Emergency control load-shedding is a key solution to prevent blackouts in the power system. This paper proposed a new model of emergency controls load shedding based on the fast identification of the unstable state of the power system. K-means clustering algorithm divided the instability mode into the clusters. The results of analysis of this cluster were used as the basis for classification control. Building load shedding strategies is consisted of the pre-designed rules based on AHP algorithm. When the recognition of the power system “instability” is detected, the signal of load shedding control is triggered immediately, therefore the decision time is greatly shortened comparing to the traditional methods. The effectiveness of the proposed method was tested on the IEEE 39-bus to overcome the limitations of the last traditional methods.

This paper discusses about control of the linear switched reluctance machines (LSRMs) network for the zero phase-difference tracking to a sinusoidal reference. The dynamics of each LSRM is derived by online system identification and modeled as a second-order linear system. Accordingly, based on the coupled harmonic oscillators synchronization manner, a distributed control is proposed to synchronize each LSRM state to a virtual LSRM node representing the external sinusoidal reference for tracking it with zero phase-difference. Subsequently, a simulation scenario and an experimental platform with the identical parameter setup are designed to investigate the tracking performance of the LSRMs network constructed by the proposed distributed control. Finally, the simulation and experimental results verify the effectiveness of the proposed LSRMs network controller, and also prove that the coupled harmonic oscillators synchronization method can improve the synchronization tracking performance and precision.

Aim: This study aims to analyze the structure of the co-authorship network in viral hepatitis research from 2000 to 2023 using data from the Web of Science (WoS) Core Collection. The objective is to identify key researchers, evaluate the collaborative dynamics, and understand the evolution of scientific contributions in this field. Method: This study utilized network analysis techniques to evaluate 60,720 publications related to viral hepatitis research indexed in the WoS Core Collection between 2000 and 2023. The analysis was conducted using Python (Version 3.10.5) in the PyCharm development environment (Software Version 2022.1.3). The co-authorship networks were assessed using macro-level indicators such as network density (the ratio of actual to possible connections), clustering coefficient (degree of node clustering), number of components (distinct connected subgroups), and average path length (average distance between nodes). Micro-level indicators including degree centrality (importance based on the number of connections), closeness centrality (proximity to other nodes), and betweenness centrality (frequency of a node on the shortest paths between others) were also analyzed.Result: The findings reveal that the viral hepatitis research network is characterized by low network density, indicating sparse overall collaboration. However, the clustering coefficient is high, suggesting strong collaborations within small, cohesive groups. Over the years, researchers such as Stefan Zeuzem, Maria Buti, and Fabien Zoulim have played pivotal roles, serving as central figures in the network. A noticeable increase in network density and clustering from 2020-2023 suggests growing collaboration in recent years.Conclusion: This study underscores the importance of international collaboration in advancing viral hepatitis research. Key researchers have emerged as influential contributors, facilitating global research activities. Network analysis provides valuable insight into the structure of these collaborations and helps identify potential areas for future research and partnerships to combat viral hepatitis globally. The results of this study should be used to reduce global healthcare disparities, promote research collaboration, and address viral hepatitis as a global public health problem.

Aim: This study aims to analyze the collaborative networks and identify key players in autoimmune pancreatitis (AIP) research from 2000 to 2023. Using data from the Web of Science (WoS) Core Collection, I assess the structure and evolution of co-authorship networks to understand collaboration trends and influential researchers in the field.Method: I conducted a network analysis of co-authorship patterns in AIP research using Python (Version 3.10.5) in the PyCharm development environment (Software Version 2022.1.3). The analysis included macro-level indicators: network density, clustering coefficient, components, and average distance, as well as micro-level indicators: degree centrality, closeness centrality, and betweenness centrality. These metrics were used to evaluate the connectivity, clustering, and key nodes within the network across three distinct periods: 2000-2009, 2010-2019, and 2020-2023.Result: The analysis revealed that the co-authorship network in AIP research evolved from a fragmented structure with limited collaboration in the early 2000s to a more interconnected but still dispersed network in recent years. Despite an increase in network density and a decrease in the number of disconnected components over time, the overall structure remains highly clustered, with many researchers operating within isolated groups. Key figures, such as Kazuichi Okazaki, Terumi Kamisawa, and Shigeyuki Kawa from Japan, consistently ranked high in centrality measures, highlighting their significant influence and leadership in the field. The findings suggest that while local collaborations are strong, broader international connections are still developing.Conclusion: This study provides a comprehensive overview of the collaborative landscape in AIP research, identifying central researchers and highlighting persistent fragmentation within the network. The prominent role of Japanese researchers in shaping the field underscores the importance of fostering greater international collaboration to bridge gaps between research clusters. Enhancing global partnerships could lead to more integrated and impactful research outcomes, ultimately advancing the understanding and management of autoimmune pancreatitis.

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

Aim: This study aims to analyze the structure of the co-authorship network in Budd-Chiari syndrome (BCS) research from 2000 to 2023 using data from the Web of Science (WoS) Core Collection. The objective is to identify key researchers, evaluate the collaborative dynamics, and understand the evolution of scientific contributions in this field. Method: This study utilized network analysis techniques to evaluate 2,877 publications related to BCS research indexed in the WoS Core Collection between 2000 and 2023. The analysis was conducted using Python (Version 3.10.5) in the PyCharm development environment (Software Version 2022.1.3). The co-authorship networks were assessed using macro-level indicators such as network density (the ratio of actual to possible connections), clustering coefficient (degree of node clustering), number of components (distinct connected subgroups), and average path length (average distance between nodes). Micro-level indicators including degree centrality (importance based on the number of connections), closeness centrality (proximity to other nodes), and betweenness centrality (frequency of a node on the shortest paths between others) were also analyzed.Result: The results revealed a highly fragmented network structure in the early years (2000-2009), characterized by low network density (0.0017) and a large number of disconnected components (533). Key researchers such as Aurelie Plessier and Dominique Valla emerged as central figures in terms of degree and closeness centrality. In the 2010-2019 period, the network showed slight improvements, with density decreasing to 0.0016 but an increase in the number of components to 645, indicating persistent fragmentation. From 2020 to 2023, the network demonstrated increased cohesiveness with a density of 0.0032 and a reduction in components to 376. Influential researchers in the final period included Virginia Hernandez-Gea and Valerie Paradis, who played pivotal roles in connecting disparate research clusters.Conclusion: The co-authorship network analysis of BCS research over the past two decades highlights a gradual yet incomplete evolution towards greater collaboration and integration among researchers. While the network's cohesiveness has improved, significant fragmentation remains, suggesting that further efforts are needed to enhance global and interdisciplinary collaboration. Addressing these challenges is crucial for fostering a more connected and productive research community that can advance the understanding and management of BCS.

Aim: This study aims to analyze the evolution of co-author networks in Gastroesophageal Reflux Disease (GERD) research from 2000 to 2023, using data from the Web of Science (WoS) Core Collection. The objective is to provide a structural overview of researcher collaborations in this specialized field, highlighting key contributors and the impact of international cooperation. Method: I conducted a co-author network analysis on 19,463 GERD -related articles indexed in the WoS Core Collection between 2000 and 2023. Using Python (Version 3.10.5) within the PyCharm development environment (Software Version 2022.1.3), I assessed macro-level indicators including network density, clustering coefficient, number of components, and average distance. Micro-level indicators such as degree centrality, closeness centrality, and betweenness centrality were also evaluated to understand the roles of individual researchers in the network.Result: The GERD co-authorship network exhibited a sparse structure with low network density, indicating limited realized collaborations compared to potential connections. The clustering coefficient was consistently high across the analyzed periods, suggesting that researchers frequently formed tight-knit groups. The network was fragmented into numerous components, with significant disconnection between groups. Degree centrality highlighted key researchers such as Dent, J., and Shaheen, N.J., who had extensive collaborative reach. In contrast, closeness and betweenness centrality identified strategic intermediaries like Bredenoord, A.J. and Kahrilas, P.J., who facilitated connections across otherwise isolated segments of the network.Conclusion: The co-authorship network analysis revealed a persistently fragmented landscape in GERD research, with considerable room for enhancing collaboration among researchers. Identifying key contributors and understanding their roles within the network can guide future efforts to foster more integrated and comprehensive research collaborations. This study underscores the importance of strategic networking and partnership development in advancing GERD research and optimizing the field's collaborative potential.

In aerial image object detection, small targets present significant challenges due to limited pixel information, complex backgrounds, and sensitivity to bounding box perturbations. To tackle these issues, we propose SO-RTDETR for small object detection. The model introduces a Cross-Scale Feature Fusion with S2 (S2-CCFF) module, a Parallelized Patch-Aware attention (PPA) module, and the Normalized Wasserstein Distance (NWD) loss function, leading to significant performance improvements. Specifically, the S2-CCFF module enhances small object information by incorporating an additional S2 layer, while SPDConv downsampling maintains key details and reduces computational cost. The CSPOK-Fusion mechanism integrates global, local, and large branch features, capturing multi-scale representations and effectively mitigating interference from complex backgrounds and occlusions, thereby enhancing the spatial representation of features across scales. The PPA module, embedded in the Backbone network, leverages multi-level feature fusion and attention mechanisms to retain and strengthen small object features, addressing the issue of information loss. The NWD loss function, by focusing on the relative positioning and shape differences of bounding boxes, increases robustness to minor perturbations, enhancing detection accuracy. Experimental results on the VisDrone and NWPU VHR-10 aerial datasets demonstrate that our approach outperforms state-of-the-art detectors.

The agriculture industry is critical to the global economy, with product quality having a direct impact on marketability and waste management. Apples, one of the most extensively produced fruits, are affected by a variety of diseases that can reduce productivity and quality. Accurate diagnosis of diseases is critical, but traditional manual approaches are time-consuming, error-prone, and ineffective. Inadequate labeled data and a wide range of disease symptoms make it necessary to design an automated, robust, and accurate system. This article describes a hybrid model for Apple Fruit Disease Detection (HMAFDD) that combines the strengths of three pre-trained convolutional neural network (CNN) models: ResNet50, DenseNet121, and EfficientNetB0. It accomplish this by using multi-architecture feature extraction. The hybrid system, which combines both models, is able to recognize a wide range of features, from simple textures to complex patterns unique to a certain diseases. Grad-CAM, or gradient-weighted class activation mapping, creates heatmaps that highlight significant regions for prediction, which enhances the interpretability of the model.To increase robustness and accuracy, techniques such as spectral-shifted adversarial perturbation for data augmentation and spectrally-weighted global average pooling for feature aggregation are used. This technique provides 99.75% accuracy with minimal processing needs, making it acceptable for real-time applications in agricultural situations. This considerably improves apple disease management.

High purity hydrogen is a necessary need for fuel cell. Pressure swing adsorption (PSA) technology is one of the effective methods for hydrogen purification and separation. A layered adsorption bed packed with activated carbon and zeolite 5A for five-component gas mixture (H2/CH4/CO/N2/CO2=56.4/26.6/8.4/5.5/3.1 mol%) PSA model was built. The model was validated by breakthrough curves and comparing the results with the experimental data. The purification performance of six-step layered bed PSA cycle was studied using the model. In order to optimize the cycle, the Box-Behnken design (BBD) method was used, as implemented in Design Expert™. In addition to adsorption time, the pressure equalization time and the feed flow rate were considered as independent optimization parameters. Quadratic regression equations were then obtained for three responses of the system, namely purity, recovery, and productivity. To explore a better optimization solution, a novel optimization method of machine learning with back propagation neural network (BPNN) was proposed in this work, a kind of heuristic algorithm of genetic algorithm (GA) is introduced to optimize the structure of BPNN. The predicted outputs of hydrogen production using two kinds of models based on back propagation neural network-genetic algorithm (BPNN-GA) and BBD method integrated with BPNN-GA (BBD-BPNN-GA) models. The results showed that the BBD-BPNN-GA model have a better performance with the mean square error (MSE) of 0.0005, while the MSE of BPNN-GA model was 0.0035. And the correlation coefficient of R-values were much closer to 1 of the BBD-BPNN-GA model, which was illustrated that the BBD-BPNN-GA model can be effectively applied to the prediction and optimization of PSA process.

Climate change is a global issue that has driven the adoption of renewable energies due to their sustainability and environmental benefits. However, these energies face limitations, such as the lack of regional studies on wind or solar dynamics and the efficiency of energy systems. Tools that simulate and calculate energy potential while considering uncontrollable climatic variables are crucial for optimizing the design of these systems. Artificial intelligence, particularly multilayer neural networks, has proven effective in data prediction across industries. This paper focuses on training a 3-layer neural network using the ReLU activation function and quadratic error to predict wind potential density in Mexico, aiming to identify key areas for renewable energy development.

This paper surveys the landscape of security and data attacks on machine unlearning, with a focus on financial and e-commerce applications. We discuss key privacy threats such as Membership Inference Attacks and Data Reconstruction Attacks, where adversaries attempt to infer or reconstruct data that should have been removed. In addition, we explore security attacks including Machine Unlearning Data Poisoning, Unlearning Request Attacks, and Machine Unlearning Jailbreak Attacks, which target the underlying mechanisms of unlearning to manipulate or corrupt the model. To mitigate these risks, various defense strategies are examined, including differential privacy, robust cryptographic guarantees, and Zero-Knowledge Proofs (ZKPs), offering verifiable and tamper-proof unlearning mechanisms. These approaches are essential for safeguarding data integrity and privacy in high-stakes financial and e-commerce contexts, where compromised models can lead to fraud, data leaks, and reputational damage. This survey highlights the need for continued research and innovation in secure machine unlearning, as well as the importance of developing strong defenses against evolving attack vectors.

In the context of smart agriculture, accurately estimating plant leaf chemical parameters is crucial for optimizing crop management and improving agricultural yield. Hyperspectral imaging, with its ability to capture detailed spectral information across various wavelengths, has emerged as a powerful tool in this regard. However, the complex and high-dimensional nature of hyperspectral data poses significant challenges in extracting meaningful features for precise estimation. To address this challenge, this study proposes an end-to-end estimation network for multiple chemical parameters of Astragalus leaves based on attention mechanism (AM) and multivariate hyperspectral features (AM-MHENet). We leveraging HybridSN and multilayer perception (MLP) to extract prominent features from the hyperspectral data of Astragalus membranaceus var. mongholicus (AMM) leaves and stems, as well as the surface and deep soil surrounding AMM roots. This methodology allows us to capture the most significant characteristics present in these hyperspectral data with high precision. The AM is subsequently used to assign weights and integrate the hyperspectral features extracted from different parts of the AMM. The MLP is then employed to simultaneously estimate the chlorophyll content (CC) and nitrogen content (NC) of AMM leaves. Compared with estimation networks that utilize only hyperspectral data from AMM leaves as input, our proposed end-to-end AM-MHENet demonstrates superior estimation performance. Specifically, AM-MHENet achieves an R2 of 0.983 with an RMSE of 0.73 for the estimation of CC in AMM leaves. For NC estimation, AM-MHENet achieves an R2 value of 0.977 with an RMSE of 0.27. These results underscore AM-MHENet’s effectiveness in significantly enhancing the accuracy of both CC and NC estimation in AMM leaves. Moreover, these findings indirectly suggest a strong correlation between the development of AMM leaves and stems, as well as the surface and deep soil surrounding the roots of AMM, and directly highlight the ability of AM to effectively focus on the relevant spectral features within the hyperspectral data. This findings from this study could offer valuable insights into the simultaneous estimation of multiple chemical parameters in plants, thereby making a contribution to the existing body of research in this field.

The study compares three machine learning and deep learning models—Support Vector Regression (SVR), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM)—for predicting market prices using the NGX All-Share Index dataset. The models were evaluated using multiple error metrics, including Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Mean Percentage Error (MPE), and R-squared. RNN and LSTM were tested with both 30 and 60-day windows, with performance compared to SVR. LSTM delivered better R-squared values, with a 60-day LSTM achieving the best accuracy (R-squared = 0.993) when using a combination of endogenous market data and technical indicators. SVR showed reliable results in certain scenarios but struggled in fold 2 with sudden spike that shows high probability of not capturing the entire underlying NGX pattern in the dataset correctly as witnessed with the high validation loss during the period. Additionally, RNN faced the vanishing gradient problem that limits its long-term performance. Despite challenges, LSTM's ability to handle temporal dependencies, especially with the inclusion of On-Balance Volume, led to significant improvements in prediction accuracy. The use of the Optuna optimization framework further enhanced model training and hyperparameter tuning, contributing to the performance of the LSTM model.

To analyze the impact of weather factors on the resilience of airport flight operations, particularly on flight operation, economic performance, and transportation capacity, Kolmogorov-Arnold Network (KAN) model was used to identify key weather features and establish the mapping relationship between weather factors and airport operational resilience. Taking Xi'an Xianyang International Airport as an example, the weights of each route were determined using the Grey Relational Analysis method considering average daily flight volume, flight distance, and airport flow stability indicators. Flight operation records and weather data were utilized to calculate the importance of key weather factors on the resilience of critical flight operation indicators. The results indicate significant differences in average daily flight volume, flight distance, and airport flow stability across different routes, with routes in economically developed areas having a greater impact on airport flow stability. Temperature and wind speed changes are the key factors affecting flight operation and economic indicators, with importance values of 0.35 and 0.32 respectively. Wind direction change and wind speed change have the greatest impact on flight transportation capacity, with importance values of 0.7 and 0.65 respectively. Therefore, when conducting flight scheduling and risk assessment, special attention should be paid to key weather factors such as temperature and wind speed, while also considering the weight of each route to ensure flight safety, efficiency, and economic benefits.

Drug development is a lengthy process with a high failure rate. Increasingly, machine learning is utilized to facilitate the drug development processes. These models aim to enhance our understanding of drug characteristics, including their activity in biological contexts. However, a major challenge in drug response (DR) prediction is model interpretability as it aids in the validation of findings. This is important in biomedicine, where models need to be understandable in comparison with established knowledge of drug interactions with proteins. drGAT, a graph deep learning model, leverages a heterogeneous graph composed of relationships between proteins, cell lines, and drugs. drGAT is designed with two objectives: DR prediction as a binary sensitivity prediction and elucidation of drug mechanism from attention coefficients. drGAT has demonstrated superior performance over existing models, achieving 78\% accuracy (and precision), and 76\% F1 score for 269 DNA-damaging compounds of the NCI60 drug response dataset. To assess the model's interpretability, we conducted a review of drug-gene co-occurrences in Pubmed abstracts in comparison to the top 5 genes with the highest attention coefficients for each drug. We also examined whether known relationships were retained in the model by inspecting the neighborhoods of topoisomerase-related drugs. For example, our model retained TOP1 as a highly weighted predictive feature for irinotecan and topotecan, in addition to other genes that could potentially be regulators of the drugs. Our method can be used to accurately predict sensitivity to drugs and may be useful in the identification of biomarkers relating to the treatment of cancer patients.

The ovary is the major determinant of female reproductive health. Ovarian functions are mainly related to the primordial follicle pool, which is gradually loss with aging. Ovarian aging and reproductive dysfunctions share oxidative stress as common underlying mechanism. ROS signaling is essential for normal ovarian processes yet can contribute to various ovarian disorders when disrupted. Therefore, balance in the redox system is crucial for proper ovarian functions. In the present study, by focusing on mRNAs and ncRNAs described in the ovary and taking into account only validated ncRNA interactions, we built up an ovarian antioxidant ceRNA network, namely OvAnOx ceRNA, composed of 5 mRNAs (SOD1, SOD2, CAT, PRDX3, GR), 10 miRNAs and 5 lncRNAs (XIST, FGD5-AS1, MALAT1, NEAT1, SNHG1). Our bioinformatic analysis indicated that the components of the OvAnOx ceRNA not only contribute to antioxidant defence, but are also involved in other ovarian functions. Indeed, antioxidant enzymes encoded by mRNA of OvAnOx ceRNA operate within a regulatory network that impacts ovarian reserve, follicle dynamics, and oocyte maturation in normal and pathological conditions. The OvAnOx ceRNA represents a promising tool to unravel the complex dialogue between redox potential and ovarian signalling pathways involved in reproductive health, aging and diseases.

The microbial communities are closely related to the overall health and quality of soil, but studies on microbial ecology in apple-pear orchard soils are limited. In the current study, 28 soil samples were collected from three apple-pear orchards in northeastern China, and the composition and structure of fungal and bacterial communities were investigated by high-throughput sequencing. Molecular ecological network showed that the keystone taxa of bacterial communities were Actinobacteria, Proteobacteria, Gemmatimonadetes, Acidobacteria, Nitrospirae, and Chloroflexi, and the keystone taxa of fungal communities was Ascomycota. Mantel tests showed that soil texture and pH were important factors shaping soil bacterial and fungal communities, and soil water soluble organic carbon (WSOC) and nitrate nitrogen (NO3--N) were also closely related to soil bacterial communities. Canonical correspondence analysis (CCA) and variation partition analysis (VPA) analysis revealed that geographic distance, soil texture, pH, and other soil properties could explain 10.55%, 13.5%, and 19.03% of the overall variation of bacterial communities, and they explained 11.61%, 13.03%, and 20.26% of the overall variation of fungal communities, respectively. The key stone taxa of bacterial and fungal communities in apple-pear orchard soils and their strong correlation with soil properties could provide useful clues toward sustainable management of orchards.

With the widespread use of the Internet of Things, underwater control and monitoring systems for purposes such as ocean data sampling, natural disaster prevention, underwater surveillance, submarine exploration, and the like have become a popular and challenging topic in computers. So far, various topology control and routing solutions have been proposed for these networks. However, as technology expands and applications grow, so does the need for a stable underwater communication platform. On the other hand, underwater communication is associated with challenges such as node mobility, long propagation delays, low bandwidth, limited resources, and high error rates. In this research, for the first time, a topology control platform based on the RPL tree is modelled by applying its structural changes underwater. The proposed RPLUW methods in the case of RPLUWM fixed nodes are introduced to support the mobility of nodes underwater. Flexible objective functions, utilisation of decision-making systems, and application of control schedules in these methods have increased network life, reduced overhead, and increased node efficiency. The simulation results of the proposed method, in comparison with recent methods in this field, show an increase in network efficiency.

Temperature and pressure sensors currently encounter challenges such as slow response times, large sizes, and insufficient sensitivity. To address these issues, we developed tetraphenylethylene (TPE)-doped polyvinylidene fluoride (PVDF) nanofiber membranes using electrospinning, with process parameters optimized through a convolutional neural network (CNN). We systematically analyzed the effects of PVDF concentration, spinning voltage, tip-to-collector distance, and flow rate on fiber morphology and diameter. The CNN model achieved high predictive accuracy, resulting in uniform and smooth nanofibers under optimal conditions. Incorporating TPE enhanced the hydrophobicity and mechanical properties of the nanofibers. Additionally, the fluorescent properties of the TPE-doped nanofibers remained stable under UV exposure and exhibited significant linear responses to temperature and pressure variations. The nanofibers demonstrated a temperature sensitivity of -0.976 gray value/°C and pressure sensitivity with an increase in fluorescence intensity from 537 a.u. to 649 a.u. under 600 g pressure. These findings highlight the potential of TPE-doped PVDF nanofiber membranes for advanced temperature and pressure sensing applications.

The rapid advancements in satellite technology have led to a significant increase in high-resolution remote sensing (RS) images, necessitating advanced processing methods. Additionally, a patent analysis revealed a significant increase in deep learning and machine learning applications in remote sensing, highlighting the growing importance of these technologies. Therefore, this paper introduces the Kolmogorov-Arnold Network (KAN) model to remote sensing, aiming to enhance efficiency and performance in RS applications. We conducted several experiments to validate KAN's applicability, starting with the EuroSAT dataset, where we combined the KAN layer with multiple pretrained CNN models. The optimal performance was achieved with ConvNeXt, leading to the development of the KonvNeXt model. KonvNeXt was evaluated on the Optimal-31, AID, and Merced datasets for validation, and it achieved accuracies of 90.59%, 94.1%, and 98.1%, respectively. The model also showed fast processing speed, with the Optimal-31 and Merced datasets completed in 107.63 seconds each, while the bigger and more complicated AID dataset took 545.91 seconds. This result is meaningful since it achieved faster speeds and comparable accuracy compared to the existing study which utilized VIT and proved KonvNeXt's applicability for remote sensing classification tasks. Furthermore, we investigated the model's interpretability by utilizing Occlusion Sensitivity and by displaying the influential regions, it validated its potential use in a variety of domains including medical imaging and weather forecasting. This paper is meaningful in that it is the first use of KAN in remote sensing classification, proving its adaptability and efficiency.

Considering that emotional events diversify as one ages, this study formulates the Salient Episodic Memory Aggregation Hypothesis, which claims that aging induces homogenization of episodic memory and consequently increases the salience of emotional episodes. To test this hypothesis, the study focused on sadness episodic memory and conducted a web-based survey and a combined analysis consisting of natural language processing, machine learning, and network graph analysis. A sample of 2,954 adults aged between their 20s and over 70s participated in this study. They were asked to describe a sad event they had experienced and assess the psychological properties of the recalled episodes. After isolating and lemmatizing episodic words using natural language processing, vocabulary frequency was counted for each generation, and network graph analysis based on machine learning was performed to compare the structures of sadness episodes between generations. As a result, there were mainly two types of episodic words for which frequencies either declined or increased with age. The network structures of episodic words for the older generations possessed higher proximity (shortest path length) to higher concentrations of episodic words. These findings support the current hypothesis, indicating that the nature of sadness episodes differ between generations, and that older people have more aggregated episodic memory structures.

Interoperable multilayer networks are pivotal and transformative in public digital health. They not only enhance the delivery of healthcare services but also contribute significantly to improving public health outcomes. Through better accessibility, efficiency, and data-driven decision-making, these networks are revolutionizing how we approach public health. The seamless data exchange and integration they facilitate across different healthcare systems and providers can lead to substantial cost savings for public healthcare systems. These networks pave the way for a more efficient and effective healthcare system by reducing redundancies, optimizing resource allocation, and minimizing unnecessary procedures. This study combines the pressing issues of public digital health with the innovative interpretation of multilayer network theory, proposing practical solutions that inspire academics and practitioners alike.Public digital health is not just about improving care access and patient engagement. It is also about ensuring the financial sustainability of our healthcare systems. Innovative multilayer network analysis is critical in this game, improving interoperability and reducing spatial and temporal constraints. These networks streamline processes and improve efficiency by easing complex interactions within healthcare systems. This process, in turn, allows healthcare providers to deliver high-quality care at a lower cost, transforming, whenever possible, in-patients and out-patients into home-patients. Networks are a cornerstone and a beacon of hope for transforming public digital health. They are increasing the Value for Money and enhancing a patient-centric approach, making us optimistic about the future of healthcare.This study shows that revolutionizing digital healthcare methodologies has a profound impact on crucial elements like resilience, interoperability, and patient well-being within public health. The enhancement of interoperability facilitates the smooth flow of data exchange across various platforms and healthcare providers, fostering improved collaboration and decision-making processes and elevating the safety of patients.

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

We leverage the explainability feature of KAN network and build an explainable language model where certain neurons encode individual words and neuron activation is fully interpretable in terms of the basis of a word. To do that, we propose a continuous word2vec model where a meaning of a word is expressed by a continuous profile of distances of this word from the words in the basis of words which is interpolated. As a result, the whole KAN network can be interpreted as a sequential procedure with word expressions. We then proceed from words to logic programs and develop a clause learning technique based on KAN. A logic program construction process from facts now become fully interpretable. We follow the differentiable inductive logic programming technique, representing a logic program as a matrix learned by KAN. Hence, we obtain an efficient and fully interpretable rule learning approach.

Securing the structural safety of blades has become crucial, owing to the increasing size and weight of blades resulting from the recent development of large wind turbines. Composites are primarily used for blade manufacturing because of their high specific strength and specific stiff-ness. However, in composite blades, joints may experience fractures from the loads generated during wind turbine operation, leading to deformation caused by changes in the structural stiff-ness. In this study, 7,132 debonding damage data, classified by damage type, position, and size, are selected to predict debonding damage based on natural frequency. The change in the natural frequency caused by debonding damage is acquired through finite element (FE) modeling and modal analysis. Synchronization between the FE analysis model and manufactured blades is achieved through modal testing and data analysis. Finally, the relationship between the debond-ing damage and the change in natural frequency is examined using artificial neural network techniques

Wireless Sensor Network (WSN) and the sensing devices are considered part of the core components of the Internet of Things (IoT). Hence, the modeling of IoT-WSNs is fundamental to having a better understanding, management, and deployment of this kind of technology. A fundamental issue in WSN is energy consumption due to the inherent limitations of this resource in the sensor devices. On the other hand, several issues arise in heterogeneous scenarios due to the coexistence of different sensor devices. Therefore, the modeling process becomes challenging and must consider the different transmission and operation cycles and modes that the transmission protocol implements to assure successful functioning in terms of transmission, synchronization, and energy savings. A duty-cycled MAC WSN protocol (PSA-MAC) has been modeled based on a pair of two-dimensional Discrete-Time Markov Chain (2D-DTMC), whose solution in terms of stationary probability distribution is used by expressions that have been derived to evaluate the energy consumption of sensor devices that could be used for WSN-based IoT applications. Analytical results of average energy consumption are obtained, where the synchronization, data, and sleep periods of a full transmission cycle are considered in a heterogeneous scenario with different node classes and priority assignments. Also, the normal and awake operation cycles are considered to assure synchronization and energy savings. Moreover, the transmission schemes of SPT (transmission of single packets) and APT (transmission of packets in aggregation) are also considered in the model. These results are validated through discrete event-based simulations, and the obtained results are accurate.

Sparse training (ST) aims to ameliorate deep learning by replacing fully connected artificial neural networks (ANNs) with sparse or ultra-sparse ones, such as brain networks are, therefore it might benefit to borrow brain-inspired learning paradigms from complex network intelligence theory. Here, we launch the ultra-sparse advantage challenge, whose goal is to offer evidence on the extent to which ultra-sparse (around 1% connection retained) topologies can achieve any leaning advantage against fully connected. Epitopological learning is a field of network science and complex network intelligence that studies how to implement learning on complex networks by changing the shape of their connectivity structure (epitopological plasticity). One way to implement Epitopological (epi- means new) Learning is via link prediction: predicting the likelihood of non-observed links to appear in the network. Cannistraci-Hebb learning theory inspired the CH3-L3 network automata rule for link prediction which is effective for general-purpose link prediction. Here, starting from CH3-L3 we propose Epitopological Sparse Meta-deep Learning (ESML) to apply Epitopological Learning to sparse training. In empirical experiments, we find that ESML learns ANNs with ultra-sparse hyperbolic (epi-)topology in which emerges a community layer organization that is meta-deep (meaning that each layer also has an internal depth due to power-law node hierarchy). Furthermore, we discover that ESML can in many cases automatically sparse the neurons during training (arriving even to 30% neurons left in hidden layers), this process of node dynamic removal is called percolation. Starting from this network science evidence, we design Cannistraci-Hebb training (CHT), a 4-step training methodology that puts ESML at its heart. We conduct experiments on 7 datasets and 5 network structures comparing CHT to dynamic sparse training SOTA algorithms and the fully connected counterparts. The results indicate that, with a mere 1% of links retained during training, CHT surpasses fully connected networks on VGG16, GoogLeNet, ResNet50, and ResNet152. This key finding is an evidence for ultra-sparse advantage and signs a milestone in deep learning. CHT acts akin to a gradient-free oracle that adopts CH3-L3-based epitopological learning to guide the placement of new links in the ultra-sparse network topology to facilitate sparse-weight gradient learning, and this in turn reduces the convergence time of ultra-sparse training. Finally, CHT offers the first examples of parsimony dynamic sparse training because, in many datasets, it can retain network performance by percolating and significantly reducing the node network size. Our code is available at: https://github.com/biomedical-cybernetics/Cannistraci-Hebb-training.

Facial Emotion Recognition (FER) is crucial across psychology, neuroscience, computer vision, and machine learning due to the diversified and subjective nature of emotions, varying considerably across individuals, cultures, and contexts. This paper investigates the impact of histogram equalization, data augmentation and model optimization strategies on three well-known FER datasets using pre-trained VGG models. Additionally, this paper showcases the effectiveness of different regularization techniques, callbacks, and learning schedulers in enhancing model performance by conducting extensive experiments. The model evaluation is discussed in terms of the following metrics: Accuracy, Area Under the Receiver Operating Characteristic Curve (AUC-ROC), Area Under the Precision-Recall Curve (AUC-PRC), and Weighted F1 score. Notably, the fine-tuned VGG models exhibit state-of-the-art performance compared to more complex conventional transfer learning models resulting in accuracies of 100%, 95.92%, and 69.65% on the CK+, KDEF, and FER2013 datasets, respectively.

Generalized zero-shot learning (GZSL) aims to simultaneously recognize both seen classes and unseen classes by training only on seen class samples and auxiliary semantic descriptions. Recent state-of-the-art methods infer unseen classes based on semantic information or synthesize unseen classes using generative models based on semantic information, all of which rely on the correct alignment of visual-semantic features. However, they often overlook the inconsistency between original visual features and semantic attributes. Additionally, due to the existence of cross-modal dataset biases, the visual features extracted and synthesized by the model may also mismatch with some semantic features, which could hinder the model from properly aligning visual-semantic features. To address this issue, this paper proposes a GZSL framework that enhances the consistency of visual-semantic features using self-distillation and disentanglement network (SDDN). The aim is to utilize self-distillation and disentanglement network to obtain semantically consistent refined visual features and non-redundant semantic features to enhance the consistency of visual-semantic features. Firstly, SDDN utilizes self-distillation technology to refine the extracted and synthesized visual features of the model. Subsequently, the visual-semantic features are then disentangled and aligned using a disentanglement network to enhance the consistency of the visual-semantic features. Finally, the consistent visual-semantic features are fused to jointly train a GZSL classifier. Extensive experiments demonstrate that the proposed method achieves more competitive results on four challenging benchmark datasets (AWA2, CUB, FLO, and SUN).

Few-shot object detection (FSOD) aims to address the challenge of requiring a substantial amount of annotations for training in conventional object detection, which is very labor-intensive. However, existing few-shot methods achieve high precision with the sacrifice of time-consuming for exhaustive fine-tuning, or take poor performance in novel-class adaptation. We presume the major reason is that the valuable correlation feature among different categories is insufficiently exploited, hindering the generalization of knowledge from base to novel categories for object detection. In this paper, we propose Few-Shot object detection via Correlation-RPN and Transformer Encoder-Decoder (CRTED), a novel training network to learn object-relevant features of inter-class correlation and intra-class compactness while suppressing object-agnostic features in the background with limited annotated samples. And we also introduce a 4-way tuple-contrast training strategy to positively activate the training progress of our object detector. Experiments over two few-shot benchmarks (Pascal VOC, MS-COCO) demonstrate that, our proposed CRTED without further fine-tuning can achieve comparable performance with current state-of-the-art fine-tuned works. The codes and pre-trained models will be released.

Underwater image often exhibit detail blurring and color distortion due to light scattering, impurities, and other influences, obscuring essential textures and details. This presents a challenge for existing super-resolution techniques in identifying and extracting effective features, making high-quality reconstruction difficult. This research aims to innovate underwater image super-resolution technology to tackle this challenge. Initially, an underwater image degradation model was created by integrating random subsampling, Gaussian blur, mixed noise, and suspended particle simulation to generate a highly realistic synthetic dataset, thereby training the network to adapt to various degradation factors. Subsequently, to enhance the network's capability to extract key features, improvements were made based on the symmetrically structured Blind Super-Resolution Generative Adversarial Network (BSRGAN) model architecture. An attention mechanism based on energy functions was introduced within the generator to assess the importance of each pixel, and a weighted fusion strategy of adversarial loss, reconstruction loss, and perceptual loss was utilized to improve the quality of image reconstruction. Experimental results demonstrate that the proposed method achieved significant improvements in Peak Signal-to-Noise Ratio (PSNR) and Underwater Image Quality Measure (UIQM) by 0.85 dB and 0.19, respectively, significantly enhancing the visual perception quality and indicating its feasibility in super-resolution applications.

Gene regulation is vital for cellular function and homeostasis, involving diverse mechanisms controlling specific gene products and contributing to tissue-specific gene expression. Dysregulation leads to diseases, emphasizing the need for understanding these mechanisms. Non-coding regions, notably enhancers and super-enhancers (SEs), act as crucial gene regulators, orchestrating transcriptional activity via transcription factors (TFs). SEs, with high activity, are pivotal in cell identity and disease progression. Current computational approaches focus on individual regulators like TFs and miRNAs, neglecting SE interactions. We emphasize incorporating SEs into models to enhance understanding. Experimental studies have recently linked miRNAs and TFs to SEs. Chromatin immunoprecipitation followed by sequencing (ChIP-Seq) provides valuable SE information. In this review, we categorize computational methods leveraging TF and miRNA data into three areas and explore challenges integrating enhancers/SEs. These include unraveling indirect regulatory networks, identifying network motifs, and enriching pathway identification by dissecting gene regulators, including SEs. We hypothesize that addressing these challenges will enhance our understanding of gene regulation, aiding in identifying therapeutic targets and disease biomarkers. We believe that understanding the role of ChIP-Seq data in predicting the effect of miRNA on gene regulation is crucial to construct statistical/computational model that would tackle these challenges.

Sharding shows great potential for extending the blockchain. The current challenge facing sharded blockchain technology lies in addressing the extended transaction confirmation times caused by isolated states between shards and unbalanced transaction allocation strategies. These factors contribute to an increase in cross-shard transactions and disproportionate shard workload, ultimately resulting in indefinite confirmation delays for cross-shard transactions. A critical priority for sharded blockchain systems is to conduct a comprehensive qualitative analysis to better understand and mitigate the prolonged transaction confirmation times. We introduce a Product-Form Queue Network (PFQN) model to address the transaction confirmation time problem in sharded blockchains and incorporate a new confirmation queue to more accurately simulate the actual transaction confirmation process in the blockchain. In addition, we provide a detailed quantitative analysis of the relationship between network load, consensus efficiency, and security in sharded blockchains, laying a theoretical foundation for achieving robustness and efficiency in sharded blockchains. This research not only contributes to addressing the scalability issues in sharded blockchains but also offers a new perspective for future research directions.

In the age of social media, images come from unreliable sources that may change their content to fit a narrative. Automated detection of forged images is a complex task, especially considering recent technological advances in image manipulation software. However, in the existing literature, it is possible to identify two general approaches adopted by detection methods, active and passive. Active techniques preemptively act on an image by inserting structures before any manipulation is made that can verify its authenticity. In contrast, passive methods analyze the content of an image in search of traces of manipulation. In this way, this research proposes a novel approach to image manipulation detection, combining two passive methods through neural networks, creating a generalist approach capable of detecting with greater accuracy than the methods that compose it. Furthermore, this work used a combination of four datasets available in the literature for training and evaluation. After training, the merged approach obtained an accuracy of 89.59% in the set of validation images, significantly higher than the model trained with only unaltered images, which obtained 78.64%, and the two other models trained using images with a feature selection method applied to enhance inconsistencies that obtained 68.02% for Error-Level Analysis images and 50.70% for the method using Discrete Wavelet Transform. In addition to the performance improvement, the proposed approach’s accuracy variation was lower than the other models.

The exceptional performance advantages of the fiber optic gyroscope (FOG) position it as a dominant player in middle and high-end inertial navigation systems. To prevent the loss of sensor precision caused by algorithm design and simplify the complex modeling strategy in traditional methods. We gradually demonstrate the significant role of Convolutional Neural Network (CNN) in the navigation system based on FOG, and utilize the particle swarm optimization algorithm (PSO) to expedite the convergence of the network. The experimental results demonstrate that the initial alignment method based on deep learning is more accurate than the traditional method. The attitude angle error is reduced by 81.25%, 92.54% and 36.53% respectively. The research provides support for the future application of deep learning in optical navigation systems.

In this paper, a class of coupled competitive neural networks, which subject to disturbance and discontinuous activation functions, is concerned. To realize the fixed-time quasi-bipartite synchronization, an aperiodic intermittent controller is initially designed. Subsequently, by combining the fixed-time stability theory and nonsmooth analysis, several criteria are established to ensure the bipartite synchronization in fixed time. Moreover, synchronization error bounds and settling time estimates are provided. Finally, numerical simulations are presented to verify the main results.

This study introduces a cybernetic control and architectural framework for a robotic fish avatar operated by a human. The behavior of the robot fish is influenced by the electromyographic (EMG) signals of the human operator, triggered by stimuli from the surrounding objects and scenery. An deep artificial neural network (ANN) with perceptrons classifies EMG signals, discerning the type of muscular stimuli generated. The research unveils a fuzzy-based oscillation patterns generator (OPG) designed to emulate functions akin to a neural central pattern generator, producing coordinated fish undulations. The OPG generates swimming behavior as an oscillation function, decoupled into coordinated step signals, right and left, for a dual electromagnetic oscillator in the fish propulsion system. Furthermore, the research presents an underactuated biorobotic mechanism of the subcarangiform type, comprising a two-solenoid electromagnetic oscillator, an antagonistic musculoskeletal elastic system of tendons, and a multi-link caudal spine composed of helical springs. The biomechanics dynamic model and control for swimming, as well as the ballasting system for submersion and buoyancy, are deduced. Experimental results encompass EMG pattern recognition, OPG, and coordinated fish locomotion, with additional topics illustrated through numerical simulations.

This study presents an in-depth analysis and evaluation of self-healing networks as an innovative solution to combat the escalating threat of ransomware attacks. Recognizing the limitations of traditional network security methods in the face of advanced cyber threats, the research focuses on the development and implementation of self-healing networks, characterized by their dynamic, intelligent response systems. Utilizing a combination of artificial intelligence and machine learning algorithms, these networks demonstrate remarkable adaptability and resilience. Through rigorous simulations, the study examines the efficacy of self-healing networks in detecting, isolating, and recovering from ransomware attacks, with an emphasis on their ability to learn and evolve from each incident. The research highlights the strengths and limitations of these networks and discusses their potential applications in various sectors. The findings suggest that self-healing networks, with their proactive and adaptive defense mechanisms, represent a significant advancement in cybersecurity strategies, offering a robust solution against a range of cyber threats. Future work is recommended to further enhance the capabilities of self-healing networks, particularly in the areas of speed, detection accuracy, and quantum-resistant security measures.

The research presented in this paper examines a new proposed approach for identifying safety improvement sites on rural highways. Unlike conventional approaches, the proposed approach does not require crash history, but rather utilizes classified variables for traffic volume, geometric features, and roadside characteristics that do not require access to exact data or extensive technical expertise. The research validates the performance of the proposed approach using field data from a large sample of rural two-lane highway segments in the state of Oregon including traffic, roadway, and crash data. Using observed crash history as a reference, the performance of the proposed ap-proach was compared to two of the well-established methods in practice, namely: the Empirical Bayes (EB) and the Potential for Safety Improvement (PSI) methods. The study results suggest that, using crash density for highway segments, the performance of the proposed method was lower than that of the EB and PSI methods. This is despite the high R-square value of the predictive model used in the proposed method. However, when using crash frequencies for highway segments, the per-formance of the proposed method was found comparable to the well-established EB and PSI methods.

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

During geomagnetic storms, which are a result of solar wind interaction with the Earth’s magnetosphere, geomagnetically induced currents (GICs) begin to flow in the long-distance high-voltage power grids on the Earth’s surface. It causes a number of negative phenomena that affect the normal operation of the entire electric power system. To investigate the nature of the phenomenon and its possible effects on transformers, a GIC monitoring system was created in 2011, the devices of which were installed at five substations of the Kola-Karelian power transit in northwestern Russia. Over 12 years of operating the system a large amount of data has been accumulated, which cannot be analyzed manually within a reasonable amount of time. To analyze the constantly growing volume of recorded data effectively, a method for automatic classification of GIC in autotransformer neutral was proposed. The method is based on a continuous wavelet transform of the neutral current data combined with a convolutional neural network (CNN) to classify the obtained scalogram images. As the result of comparing four CNNs with different architectures, a model that showed excellent GIC classification performance on the validation set (100.00% accuracy and loss of 0.0115) was chosen.

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

In this paper, we demonstrate that fixed-weight layers, generated from random distribution or logistic functions, can effectively extract significant features from input data, resulting in high accuracy on a variety of tasks, including Fisher’s iris, Wisconsin Breast Cancer, and MNIST datasets. We have observed that logistic functions yield high accuracy with less dispersion in results. We have also assessed the precision of our approach under conditions of minimizing spikes number generated in the network, it is a practically useful for reducing energy consumption in spiking neural networks. Our findings reveal that the proposed method demonstrates a highest accuracy on Fisher’s iris and MNIST datasets with logistic regression. Furthermore, they surpass the accuracy of the conventional (non-spiking) approach using logistic regression in the case of Wisconsin Breast Cancer. We have also investigated the impact of non-stochastic spike generation on accuracy.

Traffic congestion and frequent traffic accidents have become main problems affecting urban traffic. Effective location prediction of vehicle trajectory can help alleviate traffic congestion, reduce the occurrence of traffic accidents, and optimize the urban traffic system. Vehicle trajectory is closely related to the surrounding Points of Interest (POI). POI can be considered as the spatial feature and can be fused with trajectory points to improve prediction accuracy. A Local Dynamic Graph Spatiotemporal- Long Short-Term Memory (LDGST-LSTM) is proposed in this paper to extract and fuse the POI knowledge and realize next location prediction. POI semantic information is learned by constructing the traffic knowledge graph, and spatial and temporal features are extracted by combining Graph Attention Network (GAT) and temporal attention mechanism. Moreover, the weights of POI that influence location prediction are visualized to improve the interpretability of the proposed model. The effectiveness of LDGST-LSTM is verified on two datasets, including Chengdu taxi trajectory data in October 2018 and August 2014. The accuracy and robustness of the proposed model are significantly improved compared with the benchmark models.

In the field of maneuvering target tracking, the combined observations of azimuth and Doppler may cause weak observation or non-observation in the application of traditional target tracking algorithms. Additionally, traditional target-tracking algorithms require pre-defined multiple mathematical models to accurately capture the complex motion states of targets, while model mismatch and unavoidable measurement noise lead to significant errors in target state prediction. To address those above challenges, in recent years, the target-tracking algorithms based on neural networks, such as recurrent neural networks (RNNs), long short-term memory (LSTM) networks, and Transformer architectures, have been widely used for their unique advantages to achieve accurate predictions. To better model the nonlinear relationship between the observation time series and the target state time series, as well as the contextual relationship among time series points, we present a deep learning algorithm called recursive downsample-convolve-interact neural network (RDCINN) based on convolutional neural network (CNN) that downsamples time series into sub-sequences and extracts multi-resolution features to enable the modeling of complex relationships between time series, which overcomes the shortcomings of traditional target-tracking algorithms in using observation information inefficiently due to weak observation or non-observation. The experimental results show that our algorithm outperforms other existing algorithms in the scenario of strong maneuvering target tracking with the combined observations of azimuth and Doppler.

Chronic Low Back Pain (CLBP), defined as pain persisting for at least 12 weeks, is a significant public health issue, with prevalence intensifying due to an ageing global population, amassing approximately 619 million cases in 2020 and projected to escalate to 843 million by 2050. Given the multitude of therapeutic modalities available for CLBP, this research sought to ascertain their respective efficacies in ameliorating pain and disability. We specifically scrutinized Multidisciplinary Biopsychosocial Rehabilitation (MBR) among adults enduring non-specific low back pain for over 12 weeks, excluding acute pain conditions and pre-study surgical interventions. MBR is an approach encompassing various modalities, including exercise, behavioral therapies, educational programs, and work conditioning aspects, necessitating a comprehensive Network Meta-Analysis (NMA) to fully grasp the extensive scope of its impact. The constructed network comprised diverse MBR modalities (behavioral, educational, and work conditioning) alongside exercise therapy (ET), minimal intervention, and usual care, serving as controls with pain and disability as outcomes. Through the analysis of 4,619 initially identified studies, 93 were included, encompassing a total of 8,059 participants. The NMA conducted substantiated that both ET and MBR modalities were notably effective in alleviating CLBP, with education-oriented MBR emerging as the most efficacious for pain mitigation and behavior-focused MBR for disability reduction. Nevertheless, the discerned differences amongst the treatments were minimal and uncertain, highlighting that no modality was definitively superior to the others. The analysis revealed low global and local inconsistency within the network, underscoring the reliability of the observed outcomes. Given the intricate nature of CLBP, embodying various facets, our findings advocate for a combined therapeutic approach to optimize treatment efficacy. Nonetheless, the presence of high study heterogeneity and potential biases necessitates cautious interpretation of the results, prompting future research.

Human keratinocytes and melanoma can stick together to form clusters after eight days in co-culture. As in dynamic system concepts, one can consider cluster formation as the system attractor, cell seeding as the initial condition, and density change over time as a path within the basin of attraction. Herein, Cellular Automata, which is a class of Agent-Based Models, and Boolean Networks are discrete modeling methods used in population dynamics such that running the dynamics of cellular automata backward reveals an underlying network in terms of basin of attraction, also known as global dynamics. Thus, we hypothesize that one can estimate the local dynamic of an agent-based model from the basin of attraction of a boolean network. Here, we propose an approach to estimating these agent-based model rules, which consists of comparing the density states within each state transition and reaching a consensus among state transitions belonging to a basin of attraction of a boolean network. The objectives of this study are: (1) to infer a boolean network from the co-culture growth curve; (2) to estimate the rules of agent-based models; and (3) to implement spatial dynamics simulations. The binarization of the growth curve shows high population density after four days; the estimated agent-based model rules were compatible with cell proliferation and migration in agreement with literature, so we had to propose individual rules for survival and death. Spatial dynamics shows that (1) keratinocytes exhibit a higher density in neighborhoods where melanoma is present; (2) the chance of keratinocyte migration increases until the fourth day, then decreases, and the probability of survival increases substantially after four days; and (3) cells with low proliferation capacity die and free space for those with high ones. Our approach suggests that the attractor state of cell co-culture is induced mainly by an increase in keratinocyte migration and survival. Our approach has the potential to offer valuable clues about microenvironmental interactions or configurations that drive population dynamics.

Due to the complexity of the microstructure of porous media, it is of great significance to explore the heat transport mechanism in porous media in many engineering applications. In this study, an expression for effective thermal conductivity（ETC） of porous media with randomly distributed damaged tree-like bifurcation networks is derived based on the theory of thermodynamics and fractal features of tree-like bifurcation networks. We investigate the effect of heat conduction and heat convection in porous media with randomly distributed damaged tree-like bifurcation networks on the ETC of the porous media. It is found that our fractal model is in good consistency with the existing available experimental data. In addition, the influence of the micro-structural parameters of the model on heat transfer in the porous media have been analyzed in detail. The research results can provide significant theoretical guidance for the development and design of heat transfer systems.

Keywords: Аrtificial neural network, electric drive system, database, stability, training algorithm, technological mechanisms.

It’s been reported that Mori Folium (MF) and Eucommiae Cortex (EC) exhibit pharmacological effects on the treatment of immunosuppression. However, the mechanism of MF and EC against immunosuppression remains unclear. This study aims to explore the mechanism of action of MF and EC for the treatment of immunosuppression through network pharmacology, molecular docking, molecular dynamics simulations and animal experiments. As a result, 11 critical components, 9 hub targets, and related-signaling pathways of treatment of immunosuppression were obtained based on network pharmacology. The molecular docking suggested that 11 critical components exhibited great binding affinity to 9 hub targets of immunosuppression. The molecular dynamics simulations results showed that (-)-Tabernemontanine-AR, beta-sitosterol-AR and Dehydrodieugenol-HSP90AA1 complexes are stably bound. Additionally, in the animal experiments, the treated group results compared to the control group suggest that MF and EC have a significant effect on the treatment of immunosuppression. Therefore, the MF and EC treatment for immunosuppression may take effects in a multi-component, multi-target, and multi-pathway manner. The results would provide novel insights into the treatment of immunosuppression in humans.

Underwater image processing faces significant challenges due to the absorption and scattering of light as it travels through water. A self-supervised learning network based on the self-attention mechanism is proposed for underwater visual applications in this paper. The goal is to improve the effectiveness and stability of feature extraction from underwater images. By incorporating self-attention mechanism, the sensitivity of the original network architecture to degraded features of blurred underwater images is enhanced. The network proposed in this paper is trained using transfer learning and evaluated on various underwater image datasets. With distributive, quantitative, and qualitative advantages compared with other methods, experimental results have demonstrated that the algorithm presented shows a slighter decline in feature extraction ability for blurred images as the turbidity of water increases.

In Holter monitoring, the precise detection of standard heartbeats and Ventricular Premature Contractions (PVCs) is paramount for accurate cardiac rhythm assessment. This study introduces a novel application of the 1D U-Net neural network architecture aimed at enhancing PVC detection in Holter recordings. Training data comprised the Icentia11k, INCART DB, and our custom dataset. The model’s efficacy was subsequently validated against traditional Holter analysis methodologies across multiple databases, including AHA DB, MIT 11 DB, NST, and another custom dataset encompassing challenging real-world examples. The results underscored the 1D U-Net model’s prowess in QRS complex detection, achieving near-perfect balanced accuracy scores across all databases. PVC detection exhibited variability, with balanced accuracy scores ranging from 0.909 to 0.986. Despite some databases, like the AHA DB, showcasing lower sensitivity metrics, their robust balanced accuracy accentuates the model’s equitable performance in discerning both false positives and negatives. In conclusion, while the 1D U-Net architecture is a formidable tool for QRS detection, there’s a clear avenue for further refinement in its PVC detection capability, given the inherent complexities and noise challenges in real-world PVC occurrences.

In South Korea, demolition waste (DW) management has become increasingly significant owing to the rising number of old buildings. Effective DW management requires an efficient approach that accurately quantifies and predicts the generation of DW (DWG) of various types, which necessitates access to the required information or technology capable of achieving this. Hence, we developed an artificial intelligence-based model that predicts the generation of ten DW types, specifically from buildings in redevelopment areas. We used an artificial neural network algorithm with < 10 neurons in the hidden layer to derive individual input variables and optimal hyperparameters for each DW type. All DWG prediction models achieved an average validation and test prediction performance (R²) of 0.970 and 0.952, respectively, with their ratios of percent deviation ≥ 2.5, ver-ifying them as excellent models. Moreover, a Shapley additive explanations analysis revealed that DWG was most impacted by the floor area for all the DW types, with a positive correlation with DWG. Conversely, other factors showed either a positive or negative correlation with DWG de-pending on the DW type. The study findings will enable demolition companies and local gov-ernments in making informed decisions for efficient DW management and resource allocation by accurately predicting the generation of various types of DW.

Using traditional methods based on detection rules written by human security experts, there is a significant challenge in accurately detecting many network threats that are increasingly becoming sophisticated. In order to deal with the limitation of the traditional methods, network threat detection techniques utilizing artificial intelligence technologies such as machine learning are being extensively studied. Research has also been conducted on analyzing various string patterns in network packet payloads through natural language processing techniques to detect attack intent. However, due to the nature of packet payloads containing binary data as well as text data, a new approach is needed that goes beyond typical natural language processing techniques. In this paper, we study a token extraction method optimized for payloads using n-gram and byte pair encoding techniques. Furthermore, we generate embedding vectors that can understand the context of the packet payload using algorithms such as Word2Vec and FastText. We also compute the embedding of various header data associated with packets, such as IP addresses and ports. Given the combination of these features, we ensemble a text 1D-CNN and a multi-head attention network in a novel fashion. We validated the effectiveness of our classification technique with the CICIDS2017 open dataset and over half a million data collected by The Education Cyber Security Center (ECSC) currently operating in South Korea. The proposed model showed remarkable progress compared to previous studies, demonstrating a highly accurate classification performance with an F1-Score of 0.998. Our model can also preprocess and classify 150,000 network threats per minute to help security agents in the field divert their time to analyzing more complex attack patterns.

This study will lead to the development of a numerical data set that will assist in the design of Savonius wind turbines. A major objective of this study is to develop a better design for Savonius turbine blades in order to increase their torque coefficients, rotational speeds, and pressure coefficients. As part of the experimental design methodology, a full dataset was generated by simulating three-dimensional scale models utilizing computational fluid dynamics (CFD) simulations that were validated by wind tunnel data. This process is multi-objective optimization for optimizing turbine performance. The twist angle, aspect ratio, and overlap ratio are all important factors in determining the optimal torque and power coefficients. The group method of data handling (GMDH) algorithm was utilized to model objective functions based on input-output data. The Pareto fronts were plotted using polynomial models obtained from the evolutionary Pareto-based optimization approach (modified NSGA-II), and the optimal commercial points were determined using TOPSIS. A comparison of three- and two-objective optimization data revealed that two-objective optimization data lie within the boundaries of a three-objective optimization problem. The torque coefficient, rotational speed, and power coefficient are all improved by 13.74%, 0.071%, and 5.32%, respectively, using multi-objective optimization. As a result of the multi-objective optimization of the turbine, some significant characteristics of objective functions were discovered.

Tesso Nilo National Park is one of the protected areas designated as KPA by the Decree of the Minister of Forestry No.225/Menhut-II/2004 dated July 19, 2004 covering an area of ​​38,576 ha, then expanded again through the Decree of the Minister of Forestry No.663/Menhut/2009 dated 19 October 2009 with an area of ​​± 83,068 ha. The Tesso Nilo National Park area is experiencing the dynamics of land cover changes, namely the conversion of forest land which causes the forest area to become increasingly narrow in this area. With the reduction in forest area in this area, it causes a decrease in ecosystem network connectivity due to forest fragmentation that occurs, so that forests are separated and further apart. This study aims to analyze changes in land cover in the Tesso Nilo National Park area to find out information on changes in habitat ecosystems in the last 20 years. the observations were made using satellite images in 1999, 2010 and 2019. so that it can be seen the effect of forest fragmentation on ecosystems in the Tesso Nilo National Park area. From the results of the analysis, it was found that the area of ​​forest cover in the Tesso Nilo National Park decreased from 1999 to 2019 and caused changes in the connectivity network of forest ecosystems, which was found in the study, the weakest connectivity separated forest fragments as far as 17394.47 meters due to forest cover fragmentation.

In bioinformatics research, traditional machine learning methods have demonstrated efficacy in addressing Euclidean data. However, real-world data often encompasses non-Euclidean forms, such as graph data, which contain intricate structural patterns or high-order relationships that elude conventional machine-learning approaches. Representation learning seeks to derive valuable data representations from enhancing predictive or analytic tasks, capturing vital patterns and structures. This method has proven particularly beneficial in bioinformatics and biomedicine, as it effectively handles high-dimensional, sparse data, detects complex biological patterns, and optimizes predictive performance. In recent years, graph representation learning has become a popular research direction. It embeds graphs into a low-dimensional space while preserving the structural and attribute information of the graph, enabling better feature extraction for downstream tasks. This study extensively reviews representation learning advancements, particularly in the research of representation methods since the emergence of COVID-19. We begin with an analysis and classification of neural network-based language model representation learning techniques as well as graph representation learning methods. Subsequently, we explore their methodological innovations in the context of COVID-19, with a focus on the domains of drugs, public health, and healthcare. Furthermore, we discuss the challenges and opportunities associated with graph representation learning. This comprehensive review presents invaluable insights for researchers as it documents the development of COVID-19 and offers experiential lessons to preempt future infectious diseases. Moreover, this study guides future bioinformatics and biomedicine research methodologies.

Blasting pattern optimization is an attempt to optimize blast design parameters aiming to achieve optimum fragmentation, reduce mining operating costs as well as environmental side consequences. The present study aims to propose a multi-objective optimization model, employing artificial intelligence and metaheuristics, to simultaneously minimize the mine-to-crusher operating costs and the impact of blasting consequences including fly-rock and back-break. To achieve the purpose of the study, a multi-variable regression model was developed to model total costs from drilling to crushing. In addition to the costs, multilayer perception neural networks were implemented to predict the blast-induced back-break and fly-rock as a function of collected variables such as number of holes, hole length, burden, spacing, hole slope, stemming, blasted rock per hole, powder factor, and charge per delay. High-precise estimations for both back-break and fly-rock were achieved with the average of 99% coefficient of determination for train, test and validation data sets. Then, the developed regression model and the neural networks were used in an optimization framework, employing Grasshopper algorithm, to find the optimum blast design satisfying practical constraints. The proposed model was tested on a lead-zinc open-pit mine, where 1032 blasting patterns were recorded and analyzed. The results of the optimization model provide a Pareto set of solutions, such that any of these solutions can be implemented according to the strategy of the mining operation management team. The blast pattern with the lowest cost, result in a relatively high fly-rock and back-break, while the pattern with low fly-rock and back-break raises the cost by 20.13 % compared the minimum cost blast design.

We performed a retrospective, observational study for 51 eyes of 51 treatment-naive patients with polypoidal choroidal vasculopathy (PCV), whose lesion ranged within the 6x6mm scope of optical coherence tomography angiography (OCTA). Patients were divided into two groups based on the pattern of branching vascular network (BVN) on OCTA: ill-defined group and well-defined group. BVN morphology was not related to baseline best-corrected visual acuity (BCVA). But the BCVA in the ill-defined BVN group (-0.18 [interquartile range: -0.40 to 0.00]) was significantly improved after anti-vascular endothelial growth factor (VEGF) injections, compared with that (0.00 [interquartile range: -0.18 to 0.00]) in the well-defined group (z=2.143, p=0.032). Multiple logistic regression analysis showed that male sex, smaller number of injections, and presence of polypoidal lesions on OCTA images at baseline predicted a poor prognosis of polypoidal lesions on OCTA images after anti-VEGF therapy (all p&lt;0.05). Finally, BCVA at baseline and the number of injections were protective factors for BCVA after anti-VEGF therapy (all p&lt;0.05). In contrast, history of hypertension and macular edema at baseline were risk factors for BCVA after anti-VEGF injections (all p&lt;0.05). Our results revealed the visual and morphological prognosis of patients with active subfoveal circumscribed PCV after anti-VEGF therapy.

Internet users have significantly increased as a result of the spread of Internet of Things (IoT) technologies and 5G networks. But these developments also make people more susceptible to cybercrime. Intrusion detection systems (IDSs), which protect against cyber threats and facilitate early response, have emerged as crucial security measures to handle this expanding risk. This study intends to present a comprehensive review of IDS, how it interacts with machine learning (ML), and develop a suitable approach for attack detection in 5G and IoT environments. To accomplish this, we leverage the AWID dataset, which is the first wireless traffic dataset specifically designed for security purposes, focusing on the IEEE 802.11 standard and developed to the AWID3 dataset. In this research, we suggest a powerful machine-learning framework for wireless system intrusion detection. We perform evaluations in three stages, covering scenarios for multiple nominal classes, multiple numeric classes, and binary classes. In order to improve the performance of the intrusion detection model, we also use feature selection approaches. Additionally, we offer a model that incorporates the outcomes of three feature selection techniques, highlighting how crucial it is to comprehend the features present in wireless datasets. Our experiments demonstrate how a machine learning-based approach can detect attacks with a high level of accuracy. In particular, the boosted decision tree performs best when overlapping feature selection procedures, whereas the Logistic Regression approach obtains the maximum accuracy of 99% in the first two phases. By providing a comprehensive framework for identifying attacks in 5G and IoT contexts using machine learning approaches, this research makes a contribution to the field of intrusion detection. The results underline how important it is to comprehend wireless dataset characteristics and highlight the possibility of ML-based methods for attaining highly accurate intrusion detection.

Stevia Rebaudiana Bertoni Morita II, a perennial plant native to Paraguay and Brazil, is also widely cultivated in the state of Colima, Mexico, for its use as a sweetener in food and beverages. The op-timization of soil parameters is crucial for maximizing biomass production and stevioside levels in stevia crops. This research presents the development and implementation of a monitoring system to track essential soil parameters, including pH, temperature, humidity, electrical conductivity, ni-trogen, phosphorus, and potassium. The system employs a wireless sensor network to collect qua-si-real-time data, which is transmitted and stored in a web-based platform. A Mamdani-type fuzzy logic model is utilized to process the collected data and provide to farmers an integrated assessment of soil quality. By comparing the quality data output of the fuzzy logic model with a line-ar-regression model, the system demonstrated acceptable performance, with a determination coef-ficient of 0.532 for random data and 0.906 for gathered measurements. The system enables farmers to gain insights into the soil quality of their stevia crops and empowers them to take preventive and corrective actions to improve the soil quality specifically for stevia crops.

The total tree height (h) and diameter at breast height (dbh) relationship is an essential tool in forest management and planning. The height—diameter (h-dbh) relationship had been studied with several approaches and for several species worldwide. The nonlinear mixed effect modeling (NLMEM) has been extensively used and lately the resilient backpropagation artificial neural network (RBPANN) approach has been a trend topic for modeling this relationship. The artificial neural network (ANN) is a computing system based in artificial intelligence and inspired in biological neural network for supervised learning. In this study the NLMEN and RBPANN approaches were used for modeling the h—dbh relationship for Durango pine species (Pinus durangensis Martínez) in mixed-species forest from Mexico. The total dataset considered 1,000 (11,472 measured trees) randomly selected from 14,390 temporary forest inventory plots and the dataset was randomly divided into two parts; 50% for training and 50% for testing. An unsupervised clustering analysis was used to grouped the dataset into 10 clusters based on k-means clustering method and plot-variables like density, basal area, mean dbh, mean h, quadratic mean diameter, altitude and aspect. The RBPANN was performed for tangent hyperbolicus (RBPANN-tanh), softplus (RBPANN-softplus), and logistic (RBPANN-logistic) activation functions for functions in cross product of the covariate or neurons and the weights for the ANN analysis. For both training and testing, 10 classical statistics (e.g., RMSE, R2, AIC, BIC, logLik) were computed for the residual values and assess the approaches for h—dbh relationship. For training and testing, the ANNs approach outperformed the NLMEM approach, and the RBPANN-tanh has the best performance in both training and testing phases.

The number of fishers working on commercial fishing vessels worldwide is approximately 159,800 according to the Food and Agriculture Organization of the United Nations. The International Labour Organization estimates that the mean annual number of deaths during fishing is approximately 24,000. Most guidelines for the prevention of marine accidents have been developed with a focus on vessels involved in international navigation. As these guidelines may have parts that are unsuitable for application in small-scale boats operating in coastal areas, appropriate modifications are required. This study analyzed quantitative data on 1,790 marine accidents that occurred in trap fishery, a globally common type of fishery, and data obtained through a survey of 101 fishers in South Korea. A guideline to reduce the rate of fatal accidents was developed using the Bayesian network, a method used for the analysis of accidents, as suggested in the formal safety assessment protocol. The results of data analysis and the developed guidelines are expected to be beneficial to all fishers involved in trap fishery across many countries worldwide.

This paper presents a scenario evolution model for maritime accidents using Bayesian networks (BN) to predict the most likely causes of specific types of maritime incidents. The BN nodes encompass accident type, life loss contingency, accident severity, the quarter and time period of the accident, and the type and gross tonnage of the ships involved. We analyzed 5,660 global maritime accidents from 2005 to 2020. Using Netica software, we constructed a Tree Augmented Network (TAN) model, accounting for interdependencies among risk influencing factors. We validated the results through sensitivity analysis and historical accident records. Forward causal inference and reverse diagnostic inference were then performed on each node variable to investigate the accident development trend and evolution process under predetermined conditions. The findings indicate that the model can effectively predict the likelihood of various accident scenarios under specific conditions, as well as the extrapolation of accident consequences. Forward causal reasoning reveals that general cargo ships with a gross tonnage of 1-18,500 t are most likely to experience collision, grounding, and stranding accidents in the first quarter. Reverse diagnostic reasoning indicates that during early morning hours, container ships, general cargo ships, and chemical ships with a tonnage of 1-18,500 t are less likely to involve life loss in the event of collision accidents.

Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that affects attention and behavioral control, characterized by constant presence of inattention and hyperactivity. This article describes a study that used a database with results from tests of voluntary and automatic attentional orientation activity in a complex network of ADHD patients, in order to understand the characteristics of the elements and attentional variability of patients. Centrality metrics and the Louvain method were applied to obtain the network communities. The most important elements of the network were identified and differences in reaction times of the activities were observed in the identified communities. The study provides useful information to understand of deficit hyperactivity disorder spectrum in patients with ADHD.

This paper focuses on robust multi-criteria traffic network equilibrium problems with path capacity constraints. The concepts of robust vector equilibrium and robust vector equilibrium with respect to worst case are introduced, respectively. To generate a subset of robust vector equilibrium, an equivalent min-max optimization problem is constructed. In addition, a direct search algorithm, in which the step size without derivatives and redundant parameters, for solving this min-max problem is proposed. To find a subset of robust vector equilibrium with respect to worst case, an equivalent smoothing optimization problem based on a variant version of ReLU activation function is established. Numerical experiments are also presented to expound the advantages of the algorithms.

The IDS serves as a security system that maintains constant surveillance over network traffic and host systems in order to identify any security breaches or potentially concerning activities. Recently. the rise in cyber-attacks has driven the necessity for the development of automated and intelligent network intrusion detection systems. These systems are designed to learn the typical patterns of network traffic, allowing them to identify any deviations from normal behaviour, which can be classified as anomalous or malicious. Machine learning methods are widely used to exhibit a satisfactory effectiveness in detecting malicious payloads in the network traffic. While the volume of the data generated from IDS is increasing exponentially results in the emergence of substantial security risks, it highlighted the imperative to strengthen network security. The performance of traditional machine learning methods depends on the dataset and the data balance distribution in it. while most of IDS datasets suffer from unbalancing, this limits the performance of the machine learning method used in the system and results in missed detections and false alarms in the conventional IDSs. To address this issue, this paper presents a new model-based Generative Adversarial Network (GAN) called TDCGAN to enhance the detection rate of less of minor class in the dataset while maintaining efficiency. The proposed model consists of one generator and three discriminators with an election layer at the end of architecture. The UGR’16 data set is used for evaluation purposes. In order to demonstrate the efficacy of our proposed model, various machine learning algorithms have been utilized for comparison. The experimental findings have determined that TDCGAN presents an efficient resolution for addressing imbalanced intrusion detection and surpasses the performance of other oversampling machine learning methods.

Ion current rectification (ICR) is the ratio of ion current by forward bias to by backward bias and is a critical indicator of diode performance. In previous studies, many attempts have been continued to improve the performance of this ICR, but there is the intrinsic problem for geometric changes that induce ionic rectification due to their fabrication problem. Additionally, the high ICR could be achieved in the narrow salt concentration range only. Here, we propose a multi-layered bipolar ionic diode based on an asymmetric nanochannel network membrane (NCNM), which is realized by soft lithography and self-assembly of homogenous-sized nanoparticles. Owing to the freely changeable geometry based on soft lithography, the ICR performance can be explored according to the variation of microchannel shape. Interestingly, very stable ICR performance can be achieved using the multi-layered 3D configuration for the bipolar diode in a broad range of salt concentrations (0.1mM ~ 100 mM). This demonstrates the promising potential of multi-layered NCNM for applications in highly concentrated electrolytes, such as biosensors, desalination, or energy harvesting.

The environment is seldom optimal for plant growth and changes in abiotic and biotic signals, including temperature, water availability, radiation and pests, induce plant responses to optimise survival. The New Zealand native plant species and close relative to Arabidopsis thaliana, Pachycladon cheesemanii grows under environmental conditions that are unsustainable for many plant species. Here we compare the responses of both plant species to different stressors (low temperature, salt and UV-B radiation) to help understand how P. cheesemanii can grow in such harsh environments. The stress transcriptomes were then determined and comparative transcriptome and network analyses discovered similar and unique responses within species between different stresses, and between the two plant species. A number of widely studied plant stress processes were highly conserved in A. thaliana and P. cheesemanii. However, in response to cold stress, Gene Ontology terms related to glycosinolate metabolism were only enriched in P. cheesemanii. Salt stress was associated with alteration of the cuticle and proline biosynthesis in A. thaliana and P. cheesemanii, respectively. Anthocyanin production may be a strategy to cope with UV-B radiation stress in P. cheesemanii only. These results allowed us to construct broad stress response pathways in A. thaliana and P. cheesemanii and identify possible novel plant strategies that help mitigate environmental stress.

The main problem in pursuing multiple extended targets tracking is distinguishing the origins of the measurements. The association of measurements to the possible origins within the target’s extent is difficult, especially for the occlusions or the detection blind zone which cause the intermittent measurements. To solve the problem, a hierarchical network-based tracklets data association algorithm is proposed. At the low level, the min cost network flow model is used to extract possible tracklets from the divided measurement set. At the high-level, the trajectories are estimated from the tracks produced by the previous low level network. The experimental results show that the hierarchical network-based tracklets data association algorithm outperforms the JPDA and RFS-based method when the measurement is intermittently unavailable.

This study aimed at exploring what role artificial intelligence techniques could play in the futural numerical analysis. In this paper, a convolutional neural network techniques based on modified loss function is proposed as a surrogate of finite element method(FEM). Several surrogate-based physics-informed neural networks(PINNs) are developed to solve representative boundary value problems based on elliptic partial differential equations (PDEs). Results from the proposed surrogate-based approach are in good agreement with ones from conventional FEM. It is found that modification of the loss function could improve the prediction accuracy of the neural network. It is indicated that to some extent the artificial intelligence technique could replace conventional numerical analysis as a great surrogate model.

Deep learning has been introduced to single-image super-resolution (SISR) in the last decade. These techniques have taken over the benchmarks of SISR tasks. Nevertheless, most architectural designs necessitate substantial computational resources, leading to a prolonged inference time on embedded systems or rendering them infeasible for deployment. This paper presents a comprehensive survey of plausible solutions and optimization methods to address this problem. Then, we propose a pipeline that aggregates the latter in order to enhance the inference time without significantly compromising the perceptual quality. We investigate the effectiveness of the proposed method on a lightweight GAN-based perceptual-oriented model as a case study. The experimental results show that our proposed method leads to significant improvement in the inference time on both Desktop and Jetson Xavier NX, especially for higher resolution input sizes on the latter, thereby making it deployable in practice.

Grapes are a globally popular fruit, with grape cultivation worldwide being second only to citrus. This article focuses on the low efficiency and accuracy of traditional manual grading of red grape external appearance and proposes a small-sample red grape external appearance grading model based on transfer learning with convolutional neural networks (CNNs). Initially, the CNN transfer learning method was used to transfer the pre-trained AlexNet, VGG16, GoogleNet, InceptionV3, and ResNet50 network models on the ImageNet image dataset to the red grape image grading task. By comparing the classification performance of the CNN models of these five different network depths with fine-tuning, ResNet50 with a learning rate of 0.001 and a loop number of 10 was determined to be the best feature extractor for red grape images. Moreover, given the small number of red grape image samples in this study, different convolutional layer features output by the ResNet50 feature extractor were analyzed layer by layer to determine the effect of deep features extracted by each convolutional layer on SVM classification performance. This analysis helped to obtain a ResNet50+SVM red grape external appearance grading model based on the optimal ResNet50 feature extraction strategy. Experimental data showed that the classification model constructed using the feature parameters extracted from the 10th node of the ResNet50 network achieved an accuracy rate of 95.08% for red grape grading. These research results provide a reference for the online grading of red grape clusters based on external appearance quality and have certain guiding significance for the quality and efficiency of grape industry circulation and production.

The problem of health status prediction of insulated-gate bipolar transistors (IGBTs) gains a lot of attention in the field of health management of power electronic equipment. The performance degradation of IGBT gate oxide layer is one of the important failure modes. In view of failure mechanism analysis and easy implementation of monitoring circuit, this paper selects the gate leakage current of IGBT as the precursor parameter of gate oxide degradation, and uses time domain characteristic analysis, gray correlation degree, Mahalanobis distance, Kalman filter and other methods to carry out feature selection and fusion, and finally obtains a health indicator characterizing the degradation of IGBT gate oxide. Based on the Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) network, this paper constructs an IGBT gate oxide degradation prediction model, and performs experimental analysis on the dataset released by NASA-Ames Laboratory, and the average absolute error of performance degradation prediction is as low as 0.0216. Compared with Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Support Vector Regression (SVR) and CNN-LSTM models, CNN-LSTM network has the highest prediction accuracy. These results show the feasibility of gate leakage current as a precursor parameter of IGBT gate oxide layer failure, as well as the accuracy and reliability of the CNN-LSTM prediction model.

Multivariate predictive analysis of the Stream-Water (SW) parameters (discharge, water level, temperature, dissolved oxygen, pH, turbidity, and specific conductance) is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the meteorological and climatic features have a significant impact on the temporal distribution of the SW variables in recent days making the SW variables forecasting even more complicated for diversified water-related issues. To predict the SW variables, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-informed analysis and prediction, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, a comprehensive Explorative Data Analysis (EDA) and feature engineering were performed to prepare the dataset to obtain the best performance of the predictive model. Long Short-Term Memory (LSTM) neural network regression model is trained using over several years of daily data to predict the SW variables up to one week ahead of time (lead time) with satisfactory performance. The performance of the proposed model is found highly adequate through the comparison of the predicted data with the observed data, visualization of the distribution of the errors, and a set of error matrices. Higher performance is achieved through the increase in the number of epochs and hyperparameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time SW variables prediction.

Optimization using Genetic Algorithms (GA) is a well-known strategy in several scientific disciplines. The crossover is an essential operator of the Genetic Algorithm. It has been an active area of research to develop sustainable forms for this operand. In this work, a new crossover operand is proposed. This operand depends on giving an elicited description for the chromosome with a new structure for alleles of the parents. It is suggested that each allele has two attitudes, one attitude differs contrastingly with the other, and both of them complement the allele. Thus, in case of one attitude is good, the other should be bad. This is suitable for many systems which contain admired parameters and unadmired parameters. The proposed crossover would improve the desired attitudes and damp the undesired attitudes. The proposed crossover can be achieved in two stages: the first stage is a mating method for both attitudes in one parent to improving one attitude at the expense of the other. The second stage comes after the first improvement stage for mating between different parents. Hence, two concurrent steps for improvement would be applied. Simulation experiments for the system shows improvement in the fitness function. The proposed crossover could be helpful in different fields, especially to optimize routing algorithms and network protocols, an application that has been tested as a case study in this work.

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.

We analyze the upside and downside risk connectedness among international stock markets. We characterize the connectedness among international stock returns using the Diebold and Yilmaz spillover index approach and compute the upside and downside value-at-risk. We document that the connectedness level of the downside risk is higher than that of the upside risk and that stock markets are more sensitive when the stock market declines. We also find that specific periods (e.g., the global financial crisis, the European debt crisis, and the COVID-19 turmoil) intensify the spillover effects across international stock markets. Our results demonstrate that the EU, Ger-many, and the US acted as net transmitters of dynamic connectedness; however, Japan (JP), China (CH), and India (IN) acted as net receivers of dynamic connectedness during the sample period. These findings provide significant new information to policymakers and market participants.

Microbial biofilms cause several environmental and industrial issues, even on the human health. Although they have represented a threaten due to their resistance to antibiotics, there are currently no approved antibiofilm agents for clinical treatments. The multi-functionality of antimicrobial peptides (AMPs) including the antibiofilm activity and their potentialities to target multiple mi-crobes motivated the synthesis of AMP relatives for developing antibiofilm agents for clinical purposes. Antibiofilm peptides (ABFPs) have been organized in databases that allowed the building of prediction tools which have assisted in the discovery/design of new antibiofilm agents. However, the complex network approach has been explored yet as an assistant tool for this aim. Herein, a kind of similarity networks, called the Half-Space Proximal Network (HSPN) is applied to represent/analyse the chemical space of the ABFPs aimed to identify promising scaf-folds for the development of next generation antimicrobials, able to target both planktonic and biofilm microbial forms. Such analyses also considered the metadata associated to the ABFPs such as origin, other activities, targets, etc. in which the relationships were projected by multilayer networks called metadata networks (METNs). From the complex networks mining, a reduced but informative set of 66 ABFPs representing the original antibiofilm space was extracted. This subset retained from the most central to atypical ABFPs, having some of them, desired properties for developing next generation antimicrobials. So, this subset is advisable for assisting the search/design both new antibiofilm/antimicrobial agents. The provided ABFP motifs list, dis-covered within the HSPN communities, is also useful for the same purpose.

This paper presents a study of an automated system for identifying planktic foraminifera at the species level. The system uses a combination of deep learning methods, specifically Convolutional Neural Networks (CNNs), to analyze digital images of foraminifera taken at different illumination angles. The dataset is composed of 1437 groups of sixteen grayscale images, one group for each foraminifer, that are then converted to RGB images with various processing methods. These RGB images are fed into a set of CNNs, organized in an Ensemble Learning (EL) environment. The ensemble is built by training different networks using different approaches for creating the RGB images. The study finds that an ensemble of CNN models trained on different RGB images improves the system's performance compared to other state-of-the-art approaches. The proposed system was also found to outperform human experts in classification accuracy.

Working memory (WM) is a brain system for short-term storage and manipulation of information and plays an important role in complex cognitive tasks. In the synaptic theory of WM memorized elements are stored in the form of short-term potentiated connections in a sample population of neurons. In this paper, we show that such populations can be formed due to the mechanisms of spike-timing-dependent plasticity (STDP) – the phase dependence associated with the ratio of the pulse times of the interacting neurons. We propose a WM model considering two types of plasticity: short-term plasticity and STDP. We have shown formation of neuronal clusters encoding items in the WM model, that can be formed by external stimulation of a group of neurons due to the mechanisms of STDP and hold and reactivated by short-term plasticity mechanisms. The dynamic formation of neuronal clusters instead of pre-formed clusters gives additional flexibility to the model.

Neural networks require a large quantity of training spectra and detector responses in order to learn to solve the inverse problem of neutron spectrum unfolding. In addition, due to the under-determined nature of unfolding, non-physical spectra which would not be encountered in usage should not be included in the training set. While physically realistic training spectra are commonly determined experimentally or generated through Monte Carlo simulation, this can become prohibitively expensive when considering the quantity of spectra needed to effectively train an unfolding network. In this paper, we present three algorithms for the generation of large quantities of realistic and physically motivated neutron energy spectra. Using an IAEA compendium of 251 spectra, we compare the unfolding performance of neural networks trained on spectra from these algorithms, when unfolding real-world spectra, to two baselines. We also investigate general methods for evaluating the performance of and optimizing feature engineering algorithms.

The treatment of insulin-dependent diabetes mellitus is characterized by artificial supplementation of pancreatic β-cell ability to regulate sugar levels in the blood. Even though various insulin analogs are crucial for reasonable glycemic control, understanding the dynamic mechanism of the insulin analogs may help to improve the best-protracted insulin analog to assist people with Type 1 Diabetes (T1D) to live comfortably while maintaining tight glycemic control. Here we present the high-resolution crystal structure of NN304, known as insulin detemir, to 1.7 A resolution at cryogenic temperature. We computationally further investigated our crystal structure's monomeric-dimeric conformation and dynamic profile by comparing it with a previously available detemir structure (PDB ID: 1XDA). Our structure (PDB ID: 8HGZ) obtained at elevated pH provides a distinct alternative dimeric conformation compared to the previous structure, suggesting it might induce an intermediate state in the dissociation pathway of the insulin detemir’s hexamer:dihexamer equilibrium. Combined with orientational cross-correlation analysis by Gaussian Network Model (GNM), this alternate oligomeric conformation offers the distinct cooperative motions of a protracted insulin analog that has not been previously observed.

Social network analysis (SNA) is an effective method for characterizing networks from various specific perspectives. Global trade contracted sharply in 2020 owing to the COVID-19 pandemic, and growth is expected to be lower than the pre-pandemic trends. This study takes countries worldwide as the primary unit of analysis and uses different procedures of social network analysis (SNA), including network density, centrality, and core-periphery structure, and applies them to the field of trade in electronic integrated circuit products (ICPT). In addition to static and descriptive analysis, this study also uses of tools such as Ucinet 6.732 for visual analysis, visual analysis, and more convenient and precise display of the network structure of ICPT. The important countries play a central role in determining the overall structural features. The core-periphery structure in the network from both spatial and temporal perspectives, data on electronic integrated circuit products for the period 2015-2021 were used in SNA. This study found that the ICPT network became denser from 2015 to 2021 but declined and picked up in 2018 and 2020. Moreover, the core-peripheral structure exists in the ICPT network. The main core network countries are Taiwan, Hong Kong, Singapore, mainland China, Malaysia, Japan, the Philippines, Thailand, Vietnam, and other Asian countries, including the United States and Germany.

The aim of this work is to propose two different and complementary sensors for the structural health monitoring of concrete beams. In particular, a diffused sensing element and a split ring resonator network are presented. The first sensor is able to detect the variation of the dielectric properties of the concrete along the whole beam length, for a diffuse monitoring both during the important concrete curing phase and also for the entire life cycle of the concrete beams. The resonators instead work punctually, in their surroundings, allowing an accurate evaluation of the permittivity both during the drying phase and after. This allows the continuous monitoring of any presence of water both inside the concrete beam and in points that can be critical, in the case of beams in dams, bridges or in any case subject to a strong presence of water which could lead to deterioration, or worse, cause serious accidents. Moreover, the punctual sensors are able to detect the presence of cracks in the structure and to localize them.

Increasingly, systems biology is gaining relevance in basic and applied research. The combination of computational biology with wet lab produces a synergy that results in an exponential increase in knowledge of biological systems. The study of microorganisms such as Staphylococcus epidermidis RP62A enables the researcher to understand better its metabolic network, which allows the design of effective strategies to treat infections caused by this species or others. S. epidermidis is the second cause of infection in patients with joint implants, so treating its proliferation seems vital for public health. There are different approaches to the analysis of metabolic networks. Flux Balance Analysis (FBA) is one of the most widespread streams. It allows the study of large metabolic networks, their structural properties, the optimization of metabolic flux, and the search for intervention strategies to modify the state of the metabolic network. This work presents the validation of the Staphylococcus epidermidis RP62A metabolic network model elaborated by Díaz-Calvo et al.. Then, we elaborate further on the network analysis’s essential reactions, classifying them. Finally, we introduce some proposals to intervene in the network and design knock-outs.

The endothelium has multiple functions from maintaining vascular homeostasis, providing nutrition and oxygen to tissues, to evocating inflammation, under adverse conditions, and determining endo-thelial barrier disruption resulting in dysfunction. Endothelial dysfunction represents the typical condition associated with the pathogenesis of all the diseases of cardiovascular system, as well as of diseases of all the other human body’s systems, also including sepsis, acute respiratory distress syn-drome and COVID-19 respiratory distress. Such evidence is leading to identifying potential bi-omarkers and therapeutic targets for preserving, reverting, or restoring endothelium integrity and functionality by early treating its dysfunction. Here, it stresses some strategies for achieving these goals, even if diverse challenges exist and require a significant bench work associated with an in-creased number of clinical studies.

In heterogeneous networks, the random walks based on meta-path requires prior knowledge and lacks flexibility. And the random walks based on non-meta-path only considers the number of node types, but does not consider the influence of schema and topology between node types in real networks. To solve the above problems, this paper proposes a novel model HNE-RWTIC (Heterogeneous Network Embedding Based on Random Walks of Type & Inner Constraint). Firstly, to realize the flexible walks, we design a Type strategy, which is the node type selection strategy based on the co-occurrence probability of node types. Secondly, to achieve the uniformity of node sampling, we design an Inner strategy, which is the node selection strategy based on the adjacency relationship between nodes. The Type & Inner strategy can realize the random walks based on meta-path, the flexibility of the walks, and can sample the node types and nodes uniformly in proportion. Thirdly, based on the above strategy, a transition probability model is constructed; then, we obtain the nodes embedding based on the random walks and Skip-Gram. Finally, in classification and clustering tasks, we conducted a thorough empirical evaluation of our method on three real heterogeneous networks. Experimental results shown that F1-Score and NMI of HNE-RWTIC outperform state-of-the-art approaches.

One of the critical tools for early detection and subsequent evaluation of the incidence of lung diseases is chest radiography. This study presents a real-world implementation of a convolutional neural network (CNN) based Carebot Covid app to detect COVID-19 from chest X-ray (CXR) images. Our proposed model takes the form of a simple and intuitive application. Used CNN can be deployed as a STOW-RS prediction endpoint for direct implementation into DICOM viewers. The results of this study show that the deep learning model based on DenseNet and ResNet architecture can detect SARS-CoV-2 from CXR images with precision of 0.981, recall of 0.962 and AP of 0.993.

Driver drowsiness is one of the leading causes of traffic accidents. This paper proposes a new method for classifying driver drowsiness using deep convolution neural networks trained by wavelet scalogram images of electrocardiogram (ECG) signals. Three different classes were de-fined for drowsiness based on video observation of driving tests performed in a simulator for manual and automated modes. The Bayesian optimization method is employed to optimize the hyperparameters of the designed neural networks, such as the learning rate and the number of neurons in every layer. To assess the results of the deep network method, Heart Rate Variability (HRV) data is derived from the ECG signals, some features are extracted from this data, and finally, random forest and k-nearest neighbors (KNN) classifiers are used as two traditional methods to classify the drowsiness levels. Results show that the trained deep network achieves balanced accuracies of about 77% and 79% in the manual and automated modes, respectively. However, the best obtained balanced accuracies using traditional methods are about 62% and 64%. We conclude that designed deep networks working with wavelet scalogram images of ECG signals significantly outperform KNN and random forest classifiers which are trained on HRV-based features.

Based on the satellite attitude control method, this paper proposes an attitude control method based on neural network disturbance compensation. The paper firstly analyzes the neural network algorithm and proposes an orthogonal least squares algorithm to implement network learning. In this paper, a set of high-precision directional neural network compensation controllers is designed for the attitude control of acupuncture small satellites. The feasibility of the improved orthogonal least-squared algorithm combined with the neural network supplementary control method in satellite attitude control is verified by experiments.

Panax ginseng C.A.Mey. is an adaptogenic plant traditionally used to enhance mental and physical capacities in cases of weakness, exhaustion, tiredness, loss of concentration, and during recovery. According to ancient records, Red Ginseng root preparations enhance longevity with long-term intake. Recent pharmacokinetic studies of ginsenosides in humans and our in vitro study in neuronal cells suggest that ginsenosides are effective when their level in blood is shallow - at concentrations from 10-6 to 10-18 M. In the present study, we compared the effects of Red Ginseng root preparation HRG80TM(HRG) at concentrations from 0.01 to 10,000 ng/ml with effects of White Ginseng (WG) and purified ginsenosides Rb1, Rg3, Rg5 and Rk1 on gene expression of isolated hippocampal neurons. The aim of this study was to predict the effects of differently expressed genes on cellular and physiological functions in organismal disorders and diseases. Gene expression profiling was performed by transcriptome-wide mRNA microarray analyses in murine HT22 cells after treatment with ginseng preparations. Ingenuity pathway downstream/upstream analysis (IPA) was performed with datasets of significantly up-or downregulated genes, and expected effects on cellular function and disease were identified by IPA software. Ginsenosides Rb1, Rg3, Rg5, and Rk1 have substantially various effects on gene expression profiles (signatures) and are different from signatures of HRG and WG. Furthermore, the signature of HRG is changed significantly with dilution from 10000 to 0.01 ng/ml. Network pharmacological analyses of gene expression profiles showed that HRG exhibits predictable positive effects in neuroinflammation, senescence, apoptosis, and immune response, suggesting beneficial soft-acting effects in cancer, gastrointestinal, and endocrine systems diseases and disorders in a wide range of low concentrations in blood.

In the last few decades, glaucoma became the second biggest leading cause of irreversible vision loss. Because of its asymptotic growth, it is not properly diagnosed until the relatively late stage. To stop the severe damage by glaucoma it is needed to detect glaucoma in its early stages. Surprisingly diabetes also be the greatest cause of glaucoma. In the modern era, artificial intelligence makes great progress in the medical image processing field. Image analysis based on machine learning gives a huge success in diagnosis glaucoma without any misdiagnosis. The aim of this proposed paper is to create an automated process that can detect glaucoma and diabetic retinopathy. Here various Machine Learning models are used and results of these methods are presented.

Nowadays, we use social networks such as Twitter, Facebook, WeChat and Weibo as means to communicate with each other and get to know others. Gradually social networks has become indispensable in our everyday life, and we cannot absolutely imagine what the daily life would be like without social networks. Through social networks, we can access friends' opinions and behaviors easily and are influenced by them in turn. Thus, an effective algorithm to find the top-K influential nodes (the problem of influence maximization) in the social network is critical for various downstream tasks such as viral marketing, anticipating natural hazards, reducing gang violence, public opinion supervision etc. Solving the problem of influence maximization in real-world propagation scenarios often involves estimating influence strength (influence probability between two nodes), which cannot directly observed. To estimate influence strength, conventional approaches propose various humanly-devised rules to extract features of user interactions, the effectiveness of which heavily depends on domain expert knowledge. Besides, they are often applicable for special scenarios or specific diffusion models. Consequently, they are difficult to be generalized into different scenarios, diffusion models and even domains. Inspired by the powerful ability of neural networks in the field of representation learning, we design a deep hierarchical network embedding model HGE to map nodes (with attributes) into latent space automatically. In general, HGE takes an attributed social network as the input for learning latent network representation of each node, incorporating hierarchical community structure, node attributes and general network structure into a unified deep generative framework. Then, with the leaned latent representation of each node, we propose a HGE-GA algorithm to predict influence strength and compute the top-K influential nodes through a greedy-based maximization algorithm. Extensive experiments on real-world attributed networks demonstrate the outstanding superiority of the proposed HGE model and HGE-GA algorithm compared with the state-of-the-art methods, verifying the effectiveness of the proposed model and algorithm.

A method of direction-of-arrival (DoA) estimation for FMCW radars is presented. In addition to MUSIC and ESPRIT, which are well-known high-resolution DoA estimation algorithms, deep learning has recently emerged as a very promising alternative. It is proposed in this paper to use a 3D convolutional neural network (CNN) for DoA estimation. The 3D-CNN extracts from the radar data cube spectrum features of the region of interest (RoI) centered on the potential positions of the targets, thereby capturing the spectrum phase shift information, which corresponds to DoA, along the antenna axis. Finally, the results of simulations and field experiments are provided to demonstrate the superior performance, as well as the limitations, of the proposed 3D-CNN.

In this paper, we propose a robust video understanding model for activity recognition by learning the actor’s pair-wise correlations and relational reasoning, exploiting spatial and temporal information. In order to measure the similarity between the pair appearances and construct an actor relations map, the Zero Mean Normalized Cross-Correlation (ZNCC) and the Zero Mean Sum of Absolute Differences(ZSAD) is proposed to allow the Graph Convolution Network (GCN) to learn how to distinguish group actions. We recommend that MNASNet be used as the backbone to retrieve features. Experiments show a 38.50% and 23.7% reduction in training time in the 2-stage training process along with a 1.52% improvement in accuracy against traditional methods.

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

Considering the significant advancements in autonomous vehicle technology, research in this field is of interest to researchers. To drive vehicles autonomously, controlling steer angle, gas hatch, and brakes need to be learned. The behavioral cloning method is used to imitate humans’ driving behavior. We created a dataset of driving in different routes and conditions and using the designed model, the output used for controlling the vehicle is obtained. In this paper, the Learning of Self-driving Vehicles Based on Real Driving Behavior Using Deep Neural Network Techniques (LSV-DNN) is proposed. We designed a convolutional network which uses the real driving data obtained through the vehicle’s camera and computer. The response of the driver is during driving is recorded in different situations and by converting the real driver’s driving video to images and transferring the data to an excel file, obstacle detection is carried out with the best accuracy and speed using the Yolo algorithm version 3. This way, the network learns the response of the driver to obstacles in different locations and the network is trained with the Yolo algorithm version 3 and the output of obstacle detection. Then, it outputs the steer angle and amount of brake, gas, and vehicle acceleration. The LSV-DNN is evaluated here via extensive simulations carried out in Python and TensorFlow environment. We evaluated the network error using the loss function. By comparing other methods which were conducted on the simulator’s data, we obtained good performance results for the designed network on the data from KITTI benchmark, the data collected using a private vehicle, and the data we collected.

This study aims to develop a hybrid approach based on backpropagation Artificial Neural Network (ANN) and spatial analysis techniques to predict particulate matter of size 2.5 µm (PM2.5) from vehicle exhaust emissions in the State of California using Aerosol Optical Depth (AOD) and several climatic indicators (relative humidity, temperature, precipitation, and wind speed). The PM2.5 data were generated using Motor Vehicle Emission Simulator (MOVES), the measured climatic variables and AOD were obtained from the California Irrigation Management Information System (CIMIS), and NASA’s Moderate Resolution Spectroradiometer (MODIS). The data were resampled to a seasonal format and downscaled over grids of 10 by 10 to 150 by 150, and precipitation was determined to be the most important independent variable. Coefficient of determination ( ), Mean Absolute Percentage Error (MAPE), and Root Mean Square Error (RMSE) were used to assess the quality of the ANN prediction model. The model peaked at winter seasons with = 0.984, RMSE = 0.027, and MAPE = 25.311, whereas it had the lowest performance in summer with = 0.920, RMSE = 0.057, and MAPE = 65.214. These results indicate that the ANN model can accurately predict the PM2.5 concentration and can be used to forecast future trends.