve the classification of coupling faults. In this paper, dynamic vertexes are defined in data topology and the parameters of DIGNN classification model are optimized by changing the fault type of dynamic vertexes during training stage. The data is loaded into dynamic vertexes for classification and analysis during testing stage. The one-dimensional vibration data is converted into two-dimensional time-frequency domain data by wavelet transform making the input features of the model interpretable to reduce the uncertainty of model training. The data topology is then fed into DIGNN for fault classification, and GCN's node aggregation gives interpretability to each layer of network data processing. The method proposed in this paper can realize accurate diagnosis of independent faults on the data set, and can effectively judge the coupling mode of coupling faults, which is suitable for coupling fault analysis of mechanical equipment.

There is a considerable amount of research in online social networks, most of which focuses on the structural analysis of social graphs. The interpersonal relationships of social networks, especially friend circle, can solve the cold start and sparsity problems, and through the relationship between social networks can effectively recommend users' favorite items (items), such as music , videos, brands/products, preferred tags, location, services, etc. User relationships in social networks are diverse and there are many different perspectives on different social networks. Associations among users can form multi-layered composite networks, and multi-layered social networks present new challenges and opportunities. Different relationships can influence users' preferences to different degrees, which in turn affects their behavior. Therefore, fusing multiple social networks is an effective way to improve recommendation. Although some studies have started to address multiple social network recommendations, simple linear superposition cannot reflect the coupling and nonlinear association between multiple social networks. In this paper, we propose a graph neural network recommendation model under social relationships based on this background. We first propose to compute the 2nd order collaborative signals and their intensities directly from the neighboring matrix for updating the node embedding of the graph convolution layer. Secondly by embedding historical evaluations, various social networks constituting different dimensions, the attention integration of user preferences by different social networks is achieved, and its effectiveness and scalability are demonstrated in theoretical derivation and experimental validation. The theoretical derivation and experimental validation demonstrate its effectiveness and scalability.

In this paper, we delve into the realm of aspect-level sentiment analysis, a sophisticated analytical task focused on pinpointing and interpreting the sentiment directed towards specific elements within a sentence. Traditional methods in this domain, primarily based on neural networks, have often overlooked the critical role of syntactic structures in sentences. To bridge this gap, we have developed the Syntax-Enhanced Sentiment Graph Network (SentiSyn). This pioneering model represents a significant step forward in aspect-level sentiment analysis, bringing to the forefront the utilization of word dependency relationships to enrich sentiment analysis. SentiSyn stands out by its innovative use of a dependency graph, a tool that meticulously maps out the intricate web of syntactic relationships surrounding a target aspect in a sentence. This approach allows SentiSyn to effectively capture and channel sentiment-related characteristics that are deeply rooted in the syntactic context of the aspect target. By doing so, SentiSyn unlocks a deeper understanding of sentiment dynamics in textual content, enabling a more nuanced and accurate sentiment analysis. Our comprehensive experimental evaluation of SentiSyn showcases its remarkable capabilities. When combined with advanced embedding techniques like GloVe and BERT, SentiSyn demonstrates a superior performance edge over several existing sentiment analysis methods. This performance leap is not just incremental; it represents a significant enhancement in the field of sentiment analysis, underscoring the importance of syntactic context in understanding sentiments. Furthermore, our analysis delves into how SentiSyn effectively leverages these embeddings to gain a more profound and contextually rich insight into sentiment dynamics. The results from our tests indicate that SentiSyn, with its unique approach to integrating syntactic structures and advanced embeddings, sets a new benchmark in aspect-level sentiment analysis, offering both enhanced accuracy and deeper sentiment understanding.

This study explores novel techniques to improve the detection accuracy of skarn iron deposits using advanced image processing methodologies. Leveraging the capabilities of Aster image, Band Ratio (BR) images, and Principal Component Analysis (PCA), alongside the power of 3D Convolutional Neural Networks (3D-CNN), the research aims to enhance the precision and efficiency of ore detection in complex geological environments. The proposed method employs a specific 3D-CNN architecture, accepting input as a 7×7×C image patch, where C represents the combined number of selected Aster image bands, Principal Component (PC) bands, and computed BR images. To evaluate the accuracy of the proposed method, five distinct image bands combinations, including the proposed bands combination, were tested and evaluated based on the overall accuracy (OA), average accuracy (AA), and kappa coefficient. The results demonstrated that while the incorporation of BR images alongside Aster bands initially seemed promising, it introduced significant confusion in certain classifications, leading to unexpected mis-classification rates. Surprisingly, utilizing solely Aster bands as input parameters yielded higher accuracy rates (OA= 93.13%, AA = 91.96%, Kappa = 90.91%) compared to scenarios involving the integration with band ratios (OA = 87.02%, AA = 79.15, and Kappa = 82.60%) or the integration of BR images to PC bands (OA= 87.78%, AA = 82.39%, Kappa = 83.81%). However, the amalgamation of Aster bands with selected PC bands showed slight improvements in accuracy (OA= 94.65%, AA = 92.93%, Kappa = 93.45%), although challenges in accurately classifying certain features persisted. Ultimately, the proposed combination of Aster bands, PC bands, and BR images (proposed bands combination) presented the most visually appealing and statistically accurate results (OA = 96.95%, AA= 94.87%, and Kappa = 95.93%), effectively addressing misclassifications observed in the other combinations. These findings underscore the synergistic contributions of each of the Aster bands, PC bands, and BR images, with Aster bands proving pivotal for optimal skarn classification, PC bands enhancing intrusions classification accuracy, and BR images strengthening wall rock classification accuracy. In conclusion, the proposed combination of input image bands emerges as a robust and comprehensive methodology, demonstrating unparalleled accuracy in the remote sensing detection of skarn iron minerals.

Land cover segmentation, a fundamental task within the domain of remote sensing, boasts a broad spectrum of application potential. In this article, we focus on the land cover segmentation tasks and complete the following research work: Firstly, to address the issues of uneven distribution of foreground and background and significant differences in target scales in remote sensing images, we propose a decoder called MDCFD based on multi-dilation rate convolution fusion. The decoder utilizes dilated convolution to expand the receptive field, enhancing the model's ability to capture global features and thus improving the model's ability to distinguish between foreground and background. Meanwhile, we design a multi-dilation rate convolution fusion module (MDCFM), which fuses the outputs of different dilation rate convolution layers. Secondly, aiming at the problems of diverse scenes, significant differences between categories, and many background interferences in remote sensing images, we propose a hybrid attention module called LKSHAM based on large kernel convolution. This module combines spatial attention and channel attention mechanisms and combines the two attention modules in series. By introducing large kernel convolution, the model's ability to extract contextual information is improved. At the same time, we adopt a strategy of decomposing large kernel convolution into multiple depthwise convolutions to reduce computational complexity. The improved network models designed by this paper can achieve an improvement of over 1.1% in the mIoU metric on segmentation tasks on the Potsdam and Vaihingen datasets.

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.

A convolutional neural network (CNN) is sometimes understood as a black box in the sense that while it can approximate any function, studying its structure will not give us any insights into the nature of the function being approximated. In other terms, the discriminative ability does not reveal much about the latent representation of a network. This research aims to establish a framework for interpreting the CNNs by profiling them in terms of interpretable visual concepts and verifying them by means of Integrated Gradient. We also ask the question, "Do different input classes have a relationship or are they unrelated?" For instance, could there be an overlapping set of highly active neurons to identify different classes? Could there be a set of neurons that are useful for one input class whereas misleading for a different one? Intuition answers these questions positively, implying the existence of a structured set of neurons inclined to a particular class. Knowing this structure has significant values; it provides a principled way for identifying redundancies across the classes. Here the interpretability profiling has been done by evaluating the correspondence between individual hidden neurons and a set of human-understandable visual semantic concepts. We also propose an integrated gradient-based class-specific relevance mapping approach that takes the spatial position of the region of interest in the input image. Our relevance score verifies the interpretability scores in terms of neurons tuned to a particular concept/class. Further, we perform network ablation and measure the performance of the network based on our approach.

Abstract: With the growing integration of the Internet of Things (IoT) in smart buildings, it is crucial to ensure the precise implementation and operation of wireless sensor networks (WSNs). This paper aims to study the implementation aspect of Wireless Sensor Networks (WSNs) in a commercial multi-story building, specifically addressing the difficulty of dealing with variable environmental conditions on each floor. This research addresses the disparity between simulated situations and actual deployments, offering valuable insights that have the potential to signifi-cantly improve the efficiency and responsiveness of building management systems. We obtain real-time sensor data to analyze and evaluate the system’s performance. Our investigation is grounded in the growing importance of incorporating WSNs into buildings to create intelligent environments. By leveraging the capabilities of Contiki operating system, this study employs a specialized simulator to generate simulated data, allowing for a comparison between real-world and simulated scenarios. We provide an in-depth analysis to scrutinize the disparities and commonalities between the datasets obtained from real-world deployments and simulated en-vironments. We highlight the necessity of precise simulation to validate real-life sensor data, shedding light on the challenges and opportunities associated with implementing WSNs in in-telligent buildings. Results obtained show the significance of accurate simulation models for re-liable data representation, providing a roadmap for further developments in the integration of WSNs into intelligent building scenarios. The findings highlight the potential for optimizing living and working conditions based on the real-time monitoring of critical environmental pa-rameters. This includes insights into temperature, humidity, and light intensity, offering oppor-tunities for enhanced comfort and efficiency in intelligent environments.

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.

: In the last years, materializations of neuromorphic circuits based on nanophotonic arrangements have been proposed, which contain complete optical circuits, laser, photodetectors, photonic crystals, optical fibers, flat waveguides, and other passive optical elements of nanostructured materials, which eliminate the time of simultaneous processing of big groups of data, taking advantage of the quantum perspective and thus highly increasing the potentials of contemporary intelligent computational systems. This article is an effort to record and study the research that has been conducted concerning the methods of development and materialization of neuromorphic circuits of Neural Networks of nanophotonic arrangements. In particular, an investigative study of the methods of developing nanophotonic neuromorphic processors, their originality in neuronic architectural structure, their training methods and their optimization has been realized along with the study of special issues such as optical activation functions and cost functions.

Precision agriculture is a technology used by farmers to help food sustainability amidst growing population. One of the tools of precision agriculture is yield monitoring, which helps a farmer manage his production. Yield monitoring is usually done during harvest, however it could also be done early in the growing season. Early prediction of yield, specifically for fruit trees, aids the farmer in the marketing of their product and assists in managing production logistics such as labor requirement and storage needs. In this study, a machine vision system is developed to estimate fruit yield early in the season. The machine vision system uses a color camera to capture images of fruit trees during the full bloom period. An image segmentation algorithm based on an artificial neural network was developed to recognize and count the blossoms on the tree. The artificial neural network segmentation algorithm uses color information and position as input. The resulting correlation between the blossom count and the actual number of fruits on the tree shows the potential of this method to be used for early prediction of fruit yield.

Accurate electricity price forecasting has become a substantial requirement since the liberalization of the electricity markets. Due to the challenging nature of the electricity prices, which includes high volatility, sharp price spikes and seasonality, various types of electricity price forecasting models still compete and can not outperform each other consistently. Neural Networks have been successfully used in machine learning problems and Recurrent Neural Networks (RNNs) have been proposed to address time-dependent learning problems. In particular, Long Short Term Memory and Gated Recurrent Units (GRU) are tailor-made for time series price estimation. In this paper, we propose to use Gated Recurrent Units as a new technique for electricity price forecasting. We have trained a variety of algorithms with rolling 3-year window and compared the results with the RNNs. In our experiments, 3-layered GRUs outperformed all other neural network structures and state of the art statistical techniques in a statistically significant manner in the Turkish day-ahead market.

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.

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.

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.

Energy consumption is a critical issue in the energy sector, and recent events such as the global energy crisis, costs, the need to reduce greenhouse emissions, and extreme weather conditions have increased the demand for energy efficiency. Accurately predicting energy consumption is one of the key steps to addressing inefficiency in energy consumption, and its optimization. In this regard, accurate predictions of energy consumption would not only help to minimize wastage, but also to save cost. In this article, we propose intelligent models using an ensemble of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) neural networks for predicting energy consumption in smart buildings. The proposed model outperforms other state-of-the-art deep learning models for predicting minute energy consumption, with a mean square error of 0.109. The proposed model also accurately captures latent trends in the data that other models struggle to capture. The results highlight the potential of using hybrid deep learning models for improved energy efficiency management in smart buildings.

The study of the brain networks using analysis of electroencephalography (EEG) data based on statistical dependencies (functional connectivity) and mathematical graph theory concepts is common in neuroscience and cognitive sciences for examinations of patient and healthy individuals. The Consciousness Fields according to Taheri theory and applications in the optimization of system under study have been investigated in various studies. In this study, we examine the results of working with Faradarmani Consciousness Field (FCF) in the brain of Faradarmangars. Faradarmangars are one of the necessary components in mind mediation of the function of Faradarmani Consciousness Fields according to Taheri. For this purpose, the functional and effective connectivity and the corresponding brain graphs of EEG from the brain of Faradarmangars is compared with that of non Faradarmangar groups during FCF connection. According to the results of the present study, the brain of the Faradarmangars shows significant decreased activity in delta (BA8), beta2 (BA4/6/8/9/10/11/32/44/47) and beta3 (in 34 of 52 BA) frequency bands mainly in frontal lobe and after that in parietal and temporal lobes in the comparison with the non Faradarmangars. Moreover, the functional and effective connectivity analysis in the frontal network shows dominant multiple decreased connectivity mainly in the case of beta3 frequency band in all parts of the frontal network. On the other hand, the graph theory analysis of the Faradarmangar brain shows an increase in the activity of the O2-T5-F4-F3-FP2-F8 areas and significant decrease in the characteristic path length and increases in global efficiency, clustering coefficient and transitivity. In conclusion, the unique higher graph function efficiency and the reduction in the brain activity and connectivity during the Faradarmani Consciousness Field mind mediation, shown the passive and detector like function of the human brain in this task.

The detection and recognition of tables in image-based documents is a challenging and essential task for automated data extraction and anal- ysis. This paper introduces a methodology that utilizes Convolutional Neural Networks (CNNs) to address this problem. By harnessing the ro- bust visual recognition abilities of CNNs, the proposed method effectively detects and extracts tables from image-based documents. Additionally, an Encoder-Dual Decoder (EDD) architecture is employed to extract the textual content from table cells, enabling the transformation of visual data into structured, machine-readable formats. This structured data is then further processed using a Vector Space Model (VSM)-based language modeling technique for query-based table retrieval. The methodology’s accuracy is assessed by analyzing the spatial relationships between the extracted cells and comparing them against a pre-defined table structure. The results provide an evidence to the effectiveness of the proposed ap- proach, with an impressive 85% accuracy rate and a corresponding error rate of 15%. This accurate extraction and recognition of tables from image-based documents can significantly enhance applications in data analysis, information retrieval, and knowledge extraction.

Graph visualization has evolved significantly over time, offering various methods to effectively represent complex data structures. This study introduces a novel force-directed algorithm for 3D data visualization, specifically tailored for commonly used datasets in linked data visualization. Leveraging the power of graph theory and methods, the algorithm aims to address the challenge of creating visually appealing and easily interpretable visualizations, which often necessitate advanced user interaction. By utilizing 3D space and the Unity Engine, the research successfully visualizes data and develops interactive visualizations, overcoming limitations of basic force-directed implementations. The main contribution of presented research is in the force-directed algorithm with springs and controlled placement as a visualization technique that combines the use of springs and attractive forces to stabilize a graph in a 3D environment. The combination of these two techniques also helps prevent the formation of a single large cluster within the graph, enhancing the overall visualization quality.

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.

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects’ boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and we develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combine different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask which is more suitable for combining transformers in an ensemble. In our extensive experimental evaluation, the proposed ensembles exhibit state-of-the-art performance.

Identifying influential actors within social networks is pivotal for optimizing information flow and mitigating the spread of both rumors and diseases. Several methods have emerged to pinpoint these influential entities in networks that are represented as graphs. In these graphs, nodes corre-spond to individuals and edges indicate their connections. This study focuses on centrality measures, prized for their straightforwardness and effectiveness. We categorize structural central-ity into two: local, considering a node's immediate vicinity, and global, accounting for overarching path structures. Some techniques blend both centralities to highlight nodes influential at both mi-cro and macro levels. Our paper presents a novel centrality measure, accentuating node degree and incorporating the network's broader features, especially paths of different lengths. Through Spearman and Pearson's correlations tested on seven standard datasets, our method proves its merit against traditional centrality measures. Additionally, we employ the SIR model, portraying disease spread, to further validate our approach. The ultimate influential node is gauged by its capacity to infect the most nodes during the SIR model's progression. Our results indicate a nota-ble correlative efficacy across various real-world networks relative to other centrality metrics.

Autosomal Dominant Polycystic Kidney Disease (ADPKD) is a genetic disorder characterized by the development and progression of multiple renal cysts, leading to progressive renal function decline. To date, the only approved treatment for this condition is able to slow down the loss of annual renal function, without stopping the disease progression. Furthermore, this therapy is approved only for patients with rapid disease progression and its compliance is problematic because of the impact of this drug on quality of life. The recent literature suggests that cystic cells are subject to metabolic dysregulation in the glucose pathway (Warburg Effect). This finding paved the way for new lines of research targeting potential therapeutic interventions for ADPKD. In particular, this review highlights the latest studies on the use of ketosis, through ketogenic dietary interventions (daily calorie restriction, intermittent fasting, time-restricted feeding, and ketogenic diets), as a potential strategy for patients with ADPKD, and the possible involvement of microbiota in the ketogenic interventions’ effect.

Satellite communication is expected to play a vital role in realizing Internet of Remote Things (IoRT) applications. This article considers an intelligent reflecting surface (IRS)-assisted downlink low Earth orbit (LEO) satellite communication network, where IRS provides additional reflective links to enhance the intended signal power. We aim to maximize the sum-rate of all the terrestrial users by jointly optimizing the satellite’s precoding matrix and IRS’s phase shifts. However, it is difficult to directly acquire the instantaneous channel state information (CSI) and optimal phase shifts of IRS due to the high mobility of LEO and the passive nature of reflective elements. Moreover, most conventional solution algorithms suffer from high computational complexity and are not applicable to these dynamic scenarios. A robust beamforming design based on graph attention networks (RBF-GAT) is proposed to establish a direct mapping from the received pilots and dynamic network topology to the satellite and IRS’s beamforming, which is trained offline using the unsupervised learning approach. The simulation results corroborate that the proposed RBF-GAT can achieve approximate performance compared to the upper bound with low complexity.

We study how abstract representations emerge in a Deep Belief Network (DBN) trained on benchmark datasets. Our analysis targets the principles of learning in the early stages of information processing, starting from the “primordial soup" of the under-sampling regime. As the data is processed by deeper and deeper layers, features are detected and removed, transferring more and more “context-invariant” information to deeper layers. We show that the representation approaches an universal model – the Hierarchical Feature Model (HFM) – determined by the principle of maximal relevance. Relevance quantifies the uncertainty on the model of the data, thus suggesting that “meaning" – i.e. syntactic information – is that part of the data which is not yet captured by a model. Our analysis shows that shallow layers are well described by pairwise Ising models, which provide a representation of the data in terms of generic, low order features. We also show that plasticity increases with depth, in a similar way as it does in the brain. These findings suggest that DBNs are capable of extracting a hierarchy of features from the data which is consistent with the principle of maximal relevance.

In this essay, I revisit Neural Networks (NNs) through the lens of evolutionary dynamics. From the two most important features of NNs, I recover the two most general equations of evolutionary dynamics. These two equations may thus serve as a connection between NNs and a body of knowledge that has been built over multiple centuries and has found application across a vast range of disciplines. This connection may therefore also help explain why NNs with the two features in question are applicable across a much broader range of domains than initially envisioned.

Creating self-learning algorithms, developing deep neural networks and improving other methods that "learn" for various areas of human activity is the main goal of the theory of machine learning. It helps to replace the human with a machine, aiming to increase the quality of production. The theory of artificial neural networks, which already have replaced the humans in problems of detection of moving objects, recognition of images or sounds, time series prediction, big data analysis and numerical methods remains the most dispersed branch of the theory of machine learning. Certainly, for each area of human activity it is necessary to select appropriate neural network architectures, methods of data processing and some novel tools from applied mathematics. But the universal problem for all these neural networks with specific data is the achieving the highest accuracy in short time. Such problem can be resolved by increasing sizes of architectures and improving data preprocessing, where the accuracy rises with the training time. But there is a possibility to increase the accuracy without time growing, applying optimization methods. In this survey we demonstrate existing optimization algorithms of all types, which can be used in neural networks. There are presented modifications of basic optimization algorithms, such as stochastic gradient descent, adaptive moment estimation, Newton and quasi-Newton optimization methods. But the most recent optimization algorithms are related to information geometry, for Fisher-Rao and Bregman metrics. This approach in optimization extended the theory of classic neural networks to quantum and complex-valued neural networks, due to geometric and probabilistic tools. There are provided applications of all introduced optimization algorithms, what delighted many kinds of neural networks, which can be improved by including any advanced approaches in minimization of the loss function. Afterwards, we demonstrated ways of developing optimization algorithms in further researches, engaging neural networks with progressive architectures. Classical gradient based optimizers can be replaced by fractional order, bilevel and, even, gradient free optimization methods. There is a possibility to add such analogues in graph, spiking, complex-valued, quantum and wavelet neural networks. Besides the usual problems of image recognition, time series prediction, object detection, there are many are other tasks for modern theory of machine learning, such as solving problem of quantum computations, partial differential and integro-differential equations, stochastic processes and Brownian motion, making decisions and computer algebra.

Creating intelligent systems capable of recognizing emotions is a difficult task, especially when looking at emotions in animals. This paper describes the process of designing a “proof of concept” system to recognize emotions in horses. This system is formed by two elements, a detector and a model. The detector is a fast region-based convolutional neural network that detects horses in an image. The model is a convolutional neural network that predicts the emotions of those horses. These two elements were trained with multiple images of horses until they achieved high accuracy in their tasks. 400 images of horses were collected and labeled to train both the detector and the model while 80 were used to validate the system. Once the two components were validated, they were combined into a testable system that would detect equine emotions based on established behavioral ethograms indicating emotional affect through head, neck, ear, muzzle and eye position. The system showed an accuracy of between 69% and 74% on the validation set, demonstrating that it is possible to predict emotions in animals using autonomous intelligent systems. Such a system has multiple applications including further studies in the growing field of animal emotions as well as in the veterinary field to determine the physical welfare of horses or other livestock.

In recent years, the field of deep learning achieved considerable success in pattern recognition, image segmentation and may other classification fields. There are a lot of studies and practical applications of deep learning on images, video or text classification. In this study, we suggest a method for changing the architecture of the most performing CNN models with the aim of designing new models to be used as stand-alone networks or as a component of an ensemble. We propose to replace each activation layer of a CNN (usually a ReLu layer) by a different activation function stochastically drawn from a set of activation functions: in this way the resulting CNN has a different set of activation function layers.

In this paper, we leverage state of the art models on Imagenet data-sets. We use the pre-trained model and learned weighs to extract the feature from the Dog breeds identification data-set. Afterwards, we applied fine-tuning and dataaugmentation to increase the performance of our test accuracy in classification of dog breeds datasets. The performance of the proposed approaches are compared with the state of the art models of Image-Net datasets such as ResNet-50, DenseNet-121, DenseNet-169 and GoogleNet. we achieved 89.66% , 85.37% 84.01% and 82.08% test accuracy respectively which shows the superior performance of proposed method to the previous works on Stanford dog breeds datasets.

We revise the definition of graph operations in [WDK2018] and adapt correspondingly the construction of graph term algebras. As a first contribution to a prospective research field Universal Graph Algebra, we generalize some basic concepts and results from algebras to graph algebras. To tackle this generalization task, we revise and reformulate traditional set-theoretic definitions, constructions and proofs in Universal Algebra by means of more category-theoretic concepts and constructions. Especially, we generalize the concept generated subalgebra and prove that all monomorphic homomorphisms between graph algebras are regular. Derived graph operations are the other main topic. After an in depth analysis of terms as representations of derived operations in traditional algebras, we identify three basic mechanisms to construct new graph operations out of given ones: parallel composition, instantiation, and sequential composition. As a counterpart of terms, we introduce graph operation expressions with a structure as close as possible to the structure of terms. We show that the three mechanisms allow us to construct for any graph operation expression a corresponding derived graph operation in any graph algebra.

Berberine (BER) is a natural alkaloid found in various Berberis species, used traditionally in herbal medicine and dietary supplements. BER exhibited various biological activities, including anti-inflammatory, antioxidant, antidiabetic, and anti-tumour properties by modulating cellular pathways and influencing gene expression. While BER shows promise in various health applications, its possible toxicity raises concerns. In 2023, EFSA issued a call for data on BER- and protoberberine (PROTBER)-containing products, to comprehensively assess its safety and potential health claims. With these premises, new data was collected by assessing: i) the phytochemical profile of BER- and PROTBER-containing preparations by newly developed HPLC-DAD method; ii) in silico and in vitro investigation of pharmacokinetics properties of BER; iii) in vitro cytotoxicity in different human cell lines and, iv) biological and molecular activities of extracts containing BER and PROTBER in in vitro human non-cancer cells. By testing 16 commercial Berberis extracts, the evidence collected showed a good qualitative reliability in terms of phytochemical profile and limited relapses on cytotoxicity even at 200 µg/ml after a 24h of exposure, while evidencing a good cellular bioavailability and cell migration inhibition. The potential for plant-drug interactions affecting CYP450 proved to be minimal. Overall, our work provides a useful overview to better elucidate potential concerns on botanicals containing BER and minor PROTBER commonly used in food supplement.

This study examines the feasibility of using event-related potentials (ERPs) obtained from electroencephalographic (EEG) recordings as biomarkers for long-term memory item classification. Previous studies have identified old/new effects in memory paradigms associated with explicit long-term memory and familiarity. Recent advancements in convolutional neural networks (CNNs) have enabled the classification of ERP trials under different conditions and identification of features related to neural processes at the single-trial level. We employed this approach to compare three CNN models with distinct architectures using experimental data. Participants (N = 25) performed an association memory task while recording ERPs that were used for training and validation of the CNN models. The EEGNET-based model achieved the most reliable performance in terms of precision, recall, and specificity compared with the shallow and deep convolutional approaches. The classification accuracy of this model reached 70% for known items and 62% for unknown items. Good overall accuracy requires a trade-off between recall and specificity and depends on the architecture of the model and the dataset size. These results suggest the possibility of integrating ERP and CNN into online learning tools and identifying the underlying processes related to long-term memorization.

With the rapid development of technology and the advancement of Internet technology, various social networking platforms are gradually coming into people's view and occupying a higher and higher position. In the recommendation scenario, the user-item interaction naturally forms a bipartite heterogeneous graph structure and with the development of graph embedding and graph neural network technologies based on deep learning to process graph domain information, the combination of graph information and recommendation systems shows strong research potential and application prospects. The methodological improvement of the recommendation algorithm based on collaborative filtering takes advantage of the nature that user-items can form a bipartite graph in the recommendation scenario. The existing methods still have some shortcomings. The methods that only use weights or convolutional recurrent neural networks to implicitly model different historical behaviors lack explicit modeling of video switching relationships in serialized behaviors. The user's interest is changing all the time, so it is not possible to recommend based on the user's history, and it is necessary to consider both the long-term and short-term interest of the user according to the video content in order to achieve accurate recommendation of short videos. In this paper, we design a recommendation model based on graph neural network, which models users' long-term and short-term interests by two vector propagation methods, respectively.

Graph coloring is a manifestation of graph partitioning, wherein, a graph is partitioned based on the adjacency of its elements. Partitioning serves potentially as a compartmentalization for any structural problem. Vertex coloring is the heart of the problem which is to find the chromatic number of a graph. The fact that there is no general efficient solution to this problem that may work unequivocally for all graphs opens up the realistic scope for combinatorial optimization algorithms to be invoked. The algorithmic complexity of graph coloring is non-deterministic in polynomial time (NP) and hard. To the best of our knowledge, there is no algorithm as yet that procures an exact solution of the chromatic number comprehensively for any and all graphs within the polynomial (P) time domain. However, several heuristics as well as some approximation algorithms have been attempted to obtain an approximate solution for the same. Here, we present a novel heuristic, namely, the 'trailing path', which returns an approximate solution of the chromatic number within polynomial time, and, with a better accuracy than most existing algorithms. The ‘trailing path’ algorithm is effectively a subtle combination of the search patterns of two existing heuristics (DSATUR and Largest First), and, operates along a trailing path of consecutively connected nodes (and thereby effectively maps to the problem of finding spanning tree(s) of the graph) during the entire course of coloring, where essentially lies both the novelty and the apt of the current approach. The study also suggests that the judicious implementation of randomness is one of the keys towards rendering an improved accuracy in such combinatorial optimization algorithms. Apart from the algorithmic attributes, essential properties of graph partitioning in random and different structured networks have also been surveyed, followed by a comparative study. The study reveals the remarkable stability and absorptive property of chromatic number across a wide array of graphs. Finally, a case study is presented to demonstrate the potential use of graph coloring in protein design – yet another hard problem in structural and evolutionary biology.

In this proposed work, five systems were developed to classify four motor functions—forward hand movement (FW), grasp (GP), release (RL), and reverse hand movement (RV)—from EEG signals. The dataset used is WAY-EEG-GAL, involving participants performing a sequence of hand movements. During preprocessing, bandpass filtering was applied to remove artifacts and focus on the mu and beta frequency bands. The first system, a preliminary study model, explored the overall framework of EEG signal processing and classification. It utilized time-domain features like variance and frequency-domain features like alpha and beta power, with classification performed using a KNN model. Insights from this system informed the development of a baseline system, which uses the same dataset but different feature extraction and classification paradigms. This baseline system combined the common spatial patterns (CSP) method with continuous wavelet transform (CWT) for feature extraction and employed a GoogLeNet classifier with transfer learning. Classification was performed on six unique pairs of events derived from the four motor functions, using both intrasubject and intersubject methods. The baseline system achieved the highest accuracy of 99.73% for the GP-RV pair and the lowest accuracy of 80.87% for the FW-GP pair in intersubject classification. Building on this, three additional systems were developed to perform 4-way classification. Among these, the final model, ML-CSP-OVR, achieved the highest intersubject classification accuracy of 78.08% using all combined data and 76.39% for leave-one-out intersubject classification. This proposed model, which features a novel combination of CSP-OVR, CWT, and GoogLeNet, demonstrates strong potential as a general system for motor imagery (MI) tasks without being subject-dependent.

Recurrent Neural Networks (RNNs) have significantly advanced the field of machine learning by enabling the effective processing of sequential data. This paper provides a comprehensive review of RNNs and their applications, highlighting advancements in architectures such as Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRUs), Bidirectional LSTM (BiLSTM), and stacked LSTM. The study examines the application of RNNs in different domains, including natural language processing (NLP), speech recognition, financial time series forecasting, bioinformatics, autonomous vehicles, and anomaly detection. Additionally, the study discusses recent innovations, such as the integration of attention mechanisms and the development of hybrid models that combine RNNs with convolutional neural networks (CNNs) and transformer architectures. This review aims to provide machine learning researchers and practitioners with a comprehensive overview of the current state and future directions of RNN research.

With the exponential growth of machine learning and development of Artificial Neural Network (ANNs) in recent years, there is great opportunity to leverage this approach and accelarate bio-logical discoveries through applications on the analysis of bioinformatics data. Various types of datasets including for example protein or gene interaction networks, molecular structures and cellular signalling pathways, have already been used for machine learning by training ANNs for inference and pattern classification. However, unlike regular data structures that are commonly used in the computer science and engineering fields, bioinformatics datasets present challenges that require unique algorithmic approaches. The recent development of the geometric and deep learning approach within the machine learning field, is very promising towards accelerating analysis complex bioinformatics datasets. The principles of ANNs and their importance for bio-informatics machine learning is demonstrated herein, through presentation of the undelying mathematical and statistical foundations from group theory, symmetry, linear algebra. Further-more, the structure and functions of ANN algorithms that form the core principles of artificial intelligence are explained, in relation to the bioinformatics data domain. Overall, the manuscript provides guidance for researchers to understand the principles required for practicing machine learning and artificial intelligence, with the special considerations towards bioinformatics applications.

Autonomous image recognition has numerous potential applications in the field of planetary science and geology. For instance, having the ability to classify images of rocks would allow geologists to have immediate feedback without having to bring back samples to the laboratory. Also, planetary rovers could classify rocks in remote places and even in other planets without needing human intervention. Shu et al. classified 9 different types of rock images using a Support Vector Machine (SVM) with the image features extracted autonomously. Through this method, the authors achieved a test accuracy of 96.71%. In this research, Convolutional Neural Networks(CNN) have been used to classify the same set of rock images. Results show that a 3-layer network obtains an average accuracy of 99.60% across 10 trials on the test set. A version of Self-taught Learning was also implemented to prove the generalizability of the features extracted by the CNN. Finally, one model has been chosen to be deployed on a mobile device to demonstrate practicality and portability. The deployed model achieves a perfect classification accuracy on the test set, while taking only 0.068 seconds to make a prediction, equivalent to about 14 frames per second.

This work describes and compares the backpropagation algorithm with the Extended Kalman filter, a second-order training method which can be applied to the problem of learning neural network parameters and is known to converge in only a few iterations. The algorithms are compared with respect to their effectiveness and speed of convergence using simulated data for both, a regression and a classification task.

At the beginning of any electric arc welding process, a regime called transient regime will always occur, characterized by the continuous variation of the energy flow, also resulting in the variation of the cooling rate of the welded joint. Consequently, the weld bead hardness varies from a maximum value to an approximately constant value, and this phenomenon can be represented by an asymptotic exponential function. For several welded specimens, it would be possible to fit a non-linear regression for each specimen, however, it would be a difficult task to combine different regressions in a single analysis. The objective of this study is to evaluate the applicability of mixed-effects models and artificial neural networks to predict the longitudinal hardness of the weld bead in the initial transient regime. To this end, linearized and nonlinear mixed-effects models and artificial neural networks with different architectures were fitted. Finally, valid models were obtained with all approaches, with artificial neural network model slightly better fitted. However, the explainability capacity of the linearized mixed-effects model was superior, showing that the relative thickness, one of the predictor variables, was responsible for 48% of the variation in longitudinal hardness of weld bead.

This research addresses the formidable challenge of achieving precise trajectory tracking for autonomous vehicle formations in uncertain environments. It introduces an adaptive control system tailored for autonomous vehicles, with a primary focus on ensuring prescribed performance in trajectory tracking within a leader-follower formation paradigm. The system incorporates a guidance law that allows the leader vehicle to dynamically adjust desired yaw angles and speeds for follower vehicles based on the established reference trajectory, enhancing tracking accuracy and responsiveness to environmental changes. To address practical external disturbances, the study utilizes Radial Basis Function Neural Networks (RBFNN) in conjunction with second-order filters for error approximation. This approach is further strengthened by a carefully formulated adaptive law. The innovative integration of a barrier Lyapunov function with the backstepping method significantly enhances the system’s adaptability and robustness, ensuring trajectory tracking performance meets predetermined standards. Simulation results illustrate the control system’s adept handling of various external disturbances, consistently maintaining trajectory tracking errors within predefined limits. This underscores the system’s potential to markedly enhance the operational reliability and efficiency of autonomous vehicle formations in unpredictable environmental conditions.

The stability and optimal control for an SIS epidemic model with demographics and heterogeneous control strategies (immunization and quarantine) on complex networks are investigated. The epidemic threshold, disease-free and endemic equilibria are derived. Then, global asymptotical stability about the two equilibria are studied based on different methods. Furthermore, the optimal control issue about the system is also considered. We obtain the existence and uniqueness of the optimal control and optimal control tactics. Some numerical simulations were conducted to illustrate and supplement the theoretical results. Meanwhile, the effects of the combination of various immunization and quarantine schemes are studied and also compared with the optimal control strategies.

This paper is focused on two topics very relevant in water distribution networks (WDNs): vulnerability assessment and the optimal placement of water quality sensors. The main novelty element of this paper is to represent the data of the problem, in this case all objects in a graph underlying a water distribution network, as discrete probability distributions. For vulnerability (and the related issue of re-silience) the metrics from network theory, widely studied and largely adopted in the water research community, reflect connectivity expressed as closeness centrality or, betweenness centrality based on the average values of shortest paths between all pairs of nodes. Also network efficiency and the related vulnerability measures are related to average of inverse distances. In this paper we propose a different approach based on the discrete probability distribution, for each node, of the node-to-node distances. For the optimal sensor placement, the elements to be represented as dis-crete probability distributions are sub-graphs given by the locations of water quality sensors. The objective functions, detection time and its variance as a proxy of risk, are accordingly represented as a discrete e probability distribution over contamination events. This problem is usually dealt with by EA algorithm. We’ll show that a probabilistic distance, specifically the Wasserstein (WST) distance, can naturally allow an effective formulation of genetic operators. Usually, each node is associated to a scalar real number, in the optimal sensor placement considered in the literature, average detection time, but in many applications, node labels are more naturally expressed as histograms or probability distributions: the water demand at each node is naturally seen as a histogram over the 24 hours cycle. The main aim of this paper is twofold: first to show how different problems in WDNs can take advantage of the representational flexibility inherent in WST spaces. Second how this flexibility translates into computational procedures.

Background/Objectives: the prevalence of metabolic syndrome (MetS) is increasing worldwide, and an increasing number of cases are diagnosed in younger age groups. This study aimed to propose predictive models based on demographic, anthropometric and clinical non-invasive variables to predict MetS in adolescent. Methods: a total of 2,064 adolescents aged 18-19 from São Luís-Maranhão-Brazil were enrolled. Demographic, anthropometric, and clinical variables were considered, and three criteria for diagnosing MetS were employed: Cook et al. (2003), De Ferranti et al. (2004), and the International Diabetes Federation (IDF, 2007). A feed-forward artificial neural network (ANN) was trained to predict MetS. Accurate, sensitivity, and specificity were calculated to assess the ANN performance. The ROC curve was constructed, and the area under the curve was analyzed to assess the discriminatory power of the networks. Results: the prevalence of MetS in adolescents ranged from 5.7% to 12.3%. The ANN that used the Cook et al. criterion performed best in predicting MetS. ANN 5, which included age, sex, waist circumference, weight, and systolic and diastolic blood pressure, showed the best performance and discriminatory power (sensitivity, 89.8%; accuracy, 86.8%). ANN 3 considered the same variables, except for weight, and exhibited good sensitivity (89.0%) and accuracy (87.0%). Conclusions: using non-invasive measures allows for predicting MetS in adolescents, thereby guiding the flow of care in primary healthcare and optimizing the management of public resources.

Standard ANNs lack flexibility when handling corrupted input due to their fixed structure. Spiking Neural Networks (SNNs) can utilize biological temporal coding features, such as noise-induced stochastic resonance and dynamical synapses to increase a model’s performance when its parameters are not optimized for a given input. Using the analog XOR task as a simplified Convolutional Neural Network analog, this paper demonstrates two key results: (1) SNNs solve the problem linearly inseparable in ANN with over 10% improvement in the optimal setting, and (2) in SNNs, the synaptic noise and dynamical synapses compensate for non-optimal parameters, achieving near-optimal results.

Background: Prediction of neurorehabilitation outcomes after a Spinal Cord Injury (SCI) is crucial for healthcare resource management and improving prognosis and rehabilitation strategies. Arti-ficial neural networks (ANNs) have emerged as a promising alternative to conventional statistical approaches for identifying complex prognostic factors in SCI patients. Materials: a database of 1256 SCI patients admitted for rehabilitation was analyzed. Clinical and demographics data and SCI characteristics, were used to predict functional outcomes using both ANN and linear regression models. The former was structured with input, hidden, and output layers, while the linear regression identified significant variables affecting outcomes. Both ap-proaches aimed to evaluate and compare their predictive accuracy for rehabilitation outcomes measured by the Spinal Cord Independence Measure (SCIM) score. Results: Both ANN and linear regression models identified key predictors of functional outcomes, such as age, injury level, and initial SCIM scores (correlation with actual outcome: R=0.75 and 0.73, respectively). When alimented also with parameters recorded during hospitalization, the ANN highlighted the importance of these additional factors like motor completeness and compli-cations during hospitalization, showing an improvement in its predictive accuracy (R=0.87). Conclusion: ANN seemed to be not widely superior to classical statistics in general, but, taking into account complex and non-linear relationships among variables, emphasized the impact of complications during the hospitalization on recovery, particularly respiratory issues, deep vein thrombosis, and urological complications. These results suggested that the management of com-plications is crucial for improving functional recovery in SCI patients.

Methotrexate is an antimetabolic agent with proliferative and immunosuppressive activity. It has been demonstrated to be an effective treatment for acute lymphoblastic leukemia (ALL) in children. However, there is evidence of an association between methotrexate and toxicity risks, which influences the personalization of treatment, particularly in the case of childhood ALL. This article presents the development and implementation of an algorithm based on artificial neural networks to detect methotrexate toxicity in pediatric patients with acute lymphoblastic leukemia. The algorithm utilizes historical clinical and laboratory data, with an effectiveness of 99% in the tests performed with the patients dataset. The use of neural networks in medicine is often linked to disease diagnosis systems. However, neural networks are not only capable of recognizing examples, but also hold very important information. For this reason, one of the main areas of application of neural networks is the interpretation of medical data. In this article we diagnose with the application of neural networks in medicine with a concrete example: Detecting Methotrexate in Pediatric Patient in its early stages.

The Spiking Neural Network (SNN) has attracted more and more attention recently. It adopts binary spike signals to transmit information. Benefitting from the information passing paradigm of SNNs, the multiplications of activations and weights can be replaced by additions, which are more energy-efficient. However, its ``Hard Reset" mechanism for the firing activity would ignore the difference among membrane potentials when the membrane potential is above the firing threshold, causing information loss. Meanwhile, quantifying the membrane potential to 0/1 spikes at the firing instants will inevitably introduce the quantization error thus bringing about information loss too. To address these problems, we propose to use the ``Soft Reset" mechanism for the supervised training-based SNNs, which will drive the membrane potential to a dynamic reset potential according to its magnitude, and Membrane Potential Rectifier (MPR) to reduce the quantization error via redistributing the membrane potential to a range close to the spikes. Results show that the SNNs with the ``Soft Reset" mechanism and MPR outperform their vanilla counterparts on both static and dynamic datasets.