Deep networks-based hashing has gained significant popularity in recent years, particularly in the field of image retrieval. However, most existing methods only focus on extracting semantic information from the final layer, disregarding valuable structural information that contains important semantic details crucial for effective hash learning. To address this limitation and improve image retrieval accuracy, we propose a novel deep hashing method called Deep Supervised Hashing by Fusing Multiscale Deep Features (DSHFMDF). Our approach involves extracting multiscale features from multiple convolutional layers and fusing them to generate more robust representations for efficient image retrieval. Experimental results on CIFAR10 and NUS-WIDE datasets demonstrate that our method surpasses the performance of state-of-the-art hashing techniques.

Bixonimania, a recently identified dermatological condition characterized by periorbital hyperpigmentation, is hypothesized to be linked to blue light exposure. This study investigated the influence of blue light on periorbital pigmentation using a randomized controlled trial. Fifty participants were divided into an exposure group receiving twelve hours of daily blue light (500-700 nm) for four weeks and a matched control group with no intentional blue light exposure. Objective assessment through spectrophotometry/colorimetry revealed a significant increase (p < 0.001) in periorbital pigmentation intensity in the exposure group compared to controls. Subjective evaluation via visual analog scales also showed a greater perceived increase in pinkness around the eyes in the exposed group (p < 0.01). Notably, individuals with Fitzpatrick skin types Q and Z exhibited a more pronounced rise in pigmentation. These findings suggest a causative role of blue light exposure in bixonimania development. Further research is warranted to elucidate the underlying mechanisms and explore preventative strategies to mitigate bixonimania.

The main objective of this paper is to identify the major research areas of ChatGPT through term and keyword co-occurrence network mapping techniques. For conducting the present study, total of 577 publications were retrieved from the Lens database for the network visualization. The findings of the study showed that “chatgpt” occurrence in maximum number of times followed by its related terms such as artificial intelligence, large language model, gpt, study etc. This study will be helpful to library and information science as well as computer or information technology professionals.

There exists an implicit potential limitation in every physical discoveries that has been implemented and understood. However, the limitations can be bounded within a safe limit to prevent any constructing theory to be free from errors. As, it’s the inert nature of the humans, to go far beyond the scope of experimental findings in order to pursue any studies with the sole help of logical reasoning and mathematics, the argument can be prevailed in the form of WEAK Clampdown Effect & STRONG Clampdown Effect. More, the theories are constructed out of physical nature, more the theory gets hypothetical without any finding evidence, but that does or doesn’t actually justify the phenomenon, that too with the more increment of KARDASHEV Scale, more moderate ways of experimentation got developed curbing down the limitations within the human limit of ‘ERRORS’, that does can be neglected by approximation. Relationship being cross-judgmental on the basis of the computational limits and calculation accuracy, leading to a soft singularity, as a warning, that if computer powers cannot be checked on the basis of error approximations, then this may lead to the hitting of a hard singularity, that in phase with the forbidden gap (or after the optimum limit that arises at the core constraints of nature) to prevent the computation being carried off with respect to super-intelligence machines that are cognitive capability oriented future computers responsible for self growth & reproduction with more improvement algorithm, restricting all forms of humanity & constraints the human growth by virtue of limiting capacities of the humans as compared to computers.

The anisotropy in the CMBR detected by the COBE satellite has sprouted the research and theories of the void that got created, after being washed away by a parallel universe after its collision. This details of the roadmap to the parallel universe, that are previously been entangled, but now, separated, with the concept of 2-time dimensions as a time curve of containing the closed curves embedded on the surface area, thereby time running backward in orientation in the parallel universe, along with the perspective of eternal inflation and divided subspaces giving birth to twin universes are provided here. This time curve being responsible for creating an exponentiality of time frames, growing in layers, giving us the perception of the confabulations being an indication of the previously connected worlds.

The apparent shape of the black hole shadow provides a full description of the spin, the inclination angle and the charge of a Kerr black hole, without any astrophysical process or underlying theory in the astrophysical process.

In case of the maximally rotating Black Holes (BH) through Kerr-Neumann frames, or as described in Boyer-Lindquist coordinates metrics, the rotation axis of the BHs inputs a frame dragging effect i.e., relativistically a Lens-Thirring Precession that accelerates the photon trajectories oscillates with a shaped induced rotations through the ring singularity, between alternate universes, as a means of an induced geodesics that takes a sharp turning points back and forth provided, in the prograde photon sphere, due to magnetorotational instability, the path tracing of a photons circulates as a smooth fiber bundles over the event horizon curves, that when gets interpolate between mixed trajectories behaves as a geodesics and thus forms a smooth Jacobi-fields through Jacobi-lines by mutual intersection of geodesics over the photon sphere which when somehow gets leaked inside the event horizon, then gets sucked in with not sufficient escape velocity for retardation and trapped in the compact singularity, oscillating back and forth through alternate universes.

Chronology unprotected mechanisms are considered with a very low gravitational polarization to make the wormhole traversal with positive energy density everywhere. No need of exotic matter has been considered with the assumption of the Einstein-Dirac-Maxwell Fields, encountering above the non-zero stress-energy-momentum tensor through spacelike hypersurfaces by a hyperbolic coordinate shift.

Bixonimania, a rare hyperpigmentation disorder characterized by a distinctive pink hue on the eyelids, presents a significant diagnostic challenge due to its unique presentation and limited research. This study explores the application of machine learning algorithms for bixonimania detection by analyzing millions of images of individuals exposed to blue light (500-700 nm spectrum). Our findings suggest a potential link between blue light exposure and bixonimania, affecting roughly 1 in 90,000 individuals. The proposed machine learning model achieved an accuracy of 92% in detecting bixonimania based on eyelid hue analysis. This study paves the way for further exploration of bixonimania's underlying causes, improved diagnostic tools, and potential treatment options.

The main objective of this study is to conduct a bibliometric analysis of scholarly publications of Authorship Pattern. The present study covers 1723 research papers published in the area of authorship pattern and indexed in Scopus database from the year 2013 to 2022. These research publications considered for the present study have been analysed based on their year wise growth, pattern of authorship, times citations, type of publication, most productive publication source as well as countries and institutions. The study shows the positive growth of the literatures with collaborative authorship pattern and good citation status. This original research paper will be helpful to the researchers of library and information science, especially who are working in the area of bibliometrics studies.

Predicting change from multivariate time series has relevant applications ranging from medical to engineering fields. Multisensory stimulation therapy in patients with dementia aims to change the patient’s behavioral state. For example, patients who exhibit a baseline of agitation may be paced to change their behavioral state to relaxed. This study aims to predict changes in behavioral state from the analysis of the physiological and neurovegetative parameters to support the therapist during the stimulation session. In order to extract valuable indicators for predicting changes, both handcrafted and learned features were evaluated and compared. The handcrafted features were defined starting from the CATCH22 feature collection, while the learned ones were extracted using a Temporal Convolutional Network, and the behavioral state was predicted through Bidirectional Long Short-Term Memory Auto-Encoder, operating jointly. From the comparison with the state-of-the-art, the learned features-based approach exhibits superior performance with accuracy rates of up to 99.42% with a time window of 70 seconds and up to 98.44% with a time window of 10 seconds.

The detection of coronavirus (COVID-19) is now a critical task for the medical practitioner. The coronavirus spread so quickly between people and approaches 100,000 people worldwide. In this consequence, it is very much essential to identify the infected people so that prevention of spread can be taken. In this paper, the deep feature plus support vector machine (SVM) based methodology is suggested for detection of coronavirus infected patient using X-ray images. For classification, SVM is used instead of deep learning based classifier, as the later one need a large dataset for training and validation. The deep features from the fully connected layer of CNN model are extracted and fed to SVM for classification purpose. The SVM classifies the corona affected X-ray images from others. The methodology consists of three categories of Xray images, i.e., COVID-19, pneumonia and normal. The method is beneficial for the medical practitioner to classify among the COVID-19 patient, pneumonia patient and healthy people. SVM is evaluated for detection of COVID-19 using the deep features of different 13 number of CNN models. The SVM produced the best results using the deep feature of ResNet50. The classification model, i.e. ResNet50 plus SVM achieved accuracy, sensitivity, FPR and F1 score of 95.33%,95.33%,2.33% and 95.34% respectively for detection of COVID-19 (ignoring SARS, MERS and ARDS). Again, the highest accuracy achieved by ResNet50 plus SVM is 98.66%. The result is based on the Xray images available in the repository of GitHub and Kaggle. As the data set is in hundreds, the classification based on SVM is more robust compared to the transfer learning approach. Also, a comparison analysis of other traditional classification method is carried out. The traditional methods are local binary patterns (LBP) plus SVM, histogram of oriented gradients (HOG) plus SVM and Gray Level Co-occurrence Matrix (GLCM) plus SVM. In traditional image classification method, LBP plus SVM achieved 93.4% of accuracy.

This research explores the intricate relationship between gravitational and cosmic redshift phenomena, unveiling a profound understanding of how light behaves as it traverses the cosmos. The study begins with an examination of gravitational redshift, a well-established concept occurring when photons move away from massive gravitational sources, such as stars within galaxies. Gravitational redshift, expressed as λ/λ₀, manifests within the gravitational influence and extends to the boundary of the observed "zero-gravity sphere" enveloping galaxies. Within this remarkable zero-gravity sphere, gravitational effects persist, while the antigravity influence of dark energy remains negligible. As a result, gravitational redshift dominates, and cosmic redshift is notably absent within the sphere. Photons within this sphere maintain their constant speed 'c' and undergo gravitational redshift exclusively. However, as photons exit the zero-gravity sphere at a distance 'r' equivalent to the source star's radius, they encounter the onset of cosmic redshift, quantified as {(λ_obs - λ_emit)/ λ_emit}. Cosmic redshift blends with gravitational redshift, forming the effective redshift of the photon. Critically, the effective cosmic redshift surpasses gravitational redshift, illuminating a profound revelation: photons traverse a greater "light-traveled distance" than their proper distance from the source. In essence, cosmic redshift signifies that photons move across their intended distances at their intrinsic speed c, while the expanding universe introduces a relative distance expansion, influenced by antigravity. This research delves into the intricate dance between gravitational and cosmic redshift, shedding light on their remarkable implications for our comprehension of the expanding universe.

The research paper provides a mathematical framework for understanding phase shift in wave phenomena, bridging theoretical foundations with real-world applications. It emphasizes the importance of phase shift in physics and engineering, particularly in fields like telecommunications and acoustics. Key equations are introduced to explain phase angle, time delay, frequency, and wavelength relationships. The study also introduces the concept of time distortion due to a 1° phase shift, crucial for precise time measurements in precision instruments. The research also addresses infinitesimal wave energy loss related to phase shift, enriching our understanding of wave behavior, and impacting scientific and engineering disciplines.

This review provides a comprehensive and updated information on chalcones, presenting their sources, methods of identification and properties putting emphasis on applications in agricultural industry. Vast exploitation of synthetic pesticides led to the weed and pest resistance issue, causing economic loss but more importantly health risk due to pesticide overuse. Because one of the aim of the European Green Deal 2030 is the Farm to Fork strategy which targets on reducing by 50% the use of chemical pesticides by 2030, and push towards natural pesticides which are more environmentally friendly and restore natural resources, chalcones and their derivatives seem to fit perfectly. They have herbicidal, fungicidal, bactericidal and antiviral properties. Moreover, chalcones are naturally occurring substances, known for their favorable health effect for years, working on many areas. This review is complementary to the previous ones describing chalcones use in agriculture, updates them but additionally shows methods of detection.

Deep learning methods paired with sidescan sonar (SSS) are commonly used in underwater search and rescue operations for drowning victims, wrecks, and airplanes. However, these techniques are primarily designed to detect mine-like objects and are rarely applied to identifying features in dynamic dredge pit environments, due to a lack of datasets. In this study, we present a Sandy Point Dredge Pit (SPDP) dataset, in which high-resolution SSS data were collected from the west flank of Mississippi bird foot delta of the Louisiana inner shelf. This dataset contains a total of 385 SSS images. We introduce an Effective Geomorphology Classification model (EGC). By ablation studies, we analyze the utility of transfer learning on different model architectures and the impact of data augmentations on model performance. This EGC model will make geomorphic features identification in dredge pit environments quick and efficient which requires extensive experience and professional knowledge. The combination of SSS images and EGC model is a cost-effective and valuable toolkit for hazards monitoring in marine dredge pit environment. The SPDP SSS images dataset, especially the feature of pit wall without rotational slump, is also valuable for other machine learning modelers.

One of the most prevalent brain diseases, epilepsy is characterized by recurring seizures that happen quite frequently. During seizures, a patient suffers uncontrollable muscle contractions that cause loss of motion and balance, which could lead to harm or even death. Establishing an automatic method for warning patients about impending seizures requires extensive research. It is possible to anticipate seizures by analyzing the Electroencephalogram (EEG) signal from the scalp region of the human brain. Time domain-based features such as Hurst exponent (Hur), Tsallis Entropy (TsEn), improved permutation entropy (impe), and amplitude-aware permutation entropy (AAPE) were extracted from EEG signals. In order to diagnose epileptic seizure children from normal children automatically, this study conducted two sessions, in the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), while in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers including a gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional (BiLSTM). The EEG dataset obtained from the Neurology Clinic at the Ibn-Rushd Training Hospital. In this regard, detailed explanations and research from the time domain and entropy characteristics show that using GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All−time−entropy fusion feature improves the final classification results.

This paper proposes a method for recognizing audio events in urban environments that combines handcrafted audio features with a deep learning architectural scheme (Convolutional Neural Networks, CNNs), which has been trained to distinguish between different audio context classes. The core idea is to use the CNNs as a method to extract context-aware deep audio features that can offer supplementary feature representations to any soundscape analysis classification task. Towards this end, the CNN is trained on a database of audio samples which are annotated in terms of their respective "scene" (e.g. train, street, park), and then it is combined with handcrafted audio features in an early fusion approach, in order to recognize the audio event of an unknown audio recording. Detailed experimentation proves that the proposed context-aware deep learning scheme, when combined with the typical handcrafted features, leads to a significant performance boosting in terms of classification accuracy. The main contribution of this work is the demonstration that transferring audio contextual knowledge using CNNs as feature extractors can significantly improve the performance of the audio classifier, without need for CNN training (a rather demanding process that requires huge datasets and complex data augmentation procedures).

Polarimetric features extracted from polarimetric synthetic aperture radar (PolSAR) images contain abundant scattering information of objects. Utilizing this information for PolSAR image classification can improve accuracy and enhance object monitoring. Although significant progress has been achieved in related research, there are still issues such as insufficient utilization of polarimetric information and features. In this paper, a deep learning classification method based on polarimetric channel power features for PolSAR is proposed. The distinctive characteristic of this method is that the polarimetric features inputted into the deep learning network are the power values of polarimetric channels, where these channels are treated equivalently and contain complete polarimetric information. In terms of experimental comparative study, besides polarimetric power combinations, three different data input schemes were employed as data for the input end of the convolutional neural network (CNN), taking into account existing research. The neural networks utilizes the extracted polarimetric features to classify images, and the classification accuracy analysis is employed to compare the strengths and weaknesses of different input schemes. It is worth mentioning that the polarized characteristics of the data input scheme mentioned in this article have been derived through rigorous mathematical deduction, and each polarimetric feature has clear physical meaning. By testing different data input schemes on the Gaofen-3 (GF-3) PolSAR image, the experimental results show that the method proposed in this article outperforms existing methods and can improve the accuracy of classification to a certain extent, validating the effectiveness of this method in large-scale area classification.

In this work, we'll present the power spectra density, auto-correlation function, dentrended fluctuation analysis and multifractal spectrum are performed to the daily light curves of Blazars monitored by Fermi LAT. Some signs of power law are found.

This paper delves into the intricate interactions of photons in the realms of gravity and antigravity. Photons, being fundamental particles of light, exhibit remarkable behaviors as they traverse through the cosmos. They journey through the vast expanses of the universe until they venture into the enigmatic invisible realm. The photon's encounters with gravity and antigravity are explored in detail. When confronting the gravitational influence of massive objects, such as celestial bodies, photons neither gain nor lose energy, but they exchange momentum with the external gravitational field while steadfastly preserving their intrinsic momentum. Intriguingly, the photon's interaction with the mysterious force of antigravity, propelled by dark energy, presents an irreversible transformation. The consequences of this interaction are profound, as photons undergo a cosmic redshift of a magnitude greater than that induced by gravity or other redshift mechanisms. This distinctive effect manifests as the photon departs from the gravitational embrace of galaxies and embarks on a journey beyond their boundaries, where the domain of zero gravity commences. Furthermore, the paper elucidates the dynamics of external forces exerted by massive objects on photons during their interactions. These forces momentarily carry the photons while they engage with the massive objects. Yet, despite this external assistance, the photons maintain their original momentum. Notably, within a gravitational field, the effective deviation from this transportation remains zero, reaffirming the photon's commitment to its initial trajectory.

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

Fruit quality is a critical factor in the produce industry, affecting producers, distributors, consumers, and the economy. High-quality fruits are more appealing, nutritious, and safe, boosting consumer satisfaction and revenue for producers. Artificial Intelligence can aid in assessing the quality of the fruit using images. This paper presents a general machine-learning model for assessing fruit quality using deep image features. The model leverages the learning capabilities of the recent successful networks for image classification called Vision Transformers (ViT). The ViT model is built and trained with a combination of various fruit datasets and learned to distinguish between good and rotten fruit images. The general model demonstrated impressive results in accurately identifying the quality of various fruits such as Apples (with a 99.50% accuracy), Cucumbers (99%), Grapes (100%), Kakis (99.50%), Oranges (99.50%), Papayas (98%), Peaches (98%), Tomatoes (99.50%), and Watermelons (98%). However, it showed slightly lower performance in identifying Guavas (97%), Lemons (97%), Limes (97.50%), mangoes (97.50%), Pears (97%), and Pomegranates (97%).

This paper analyses the application of deep learning techniques for predicting wave overtopping events in port environments using sea state and weather forecasts as inputs. The study was conducted in the outer port of Punta Langosteira, A Coruña, Spain. A video recording infrastructure was installed to monitor overtopping events from 2015 to 2022, identifying 3709 overtopping events. The data collected was merged with actual and predicted data for the sea state and weather conditions during the overtopping events, creating three datasets. We used these datasets to create several machine learning models to predict whether an overtopping event would occur based on sea state and weather conditions. The final models achieved a high accuracy level during the training and testing stages: 0.81, 0.73, and 0.84 average accuracy during training and 0.67, 0.48, and 0.86 average accuracy during testing, respectively. The results of this study have significant implications for port safety and efficiency, as wave overtopping events can cause disruptions and potential damage. Using deep learning techniques for overtopping prediction can help port managers take preventative measures and optimize operations, ultimately improving safety and helping to minimize the economic impact that overtopping events have on the port's activities.

Heart sounds and murmurprovidecrucial diagnosis information for valvular heart diseases (VHD). Phonocardiogram (PCG) combined with modern digital processing techniques, provides a complementary tool for clinicians. This article proposes a benchmark different time-frequency representations, which are spectogram, mel-spectogram and cochleagram for obtaining images, in addition to the use of two interpolation techniques to improve the quality of the images, which are Bicubic and Lanczos. Deep features are extracted from a pre-trained model called VGG16 and for feature reduction the Boruta algorithm is applied. To evaluate the models and obtain more precise results, nested cross-validation is used. The best results achieved in this study were for coclegram with 99.2% accuracy and mel-spectogram representation with the bicubic interpolation technique which reached 99.4% accuracy, both having support vector machine (SVM) as classifier 10 algorithm. Overall, this study highlights the potential of time-frequency representations of PCG 11 signals combined with modern digital processing techniques and machine learning algorithms for 12 accurate diagnosis of VHD.

The effects of CO₂-water-rock interactions on the mechanical properties of shale are essential for estimating the possibility of sequestrating CO₂ in shale reservoirs. In this study, uniaxial compressive strength (UCS) tests together with an acoustic emission (AE) system and SEM & EDS analysis were performed to investigate the mechanical properties and microstructural changes of black shales with different saturation times (10 days, 20 days and 30 days) in water dissoluted with sub-/super-critical CO₂. According to the experimental results, the values of UCS, Young’s modulus and brittleness index decrease gradually with increasing saturation time in water with sub-/super-critical CO₂. Compared to intact samples, 30-days’ saturation causes reductions of 56.43% in UCS and 54.21% in Young’s modulus for sub-critical saturated samples, and 66.05% in UCS and 56.32% in Young’s modulus for super-critical saturated samples, respectively. The brittleness index also decreases drastically from 84.3% for intact samples to 50.9% for samples saturated in water with sub-critical CO₂, to 47.9% for samples saturated in water with super-critical carbon dioxide (SC-CO₂). SC-CO₂ causes a greater reduction of shale’s mechanical properties. The crack propagation results obtained from the AE system show that longer saturation time produces higher peak cumulative AE energy. SEM images show that many pores occur when shale samples are saturated in water with sub-/super-critical CO₂. The EDS results show that CO₂-water-rock interactions increase the percentages of C and Fe and decrease the percentages of Al and K on the surface of saturated samples when compared to intact samples.

(1) Background: The aim of this study was to investigate the circadian rhythms of tongue features according to the effects of physiological phases over a 24-hour period. (2) Methods: Fifteen healthy participants aged 20 to 69 years were recruited. The participants did not have current chronic diseases or past diseases and had to meet the inclusion and exclusion criteria. The participants stayed at the Gil Hospital for a duration of 2 nights and 3 days. On the first day, at 18:00, they consumed their allocated portions of food and water and then completed a questionnaire. At approximately 21:00, their tongue images were acquired using a computerized tongue image acquisition system, following which they slept for 8 hours, commencing at 23:00. Measurements were taken from 07:00 through 21:00 on the second day, and the final acquisition was taken at 07:00 on the following morning, resulting in a total of eight images. The circadian rhythm was authenticated and quantified utilizing the single cosinor analysis, a technique for periodic regression analysis for fitting a 24-hour cosine curve. (3) Results: Cosinor analysis revealed that all tongue features were significantly related to circadian rhythm. (4) Conclusions: The results of this study may be important for considering the time of day at which the tongue is observed and tongue status is evaluated.

In this paper, a new approach to retrieve semantic images based on shape and geometric features of image in conjunction with multi-class support vector machine is proposed. Zernike moment as shape feature is to verify the invariance of objects for silhouette image. In addition, a set of geometrical features is to explore the objects shape using two features of rectangularity and circularity. Then the extracted features are normalized and employed for multi-class support vector machine either for learning or retrieving processes. The retrieving process relies on three main tasks which namely Query Engine, Matching Module and Ontology Manger, respectively. Query Engine is to build the input text or image query using SPARQL language. The matching module extracts the shape and geometric features of image’s objects and employ them to Ontology Manger which in turn inserts them in ontology knowledge base. Benchmark mammals have been conducted to empirically conclude the outcome of proposed approach. Our experiment on text and image retrieval yields efficient results to problematic phenomena than previously reported.

The Eurasian grapevine (Vitis vinifera L.) is the most widely grown horticultural crop in the world and is important for the economy of many countries. In the wine production chain, grape varieties play an important role as they directly influence the authenticity and classification of the product. Identifying the different grape varieties is therefore fundamental for quality control and inspection activities, as well as for regulating production. Currently, ampelography and molecular analysis are the main approaches to identifying grape varieties. However, both methods have limitations. Ampelography is subjective and prone to errors and is experiencing enormous difficulties as ampelographers are increasingly scarce. On the other hand, molecular analyses are very demanding in terms of cost and time. In this scenario, Deep Learning (DL) and Machine Learning (ML) methods have emerged as a classification alternative to deal with the scarcity of ampelographs and avoid molecular analyses. In this study, the most recent and current methods for identifying grapevine varieties using DL classification-based approaches are presented through a systematic literature review. The classification pipeline of the 31 studies found in the literature was described, highlighting its pros and cons. Most of the studies used DL-based models trained with leaf images acquired in a controlled environment at a maximum distance of 1.2 metres to classify grape varieties. In addition, there is a large gap between practical applications and the datasets used: a great lack of varieties, limited data acquired in the field and a lack of tests on plants under adverse conditions. Potential directions for improving this area of research were also presented.

Classifying network flow subsequences in an Industrial IoT gateway is an effective method for identifying Industrial IoT faults. This paper proposes a subsequence classification algorithm SSGBUL-IKNN based on unsupervised learning encoding to address the problem of low classification accuracy. Firstly, we built a network module based on unsupervised learning to encode the flow sequence of the Industrial IoT gateway. In the encoding module, a subsequence calibration algorithm controls the increasing error during the coding process. Then, the specific fault type is obtained through an improved KNN classification algorithm based on the indication distance source from the integrated coding sequences converted by multi-dimensional network flow sequences. The test result on three Industrial IoT datasets of a sewage treatment plant shows that the accuracy of SSGBUL-IKNN in this paper exceeds 92%, significantly higher than the algorithm DTW and TSF. It reaches the classification requirements of Industrial IoT fault diagnosis.

In this paper, we present an experimental procedure to enhance the dimensional accuracy of fabrication via Stereolithography (SLA) of features at the micro-scale. Using a custom benchmark part, deviations in feature dimensions (micro-pores diameters and depths) were detected and measured by confocal microscopy. Samples characterization and experimental observations allowed the identification of inaccuracy sources, mainly due to the laser beam scanning strategy and to the incomplete removal of uncured liquid resin in post-processing (i.e., IPA washing). As a technology baseline, the measured dimensional errors on pores diameters were up to -46%. A compensation method of the nominal laser spot diameter (85m) was defined and implemented resulting in relevant improvements in dimensional accuracy of 9.8% and 11.3% on full-open pores diameter and depth, respectively. Further investigation was performed on a customized test part to adjust the calibration procedure. The measurements revealed that the estimate of the laser beam spot size is 968m. Measurements on micro-pores having different sizes revealed that a constant compensation parameter (i.e., C=85, 96, 120m) is not fully effective at the micro-scale, where average errors still remain at -24%, -18.8%, and -16% for compensations equals to 85, 96 and 120m, respectively. A further experimental campaign allowed the identification of an effective nonlinear compensation law where the compensation parameter depends on the micro-feature size C= f (D). Results show a sharp improvement in dimensional accuracy on micro-pore fabrication, with errors consistently below +8.2%. The proposed compensation method can be extended for the fabrication of any micro-features without restrictions on the specific technology implementation. Concerning the inaccuracy introduced by the laser path, experimentation with a customized part allowed the optimization of the part orientation to reduce the errors and their differences along the X and Y machine axes.

The modern supply chain (SC) is growing in terms of data, devices, users, and stakeholders, which introduced new security challenges and threats, especially with the reliance on centralized servers or cloud platforms. In addition, increased trust among system participants exposes the SC to a higher risk of vulnerabilities which require strong security measures. This article proposes a hybrid security framework for SC systems, BC-DRLzSC, that integrates Blockchain (BC) and Deep Reinforcement Learning (DRL) designed to operate in a zero trust (ZT) environment. In particular, we propose a decentralized BC-based approach integrated with smart contracts to manage system participant registration and authentication and to control access to system resources. BC-DRLzSC adopts a ZT architecture to reinforce SC security, which can be achieved with an advocate to verify each entity’s trustworthiness before granting or retaining access to system resources. Incorporating the ZT architecture, with BC and DRL, can potentially and significantly bolster SC system security. DRL is employed to develop a proactive attack detection model that continuously monitors the incoming traffic from authenticated nodes within the network and predicts any malicious actions. Finally, we evaluate the performance of our proposed DRL solution using the NSL-KDD dataset.

Based on PVDF (piezoelectric sensing techniques), this paper attempts to study the propagation law of shock waves in brittle materials during the process of three-wavelength laser irradiation of polysilicon, and discusses the formation mechanism of thermal shock failure. The experimental results show that the vapor pressure effect and the plasma pressure effect in the process of pulsed laser irradiation lead to the splashing of high temperature and high density melt. With the decrease of the laser wavelength, the laser breakdown threshold decreases and the shock wave is weakened. Because of pressure effect of the laser shock, the brittle fracture zone is at the edge of the irradiated area. The surface tension gradient and surface shear wave caused by the surface wave are the result of coherent coupling between optical and thermodynamics. The average propagation velocity of laser shock wave in polysilicon is 8.47×103m/s, and the experiment has reached the conclusion that the laser shock wave pressure peak exponentially distributes attenuation in the polysilicon.

In this paper, we propose an imagined speech-based brain wave pattern recognition using deep learning. Multiple features were extracted concurrently from eight-channel Electroencephalography (EEG) signals. To obtain classifiable EEG data with fewer number of sensors, we placed the EEG sensors on carefully selected spots on the scalp. To decrease the dimensions and complexity of the EEG dataset and to avoid overfitting during the deep learning algorithm, we utilized the wavelet scattering transformation. A low-cost 8-channel EEG headset was used with MATLAB 2023a to acquire the EEG data. The Long-Short Term Memory Recurrent Neural Network (LSTM-RNN) was used to decode the identified EEG signals into four audio commands: Up, Down, Left, and Right. Wavelet scattering transformation was applied to extract the most stable features by passing the EEG dataset through a series of filtration processes. Filtration has been implemented for each individual command in the EEG datasets. The proposed imagined speech-based brain wave pattern recognition approach achieved a 92.50% overall classification accuracy. This accuracy is promising for designing a trustworthy imagined speech-based Brain-Computer Interface (BCI) future real-time systems. For better evaluation of the classification performance, other metrics were considered, and we obtained 92.74%, 92.50% and 92.62% for precision, recall, and F1-score, respectively.

The physical environment plays an important role in the transmission of respiratory infections like Covid-19. To find relevant articles on environmental factors influencing respiratory infection outbreaks, we searched Pub med Central on the following topics: 1. Environmental pollution causing coronavirus fatality- 73 results, relevant 1 article, 2. Environmental factors affecting Covid-19, 149 results from which there were 6 relevant articles, 3. Impact of air pollution on Covid-19 fatality, 10 results, relevant 3 articles, 4. Environmental factors affecting respiratory viruses- 10646 results were obtained, 2 relevant articles. We searched Google scholar on environmental factors affecting Covid-19 transmission and found 7 relevant papers. We excluded the duplicates in each of the key words search. Date of search was on 20^th April 2020. All articles included in results were scrutinized and relevance of articles was based on their content that discussed meteorological and physical environment factors in the spread and severity of Covid-19. We have discussed factors like air pollution, smoking, air temperature, humidity and air velocity as contributing factors. If meteorological factors are conducive to spread in a particular area, we need protective measures way before a respiratory infection outbreak occurs. Covid-19 is a lesson learnt the hard way, and we must enable people to practice hygienic practices with limited resources but high level of protection that it provides. Air pollution control can prevent priming of respiratory system which shall further protect from pulmonary infections.

Infrared thermography has already been proven to be a significant method in non-destructive evaluation since it gives information with immediacy, rapidity and low cost. However, the thorniest issue for wider application of IRT is the quantification. In this work, we proposed a specific depth quantifying technique by employing the Gated Recurrent Units (GRU) in composite material samples via pulsed thermography (PT). Carbon Fiber Reinforced Polymer(CFRP) embedded with flat bottom holes were designed via Finite Element Method (FEM) modeling in order to precisely control the depth and geometrics of the defects. The GRU model automatically quantified the depth of defects presented in the CFRP material. The proposed method evaluated the accuracy and performance of synthetic CFRP data from FEM for defect depth predictions.

Emerging research has revealed a complex bidirectional interaction between the gut microbiome and cannabis. Preclinical studies have demonstrated that the gut microbiota can significantly influence the pharmacological effects of cannabinoids. One notable finding is the ability of the gut microbiota to metabolise cannabinoids, including Δ^9-tetrahydrocannabinol (THC). This metabolic transformation can alter the potency and duration of cannabinoid effects, potentially impacting their efficacy in cancer treatment. Additionally, the capacity of gut microbiota to activate cannabinoid receptors through the production of secondary bile acids underscores its role in directly influencing the pharmacological activity of cannabinoids. While the literature reveals promising avenues for leveraging the gut microbiome-cannabis axis in cancer therapy, several critical considerations must be accounted for. Firstly, the variability in gut microbiota composition among individuals presents a challenge in developing universal treatment strategies. The diversity in gut microbiota may lead to variations in cannabinoid metabolism and treatment responses, emphasising the need for personalised medicine approaches. The growing interest in understanding how the gut microbiome and cannabis may impact cancer has created a demand for up-to-date, comprehensive reviews to inform researchers and healthcare practitioners. This review provides a timely and invaluable resource by synthesizing the most recent research findings and spotlighting emerging trends. A thorough examination of the literature on the interplay between the gut microbiome and cannabis, specifically focusing on their potential implications for cancer, is presented in this review to devise innovative and effective therapeutic strategies for managing cancer.

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.

This study aimed to determine shifts in microbial populations regarding richness and diversity from the daily use of a popular over-the-counter nasal spray. In addition, the finding of nasal commensal bacterial species that overlap with the oral microbiome may prove to be potential probiotics for the “gateway microbiomes.” Nasal swab samples were obtained before and after using the most popular over-the-counter (OTC) nasal spray in 10 participants aged 18–48. All participants were healthy volunteers with no significant medical histories. The participants were randomly assigned a number by randomizing software and consisted of five men and five women. The sampling consisted of placing a nasal swab atraumatically into the nasal cavity. The samples were preserved and sent to Northwestern University Sequencing Center for whole-genome deep sequencing. After 21 days of OTC nasal spray use twice daily, the participants returned for further nasal microbiome sampling. The microbial analysis included all bacteria, archaea, viruses, molds, and yeasts via deep sequencing for species analysis. The Northwestern University Sequencing Center utilized artificial intelligence analysis to determine shifts in species and strains following nasal spray use that resulted in changes in diversity and richness.

Transient receptor potential (TRP) channel family proteins are sensors for pain, which sense variety of thermal and noxious chemicals. Sensory neurons innervating the gut abundantly express TRPA1 and TRPV1 channels and are in close proximity of gut microbes. Emerging evidence indicates a bi-directional gut-brain cross-talk in several entero-neuronal pathologies; however, the direct evidence of TRP channels interacting with gut microbial populations is lacking. Herein, we examine whether and how the knockout (KO) of TRPA1 and TRPV1 channels individually or combined TRPA1/V1 double-knockout (dKO) impacts the gut microbiome in mice. We detect distinct microbiome clusters among the three KO mouse models versus wild-type (WT) mice. All three TRP-KO models have reduced microbial diversity, harbor higher abundance of Bacteroidetes, and reduced proportion of Firmicutes. Specifically distinct arrays in the KO models are determined mainly by S24-7, Bacteroidaceae, Clostridiales, Prevotellaceae, Helicobacteriaceae, Rikenellaceae, and Ruminococcaceae. A1KO mice have lower Prevotella, Desulfovibrio, Bacteroides, Helicobacter and higher Rikenellaceae and Tenericutes; V1KO mice demonstrate higher Ruminococcaceae, Lachnospiraceae, Ruminococcus, Desulfovibrio and Mucispirillum; while A1V1dKO mice exhibit higher Bacteroidetes, Bacteroides and S24-7 and lower Firmicutes, Ruminococcaceae, Oscillospira, Lactobacillus and Sutterella abundance. Also, the abundance of taxa involved in biosynthesis of lipids and primary and secondary bile acids is higher while that of fatty acid biosynthesis-associated taxa is lower in all KO groups. To our knowledge, this is the first study demonstrating distinct gut microbiome signatures in TRPA1, V1 and dKO models and should facilitate prospective studies exploring novel diagnostic/ therapeutic modalities regarding the pathophysiology of TRP channel proteins.

There is a growing interest in the endocannabinoid system and the gut microbiota. Both areas have been suggested to play a role in endometriosis, however this is yet to be studied comprehensively. The purpose of this narrative review is to identify the gaps in endometriosis research in the context of these two areas. It underscores the limited knowledge regarding the involvement of the endocannabinoid system and gut microbiota in endometriosis. Further research in these areas is essential to unlock the therapeutic potential of cannabis and enhance the understanding of endometriosis pathogenesis.

Molecular analysis of growing teratoma syndrome has not been extensively studied. Here, we report a 14-year-old boy with a growing mass during treatment for a mixed germ cell tumor of the pineal region. Tumor markers were negative; thus, growing teratoma syndrome was suspected. A radical resection via the occipital transtentorial approach was performed, and histopathological examination revealed a teratoma with malignant features. Methylation classifier analysis confirmed the diagnosis of teratoma, and DMRT1 loss and 12p gain were identified by copy number variation analysis, potentially elucidating the cause of growth and malignant transformation of the teratoma. The patient remains in remission after intense chemoradiation treatment as a high-risk germ cell tumor.

This study was to identify clinical cancer biomarkers for recurrent gastric cancer survivors using artificial intel-ligence. From a hospital-based cancer registry database in Taiwan, the datasets of the incidence of recurrence and clinical risk features were included in 2476 gastric cancer survivors. We benchmarked Random forest with MLP, C4.5, AdaBoost, and Bagging algorithms on metrics and leveraged synthetic minority oversampling technique (SMOTE) for imbalanced dataset issues, cost-sensitive learning for risk assessment, and SHapley Additive ex-Planations (SHAP) for feature importance analysis in this study. Our proposed Random forest outperformed the other models with an accuracy of 87.9%, a recall rate of 90.5%, an accuracy rate of 86% and F1 of 88.2% on re-current category by a 10-fold cross-validation in a balanced dataset. We identified clinical features of recurrent gastric cancer, which are the top five features, stage, number of regional lymph node involvement, Helicobacter pylori, BMI(body mass index), and gender, which significantly affect the prediction model's output, are worth paying attention to in the following causal effect analysis. Using an artificial intelligence model, the risk factors for recurrent gastric cancer could be identified and cost-effectively ranked according to their feature importance. In addition, they should be crucial clinical features to provide physicians with the knowledge to screen high-risk patients in gastric cancer survivors as well.

Timely and accurate information on tree species is crucial for the sustainable management of natural resources, forest inventory, biodiversity detection, and carbon stock calculation. The advancement of remote sensing technology and artificial intelligence has facilitated the acquisition and analysis of remote sensing data, resulting in more precise and effective classification of tree species. Multimodal remote sensing data and deep learning seem to be the current tree species classification research mainstream, whether or not. The current review on the remote sensing data and deep learning tree species classification methods perspectives to analyze the unimodal and multimodal remote sensing data and classification methods in this realm is missing. To bridge the gap, we search for major trends in the remote sensing data and tree species classification methods, provide a detailed overview of classic deep learning-based methods for tree species classification, and discuss the limitations.

Forest ecosystems make a greater contribution to carbon (C) stocks than any other terrestrial ecosystem. To understand the role of regional forest ecosystems in global climate change and carbon exchange, forest C stock and its spatial distribution within the small (2,300 km2) Liuxihe River basin were analyzed to determine the different contributors to the C stock. Forest C stocks were quantified by measuring the biomass of trees, understory vegetation, litter and roots, as well as soil organic C, using data from field samples and laboratory experiments. The results showed that forests stored 38.04 Tg C in the entire basin, with secondary and planted forests accounting for 89.82% and 10.18%, respectively, of the stored C. Five types of forests, a subtropical evergreen broad-leaved forest, a subtropical coniferous and broad-leaved mixed forest, a subtropical coniferous forest, a timber forest, and a non-wood forest, stored 257.55 ± 15.01, 218.92 ± 9.59, 195.24 ± 18.29, 177.42 ± 17.55, and 117.86 ± 6.04 Mg C ha−1, respectively. In the forest ecosystem C stocks of the basin, soils averagely contribute about 73.78%, not including root underground biomass. It provides a comprehensive method for forest ecosystem carbon investigation and forest management in small basin scale.

Vertical Indoor Farming (VIF) with hydroponics offers a promising perspective for sustainable food production. Intelligent control of VIF system components plays a key role in reducing operating costs and increasing crop yields. Modern machine vision (MV) systems use Deep Learning (DL) in combination with camera systems for various tasks in agriculture, such as disease and nutrient deficiency detection, and flower and fruit identification and classification for pollination and harvesting. This study presents the applicability of MV technology with DL modelling to detect the growth stages of chilli plants using YOLOv8 networks. The influence of different bird’s eye and side view datasets and different YOLOv8 architectures was analysed. To generate the image data for training and testing the YOLO models, chilli plants were grown in a hydroponic environment and imaged throughout their life cycle using four camera systems. The growth stages were divided into growing, flowering and fruiting classes. All trained YOLOv8 models showed reliable identification of growth stages with high accuracy. The results indicate that models trained with data from both views show better generalisation. YOLO’s middle architecture achieved the best performance.

The power of the river does not always work to the benefit of living things; rather, it has the ability to destroy human society and has negative effects on the environment. River Teesta has a prodigious significance on the riverine dweller and its changing precarious behaviour has repercussions on the lives of millions. Utilizing satellite images and 41 years of temporal analysis, the mapping of channel extraction and channel shifting has been demonstrated. Delineating the exact channel boundary is a laborious operation, but MNDWI technique is really valuable in this situation to produce valuable results. Descriptive statistics are used to analyze the Teesta River's active flow line migration trend and channel migration behaviour. A particular river's oscillating character over time has both beneficial and detrimental power, destroying important resources for environmental sustainability and human society while also providing fertile mother earth as a source of wealth. As a result, another goal of the current study was to determine how vulnerable riverine residents were. A livelihood vulnerability index (LVI) based on the riverine inhabitants' exposure, sensitivity, and capacity for adaptation was created. According to the findings, the river's erratic behaviour is putting the people who live beside it in danger. Therefore, it is vitally necessary to implement a capable management strategy to stop bank failure at the Teesta-Dharala confluence in order to save the riverine residents.

The pharmaceutical industry is one of the largest pollutants and generator of toxic solvent resi-dues for the environment and human beings. In the last decade, there has been a huge evolution in the design and development of new environmentally friendly products and processes, in re-sponse to the global environmental concern and the growing demand for products with quality ingredients and manufacturing processes aimed at achieving sustainability. Consumers are looking for products with the benefits of natural products, with sustainable and environmentally friendly formulations with few synthetic molecules as possible. Thus, based on the origins of the pharmaceutical industry, it is important to return to Nature and enjoy the benefits that natural products bring to us. Deep eutectic solvents appear as an alternative to toxic solvents commonly used to extract bioactive compounds. These solvents are considered green solvents because they are made up of natural compounds such as sugars, amino acids, and carboxylic acids. In addition, they are simple to prepare, with an atomic economy of 100%, with attractive physicochemical properties. This paper is a comprehensive review in which is described the main properties, characteristics, and production methods of deep eutectic solvents as well as its application to extract from natural sources bioactive compounds with pharmaceutical interest.

The present work was performed to evaluate the levels of phytochemical constituents and the antioxidant and antibacterial properties of marine red seaweed (Kappaphycus alvarezii) and seagrass (Cymodocea serrulata). Quantitative phytochemical analysis, antioxidant activity and antimicrobial activity against 5 potential pathogenic bacteria was investigated. In both cases were found presence of flavonoids, tannins, phenolic compounds, glycosides, steroids, carbohydrates and ashes. Alkaloids were only found in K. alvarezii, buy not in C. serrulata. The antimicrobial properties of both K. alvarezii and C. serrulata chloroform extracts were found to be antagonis-tically effective against the gram-positive bacterium Bacillus subtilis and the gram-negative bacterium Vibrio parahaemolyticus, Vibrio alginolyticus, Vibrio harveyi and Klebsiella pneu-moniae. GC‒MS analysis revealed the presence of 94 bioactive compounds in K. alvarezii and 104 C. serrulata, including phenol, decane, dodecane, hexadecane, vanillin, heptadecane, diphenyla-mine, benzophenone, octadecanoic acid, dotriaconate, benzene, phytol, butanoic acid, and 2-hydroxyl-ethyl ether, which played a vital role in antioxidant and antibacterial activities. Thus, in view of the results, both K. alvarezii and C. serrulata could be considered as sources of ingre-dients with appreciable nutritional and medicinal value.

In large-capacity energy storage systems, instructions are decomposed typically using an equalized power distribution strategy, where clusters/modules operate at the same power and durations. When dispatching shifts from stable single conditions to intricate coupled conditions, this distribution strategy inevitably results in increased inconsistency and hastened system aging. This paper presents a novel differentiated power distribution strategy comprising three control variables: the rotation status, the operating boundaries for both Depth of Discharge (DOD) and C-rates (C) within a control period. The proposed strategy integrates an aging cost prediction model developed to express the mapping relationship between these control variables and aging costs. Additionally, it incorporates the multi-colony particle swarm optimization (Mc-PSO) algorithm into the optimization model to minimize aging costs. The aging cost prediction model consists of three functions: predicting health features (HFs) based on the cumulative charge/discharge throughput quantity and operating boundaries, characterizing HFs as comprehensive scores, and calculating aging costs using both comprehensive scores and residual equipment value. Further, we elaborated on the engineering application process for the proposed control strategy. In the simulation scenarios, this strategy prolonged the service life by 14.62%, reduced the overall aging cost by 6.61%, and improved module consistency by 21.98%, compared with the traditional equalized distribution strategy. In summary, the proposed strategy proves effective in elongating service life, reducing overall aging costs, and increasing the benefit of energy storage systems in particular application scenarios.

The research and development of non-viral gene therapy has been extensive over the past decade and has received a big push thanks to the successful approval of non-viral gene therapy products in recent times. Despite these developments, gene therapy applications in cancer have been limited. One of the main causes of this has been the imbalance in development of delivery vectors as compared to nucleic acid payloads. This paper reviews non-viral vectors that can be used to deliver nucleic acids for cancer treatment. It discusses various types of vectors and highlights their current applications. Additionally, it also discusses perspective on regulatory landscape to facilitate commercial translation of gene therapy.

Classical Arabic poetry is a form of Arabic literature, and almost every piece of Arabic poetry follows one of the 16 meters. The rhythmic framework of the poems or the verses is called meters. The deep learning (DL) model was implemented using TensorFlow in this work using a large dataset of Arabic poetry. The character level encoding was used to convert text to integers for classifying the full-verse and half-verse data. The study evaluates the data without removing diacritics from the text. The train-test-split method with a 70-15-15 split was employed for classification. 15% of the total data was considered unseen test data for all models. The work was conducted with multiple deep learning models, including the Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), and Bidirectional LSTM (Bi-LSTM). The Bi-LSTM model shows the best accuracy of all the models specified, with 97.53% for full-verse and 95.23% for half-verse without removing diacritic data.

This comprehensive review explores the multifaceted landscape of supercapacitors, highlighting their pivotal role in meeting the global demand for efficient energy storage solutions. Supercapacitors, with their high power density, rapid charge-discharge cycles, and extended cycle life, offer a compelling alternative to conventional batteries and capacitors. The review delves into the fundamental mechanisms of energy storage in supercapacitors, categorizing them into Electrochemical Double-Layer Capacitors (EDLCs), pseudocapacitors, and hybrid capacitors. It discusses significant advancements in supercapacitor technology, including nanostructured materials, flexible and wearable supercapacitors, solid-state supercapacitors, and hybrid supercapacitors, highlighting their potential applications across industries such as transportation, renewable energy, consumer electronics, and industrial power management. Through continued research and development, supercapacitors are poised to play a pivotal role in driving the transition towards a greener and more efficient future.

. In today’s world, cyber attack is one of the major issues concerning the organizations that deal with technologies like cloud computing, big data, IoT etc. In the area of cyber security, intrusion detection system (IDS) plays a crucial role to identify suspicious activities in the network traffic. Over the past few years, a lot of research has been done in this area but in the current scenario, network attacks are diversifying in both volume and variety. In this regard, this research article proposes a novel IDS where a combination of information gain and decision tree algorithm has been used for the purpose of dimension reduction and classification. For experimental purpose the NSL-KDD dataset has been used. Initially out of 41 features present in the dataset only 5 high information gain valued features are selected for classification purpose. The applicability of the selected features are evaluated through various machine learning based algorithms. The experimental result shows that the decision tree based algorithm records highest recognition accuracy among all the classifiers. Based on the initial classification result a novel methodology based on decision tree has been further developed which is capable of identifying multiple attacks by analyzing the packets of various transactions in real time.

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

The application of space robotic manipulators and heightened autonomy for ios represents a paramount pursuit for leading space agencies, given the substantial threat posed by space debris to operational satellites and forthcoming space endeavors. This work presents a guidance algorithm based on drl to solve for the space manipulator path-planning during the motion synchronization phase with the mission target. The goal is the trajectory generation and control of a spacecraft equipped with a 7-dof robotic manipulator, such that its end effector remains stationary with respect to the target point of capture. The ppo drl algorithm is used to optimize the manipulator’s guidance law, and the autonomous agent generates the desired joints rates of the robotic arm, which are then integrated and passed to a model-based feedback linearization controller. The agent is first trained to optimize its guidance policy and then tested extensively to validate the results against a simulated environment representing the motion synchronization scenario of an ios mission.

Metabolic Associated Steatohepatitis Liver Disease (MASLD) currently impacts a quarter of the global population and its prevalence is expected to increase in the future. As a result, the incidence of hepatocellular carcinoma associated with MASLD is also on the rise. Notably, hepatocellular carcinoma in this group does not always develop alongside liver cirrhosis, often leading to a more advanced stage at diagnosis. The challenge lies in accurately identifying patients who are at a higher risk of hepatocellular carcinoma to tailor screening processes effectively. Additionally, several therapeutic approaches are being explored to prevent hepatocellular carcinoma, although there are yet no universally accepted guidelines

GM2 gangliosidoses are a group of pathologies characterized by GM2 ganglioside accumulation into the lysosome due to mutations on the genes encoding for the β-hexosaminidases subunits or the GM2 activator protein. Three GM2 gangliosidoses have been described: Tay-Sachs disease, Sandhoff disease, and the AB variant. Central nervous system dysfunction is the main characteristic of GM2 gangliosidoses patients that include neurodevelopment alterations, neuroinflammation, and neuronal apoptosis. Currently, there is not approved therapy for GM2 gangliosidoses, but different therapeutic strategies have been studied including hematopoietic stem cell transplantation, enzyme replacement therapy, substrate reduction therapy, pharmacological chaperones, and gene therapy. The blood-brain barrier represents a challenge for the development of therapeutic agents for these disorders. In this sense, alternative routes of administration (e.g. intrathecal or intracerebroventricular) have been evaluated, as well as the design of fusion peptides that allow the protein transport from the brain capillaries to the central nervous system. In this review, we outline the current knowledge about clinical and physiopathological findings of GM2 gangliosidoses, as well as the ongoing proposals to overcome some limitations of the traditional alternatives by using novel strategies such as molecular Trojan horses or advanced tools of genome editing.

The QCD Lagrangian is based on quark and gluonic fields -- not squarks nor gluinos. However, one can show that its hadronic eigensolutions conform to a representation of superconformal algebra, reflecting the underlying conformal symmetry of chiral QCD. The eigensolutions of superconformal algebra provide a unified Regge spectroscopy of meson, baryon, and tetraquarks of the same parity and twist as equal-mass members of the same 4-plet representation with a universal Regge slope. The predictions from light-front holography and superconformal algebra can also be extended to mesons, baryons, and tetraquarks with strange, charm and bottom quarks. % The pion $q \bar q$ eigenstate has zero mass for $m_q=0.$ % % A key tool is the remarkable observation of de Alfaro, Fubini, and Furlan (dAFF) which shows how a mass scale can appear in the Hamiltonian and the equations of motion while retaining the conformal symmetry of the action. When one applies the dAFF procedure to chiral QCD, a mass scale $\kappa$ appears which determines universal Regge slopes, hadron masses in the absence of the Higgs coupling. One also predicts the form of the nonperturbative QCD running coupling: $\alpha_s(Q^2) \propto e^{-{Q^2/4 \kappa^2}}$, in agreement with the effective charge determined from measurements of the Bjorken sum rule. One also obtains viable predictions for spacelike and timelike hadronic form factors, structure functions, distribution amplitudes, and transverse momentum distributions. % The combination of conformal symmetry, light-front dynamics, its holographic mapping to AdS$_5$ space, and the dAFF procedure thus provide new insights, not only into the physics underlying color confinement, but also the nonperturbative QCD coupling and the QCD mass scale.

Intelligent fault diagnosis techniques have replaced the time-consuming and unreliable human analysis, increasing the efficiency of fault diagnosis. Deep learning model can improve the accuracy of intelligent fault diagnosis with the help of its multilayer nonlinear mapping ability. This paper has proposed a novel method named Deep Convolutional Neural Networks with Wide First-layer Kernels (WDCNN). The proposed method uses raw vibration signals as input (data augmentation is used to generate more inputs), and uses the wide kernels in first convolutional layer for extracting feature and suppressing high frequency noise. Small convolutional kernels in the preceding layers are used for multilayer nonlinear mapping. AdaBN is implemented to improve the domain adaptation ability of the model. The proposed model addresses the problem that currently, the accuracy of CNN applied to fault diagnosis is not very high. WDCNN can not only achieve 100% classification accuracy on normal signals, but also outperform state of the art DNN model which is based on frequency features under different working load and noisy environment.

Effective agricultural management in maize production operations starts with the early quantification of seedlings. Accurately determining plant presence allows growers to optimize planting density, allocate resources, and detect potential growth issues early on. This study presents an in-depth analysis of multiple object detection models used by drones to count maize seedlings, while concurrently investigating the influence of planting density, flight altitude, and plant growth stage. The findings of this study demonstrate that one-stage models are able to more accurately detect maize seedlings than two-stage models. In particular, YOLOv8n exhibits outstanding performance, achieving an F1-score of over 0.92 under various density conditions and maintaining a stable performance, especially under densities below 105,000 plants/ha. Additionally, planting density and growth stage were observed to significantly affect detection accuracy, with performance declining as density and growth stage increased. Image resolution and detection were impacted by flight altitude, with lower flights producing higher-quality results. Ultimately, YOLOv8n displays optimal performance under various conditions, providing crucial data to support intelligent decision-making. This research offers valuable insights into the application of object detection technology and provides a basis for the future development of precision agriculture.

The advent of deep learning (DL) has revolutionized medical imaging, offering unprecedented avenues for accurate disease classification and diagnosis. DL models have shown remarkable promise for classifying brain tumor from Magnetic Resonance Imaging (MRI) scans. However, despite their impressive performance, the opaque nature of DL models poses challenges in understanding their decision-making processes, particularly crucial in medical contexts where interpretability is essential. This paper explores the intersection of medical image analysis and DL interpretability, aiming to elucidate the decision-making rationale of DL models in brain tumor classification. Leveraging state-of-the-art DL frameworks with transfer learning, we conduct a comprehensive evaluation encompassing both classification accuracy and interpretability. Using state-of-the-art DL frameworks with transfer learning, we conduct a thorough evaluation covering both classification accuracy and interpretability. We employ adaptive path-based techniques to understand the underlying decision-making mechanisms of these models. Grad-CAM and Grad-CAM++ highlight critical image regions where the tumors are located.

Cannabis, renowned for its historical medicinal use, harbours various bioactive compounds—cannabinoids, terpenes, and flavonoids. While major cannabinoids like THC and CBD have received extensive scrutiny for their pharmacological properties, emerging evidence underscores the collaborative interactions among these constituents, suggesting a collective therapeutic potential. This comprehensive review explores the intricate relationships and synergies between cannabinoids, terpenes, and flavonoids in cannabis. Cannabinoids, pivotal in cannabis's bioactivity, exhibit well-documented analgesic, anti-inflammatory, and neuroprotective effects. Terpenes, aromatic compounds imbuing distinct flavours, not only contribute to cannabis's sensory profile but also modulate cannabinoid effects through diverse molecular mechanisms. Flavonoids, another cannabis component, demonstrate anti-inflammatory, antioxidant, and neuroprotective properties, particularly relevant to neuroinflammation. The entourage hypothesis posits that combined cannabinoid, terpene, and flavonoid action yields synergistic or additive effects, surpassing individual compound efficacy. Recognizing the nuanced interactions is crucial for unravelling cannabis's complete therapeutic potential. Tailoring treatments based on the holistic composition of cannabis strains allows optimization of therapeutic outcomes while minimizing potential side effects. This review underscores the imperative to delve into the intricate roles of cannabinoids, terpenes, and flavonoids, offering promising prospects for innovative therapeutic interventions and advocating continued research to unlock cannabis's full therapeutic potential within the realm of natural plant-based medicine.

Breast cancer is the leading cause of cancer deaths worldwide in women. This aggressive tumour can be categorized into two main groups: in situ and infiltrative, with the latter being the most common malignant lesions. The current use of Magnetic Resonance Imaging (MRI) was shown to provide highest sensitivity in the detection and discrimination between benign vs. malignant lesions, when interpreted by expert radiologists. In this article, we present the prototype of a Computer-Aided Detection/Diagnosis (CAD) system that could provide valuable assistance to the radiologist for the discrimination between in situ and infiltrating tumours. The system consists of two main processing levels: 1) Localization of possibly tumoral regions of interest (ROIs) through an iterative procedure based on intensity values (ROI Hunter) followed by a deep-feature extraction and classification method for false-positive rejection; 2) Characterization of the selected ROIs and discrimination between in situ and invasive tumour, consisting of Radiomics feature extraction and classification through a machine-learning algorithm. The CAD system was developed and evaluated using a DCE-MRI image database, containing at least one confirmed mass per image, as diagnosed by an expert radiologist. When evaluating the accuracy of the ROI Hunter procedure with respect to the radiologist-drawn boundaries, sensitivity to mass detection was found to be 75%. The AUC of the ROC curve for discrimination between in situ and infiltrative tumors was 0.70.

High-throughput screening technologies continues to produce large amounts of multiomics data from different populations and cell types for various diseases, such as cancer. However, analysis of such data encounters difficulties due to cancer heterogeneity, further exacerbated by human biological complexity and genomic variability. There is a need to redefine the drug discovery development pipeline, bringing an Artificial Intelligence (AI)-powered informational view that integrates relevant biological information and explores new ways to develop effective anticancer approaches. Here, we show SynPred, an interdisciplinary approach that leverages specifically designed ensembles of AI-algorithms, links omics and biophysical traits to predict synergistic anticancer drug synergy. SynPred exhibits state-of-the-art performance metrics: accuracy – 0.85, precision – 0.77, recall – 0.75, AUROC – 0.82, and F1-score - 0.76 in an independent test set. Moreover, data interpretability was achieved by deploying the most current and robust feature importance approaches. A simple web-based application available online at http://www.moreiralab.com/resources/synpred/ was constructed to predict synergistic anticancer drug combinations requiring only the upload of the two drug SMILES to be tested, allowing easy access by non-expert researchers.

Magnetorheological (MR) fluids have been known to react to magnetic fields of sufficient magnitudes. While in the presence of the field the material develops a yield stress. The tunable property has made it attractive in e.g. semi-active damper applications in vibration control domain in particular. Within the context of a given application the fluids can be exploited in at least one of the fundamental operating modes of which the so-called gradient pinch mode has been least explored. Contrary to the other operating modes, the MR fluid volume in the flow channel is exposed to a non-uniform magnetic field in such a way that the Venturi-like contraction is developed in a flow channel solely by means of a solidified material in the regions near the walls rather than mechanically driven changes of the channel’s geometry. The pinch mode rheology of the material has made it a potential candidate in developing on a new category of MR valves. By convention, a pinch mode valve features a single flow channel with poles over which non-uniform magnetic field is induced. In this study the authors examine ways of extending the dynamic range of pinch mode valves by employing a number of such arrangements (stages) in series. To accomplish this, the authors developed a prototype of a multi-stage (three-stage) valve, and then compared its performance against that of a single-stage valve across a wide range of hydraulic and magnetic stimuli. To summarize, improvements in the pinch mode valve dynamic range are evident, however, at the same time it is hampered by the presence of serial air gaps in the flow channel.

Microscopic vision plays an important role in automated micro-assembly. However, some uncertain factors in the assembly process, such as occlusion and stains can lead to the mistakes of feature extraction. Herein, to solve the problem, the deep learning techniques are introduced into the feature recognition tasks, focusing on the attention mechanism and visualizing CNNs for DL-based microscopic vision. The main contributions are summarized as follows: The CBAM attention mechanism is combined with the YOLOv5 algorithm to improve the accuracy and robustness of feature extraction. The micropart feature occlusion experiment results show that at 70% occlusion degree, YOLOV5-CBAM can reach 97.9% [email protected], which is 4.6% higher than the original one. Visualization analysis of DL-based model is conducted using Grad-CAM to make the decision result more transparent and avoid potential visual detection risks during assembly. The heatmap matching degree between GT area and high-light area is increased by 27.81% on average, which further verify the effectiveness of attention mechanism in micropart feature localization. Additionally, micropart surface stain and droplet quality classification models based on ResNet50 are trained to replace the manual sorting. The visual results are consistent with human eye discernment and judgement, confirming the reliability of parts and droplets sorting.

In this study, seventeen faceted gem-quality chrysoberyls exhibiting an attractive canary yellow color were investigated by a series of gemological, spectral, and chemical methods. Microscopic observation reveals distinct growth lines and inclusions, including CO2 fluids, carbon, and mineral crystals such as calcite, quartz, sillimanite, and mica, identified by the Raman spectrum. The FTIR spectrum exhibits the 2405 and 2160 cm-1 feature peaks and a 3223 cm-1 peak in all samples, which can be accompanied by the 3112 cm-1 shoulder, 3301, and 3412 and 3432 cm-1 peaks. The UV-Vis spectrum shows a Fe-related peak at 440 nm, along with the 650–660 nm band and the absorption band in the blue zone of the visible light. The chemical results of EDXRF reveal a V-poor, Cr-poor, and Fe-rich feature. The spectral and chemical results could contribute to explaining the origin of the canary yellow color, which originates from the abundant amount of Fe with very little influence from Cr or V.

Machine learning methods have been a standard approach to select features that are associated with an outcome and build a prediction model when the number of candidate features is large. LASSO has been one of the most popular approaches to this end. LASSO approach selects features with large regression estimates, rather than based on statistical significance, associating the outcome, by imposing L1-norm penalty to overcome the high dimensionality of the candidate features. As a result, LASSO may select insignificant features while possibly missing significant ones. Furthermore, from our experience, LASSO has been found to select too many features. By selecting features that are not associated with the outcome, we may have to spend more cost to collect and manage them in the future use of a fitted prediction model. Using the combination of L1- and L2-norm penalties, elastic net (EN) tends to select more features than LASSO. The overly selected features that are not associated with the outcome act like white noise, so that the fitted prediction model loses the prediction accuracy. In this paper, we propose to use the standard regression methods (without any penalizing approach) with stepwise variable selection procedure to overcome these issues. Unlike LASSO and EN, this method selects features based on statistical significance. Through extensive simulations, we show that this maximum likelihood estimation based method selects very small number of features while maintaining a high prediction power, while LASSO and EN make a large number of false selections to result in loss of prediction accuracy. Contrary to LASSO and EN, the regression methods combined with a stepwise variable selection method is a standard statistical method, so that any biostatistician can use it to analyze high dimensional data even without advanced bioinformatics knowledge.

Nowadays, speed up development and use of digital devices such as smartphones have put people at risk of internet crimes. The evidence of present crimes in a computer file can be easily unreachable by changing the prefix of a file or other algorithms. In more complex cases, either file divided into different parts or the parts of a file that has information about the file type are deleted, where the file fragment recognition issue is discussed. The known files are divided into different fragments, and different classification algorithms to solve the problems of file fragment recognition. A confusion matrix measures the accuracy of type recognition. In the present study, first, the file is divided into different fragments. Then, the file fragment features, which are obtained from Binary Frequency Distribution (BFD), are reduced by 2 feature reduction algorithms; Sequential Forward Selection algorithm (SFS) as well as Sequential Floating Forward Selection algorithm (SFFS) to delete sparse features that result in increased accuracy and speed. Finally, the reduced features are given to 3 classifier algorithms, Multilayer Perceptron (MLP), Support Vector Machines (SVM), and K-Nearest Neighbor (KNN) for classification and comparison of the results. In this paper, we proposed the algorithm of file type recognition that can recognize 6 types of useful files ( pdf, txt, jpg, doc, html, exe), which may distinguish a type of file fragments with higher accuracy than the similar works done.

This observational study was ordered by the Medical Practitioners’ Chamber in Warsaw. The objective of the study was to evaluate the health status of physicians in relation to their occupational duties. Professional burnout was considered relative to different features of personality. This study was initially carried out from 2005–2008, but further analysis of burnout and personality was carried out from 2017–2018. The research tools were anonymous, validated questionnaires. The sample size was based on the size of the population— the registry of the Regional Chamber of Medical Practitioners— and literature on burnout prevalence. The respondents’ work places were randomly selected from the Mazovian District register. The test on burnout was completed by 378 respondents, while 62 subjects completed a personality test. Results showed that burnout syndrome was an occupational problem for healthcare workers. Professional burnout affected as many as 42% of respondents(n = 158). It affected two age groups in particular: physicians up to 31 years old and individuals aged 41-50. Moreover, neuroticism was found to be significantly related to burnout syndrome. In conclusion, burnout syndrome is common among medical practitioners, and neuroticism may be correlated with burnout syndrome.

We present a brief history of the construction of models of the universe, followed by calculations of quantitative characteristics of basic geometric and kinematic properties of the Standard Cosmological Model ($\Lambda$CDM). Using the Friedmann equations of uniform space, we derive equations characterizing a $\Lambda$CDM model that describes a universe corresponding to current observational data. The equations take into account the effects of radiation and ultra-relativistic neutrinos. It is shown that the universe at very early and late stages can be described to sufficient accuracy by simple formulas. Certain important moments of cosmic evolution are determined: the times when densities of the gravitational components of the universe become equal, when they contribute equally to the gravitational force, when the accelerating expansion of space begins, and several others. The dependences of different distances on redshift and the scale factor of space are derived. The distance to the sphere that expands with the speed of light (the Hubble distance), and its current and future acceleration, are found. Concepts of a horizon, second inflation, and second horizon are discussed. We consider the remote future of the universe and the opportunity, in principle, of connection with extraterrestrial civilizations.

Background: Few studies have assessed built environment correlates of active commuting in low-and-middle-income countries, but the different context could yield distinct findings. This cross-sectional study investigated associations between home neighbourhood environment characteristics and active commuting in Chennai, India. Methods: Adults (N = 370, 47.2% female, mean age = 37.9 years) were recruited from 155 wards in the metropolitan area of Chennai in southern India between January and June 2015. Participants self-reported their usual mode of commute to work, with responses recoded into three categories: (1) multi-modal or active commuting (walking and bicycling); (2) public transit; and (3) private transport. Environmental attributes around participants’ homes were assessed using the Neighborhood Environment Walkability Scale-India (NEWS-India). Associations between environmental characteristics and likelihood of active commuting and public transit use were modelled using logistic regression with private transport (driving alone or carpool) as the reference category, adjusting for age, gender, and household car ownership. Results: Consistent with other international studies, participants living in neighbourhoods with a mix of land-uses and a transit stop within a 10-minute walk from home were more likely to use active commuting (both p < 0.01). Land-use mix was significantly associated with the use of public transit compared to private transport (aOR = 5.2, p = 0.002). Contrary to findings in high-income countries, the odds of active commuting were reduced with improved safety from crime (aOR = 0.2, p = 0.003), aesthetics (aOR = 0.2, p = 0.05) and street connectivity (aOR = 0.2, p = 0.003). Conclusions: Different environmental attributes were associated with active commuting, suggesting that these relationships are complex and may distinctly differ from those in high-income countries. Unexpected inverse associations of perceived safety from crime and aesthetics with active commuting emphasize the need for high quality epidemiologic studies with greater context-specificity in the study of physical activity in LMICs. Findings have public health implications for India and suggest that caution should be taken when translating evidence across countries.

In recent years, unmanned aerial vehicles (UAVs) have become a valuable platform for many applications, including communication networks. UAV-enabled wireless communication faces challenges in complex urban and dynamic environments. UAVs can suffer from power limitations and path losses caused by non-line-of-sight connections, which may hamper better communication performance. To address these issues, reconfigurable intelligent surfaces (RIS) have been proposed as a helpful tool to enhance UAV communication networks. However, due to the high mobility of UAV, complex channel environments, and dynamic RIS configurations, it is challenging to estimate the link quality of ground users. In this paper, we propose a link quality estimation model using a gated recurrent unit (GRU) to assess the link quality of ground users for a multi-user RIS-assisted UAV-enabled wireless communication system. Our proposed framework uses a time series of user channel data and RIS phase shift information to estimate the quality of the link for each ground user. Simulation results showed that the proposed GRU model effectively and accurately estimates the link quality of the ground users in the RIS-assisted UAV-enabled wireless communication network.

Recent advances in artificial intelligence combined with behavioral sciences have led to the development of cutting-edge tools for recognizing human emotions based on text, video, audio, and physiological data. However, these data sources are expensive, intrusive, and regulated, unlike plants which have been shown to be sensitive to human steps and sounds. A methodology is proposed to use plants as human emotion detectors. Electrical signals from plants are tracked and labeled based on video data. Labeled data are then used for classification. MLP, biLSTM, MFCC-CNN, MFCC-ResNet, and additionally, Random Forests, 1-Dimensional CNN, and biLSTM without windowing models are set using a grid search algorithm with cross-validation. Finally, best-parameterized models are trained and used with the test set for classification. The performance of this methodology is measured with a case study with 54 participants, who were watching an emotionally charged video, as ground truth their facial emotions were simultaneously measured using face emotion analysis. The Random Forest model shows the best performance, particularly in recognizing high-arousal emotions, achieving an overall weighted accuracy of 55.2% and demonstrating high weighted recall in emotions such as fear 61.0% and happiness 60.4%. The MFCC-ResNet model offers decently balanced results, with Accuracy(MFCC-ResNet)=0.318 and Recall (MFCC-ResNet)=0.324. With the MFCC-ResNet model fear and anger are recognized with 75% and 50% recall respectively. Thus, using plants as an emotion recognition tool seems worth investigating, addressing both cost and privacy concerns.

Visual imagery, i.e., the mental experience of an object occurring in the absence of external visual stimulus, might encompass diverse content according to different observers. Further, subjectively experienced time is encoded in the later entorhinal cortex. Starting from these two observations, and considering Einstein’s account of spacetime, we show how, in terms of special relativity, the content of visual imagery is not stationary and fixed, rather depends on the standpoint of the observer. We elucidate how the subjective definition of time (perceived by our mind as static) might give rise to modifications in the length of the imagined object which are experimentally assessable and quantifiable. In particular, based on recent neuroscientific literature, we show how changes in our mental time windows are able to squeeze the visual content of mental imagery.

Proteins play a major role in biosensors in which they provide catalytic activity and specificity in molecular recognition. The immobilization process is however far from straightforward as it often affects the protein functionality. An extensive interaction of the protein with the surface or a significant surface crowding can lead to changes in the mobility and conformation of the protein structure. This review will provide an insight of how the analysis of the physico-chemical features of the protein surface features before the immobilization process can help to identify the optimal immobilization approach to preserve the functionality of the protein when on the surface of the biosensor.

Deep learning (DL), which is originated from an artificial neural network (ANN), is one of the major technologies of today's smart cybersecurity systems or policies to function in an intelligent manner. Popular deep learning techniques, such as Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN or ConvNet), Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM), Self-organizing Map (SOM), Auto-Encoder (AE), Restricted Boltzmann Machine (RBM), Deep Belief Networks (DBN), Generative Adversarial Network (GAN), Deep Transfer Learning (DTL or Deep TL), Deep Reinforcement Learning (DRL or Deep RL), or their ensembles and hybrid approaches can be used to intelligently tackle the diverse cybersecurity issues. In this paper, we aim to present a comprehensive overview from the perspective of these neural networks and deep learning techniques according to today's diverse needs. We also discuss the applicability of these techniques in various cybersecurity tasks such as intrusion detection, identification of malware or botnets, phishing, predicting cyber-attacks, e.g. denial of service (DoS), fraud detection or cyber-anomalies, etc. Finally, we highlight several research issues and future directions within the scope of our study in the field. Overall, the ultimate goal of this paper is to serve as a reference point and guidelines for the academia and professionals in the cyber industries, especially from the deep learning point of view.

Hybrid forecasting methods have emerged as a solution surpassing the limitations of both statistical and deep learning approaches. While the first emphasize the significance of variables, they often produce worse forecasting results when compared to newer techniques. In contrast, deep learning models remain enigmatic "black boxes" in terms of interpretability, although achieving better results in forecasting. This article introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, designed to harness the best of both approaches, enhancing forecasting accuracy while retaining model interpretability through a feature selection process. CCLR-DL blens cross-correlation analysis, lagged multiple linear regression and granger's causality procedures with deep learning architectures based on LSTM. In a practical demonstration, CCLR-DL was applied to a real database of clinical visits associated to diagnoses in Catalonia, Spain (tracking a population of 6.3 million patients during 10 years). Predicting visits enables the healthcare managers to be ready for future demand shifts. Results demonstrate a consistent and substantial improvement over standalone statistical and deep learning methods when predicting healthcare demand. This hybrid approach not only showcases its efficacy but also offers a promising solution to the challenge of balancing predictive accuracy with model explicability. In this context, this work aims to design and validate a method for feature selection and forecasting of multivariate high dimensional time series datasets not only to improve prediction accuracy but also to model transparency by identifying a subset of variables that improve predictions and G-cause the target variable.

Due to the proliferation of genetic testing, pathogenic germline variants predisposing to hereditary hematological malignancy syndrome (HHMS) have been identified in an increasing number of genes. Consequently, the field of HHMS is gaining recognition among clinicians and scientists worldwide. Patients with germline genetic abnormalities often have poor outcomes and are candidates for allogeneic hematopoietic stem cell transplantation (HSCT). However, HSCT using blood from a related donor should be carefully considered because of the risk that the patient may inherit a pathogenic variant. At present, we now face the challenge of incorporating these advances into clinical practice for patients with myelodysplastic syndrome (MDS) or acute myeloid leukemia (AML) and optimizing the management and surveillance of patients and asymptomatic carriers, with the limitation that evidence-based guidelines are often inadequate. The 2016 revision of the WHO classification added a new section on myeloid malignant neoplasms, including MDS and AML with germline predisposition. The main syndromes can be classified into three groups. Those without pre-existing disease or organ dysfunction; DDX41, TP53, CEBPA, those with pre-existing platelet disorders; ANKRD26, ETV6, RUNX1, and those with other organ dysfunctions; SAMD9/SAMD9L, GATA2, and inherited bone marrow failure syndromes. In this review, we will outline the role of the genes involved in HHMS in order to clarify our understanding of HHMS.

In this paper, we investigate an exact Universe which is observational viable and filled with binary mixture of perfect fluid and cosmological constant $\Lambda$. Owning the non-uniform expansion of cosmos, we have considered redshift drift $\dot{z} = -(1+z)H_{0}+H(z)$ and performed statistical test to obtain the best fit value of model parameters of derived Universe with its observed values. Here $H_{0}$ and $z$ denote the present value of Hubble constant and redshift respectively. We estimate the best fit values of Hubble constant and density parameters are $H_{0} = 68.58 \pm 0.84$ km/s/Mpc, $(\Omega_{m})_{0} = 0.26 \pm 0.010$ and $(\Omega_{\Lambda})_{0} = 0.71 \pm 0.025$ by bounding the derived model with latest observational Hubble data (OHD) while with joint Pantheon data and OHD, its values are $H_{0} = 71.93 \pm 0.58$ km/s/Mpc, $(\Omega_{m})_{0} = 0.272 \pm 0.06$ and $(\Omega_{\Lambda})_{0} = 0.74 \pm 0.09$. The analysis of deceleration parameter and jerk parameter show that the Universe in derived model is compatible with $\Lambda$CDM model.

Helicobacter pylori is a gastric pathogen that infects nearly half of the global population and is recognized as a group 1 carcinogen by the Word Health Organization. The global rise in antibiotic resistance has increased clinical challenges in treating H. pylori infections. Biofilm growth has been proposed to contribute to H. pylori’s chronic colonization of the host stomach, treatment failures, and the eventual development of gastric diseases. Several components of H. pylori have been identified to promote biofilm growth, and several of these may also facilitate antibiotic tolerance, including the extracellular matrix, outer membrane proteins, the coccoid morphology, modulated metabolism, efflux pumps, and virulence factors. Recent developments in therapeutic approaches targeting H. pylori biofilm have shown that synthetic compounds, such as small molecule drugs and plant-derived compounds, are effective at eradicating H. pylori biofilms. These combined topics highlight the necessity for biofilm-based research in H. pylori, to improve current H. pylori targeted therapeutic approaches and alleviate relative public health burden. In this review we discuss recent discoveries that have decoded the life cycle of H. pylori biofilms and current biofilm targeted treatment strategies.

CNN-based off-the-shelf features have shown themselves as a good baseline for trademark retrieval. However, in recent years, the computer vision area was transitioning from CNNs to a new architecture – Vision Transformer. In this paper, we investigate the performance of off-the-shelf features extracted with vision transformers and explore the effects of pre, post-processing, and pre-training on big datasets. We propose a method of joint usage of global and local features, which leverages the best aspects of both approaches. Experimental results on METU Trademark Dataset show that off-the-shelf features extracted with ViT-based models outperform off-the-shelf features from CNN-based models. The proposed method achieves the mAP value of 31.23, surpassing previous state-of-the-art results. We assume that the proposed approach for the trademark similarity evaluation will allow one to improve the protection of such data with the help of artificial intelligence methods. Moreover, this approach will allow one to identify cases of unfair use of such data and form an evidence base for litigation.

The inositol triphosphate associated proteins IRAG1 and IRAG2 are cGMP kinase substrate proteins, which regulate intracellular Ca2+. Previously, IRAG1 was discovered as a 125 kDa membrane protein at the endoplasmic reticulum, that is associated with the intracellular Ca2+ channel IP3R-I and the PKGIβ and inhibits IP3R-I upon PKGIβ-mediated phosphorylation. IRAG2 is a 75 kDa membrane protein homologue of IRAG1 and was recently also determined as a PKGI substrate protein. Several (patho-)physiological functions of IRAG1 and IRAG2 were meanwhile and recently elucidated in a variety of human and murine tissues, e.g. of IRAG1 in various smooth muscles, heart, platelets and other blood cells, of IRAG2 in pancreas, heart, platelets and taste cells. Hence, lack of IRAG1 or IRAG2 leads to diverse phenotypes in these organs, e.g. smooth muscle and platelet disorders or secretory deficiency, respectively. This review aims to highlight the recent research regarding these both regulatory proteins to envision its molecular and (patho-)physiological tasks and to unravel its functional interplay as possible (patho-)physiological counterparts.

in this work formulations of "environmentally compatible" silicone-based antifouling synthesized in the laboratory and based on copper and silver on silica/titania oxides have been characterized, capable of replacing the non-ecological antifouling paints currently on the market. The texture properties and the morphological analysis of these powders with an antifouling action indicate that their activity is linked to the nanometric size of the particles and to the homogeneous dispersion of the metal on the substrate. The presence of two metal species on the same support limits the for-mation of nanometric species and therefore the formation of homogeneous compounds. The presence of the antifouling filler (specifically the one based on TiO2 and Ag) facilitates the achievement of a higher degree of cross-linking of the pure resin, and therefore a better compactness and completeness of the coating. This leads to a consequent better degree of adhesion to the tie-coat and therefore to the steel support used for the construction of the boats.

Global demand for sleep-tracking wearables, or consumer sleep technologies (CSTs), is steadily increasing. CST marketing campaigns often feature a scientific component, but the scientific relevancy and monetary value of CST features within the sleep research community remains unquantified. Sleep medicine experts were recruited through social media and nonprobability sampling techniques to complete a survey identifying sleep metrics and device features that are most desirable to the scientific community. A hypothetical purchase task (HPT) estimated economic valuation for devices with different features by price. Forty-six (N=46) respondents with an average of 10±6 years’ experience conducting research in real-world settings completed the online survey. Total sleep time was ranked as the most important measure of sleep followed by objective sleep quality while sleep architecture/depth and diagnostic information were ranked as least important. Experts preferred wrist-worn devices that could reliably determine sleep episodes as short as 20 minutes. Economic value was greater for hypothetical devices with longer battery life. These data set a precedent to determine how scientific relevance of a product impacts the potential market value of a CST device. This is the first known attempt to establish consensus opinion or economic valuation for scientifically-desirable CST features and metrics using expert elicitation.

Face verification for unrestricted faces in the wild is a challenging task. This paper proposes a method based on two deep convolutional neural networks(CNN) for face verification. In this work, we explore to use identification signal to supervise one CNN and the combination of semi-verification and identification to train the other one. In order to estimate semi-verification loss at a low computation cost, a circle, which is composed of all faces, is used for selecting face pairs from pairwise samples. In the process of face normalization, we propose to use different landmarks of faces to solve the problems caused by poses. And the final face representation is formed by the concatenating feature of each deep CNN after PCA reduction. What's more, each feature is a combination of multi-scale representations through making use of auxiliary classifiers. For the final verification, we only adopt the face representation of one region and one resolution of a face jointing Joint Bayesian classifier. Experiments show that our method can extract effective face representation with a small training dataset and our algorithm achieves 99.71% verification accuracy on LFW dataset.

We report on magnetic studies of inhomogeneous commercial and synthesized amorphous carbon (a-C) and a-C doped with sulfur (a-CS) powders which exhibit (i) peculiar magnetic behavior and (ii) traces of two superconducting (SC) phase ~ Tc=33 and at 65 K. (i) The temperature dependence of zero-field-cooled (ZFC) curves measured up to room temperature show a well distinguish elusive peaks around 50-80 K, their origin is not yet known. These peaks are totally washed-out in the second ZFC sweeps and in the FC branches as well. As a result, in the vicinity of the peaks, the FC curves lie below the ZFC peaks (FC<ZFC), a phenomenon which is rarely observed. These magnetic anomalies are intrinsic properties of a-C and a-CS materials (ii) SC was observed in three different a-C sources: (a) The commercial a-C powder contains 0.21% of sulfur and it is suggested that two different a-CS phases (at 33 and 65 K) are the origin of the two SC states observed. The compositions of these two phases are not yet unknown. The small SC volume fractions of the 33 K phase can be enhanced by a solid reaction with additional sulfur at 250 ºC. (b) The synthesized a-C powder (obtained from decomposition of sucrose) is not SC. However, when mixed with sulfur and heated at 400 ºC under a protective atmosphere, the a-CS powder obtained also show traces of a SC phase at TC= 42 K. (c)The same occurs in a-C thin films. The as-grown films are not SC but a SC phase at Tc = 34 K emerges after the films were reacted with sulfur at elevated temperatures. It is concluded therefore, that all SC phases observed are due to different unknown a-CS phases. Since the a-C and a-CS powders possess SC and magnetic states, we believe that these powders resemble the high TC curates and Fe-As based systems in which the SC and the magnetic states are closed related to each other.

Educational institutions must identify students who are academically struggling to provide them with necessary support to improve their performance. In this context, recommendation systems powered by deep learning techniques are vital for detecting and categorizing such students. These systems help students plan their future by uncovering patterns in their historical academic data. This study introduces a new deep learning model designed to classify academically underperforming students in educational settings. The model incorporates a Gated Recurrent Neural Network (GRU) and includes specific neural network features like a dense layer, max-pooling layer, and the ADAM optimization algorithm. The model's training and evaluation were conducted using a dataset comprising 15,165 student assessment records from various academic institutions. The performance of the developed GRU model was benchmarked against other educational recommendation systems, including Recurrent Neural Network models, AdaBoost, and the Artificial Immune Recognition System v2. The proposed GRU model demonstrated remarkable accuracy, achieving an overall rate of 99.70%.

Background: Pulmonary sequestration (PS), generally diagnosed using computed tomography pulmonary angiography (CTPA), is a rare congenital developmental malformation of the lung that is characterized by nonfunctional lung tissue independent of the normal lung tissue. This study summarizes the imaging features of the supplying arteries and draining vessels in patients with PS with an aim to assist with timely clinical diagnosis and operation guidance. Materials and Methods: A total of 55 patients with PS diagnosed on CTPA from multiple clinical centers were retrospectively analyzed. Data included demographic characteristics, imaging features, disease location, isolation type, and the features of supplying and draining vessels, as shown on CTPA images. Results: Of the 55 patients reviewed, 3 (5.45%) were children, 3 (5.45%) were adolescents, and 49 (89.09%) were adults, with a mean age of 44 years. Fifty-four (98.18%) patients had intralobar sequestration and one (1.82%) had extralobar sequestration. PS was noted 3.5 times more frequently in the left lower lobe than in the right lower lobe. For the supplying arteries, 47 (85.45%) were derived from the descending thoracic aorta, 1 (1.82%) from the abdominal aorta, 7 (12.73%) from the celiac axis, and 1 (1.82%) from the bronchial artery. The draining vessels were the pulmonary veins in 49 patients (89.09%), the umbilical vein in 1 (1.82%), the venae intercostal in 1 (1.82%), the pulmonary arteries in 11 (20.00%), and not shown on the images in 2 (3.64%). Conclusion: Clinical presentations of PS are non-specific and can be easily missed or misdiagnosed. However, CTPA can help improve the diagnostic accuracy and identify the supplying arteries and draining vessels, which significantly contribute to surgical planning.

Mitochondrial carriers facilitate the transfer of small molecules across the inner mitochondrial membrane (IMM) to support mitochondrial function and core cellular processes. In addition to the classical mitochondrial carrier family SLC25, the past decade led to the discovery of additional protein families that exhibit IMM localization and transporter-like properties. These include mitochondrial pyruvate carriers, sideroflexins and mitochondrial cation/H+ exchangers that have been linked to vital physiological functions and disease. Their structures and transport mechanisms are still largely unknown and understudied. Protein sequence analysis per se can often pinpoint hotspots that are of functional or structural importance. In this review, we summarize current knowledge about sequence features of mitochondrial transporters with a special focus on the newly included SLC54, SLC55 and SLC56 families of the SLC solute carrier superfamily. Taking a step further, we combined sequence conservation analysis with transmembrane segment and secondary structure prediction methods to extract residue positions and sequence motifs that likely play a role in substrate binding, binding site gating or structural stability. We hope that our review will help guide future experimental efforts by the scientific community to unravel the transport mechanism and structure of these novel mitochondrial carriers.

The building blocks of a scientific facility based on particle beams comprise magnets and electro-magnetic devices. The design of an overall accelerator usually imposes a demanding accuracy on their exact position and orientation. Their non-geometrical functional features are frequently either not clearly defined – what is the « magnetic axis » of a magnet –, or not explicitly used along their lifecycle. Improving the process to establish and use these functional features would contribute to meeting demanding challenges. The European Spallation Source (ESS) is aiming at providing a powerful proton linear accelerator and a target system to produce pulsed neutrons. The challenging complex design and integration yielded to introducing a tool for all stakeholders along the lifecycle: the "situation features", as defined in ISO GPS (Geometrical Product Specifications) standards. This paper deals with the beyond-mechanics non-geometrical use cases and generalizes the use of the association operation to theoretically exact features. The examples of the functional specification, fiducialization (measure of the real features with respect to external marks) and installation phases of quadrupole magnets is developed. Perspectives of generic use are highlighted.

Hydroxyapatite (HAP) is the main mineral component of bones and teeth. It is widely used in medicine as a bone filler and coating for implants to promote new bone growth. Ion substitutions into the HAP structure highly affect its properties. One of the important substituents is manganese. This paper presents the new results obtained by high-precision density functional theory calculations using hybrid functionals, for studies of the Mn/Ca substitutions in HAP in a wide manganese concentration range within 2x2x2 supercell model. The experimental data on the mechanochemical synthesis of HAP-Mn samples with different Mn concentrations are also presented. The comparison between experiment and theory showed good agreement: the HAP-Mg unit cell parameters and volume decrease with increasing degree of Mn/Ca substitution. It is shown that electronic energy levels appear inside the band gap Eg of HAP, which depend on the concentration of Mn and change the photo-excitation energy of HAP, making its effective value Eg* less than the band gap Eg, and generally changing the photoelectronic properties of HAP. It was established that the energies of formation of the substitutions Mn/Ca depend on the position of the Ca atom (Ca1 or Ca2) and on the concentration of manganese. It has been shown that the replacement of calcium cations with manganese occurs predominantly at the Ca2 position.

Microsoft has implemented several measures to defend against macro viruses, including the use of Anti-malware Scan Interface (AMSI) and automatic macro blocking. Nevertheless, evidence shows that threat actors have found ways to bypass these mechanisms. As a result, phishing emails continue to apply malicious macros as their essential attack vector. In this paper, we analyze 77 obfuscation features from the attacker’s point of view and extract 46 suspicious keywords in macro. We first combine the above two types of features to train machine learning models on a public dataset. Then, we carry out the same experiment on self-constructed dataset, a collection of newly discovered samples, to see if our proposed method could discover the unseen malicious macros. Experimental results demonstrate that, comparing with the existing researches, our proposed method has a higher detection rate and better consistency. Furthermore, ensemble multi-classifiers with distinct feature selection further improve the detection performance.

Diffuse intrinsic pontine glioma (DIPG) is recognized as a pediatric brainstem cancer with a 0% survival rate. On a molecular basis, DIPG commonly results from mutations in histone H3, specifically a mutation in the H3K27M gene, that promotes tumorigenesis and results in presentation of this fatal brainstem tumor. DIPG is challenging to treat, as surgical intervention is inefficacious due to the location where the glioma resides. To date, traditional treatments such as radiation, chemotherapy, and immunotherapy have not increased survival rates and have only been successful at relieving symptoms. Future therapeutic approaches such as proton beam radiation, Chimeric Antigen Receptor T Cell (CAR-T) immunotherapy, and alternative epigenetic pharmaceuticals are under investigation for potential benefits. Various clinical trials have also explored these treatment procedures to discover potential increases in survival rates in both animal and human studies. In this review, we will evaluate the pathology and molecular characteristics of DIPG, the current and future approaches to DIPG treatment; and, lastly, we will discuss clinical trials that have been completed to develop successful treatment options.

Fabry disease (FD) is a X-linked inheritable storage disease caused by deficiency of al-pha-galactosidase causing lysosomal overload of sphingolipids. FD cardiomyopathy is character-ized by left ventricular (LV) hypertrophy and should be considered in differential diagnosis with all the other causes of LV hypertrophy. An early diagnosis of FD is very important because the enzyme replacement therapy (ERT) may change the fate of patients by blocking both cardiac and systemic involvement and improving prognosis. Diagnosis may be relatively easy in young patients with the typical signs ans symptoms of FD, but in male patients with late onset of disease and in females, diagnosis may be very challenging. Morphological and functional aspects are not specific for FD, which cannot be diagnosed or excluded by echocardiography. Cardiac magnetic resonance (CMR) with tissue characterization capability, is the preferred technique for the differential diagnosis of LV hypertrophy. The finding of decreased myocardial T1 value in LV hypertrophy is very specific for FD. Late gadolinium enhancement (LGE) is found in late stage of disease but it is useful to predict the cardiac response to ERT and to stratify the prognosis.

Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of its nodules. Radiologists need support from automated tools for precise opinion. Automated detection of the affected lungs nodule is difficult because of the shape similarity among healthy tissues. Over the years, several expert systems have been developed that help radiologists to diagnose lung cancer. In this article, we propose a framework to precisely detect lungs cancer by classifying it between benign and malignant nodules. The framework is tested using the subset of the publicly available at the Lung Image Database Consortium image collection (LIDC-IDRI). Multiple techniques including filtering and noise removing are applied for pre-processing. Subsequently, the OTSU and the semantic segmentation are used to accurately detect the unhealthy lungs nodules. In total, 13 nodules features were extracted using Principal Components Analysis (PCA) algorithm. Four optimal features are selected based on the classification performance. In the classification phase, 9 different classifiers are used along with two types of validation schemes i.e. train test holdout validation with 70-30 data split and 10 fold cross-validation. Our experiments show that the proposed system provides 99.23\% accuracy using logic boost classifier.

Obesity is related to the establishment of chronic inflammation and metabolic diseases, but it can be positively influenced by the regular practice of physical activity. The study aimed to compare the anthropometric, metabolic, and inflammatory parameters of physically active Military Police Officers (MPOs) with those who are less physically active. Sixty male MPOs, low activity (n=28) and physically active (n=32) participated. The following parameters were measured: plasma cytokine levels, C-reactive protein (CRP) levels, circulating glucose triglyceride (TAG) and high-density lipoprotein cholesterol (HDL-C) levels, and plasma glutamic oxalacetate transaminase (GOT), glutamic-pyruvate transaminase (GPT), and gamma-glutamyl transferase (GGT) activities. The physically active group presented lower body fat and reduced TAG and IL-8 levels compared to the low activity group. Moreover, a negative correlation between SPE and SBP, DBP, BPM was detected for the physically active group (p<0.05) but not in the low activity group. Furthermore, the physically active group's work time (WT) values were not correlated with the important metabolic markers SBP, DBP, BPM, GLU, TAG (p>0.05) but could be in the low activity group (p<0.05). These findings highlight the fundamental protective role of physical activity in controlling body composition, subclinical inflammation, and cardiovascular risk in MPOs.

Mobility is a vital welfare indicator which may influence broilers’ daily activities. Classical broiler mobility assessment methods are laborious and cannot provide timely insights into their conditions. Here, we proposed a semi-supervised Deep Learning (DL) model, YOLOv5, combined with Deep Sort algorithm conjoined with our newly proposed algorithm, Neo-Deep Sort, for individual broiler mobility tracking. Initially, 1,650 labeled images from five days were employed to train the YOLOv5 model. Through semi-supervised learning (SSL), this narrowly trained model was then used for pseudo-labeling 2,160 images, of which 2,153 were successfully labeled. Thereafter, the YOLOv5 model was fine-tuned on the newly labeled images. Lastly, the trained YOLOv5 and the Neo-Deep Sort algorithm were applied to detect and track 28 broilers in two pens and categorized them in terms of hourly and daily traveled distances and speeds. SSL helped in increasing the YOLOv5 model’s mean Average Precision (mAP), in detecting birds, from 81% to 98%. As compared with the manually measured covered distances of broilers, the combined model provided individual broiler's hourly moved distances with a validation accuracy of about 80%. Eventually, individual and flock level mobilities were quantified while overcoming the occlusion, false and miss detection issues.

With the widespread of embedded sensing capabilities of mobile devices, there has been unprecedented development of context-aware solutions. This allows the proliferation of various intelligent applications such as those for remote health and lifestyle monitoring, intelligent personalized services, etc. However, activity context recognition based on multivariate time series signals obtained from mobile devices in unconstrained conditions is naturally prone to imbalance class problems. This means that recognition models tend to predict classes with the majority number of samples whilst ignoring classes with the least number of samples, resulting in poor generalization. To address this problem, we propose to augment the time series signals from inertia sensors with signals from ambient sensing to train deep convolutional neural networks (DCNN) models. DCNN provides the characteristics that capture local dependency and scale invariance of these combined sensor signals. Consequently, we developed a DCNN model using only inertial sensor signals and then developed another model that combined signals from both inertia and ambient sensors aiming to investigate the class imbalance problem by improving the performance of the recognition model. Evaluation and analysis of the proposed system using data with imbalanced classes show that the system achieved better recognition accuracy when data from inertial sensors are combined with those from ambient sensors such as environment noise level and illumination, with an overall improvement of 5.3% accuracy.