This research investigates the application of deep learning in sentiment analysis of Canadian maritime case law. It offers a framework for improving maritime law and legal analytics policy-making procedures. The automation of legal document extraction takes center stage, underscoring the vital role sentiment analysis plays at the document level. Therefore, this study introduces a novel strategy for sentiment analysis in Canadian maritime case law, combining sentiment case law approaches with state-of-the-art deep learning techniques. The overarching goal is to systematically unearth hidden biases within case law and investigate their impact on legal outcomes. Employing Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) based models, this research achieves a remarkable accuracy of 98.05% for categorizing instances. In contrast, Conventional Machine Learning techniques such as Support Vector Machines (SVM) yield an accuracy rate of 52.57%, Naive Bayes at 57.44 %, and Logistic Regression at 61.86%. The superior accuracy of the CNN and STM model combination underscores its usefulness in legal sentiment analysis, offering promising future applications in diverse fields like legal analytics and policy design. These findings mark a significant choice for AI-powered legal tools, presenting more sophisticated and sentiment-aware options for the legal profession.

In this paper, we present a framework to study the spatial structure of noctilucent clouds formed by ice particles in the upper atmosphere at mid and high latitude during summer. We study noctilucent cloud activity in optical images taken from three different locations and under different atmospheric conditions. In order to identify and distinguish noctilucent cloud activity from other objects in the scene, we employ linear discriminant analysis (LDA) with feature vectors ranging from simple metrics to higher-order local autocorrelation (HLAC), and histogram of oriented gradients (HOG). Finally, we propose a Convolutional Neural Networks (CNN) based method for the detection of noctilucent clouds. The results clearly indicate that the CNN based approach outperforms LDA based methods used in this article. Furthermore, we outline suggestions for future research directions to establish a framework that can be used for synchronizing the optical observations from ground based camera systems with echoes measured with radar systems like EISCAT in order to obtain independent additional information on the ice clouds.

In the intricate domain of text analysis, syntactic dependency trees play a crucial role in unraveling the web of relations among entities embedded in the text. These trees provide a structural roadmap, guiding us through the complex syntax to pinpoint the interactions and connections between different entities. However, the challenge lies in sifting through this intricate structure to extract relevant information, a task that requires precision and discernment. Traditional approaches often rely on rule-based pruning methods to simplify these dependency structures, focusing on certain parts while discarding others. Yet, this approach has its pitfalls, as it can overlook critical nuances and connections that are vital for a comprehensive understanding of the text. Addressing this gap, our research introduces the Syntactic Dependency-Aware Neural Networks (SDANNs), a groundbreaking model designed to harness the full power of the entire dependency tree. This approach marks a significant departure from the conventional methods. Instead of the rigid rule-based pruning, SDANNs implement a more flexible and dynamic 'soft-pruning' technique. This method allows the model to adaptively focus on the sub-structures within the dependency tree that are most relevant for understanding the relationships between entities. By doing so, it ensures that no vital information is overlooked, and all potential connections are considered. The efficacy of SDANNs is not just theoretical but has been empirically validated through extensive testing and evaluations across a wide range of tasks. These tasks include the extraction of complex relations spanning multiple sentences, as well as detailed analyses at the sentence level. In each of these scenarios, SDANNs have demonstrated a remarkable ability to leverage the full structural complexity of dependency trees. This capability sets them apart from existing models, enabling a more nuanced and comprehensive analysis of textual relations. The results of these evaluations consistently show that SDANNs not only meet but significantly exceed the performance of prior models. This superiority is evident in the way SDANNs handle the multifaceted and often subtle interactions within the text, offering insights that were previously inaccessible with conventional methods. In summary, the Syntactic Dependency-Aware Neural Networks represent a significant advancement in the field of text analysis. By fully embracing the complexity of syntactic dependency trees and employing a sophisticated 'soft-pruning' approach, SDANNs open new avenues for exploring and understanding the intricate relationships that exist within written language. This model stands as a testament to the potential of combining advanced neural network architectures with a deep understanding of linguistic structures, paving the way for more accurate, nuanced, and comprehensive analyses of text.

Peptides are promising drug development frameworks thanks to their high target selectivity, tolerability and relatively low production cost. However, despite the fact that several thousand potentially therapeutic peptides reported, only sixty have arrived at the market. This concerning low proportion is partially explained by undesired properties such as peptide-induced hemolytic activity. Hence, we aim to get a better insight into the chemical space of hemolytic peptides using a novel approach based on network science and interactive data mining as an alternative to design more effective peptide drugs with low hemolytic activity. Metadata networks (METNs) were used to characterize and find general patterns associated to hemolytic peptides, whereas Half-Space Proximal Networks (HSPNs), created using five different two-way dissimilarity measures, represented the hemolytic peptide space. Then, using the best candidate HSPNs, we extracted various scaffolds that capture information of almost all the chemical space but avoiding peptide overrepresentation. Such scaffolds can have many applications, such as training accurate ML-based prediction models, constructing one-class multi-query similarity searching models and characterizing the diversity of hemolytic peptides using a manageable set of peptides. Finally, by means of an alignment-free approach, we reported 47 putative hemolytic motifs, which might provide hints about the mechanisms of hemolysis and can also be used as toxic signatures when developing novel peptide-based drugs.

Over the years, network analysis became a promising strategy to analyze complex system, i.e. systems composed by a large number of interacting elements. In particular, multilayer networks have emerged as a powerful framework for modelling and analysing complex systems with multiple types of interactions. Network analysis can be applied to pharmacogenomics to gain insights into the interactions between genes, drugs, and diseases. By integrating network analysis techniques with pharmacogenomic data, the goal consists to uncover complex relationships and identify key genes to use in pathway enrichment analysis to figure out biological pathways involved in drug response and adverse reactions. In this study, we model omics, diseases and drugs data together through the multilayer network representation. Then, we mined the multilayer network with a community detection algorithm by obtaining top communities. After that, we used the identified list of genes from the communities to perform pathway enrichment analysis (PEA) to figure out the biological function affected form the selected genes. The results show that the genes forming the top community have the multiple roles through different pathways.

This paper aims to analyze the intellectual structure and research fronts in application information security in smart cities to identify research boundaries, trends, and new opportunities in the area. It applies bibliometric analyses to identify the main authors and their influences on the information security and smart city area. Moreover, this analysis focuses on journals indexed in Scopus databases. The results indicate that there is an opportunity for further advances in the adoption of information security policies in government institutions. Moreover, the production indicators presented herein are useful for the planning and implementation of information security policies, and the knowledge of the scientific community about smart cities. The bibliometric analysis provides support for the visualization of the leading research technical collaboration networks among authors, co-authors, countries, and research areas. The methodology offers a broader view of the application information security in smarty city areas and makes it possible to assist new research that may contribute to further advances. The smart city topic has been receiving much attention in recent years, but to the best of our knowledge, there is no research on reporting new possibilities for advances. Therefore, this article may contribute to an emerging body of literature that explores the nature of application information security and smart city research productivity to assist researchers in better understanding the current emerging of the area.

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines, using machine learning, deep learning and neural networks. AI enables machines to learn from experience and perform human-like tasks. The field of AI research has been developing fast over the past five to ten years, due to the rise of ‘big data’ and increasing computing power. In the medical area, AI can be used to improve diagnosis, prognosis, treatment, surgery, drug discovery, or for other applications. Therefore, both academia and industry are investing a lot in AI. This review investigates the biomedical literature (in the PubMed and Embase databases) by looking at bibliographical data, observing trends over time and occurrences of keywords. Some observations are made: AI has been growing exponentially over the past few years; it is used mostly for diagnosis; COVID-19 is already in the top-5 of diseases studied using AI; the United States, China, United Kingdom, South Korea and Canada are publishing the most articles in AI research; MIT is the world’s leading university in AI research; and convolutional neural networks are by far the most popular deep learning algorithms at this moment. These trends could be studied in more detail, by studying more literature databases or by including patent databases. More advanced analyses could be used to predict in which direction AI will develop over the coming years. The expectation is that AI will keep on growing, in spite of stricter privacy laws, more need for standardization, bias in the data, and the need for building trust.

Skin detection, the process of distinguishing between skin and non-skin regions in a digital image, is widely used in a variety of applications ranging from hand gesture analysis to body part tracking to facial recognition. Skin detection is a challenging problem that has received a lot of attention from experts and proposals from the research community in the context of intelligent systems, but the lack of common benchmarks and unified testing protocols has hampered fairness among approaches. Comparisons are very difficult. Recently, the success of deep neural networks has had a major impact on the field of image segmentation detection, resulting in various successful models to date. In this work, we survey the most recent research in this field and propose fair comparisons between approaches using several different datasets. The main contributions of this work are: (i) a comprehensive literature review of approaches to skin color detection and a comparison of approaches that may help researchers and practitioners choose the best method for their application; (ii) a comprehensive list of datasets that report ground truth for skin detection; (iii) a framework for evaluating and combining different skin detection approaches. Moreover, we proposed an ensemble of convolutional neural networks and transformers that obtains state of the art performance. All the code is made publicly available at https://github.com/LorisNanni

This paper analyzes the robust dissipativity of uncertain stochastic generalized neural networks (USGNNs) with Markovian jumping parameters and time-varying delays. In practical applications most of the systems refer to uncertainties, hence, the norm-bounded parameter uncertainties and stochastic disturbance are considered. Then, by constructing an appropriate Lyapunov-Krasovskii functional (LKF) and by employing integral inequalities LMI-based sufficient conditions of the considered systems are established. Numerical simulations are given to show the merit of the presented results.

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

This article explores the required amount of time series points from a high-speed traffic network to accurately estimate the Hurst exponent. The methodology consists in designing an experiment using estimators that are applied to time series, followed by addressing the minimum amount of points required to obtain accurate estimates of the Hurst exponent in real-time. The methodology addresses the exhaustive analysis of the Hurst exponent considering bias behavior, standard deviation, mean square error, and convergence using fractional Gaussian noise signals with stationary increases. Our results show that the Whittle estimator successfully estimates the Hurst exponent in series with few points. Based on the results obtained, a minimum length for the time series is empirically proposed. Finally, to validate the results, the methodology is applied to real traffic captures in a high-speed network based on the IEEE 802.3ab standard.

The definition of artificial intelligence (AI) is the capacity of a computer or machine to mimic or simulate human intelligence. AI has been applied in different areas, including medicine. In cardiology, AI techniques have revolutionized the field of cardiac diagnosis, enabling the detection and prediction of cardiovascular diseases to be more accurate and efficient. This article provides an overview of machine learning, deep learning, and neural networks as they pertain to cardiac diagnosis. We will investigate how these techniques harness the power of data and algorithms to analyze complex patterns in cardiac data, thereby facilitating early detection, risk assessment, and treatment decision-making.

Created in 1905, the Société des Artistes Meridionaux organized annual exhibitions in Toulouse, in order to promote regional arts and (re)created a "Latin" - and modern - style. Based on a corpus of 11,486 artworks exhibited at the SAM between 1907 and 1939, this paper seeks to measure the contours and particularities of the Salons des Artistes Meridionaux, using a computational approach.

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

We propose an advanced filtering scheme based on Recurrent Neural Networks (RNNs) and Deep Learning to enable efficient control strategies for Vertical Farming (VF) applications.  We demonstrate that the best RNN model incorporates five neuron layers, with the first and second containing ninety Long Short-Term Memory neurons.  The third layer implements one Gated Recurrent Units neuron.  The fourth segment incorporates one RNN network, while the output layer is designed by using a single neuron exhibiting a rectified linear activation function.  By utilizing this RNN digital filter, we introduce two variations: (1) A scaled RNN model to tune the filter to the signal of interest, and (2) A moving average filter to eliminate harmonic oscillations of the output waveforms. The RNN models are contrasted with conventional digital Butterworth, Chebyshev I, Chebyshev II, and Elliptic Infinite Impulse Response (IIR) configurations.  The RNN digital filtering schemes avoid introducing unwanted oscillations, which makes them more suitable for VF than their IIR counterparts.  Finally, by utilizing the advanced features of scaling of the RNN model, we demonstrate that the RNN digital filter can be pH selective, as opposed to conventional IIR filters.

1). As on-the-ground projects come into existence and continue to expand to adapt to climate change and empower women, it is important to understand their location within TANs. Using the Bhungroo technology as a case study, we aim to assess the potential of TANs to increase the scope and scale of local projects as well as the ability of similar and emerging projects to create social change at local levels. 2). We do so by analyzing interview and earned media hits data from the UNFCCC Momentum for Change. 3). We find that while TANs may help increase the scale and scope of projects, increasing their ability to effectively reach more people and areas is still up for debate 4). We conclude by considering how women’s political participation may be enhanced by similar projects.

Any effort to combat corruption can benefit from an examination of past and projected worldwide trends. In this paper, we forecast the level of corruption in countries by integrating an artificial neural network modeling and time series analysis. The data were obtained from 113 countries from 2007 to 2017. The study is carried out at two levels: (a) global level where all countries are considered as a monolithic group; and (b) cluster level, where countries are placed into groups based on their development-related attributes. For each cluster, we use the findings from our previous study on the cluster analysis of global corruption using machine learning methods that identified the four most influential corruption factors, and we use those as independent variables. Then, using the identified influential factors, we forecast the level of corruption in each cluster using a nonlinear autoregressive recurrent neural network with exogenous inputs (NARX), an artificial neural network technique. The NARX models were developed for each cluster, with the objective function in terms of the Corruption Perceptions Index (CPI). For each model, the optimal neural network is determined by finetuning the hyperparameters. The analysis was repeated for all countries as a single group. The accuracy of the models is assessed by comparing the mean square errors (MSE) of the time series models. The results suggest that the NARX artificial neural network technique yields reliable future values of CPI globally or for each cluster of countries. This can assist policymakers and organizations in assessing the expected efficacies of their current or future corruption control policies from a global perspective as well as for groups of countries.

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

The analysis and simulation of water quality in distribution networks is a complex issue of great concern today. The analysis of the evolution of water age, as a simple indicator of water quality in the network, is of great interest in both design and operation phases. Understanding the factors that have the strongest influence on water quality is key to developing adequate strategies aimed at preserving it. This paper firstly analyses the factors with biggest influence in the tanks water age, to support the selection of the most appropriate configuration from the point of view of water quality during design phases. Then, the main considerations when modelling tanks following the different mixing models considered in Epanet have been presented. Also, a real tank behaviour has been characterised through field measurements and Epanet simulations in order to determine the best fitted mixing model.

Diabetic retinopathy is the most common microvascular complication of diabetes mellitus and one of the leading causes of blindness globally. Due to the progressive nature of the disease, earlier detection and timely treatment can lead to substantial reductions in the incidence of irreversible vision-loss. Artificial intelligence (AI) screening systems have offered clinically acceptable and quicker results in detecting diabetic retinopathy from retinal fundus and optical coherence tomography (OCT) images. Thus, this systematic review and meta-analysis of relevant investigations was performed to document the performance of AI screening systems that were applied to fundus and OCT images of patients from diverse geographic locations including North America, Europe, Africa, Asia, and Australia. A systematic literature search on Medline, Global Health, and PubMed was performed and studies published between October 2015 and January 2020 were included. The search strategy was based on the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) reporting guidelines, and AI-based investigations were mandatory for studies inclusion. The abstracts, titles, and full-texts of potentially eligible studies were screened against inclusion and exclusion criteria. Twenty-one studies were included in this systematic review; 18 met inclusion criteria for the meta-analysis. The pooled sensitivity of the evaluated AI screening systems in detecting diabetic retinopathy was 0.93 (95% CI: 0.92-0.94) and the specificity was 0.88 (95% CI: 0.86-0.89). The included studies detailed training and external validation datasets, criteria for diabetic retinopathy case ascertainment, imaging modalities, DR-grading scales, and compared AI results to those of human graders (e.g., ophthalmologists, retinal specialists, trained nurses, and other healthcare providers) as a reference standard. The findings of this study showed that the majority AI screening systems demonstrated clinically acceptable levels of sensitivity and specificity for detecting referable diabetic retinopathy from retinal fundus and OCT photographs. Further improvement depends on the continual development of novel algorithms with large and gradable sets of images for training and validation. If cost-effectiveness ratios can be optimized, AI can become a financially sustainable and clinically effective intervention that can be incorporated into the healthcare systems of low-to-middle income countries (LMICs) and geographically remote locations. Combining screening technologies with treatment interventions such as anti-VEGF therapy, acellular capillary laser treatment, and vitreoretinal surgery can lead to substantial reductions in the incidence of irreversible vision-loss due to proliferative diabetic retinopathy.

The paper presents the identification and classification of steel cord failures in the conveyor belt core based on an analysis of a two-dimensional image of magnetic field changes recorded using the Diagbelt system around scanned failures in the test belt. The obtained set of identified changes in images obtained for numerous devices parameters settings were the base for statistical analysis. It makes it possible to determine the Pearson’s linear correlation coefficient between the parameters being changed and the image of the failures. In the second stage of the research, artificial intelligence methods were applied to construct a multilayer neural network (MLP) and to teach its appropriate identification of damage. In both methods were used the same data sets, which made it possible to compare methods.

Fractal behavior and long-range dependence are widely observed in measurements and characterization of traffic flow in high-speed computer networks of different technologies and coverage levels. This paper presents the results obtained when applying fractal analysis techniques on a time series obtained from traffic captures coming from an application server connected to the Internet through a high-speed link. The results obtained show that traffic flow in the dedicated high-speed network link have fractal behavior when the Hurst exponent is in the range of 0.5, 1, the fractal dimension between 1, 1.5, and the correlation coefficient between –0.5, 0. Based on these results, it is ideal to characterize both the singularities of the traffic and its impulsiveness during a fractal analysis of temporal scales. Finally, based on the results of the time series analyses, the fact that the traffic flows of current computer networks exhibit fractal behavior with a long-range dependency is reaffirmed.

Prediction of crop yield is essential for food security policymaking, planning, and trade. The objective of the current study is to propose novel crop yield prediction models based on hybrid machine learning methods. In this study, the performance of artificial neural networks-imperialist competitive algorithm (ANN-ICA) and artificial neural networks-gray wolf optimizer (ANN-GWO) models for the crop yield prediction is evaluated. According to the results, ANNGWO, with R of 0.48, RMSE of 3.19, and MEA of 26.65, proved a better performance in the crop yield prediction compared to the ANN-ICA model. The results can be used by either practitioners, researchers or policymakers for food security.

Generative adversarial networks (GAN) opened new possibilities for image processing and analysis. Inpainting, dataset augmentation using artificial samples or increasing spatial resolution of aerial imagery are only a few notable examples of utilizing GANs in remote sensing. This is due to a unique construction and training process expressed as a duel between GAN components. The main objective of the research is to apply GAN to generate an artificial Normalized Difference Vegetation Index (NDVI) using panchromatic images. The NDVI ground-truth labels were prepared by combining RGB and NIR orthophoto. The dataset was then utilized as input for a conditional generative adversarial network (cGAN) to perform an image-to-image translation. The main goal of the neural network was to generate an artificial NDVI image for each processed 256px × 256px patch using only information available in the panchromatic input. The network achieved 0.7569 ± 0.1083 Structural Similarity Index Measure (SSIM), 26.6459 ± 3.6577 Peak Signal-to-Noise Ratio (PNSR) and 0.0504 ± 0.0193 Root-Mean-Square Error (RSME) on the test set. The perceptual evaluation was performed to verify the usability of the method when working with a real-life scenario. The research confirms that the structure and texture of the panchromatic aerial remote sensing image contains sufficient information for NDVI estimation for various objects of urban space. Even though these results can be used to highlight areas rich in vegetation and distinguish them from urban background, there is still room for improvement in terms of accuracy of estimated values. The purpose of the research is to explore the possibility of utilizing GAN to enhance panchromatic images (PAN) with information related to vegetation. This opens interesting possibilities in terms of historical remote sensing imagery processing and analysis. The panchromatic orthoimagery dataset was derived from RGB orthoimagery.

This study is framed on the Information Theory as a constructive criterion to generate probabilistic distributions –through the elaboration of Bayesian Networks- and to reduce the uncertainty in the occurrence and relationship between two key psychological variables associated with the sports’ performance: Self-Determined Motivation and Competitive Anxiety. We analyzed 674 universitary students/athletes who competed in the 2017 Universitary Games (Universiade) in México, from 44 universities, with an average age of 21 years old (SD = 2.07), and with a sportive experience of 8.61 years of average (SD = 5.15). Methods: Regarding the data analysis, first of all a CHAID algorithm was carried out for to know the independence links among variables, and then two Bayesian networks (BN) were elaborated. The validation of the BN revealed AUC values ranging from 0.5 to 0.92. Subsequently, various instantations were carried out with hypothetical values applied to the “bottom” variables. Results showed two probability trees that have Extrinisic Motivation and Amotivation at the top, while the anxiety/activation due to the worry for performance was at the bottom of probabilities. The instantiations carried out support the existence of these probabilistic relationships, demonstrating the little influence on the competition anxiety generated by the intrinsic motivation. In conclusion, the reduction of the uncertainty made up by the restricted BN may aloe to re-introduce Information Theory principles in psychosocial studies, allowing authors to obtain useful probabilities values upon target psychological variables related with sportive performance.

The most frequent, noticeable, and frequent natural calamity in the karakoram region is landslides. Extreme landslides have occurred frequently along Karakoram highway, particularly during the monsoon, causing a major loss of life and property. Therefore, it was necessary to look for a solution to increase growth and vigilance in order to lessen losses related to landslides caused by natural disasters. By utilizing contemporary technologies, an early warning system might be developed. Artificial neural networks (ANNs) are widely used nowadays across many industries. This paper's major goal is to provide new integrative models for assessing landslide susceptibility in a prone area of north of Pakistan. To do this, the training of an artificial neural network (ANN) is supervised using metaheuristic and Bayesian techniques: particle swarm optimization algorithm (PSO), Genetic algorithm (GA), Bayesian optimization Gaussian process (BO_GP), and Bayesian optimization Gaussian process (BO_TPE). 304 previous landslides and the eight most prevalent conditioning elements combine to form a geographical database. The models are hyper-parameter optimized, and the best ones are employed to generate the susceptibility maps. The area under the receiving operating characteristic curve (AUROC) accuracy index found demonstrated that the maps produced by both Bayesian and metaheuristic algorithms are highly accurate. The effectiveness and efficiency of applying artificial neural networks (ANNs) for landslide mapping, susceptibility analysis, and forecasting are studied in this research it’s observed from experimentation that the performance differences for GA, BO_GP, and PSO compared to BO_TPE are relatively small, ranging from 0.3166% to 1.8399%. This suggests that these techniques achieved comparable performance to BO_TPE in terms of AUC. However, it's important to note that the significance of these differences can vary depending on the specific context and requirements of the ML task. Additionally in this study, we explore eight feature selection algorithms to determine the geospatial variable importance for landslide susceptibility mapping along the KKH. The algorithms considered include Information Gain, Gain Ratio, OneR Classifier, Subset Evaluators, Principal Components, Relief Attribute Evaluator, Correlation, and Symmetrical Uncertainty. These algorithms enable us to evaluate the relevance and significance of different geospatial variables in predicting landslide susceptibility. By applying these feature selection algorithms, we aim to identify the most influential geospatial variables that contribute to landslide occurrences along the KKH. The algorithms encompass a diverse range of techniques, such as measuring entropy reduction, accounting for attribute bias, generating single rules, evaluating feature subsets, reducing dimensionality, and assessing correlation and information sharing. The findings of this study will provide valuable insights into the critical geospatial variables associated with landslide susceptibility along the KKH. These insights can aid in the development of effective landslide mitigation strategies, infrastructure planning, and targeted hazard management efforts. Additionally, the study contributes to the field of geospatial analysis by showcasing the applicability and effectiveness of various feature selection algorithms in the context of landslide susceptibility mapping.

This study innovatively assesses the Mun River flow components in Thailand, integrating Artificial Neural Networks (ANN) and Isotopic (18O) End-Member Mixing Analysis (IEMMA). It quantifies the contributions of the Upper Mun River (UMR) and Chi River (CR) to the overall flow, revealing a discrepancy in their estimated contributions. ANN predicts the UMR and CR contribute approximately 70.1% and 29.5% respectively, while IEMMA indicates a more pronounced disparity with 84% from UMR and 16% from CR. This divergence highlights the distinct perspectives of ANN, focusing on hydrological data patterns, and IEMMA, emphasizing isotopic signatures. Despite discrepancies, both methods validate UMR as a significant contributor to the overall flow, highlighting their utility in hydrological research. The findings underscore the complexity of river systems and advocate for an integrated approach of river flow analysis for a comprehensive understanding, crucial for effective water resource management and planning.

In this paper, Lyapunov-Razumikhin technique, design of state-dependent switching laws, a fixed point theorem and variational methods are employed to derive the existence and the unique existence results of (globally) exponentially stable positive stationary solution of delayed reaction-diffusion cell neural networks under Dirichlet zero boundary value, including the global stability criteria \textbf{in the classical meaning}. Next, sufficient conditions are proposed to guarantee the global stability invariance of ordinary differential systems under the influence of diffusions. New theorems show that the diffusion is a double-edged sword in judging the stability of diffusion systems. Besides, an example is constructed to illuminate that any non-zero constant equilibrium point must be not in the phase plane of dynamic system under Dirichlet zero boundary value, or it must lead to a contradiction. Next, under Lipschitz assumptions on active function, another example is designed to prove that the small diffusion effect will cause the essential change of the phase plane structure of the dynamic behavior of the delayed neural networks via a Saddle point theorem. Finally, a numerical example illustrates the feasibility of the proposed methods.

Recently, federated learning (FL) has been receiving great attention as an effective machine learning method to avoid the security issue in raw data collection as well as to distribute the computing load to edge devices. However, even though wireless communications is a essential part for implementing FL in edge networks, there have been a few works that analyze the effect of wireless networks on FL. In this paper, we investigate FL in small-cell networks where multiple base stations (BSs) and users are located according to homogeneous Poisson point process (PPP) with different densities. We comprehensively analyze the effects of geographic node deployment on the model aggregation in FL on the basis of stochastic geometry-based analysis. We derive the closed-form expressions of coverage probability with tractable approximations and discuss the minimum required BS density for achieving a target model aggregation rate in small-cell networks. Our analysis and simulation results provide insightful information for understanding the behaviors of FL in small-cell networks, and it can be exploited as a guideline for designing the network facilitating the wireless FL.

An explosive growth in vehicular wireless services and applications gives rise to spectrum resource starvation. Cognitive radio has been used to vehicular networks to mitigate the impending spectrum starvation problem by allowing vehicles to fully exploit spectrum opportunities unoccupied by licensed users. Efficient and effective detection of licensed user is a critical issue to realize cognitive radio applications. However, spectrum sensing in vehicular environments is a very challenging task due to vehicles mobility. For instance, vehicle mobility has a large effect on the wireless channel, thereby impacting the detection performance of spectrum sensing. Thus, gargantuan efforts have been made in order to analyze the fading properties of mobile radio channel in vehicular environments. Indeed, numerous studies have demonstrated that the wireless channel in vehicular environments can be characterized by a temporally correlated Rayleigh fading. In this paper, we focus on energy detection for spectrum sensing and a counting rule for cooperative sensing based on Neyman-Pearson criteria. Further, we go into the effect of the sensing and reporting channels condition on spectrum sensing performance under temporally correlated Rayleigh sensing channel. For local and cooperative sensing, we derive some alternative expressions for average probability of miss detection. The pertinent numerical and simulating results are provided to further validate our theoretical analyses under a variety of scenarios.

Tourism is increasingly becoming one of the most important components of the economy. Coastal tourism is of particular importance in our country, this is because Albania has a very favorable geographical position. The tourist destination chosen for study in this paper is Durrës. It is analyzed as a complex dynamic system that evolves with a series of techniques and methods drawn from the area of network theory. The main objective of this paper is the comparison of technological and socio-economic networks, through different methods and techniques. The methodology of this research includes different data collection methods for both networks and their analysis. 504 nodes were taken into consideration. A significant part of the research is based on network theory, using algorithms and network analysis techniques to reveal their static and dynamic characteristics. Through this paper we show that the internet network and the socio-economic network of Durrës are similar in some aspects and have a great impact on the development of the tourist destination. The analysis of these two networks provides a deeper picture of the relations between the actors of the destination and helps to improve the tourism strategies and the economic development of the area. Thus, the research is an attempt to better understand the impact of technological and socio-economic networks in the development of the tourist destination of Durrës and uses different ways of network analysis to discover the similarities and differences between them.

One of the most effective image processing techniques is the use of convolutional neural networks, where we combine intensity values at grid points in the vicinity of each point. To speed up computations, researchers have developed a dilated version of this technique, in which only some points are processed. It turns out that the most efficient case is when we select points from a sub-grid. In this paper, we explain this empirical efficiency proving that the sub-grid is indeed optimal – in some reasonable sense. To be more precise, we prove that all reasonable optimality criteria, the optimal subset of the original grid is either a sub-grid, or a sub-grid-like set.

Optical artificial neural networks (ONNs) have significant potential for ultra-high computing speed and energy efficiency. We report a new approach to ONNs based on integrated Kerr micro-combs that is programmable, highly scalable and capable of reaching ultra-high speeds, demonstrating the building block of the ONN — a single neuron perceptron — by mapping synapses onto 49 wavelengths to achieve a single-unit throughput of 11.9 Giga-OPS at 8 bits per OP, or 95.2 Gbps. We test the perceptron on handwritten-digit recognition and cancer-cell detection — achieving over 90% and 85% accuracy, respectively. By scaling the perceptron to a deep learning network using off-the-shelf telecom technology we can achieve high throughput operation for matrix multiplication for real-time massive data processing.

AliAmbra is a project developed to explore and promote high-quality catches of the Amvrakikos Gulf GP to Artas’ wider regions. In addition, this project aimed to implement an integrated plan of action, to form a business identity with high-added value and achieve integrated business services adapted to the special characteristics of the area. The action plan for this project was to actively search for new markets, create a collective identity for the products, promote their quality and added value, engage in gastronomes and tasting exhibitions, dissemination and publicity actions, as well as enhance the quality of the products and markets based on the customer needs. The primary focus of this publication is to observe and analyze the data retrieved from various tasting exhibitions of the AliAmbra project, with a target goal of improving customer experience and product quality.

Novel applications of artificial intelligence for tuning the parameters of industrial machines for optimal performance are emerging at a fast pace. Tuning the combine harvesters and improving the machine performance can dramatically minimize the wastes during harvesting, and it is also beneficial to machine maintenance. Literature includes several soft computing, machine learning and optimization methods that had been used to model the function of harvesters of various crops. Due to the complexity of the problem, machine learning methods had been recently proposed to predict the optimal performance with promising results. In this paper, through proposing a novel hybrid machine learning model based on artificial neural networks integrated with particle swarm optimization (ANN-PSO), the performance analysis of a common combine harvester is presented. The hybridization of machine learning methods with soft computing techniques has recently shown promising results to improve the performance of the combine harvesters. This research aims at improving the results further by providing more stable models with higher accuracy.

The intracranial pressure (ICP) signal, as monitored on patients in intensive care units, contains pulses of cardiac origin where P1 and P2 subpeaks can often be observed. When calculable, the ratio of their relative amplitudes is an indicator of the patient’s cerebral compliance. This characterization is particularly informative on the overall state of the cerebrospinal system. We developed a recurrent neural network-based framework for P2/P1 ratio computation that only takes a raw ICP signal as an input. Two tasks are performed, namely pulse classification and subpeak designation. Pulse classification was achieved with an area under the curve of 0.90 on a 4,344-pulse testing dataset, while the peak designation algorithm identified pulses with a P2/P1 ratio > 1 with a 97.3% accuracy. Although it still needs to be evaluated on a larger number of labeled recordings, our automated P2/P1 ratio calculation framework appears to be a promising tool for improving bedside monitoring devices.

Delay Tolerant Networks (DTNs) are intermittently connected networks, where there is no guaranteed end-to-end connectivity between the source and destination. The link between the pair of nodes in the DTNs environments is frequently disrupted, due to the fast mobility of nodes, dissemination nature, and power outages. Due to the absence of contemporaneous paths between the nodes, the opportunities for message forwarding in DTNs usually are limited. To obtain high data delivery, the DTNs use innovation of the Store-Carry and Forward (SCF) technique which allows data transmission to successfully proceed despite the absence of continuous end-to-end paths. However, the SCF approach arises various issues such as buffer congestion and message drop which are caused due to growing number of carried messages in restricted network resources. Therefore, buffer management techniques are required to manage the buffer capacity of the nodes by deciding how to effectively drop the messages and how to schedule the messages in the node’s buffer in a perfect way. This paper evaluates the performance of six buffer management techniques, namely First-In-FirstOut, Last In First Out, Drop Largest, Drop Youngest, Evict Shortest Lifetime First and Evict Most Forwarded First, with MaxProp and Spray and Wait routing protocols under variable message’s Time-To-Live values (60 to 300 minutes with step-change 60 minutes). In addition, this study uses an Opportunistic Network Environment (ONE) simulator that is utilized for evaluating the performance of the dropping policies techniques, where it is considering five performance metrics (delivery ratio, overhead ratio, average latency, hop count, and message drop). The evaluation results of each buffer management policy are explained by these metrics briefly.

Over the past few decades, the growth of the urban population has been remarkable. Nowadays, 50% of the population lives in urban areas, and forecasts point that by 2050 this number will reach 70%. Today, 64% of all travel made is within urban environments and the total amount of urban kilometers traveled is expected to triple by 2050. Thus, seeking novel solutions for urban mobility becomes paramount for 21st century society. In this work, we discuss the performance of vehicular networks. We consider the metric Delta Network. The Delta Network characterizes the connectivity of the vehicular network through the percentage of travel time in which vehicles are connected to roadside units. This article reviews the concept of Delta Network and extends its study through the presentation of a general heuristic based on the definition of scores to identify the areas of the road network that should receive coverage. After defining the general heuristic, we show how small changes in the score computation can generate very distinct (and interesting) patterns of coverage, each one suited to a given scenario. In order to exemplify such behavior, we propose three deployment strategies based on simply changing the computation of scores. The results show that the strategies derived from the general heuristic are very interesting, all of them deploying roadside units in a circle pattern around the traffic epicenter.

Three novel iron(II) coordination polymers, [Fe(H2O)2(ttmb)2](ClO4)2·4H2O (1), [Fe(H2O)2(ttmb)2](BF4)2·4H2O (2), [Fe(ttmb)2(NCS)2] (3), were synthesized with the linker 1,3,5-tris(1H-1,2,4-triazol-1-yl)methyl)benzene (ttmb). The single-crystal structures show that all three compounds form a double chain structure with the adjacent iron atoms being bridged by two ttmb linkers. The iron(II) ions are octahedrally surrounded by four N4 donor atom from the 1,2,4-triazol-1-yl groups of four different ttmb linkers which form an equatorial plane and two trans-coordinated aqua ligands in 1 and 2 or isothiocyanato ligands in 3 in the axial positions. In view of the neutral bridging ttmb linker, there is a counter-anion in all structures; uncoordinated ClO4– and BF4–in 1 and 2 or coordinated NCS–in 3. Compounds 1 and 2 are isostructural. Interestingly, the ttmb linker only utilizes two of its three potentially coordinating triazole groups. All iron(II) coordination networks are colorless or have a light-yellow color, being indicative of the high-spin state.

This study focuses on the impact of weak partial discharges (PDs) on defect recognition accuracy in epoxy resin through phase-resolved partial discharge (PRPD) analysis. Two measurement conditions are compared until PRPD pattern saturation: one-minute and one-hour durations. The PD data specifically target three void types located at different positions within the epoxy material. The aim is to evaluate how the presence of weak PDs at the PD extinction voltage (PDEV) influences defect recognition accuracy. This research sheds light on the potential implications of neglecting the significance of weak PD signals in defect detection. A convolutional neural network (CNN) model is trained using PRPD data recorded at the PD inception voltage (PDIV) and tested using the new PRPD data from both conditions recorded from a lower PDIV to a PDEV. The trained CNN model achieves a defect recognition accuracy of 100% for a one-hour duration, highlighting the importance of not neglecting weak PD signals. This emphasizes the significance of extended measurement duration and pattern saturation in capturing and analyzing weak PD signals for improved defect recognition. This study contributes to the advancement of practical applications by understanding the behavior of the epoxy material and enhancing defect detection techniques.

The difficulty in detecting tumors in earlier stages is the major cause of mortalities of patients, despite the advancements in treatment and research regarding ovarian cancer. Deep Learning algorithms are applied to serve the purpose of a diagnostic tool by applying them on CT scan images of the ovarian region. The images go through a series of pre-processing techniques and further the tumor is segmented using the UNet model. Instances are then classified into two categories – benign and malignant tumors. Classification is performed using Deep Learning models like CNN, ResNet, DenseNet, Inception-ResNet, VGG16 and Xception along with Machine Learning models such as Random Forest, Gradient Boosting, AdaBoosting, XGBoosting. DenseNet 121 emerges as the best model on this dataset even after applying optimization on the Machine Learning models by obtaining an accuracy of 95.7%. The current work demonstrates the comparison of multiple CNN architectures among themselves and with common Machine Learning algorithms, with and without optimization techniques applied.

Multiply-accumulate calculations using a memristor crossbar array is an important method to realize neuromorphic computing. However, the memristor array fabrication technology is still immature, and it is difficult to fabricate large-scale arrays with high-yield, which restricts the development of memristor-based neuromorphic computing technology. Therefore, cascading small-scale arrays to achieve the neuromorphic computational ability that can be achieved by large-scale arrays, which is of great significance for promoting the application of memristor-based neuromorphic computing. To address this issue, we present a memristor-based cascaded framework with some basic computation units, several neural network processing units can be cascaded by this means to improve the processing capability of the dataset. Besides, we introduce a split method to reduce pressure of input terminal. Compared with VGGNet and GoogLeNet, the proposed cascaded framework can achieve 93.54% Fashion-MNIST accuracy under the 4.15M parameters. Extensive experiments with Ti/AlOx/TaOx/Pt we fabricated are conducted to show that the circuit simulation results can still provide a high recognition accuracy, and the recognition accuracy loss after circuit simulation can be controlled at around 0.26%.

Recent progress in deep learning has led to accurate and efficient generic object detection networks. Training of highly reliable models depends on large datasets with highly textured and rich images. However, in real-world scenarios, the performance of the generic object detection system decreases when (i) occlusions hide the objects, (ii) objects are present in low-light images, or (iii) they are merged with background information. In this paper, we refer to all these situations as challenging environments. With the recent rapid development in generic object detection algorithms, notable progress has been observed in the field of object detection in challenging environments. However, there is no consolidated reference to cover state-of-the-art in this domain. To the best of our knowledge, this paper presents the first comprehensive overview, covering recent approaches that have tackled the problem of object detection in challenging environments. Furthermore, we present the quantitative and qualitative performance analysis of these approaches and discuss the currently available challenging datasets. Moreover, this paper investigates the performance of current state-of-the-art generic object detection algorithms by benchmarking results on the three well-known challenging datasets. Finally, we highlight several current shortcomings and outline future directions.

Recent improvements in deepfake creation have made deepfake videos more realistic. Moreover, open-source software has made deepfake creation more accessible, which reduces the barrier to entry for deepfake creation. This could pose a threat to the people’s privacy. There is a potential danger if the deepfake creation techniques are used by people with an ulterior motive to produce deepfake videos of world leaders to disrupt the order of countries and the world. Therefore, research into the automatic detection of deepfaked media is essential for public security. In this work, we propose a deepfake detection method using upper body language analysis. Specifically, a many-to-one LSTM network was designed and trained as a classification model for deepfake detection. Different models were trained by varying the hyperparameters to build a final model with benchmark accuracy. We achieved 94.39% accuracy on the deepfake test set. The experimental results showed that upper body language can effectively detect deepfakes.

This article discusses the use of a hand held electronic nose to obtain information on the presence of some aromatic defects in natural cork stoppers, such as haloanisoles, alkylmethoxypyrazines and ketones. The proposed prototype has been developed as an instrumentation system with up to eight commercial gas sensors. Machine learning algorithms such as k-nearest neighbors and artificial neural networks has been used. The use of this system tries to improve the current aromatic defect detection process in the cork stopper industry, which is done by gas chromatography or human test panels.

The demand of high data rate and ubiquitous coverage in heterogeneous cellular (HetNets) is increasing progressively. In order to meet this demand, sophisticated model having applied interference reduction scheme and cell association technique is needed. The small base station (sBS)are deployed inside the broadcasting area of macro base station (mBS), in heterogeneous cellular networks (HetNets). Since mBS has high transmission power therefore a large number of users get connected with mBS. This causes disproportion of load distribution across the HetNets. For load balancing users from high power mBS are migrated to low power sBS to increase network capacity and to decrease the load from mBS. This results in interference in the communication signal because of strong mBS Interference. Hence, we need interference management technique to mitigate interference and user association and to efficiently use sBSs’ resources. Inter-cell interference (ICI) limit the HetNets’ performance. Additionally, there exist deliberate jamming interference which depends on jammers transmission power and its proximity with the target, which notably degrades the network performance. In this paper, we employ reverse frequency allocation scheme (RFA) to reduce inter cell interference, deliberate jamming interference and to accomplish load balancing. The proposed setup is analyzed inquisitively and with the help of simulations. The result shows reduction in interferences as well as balance of load distribution in the network achieved by employing RFA scheme together with cell association.

We focus on macromolecules which are modelled as sequentially growing dual scale-free networks. The dual networks are built by replacing star-like units of the primal treelike scale-free networks through rings, which are then transformed in a small-world manner up to the complete graphs. In this respect, the parameter γ describing the degree distribution in the primal treelike scale-free networks regulates the size of the dual units. The transition towards the networks of complete graphs is controlled by the probability p of adding link between non-neighbouring nodes of the same initial ring. The relaxation dynamics of the polymer networks is studied in the framework of generalized Gaussian structures by using the full eigenvalue spectrum of the Laplacian matrix. The dynamical quantities on which we focus here are the averaged monomer displacement and the mechanical relaxation moduli. For several intermediate values of the parameter’s set (γ, p) we encounter for these dynamical properties regions of constant in-between slope.

ALDH+ H1975 lung adenocarcinoma stem cells (LSCs) are a rare cell population identified in lung adenocarcinoma (LUAD). LSCs can self-renew, drive tumor initiation, growth, metastasis, and recurrence, and are also the predominant cause of poor prognosis due to their intrinsic resistance to drugs and chemotherapy. Consequently, LSCs are a promising target for LUAD therapy. Noncoding RNAs (ncRNAs), including microRNAs (miRNAs), long noncoding RNAs (lncRNAs), and circular RNAs (circRNAs), exert many significant regulatory functions in the pathogenesis of human cancers, showing the necessity for a comprehensive understanding of the mechanisms that underlie lung carcinogenesis. Nonetheless, research on many known transcripts and messenger RNAs (mRNAs) has already generated new information. Unknown biomarkers in ncRNAs and systematic and comprehensive interrelation with unknown ncRNAs and mRNAs may provide further insights into the biology of LUAD. Herein, a set of novel ncRNAs that include miRNAs, lncRNAs, circRNAs, were identified and differentially expressed patterns of ncRNAs and mRNAs in LSCs and ALDH- H1975 LUAD tumor cells (LTCs) were obtained using stringent bioinformatics pipelines. Through a meta-analysis of the identified landscapes, novel competitive endogenous RNA (ceRNA) networks were constructed to reveal the potential molecular mechanisms that regulate the hallmarks of LSCs and LTCs. This study presents a summary of novel ncRNAs and the fundamental roles of differentially expressed ncRNAs implicated in the activity of LSCs and LTCs. In addition, the study also provides a comprehensive resource for the future identification of diagnostic, therapeutic, and prognostic biomarkers in LUAD.

Convolutional neural networks (CNNs), inspired by biological visual cortex systems, are a powerful category of artificial neural networks that can extract the hierarchical features of raw data to greatly reduce the network parametric complexity and enhance the predicting accuracy. They are of significant interest for machine learning tasks such as computer vision, speech recognition, playing board games and medical diagnosis [1-7]. Optical neural networks offer the promise of dramatically accelerating computing speed to overcome the inherent bandwidth bottleneck of electronics. Here, we demonstrate a universal optical vector convolutional accelerator operating beyond 10 Tera-OPS (TOPS - operations per second), generating convolutions of images of 250,000 pixels with 8-bit resolution for 10 kernels simultaneously — enough for facial image recognition. We then use the same hardware to sequentially form a deep optical CNN with ten output neurons, achieving successful recognition of full 10 digits with 900 pixel handwritten digit images with 88% accuracy. Our results are based on simultaneously interleaving temporal, wavelength and spatial dimensions enabled by an integrated microcomb source. This approach is scalable and trainable to much more complex networks for demanding applications such as unmanned vehicle and real-time video recognition.

Optical backbone networks constitute the fundamental infrastructure employed today by network operators to deliver services to users. As network capacity is a key factor influencing optical network performance, it is important to understand how topological and physical properties impact its behavior and to have the capability to estimate its value. In this context, we propose here a method to evaluate the network capacity that relies on the optical reach to account for physical layer aspects, in conjunction with constrained routing techniques for traffic routing. As this type of routing can lead to traffic blocking, particularly due to the limitation on the number of wavelengths per fiber, we also propose a fiber assignment algorithm designed to deal with this problem. We apply this method to a set of randomly generated networks using a modified Waxman model, and for a network with 60 nodes, in a scenario without blocking, we obtain capacities of about 2.5 Pbit/s for a symbol rate of 64 Gbaud and about 5 Pbit/s for a symbol rate of 128 Gbaud. Remarkably, this duplication in the total network capacity is achieved by an increase in the total fiber length of only about 51%.

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

Contact tracing is one of the oldest social network health interventions used to reduce the diffusion of various infectious diseases. However, some infectious diseases like COVID-19 amass at such a great scope that traditional methods of conducting contact tracing (e.g., face-to-face interviews) remain difficult to implement, pointing the need to develop reliable and valid survey approaches. The purpose of this research is to test the effectiveness of three different egocentric survey methods for extracting contact tracing data: (1) a baseline approach, (2) a retrieval cue approach, and (3) a context-based approach. A sample of 397 college students were randomized into one of each condition and were prompted to anonymously provide contacts and populated places visited from the past four days. After controlling for various demographic, social identity, psychological, and physiological variables, participants in the context-based condition were significantly more likely recall more contacts (medium effect size) and places (large effect size) than the other two conditions. Theoretically, the research supports suggestions by field theory that assume network recall can be significantly improved by activating relevant activity foci. Practically, the research contributes to developing innovative social network data collection methods for contract tracing survey instruments.

Rapid screening of botanical extracts for the discovery of bioactive natural products was performed using a fractionation approach in conjunction with flow-injection high-resolution mass spectrometry for obtaining chemical fingerprints of each fraction, enabling the correlation of the relative abundance of molecular features (representing individual phytochemicals) with the read-outs of bioassays. We applied this strategy for discovering and identifying constituents of Centella asiatica (C. asiatica) that protect against Aβ cytotoxicity in vitro. C. asiatica has been associated with improving mental health and cognitive function, with potential use in Alzheimer’s disease. Human neuroblastoma MC65 cells were exposed to subfractions of an aqueous extract of C. asiatica to evaluate the protective benefit derived from these subfractions against amyloid β-cytotoxicity. The % viability score of the cells exposed to each subfraction was used in conjunction with the intensity of the molecular features in two computational models, namely Elastic Net and selectivity ratio, to determine the relationship of the peak intensity of molecular features and % viability. Finally, the correlation of mass spectral features with MC65 protection and their abundance in different sub-fractions were visualized using GNPS molecular networking. Both computational methods unequivocally identified dicaffeoylquinic acids as providing strong protection against Aβ-toxicity in MC65 cells, in agreement with the protective effects observed for these compounds in previous preclinical model studies.

This study presents an in-depth analysis of land use and land cover change on the Kerch Peninsula over a period spanning three decades. Utilizing convolutional neural networks alongside satellite imagery analysis, we have mapped and quantified the changes in land use and cover, revealing significant trends and transformations within the peninsula's landscape. The research aims to elucidate the interplay between anthropogenic activities, climatic variations, and policy interventions in shaping land cover dynamics, thereby providing insights into the environmental and socio-economic impacts of these changes. Our findings indicate a marked increase in urban expansion at the expense of natural ecosystems, including forests and wetlands, underscoring the urgent need for sustainable land management strategies. The study highlights the role of agricultural intensification and expansion in altering the peninsula's ecological balance and emphasizes the critical importance of integrating change analysis and prediction. By leveraging advanced remote sensing and GIS technologies, our analysis not only enhances the understanding of the complex dynamics driving land use and land cover change but also showcases the potential of predictive modeling in forecasting future land cover scenarios. The implications of this study extend beyond the Kerch Peninsula, offering valuable lessons for managing land use changes and conserving natural landscapes in similar regions globally.

Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been utilised to forecast the foreign exchange market (Forex). However, such models usually exhibit unstable behaviour, as data perturbations often downgrade the functionality of the entire network due to their monolithic architecture. Hence, this study proposes a novel neuroscience-informed modular network applied to the closing prices and the sentiments retrieved from Yahoo Finance and Twitter APIs, aiming to anticipate better price fluctuations in Euro to British Pound Sterling (EUR/GBP) rather than monolithic methods. The proposed model is based on a new modular CNN, replacing pooling layers with orthogonal kernel initialisation RNNs coupled with Monte Carlo Dropout (MCD), namely MCoRNNMCD. It combines two modules: i) a convolutional simple RNN and ii) a convolutional Gated Recurrent Unit (GRU), where orthogonality and MCD are added to reduce the overfitting, assessing each module's uncertainty. These parallel feature extraction modules concatenate their outputs to a final three-layer Artificial Neural Network (ANN) decision-making module. A comprehensive comparison viewing objective evaluation metrics such as the Mean Square Error (MSE) proved that the proposed MCoRNNMCD-ANN outperformed single CNN, LSTM, GRU, and the state-of-the-art hybrid BiCuDNNLSTM, CLSTM, CNN-LSTM, and LSTM-GRU in forecasting hourly EUR/GBP closing price fluctuations.

In recent years, Neural networks are increasingly deployed in various fields to learn complex patterns and make accurate predictions. However, designing an effective neural network model is a challenging task that requires careful consideration of various factors, including architecture, optimization method, and regularization technique. This paper aims to comprehensively overview the state-of-the-art artificial neural network (ANN) generation and highlight key challenges and opportunities in machine learning applications. It provides a critical analysis of current neural network model design methodologies, focusing on the strengths and weaknesses of different approaches. Also, it explores the use of different learning approaches, including convolutional neural networks (CNN), deep neural networks (DNN), and recurrent neural networks (RNN) in image recognition, natural language processing, and time series analysis. Besides, it discusses the benefits of choosing the ideal values for the different components of ANN, such as the number of Input/output layers, hidden layers number, activation function type, epochs number, and model type selection, which help improve the model performance and generalization. Furthermore, it identifies some common pitfalls and limitations of existing design methodologies, such as overfitting, lack of interpretability, and computational complexity. Finally, it proposes some directions for future research, such as developing more efficient and interpretable neural network architectures, improving the scalability of training algorithms, and exploring the potential of new paradigms, such as Spiking Neural Networks, quantum neural networks, and neuromorphic computing.

In urban Vehicular Ad Hoc Network (VANET) environments, buildings play a crucial role as they can act as obstacles that attenuate the transmission signal between vehicles. Quantifying the impact of buildings on the transmission quality is essential, especially in critical scenarios involving emergency vehicles, where reliable communication is of utmost importance. In this research, we propose a supervised learning approach based on artificial neural networks (ANNs) to develop a predictive model capable of estimating the level of signal degradation, represented by the bit error rate (BER), based on the obstacles perceived by moving emergency vehicles. By establishing a relationship between the level of signal degradation and the encountered obstacles, our proposed mechanism enables efficient routing decisions to be made prior to the transmission process. Consequently, data packets are routed through paths that exhibit the lowest BER. To gather the necessary training data, we employed SUMO and NS-3 simulations. The simulation results demonstrate that our developed model successfully learns and accurately estimates the BER for new data instances. Overall, our research contributes to enhancing the performance and reliability of communication in urban VANET environments, especially in critical scenarios involving emergency vehicles, by leveraging supervised learning and artificial neural networks to predict signal degradation levels and optimize routing decisions accordingly.

In this paper study, we develop a Bayesian Network model selection principle that address addresses the incommensurability of network features obtained from incongruous datasets and overcomes performance irregularities of the Minimum Description Length model selection principle. This is achieved (i) by approaching model evaluation as a classification problem, (ii) by estimating the effect that sampling error has on the satisfiability of conditional independence criterion, as reflected by Mutual Information, and (iii) by utilizing this error estimate to penalize uncertainty in the Minimum Uncertainty (MU) model selection principle. We validate our findings numerically and demonstrate the performance advantages of the MU criterion. Finally, we illustrate the advantages of the new model evaluation framework on a tRNA structural biology example.

Complex biological systems consist of large numbers of interconnected units, characterized by emergent properties such as collective computation. In spite of all the progress in the last decade, we still lack a deep understanding of how these properties arise from the coupling between the structure and dynamics. Here, we introduce the multiscale emergent functional state, which can be represented as a network where links encode the flow exchange between the nodes, calculated using diffusion processes on top of the network. We analyze the emergent functional state to study the distribution of the flow among components of 92 fungal networks, identifying their functional modules at different scales and, more importantly, demonstrating the importance of functional modules for information content of networks, quantified in terms of network spectral entropy. Our results suggest that the topological complexity of fungal networks guarantees the existence of functional modules at different scales keeping the information entropy, and functional diversity, high.

Hardy Cross originally proposed a method for analysis of flow in networks of conduits or conductors in 1936. His method was the first really useful engineering method in the field of pipe network calculation. Only electrical analogs of hydraulic networks were used before the Hardy Cross method. A problem with the flow resistance versus the electrical resistance makes these electrical analog methods obsolete. The method by Hardy Cross is taught extensively at faculties and it still remains an important tool for analysis of looped pipe systems. Engineers today mostly use a modified Hardy Cross method which threats the whole looped network of pipes simultaneously (use of these methods without computers is practically impossible). A method from the Russian practice published during 1930s, which is similar to the Hardy Cross method, is described, too. Some notes from the life of Hardy Cross are also shown. Finally, an improved version of the Hardy Cross method, which significantly reduces number of iterations, is presented and discussed. Also we tested multi-point iterative methods which can be used as substitution for the Newton-Raphson approach used by Hardy Cross, but this approach didn’t reduce number of required iterations to reach the final balanced solution. Although, many new models have been developed since the time of Hardy Cross, main purpose of this paper is to illustrate the very beginning of modeling of gas and water pipe networks or ventilation systems.

The aim of this study was to build a tool to analyze, using artificial intelligence, the sentiment perception of users who answered two questions from the CSQ – 8 questionnaires with raw Spanish free-text. Their responses are related to mindfulness, which is a novel technique used to control stress and anxiety caused by different factors in daily life. As such, we proposed an online course where this method was applied in order to improve the quality of life of health care professionals in COVID 19 pandemic times. We also carried out an evaluation of the satis-faction level of the participants involved, with a view to establishing strategies to improve fu-ture experiences. To automatically perform this task, we used Natural Language Processing (NLP) models such as swivel embedding, neural networks and transfer learning, so as to classify the inputs into the following 3 categories: negative, neutral and positive. Due to the lim-ited amount of data available - 86 registers for the first and 68 for the second - transfer learning techniques were required. The length of the text had no limit from the user’s standpoint, and our approach attained a maximum accuracy of 93.02 % and 90.53 % respectively based on ground truth labeled by 3 experts. Finally, we proposed a complementary analysis, using com-puter graphic text representation based on word frequency, to help researchers identify relevant information about the opinions with an objective approach to sentiment. The main conclusion drawn from this work is that the application of NLP techniques in small amounts of data using transfer learning is able to obtain enough accuracy in sentiment analysis and text classification stages

We describe a model of neurological disease based on dysfunctional brain oscillators. This is not a new model, but it is not one that is generally appreciated by clinicians. The value of this model lies in the predictions it makes and the utility it provides in translational applications, in particular for neuromodulation devices. We provide a perspective on the difference between neuromodulation devices that enforce an externally administered stimulus with devices that provide input to sensory receptors and thus stimulate endogenous sensory networks. Current forms of clinically applied neuromodulation are of the former type, including devices such as (implanted) deep brain stimulators (DBS) and various, noninvasive methods such as transcranial magnetic stimulation (TMS) and transcranial current methods (tACS, tDCS). The challenge with these methods is that they are not sensitive to underlying neuronal dynamics and work by applying an empirically derived electrical current waveform to affect dynamical patterns. Neuromodulation of a sensory organ accesses the same pathways that natural environmental stimuli do and, importantly, the modulatory signal will be transformed as it travels through the brain, allowing the modulation input to be consistent with regional dynamics. We present specific examples of devices that rely on sensory neuromodulation and evaluate the translational potential of these approaches. We argue that sensory neuromodulation is well suited to probe and, ideally, repair dysfunctional brain oscillators, thus providing a novel therapeutic approach for neurological diseases.

This article presents a detailed examination of the methodology and modeling tools utilized to analyze gas flow in pipelines, rooted in the fundamental principles of gas dynamics. The methodology integrates numerical simulations with modern neural network techniques, particularly focusing on the Physics-Informed Neural Network (PINN) method. This innovative approach combines artificial neural networks (ANNs) with physical equations, offering a more efficient and accurate way to model various complex processes and phenomena. The proposed mathematical model, based on the Euler equation, has been meticulously implemented using the Python language. Verification with analytical solutions ensures the accuracy and reliability of the computations. In the research, a comprehensive comparative analysis was conducted between results obtained using the PINN method and those from conventional Computational Fluid Dynamics (CFD) approaches. The analysis highlighted the advantages of the PINN method, which produced smoother pressure and velocity fluctuation profiles while reducing computation time, demonstrating its potential as a transformative modeling tool. The data derived from this study are of paramount importance for ensuring ongoing energy supply reliability and can also be used to create predictive models related to gas behavior in pipelines. The application of modeling techniques for gas flow simulation has the potential to revolutionize the integrity of our energy infrastructure and utilization of gas resources. However, it is crucial to emphasize that the effectiveness of such models relies on continuous monitoring and frequent updates to ensure alignment with real-world conditions. This research not only contributes to a deeper understanding of compressible gas flows but also underscores the crucial role of advanced modeling methodologies in the sustainable management of gas resources for both current and future generations.

Dynamic neural networks (DNN) are types of artificial neural networks (ANN) that are designed to work with sequential data where context in time is important. In contrast to traditional static neural networks that process data in a fixed order, dynamic neural networks use information about past inputs, which is important if dynamic of a certain process is emphasized. They are widely used in natural language processing, speech recognition and time series prediction. In industrial processes, their use is interesting for the prediction of difficult-to-measure process variables. In an industrial process of isomerization, it is crucial to measure the quality attributes affecting the octane number of gasoline. Process analyzers that are commonly used for this purpose are expensive and subject to failures, therefore, in order to achieve continuous production in case of malfunction, mathematical models for estimating the product quality attributes are imposed as a solution. In this paper, mathematical models were developed using dynamic recurrent neural networks (RNN), i.e., their subtype of a long short-term memory (LSTM) architecture. The results of the developed models were compared with the results of several types of other data-driven models developed for an isomerization process, such as multilayer perceptron (MLP) artificial neural networks, support vector machines (SVM) and dynamic polynomial models. The obtained results are satisfactory, which suggests a good possibility of application.

This paper details the evolution of access network sharing models from legacy DSL to the most recent fibre-based technology and the main challenges faced from a technical and business perspectives. We first give an overview of existing access sharing models, that span physical local loop unbundling and virtual unbundled local access. We then describe different types of optical access technologies and highlight how they support network sharing. Next, we examine how the concept of SDN and network virtualization has been pivotal in enabling the idea of “true multi-tenancy”, through the use of programmability, flexible architecture and resource isolation. We give examples of recent developments of cloud central office and OLT virtualization. Finally, we provide an insight into the role that novel business models, such as blockchain and smart contract technology, could play in 5G networks. We discuss how these might evolve, to provide flexibility and dynamic operations that are needed in the data and control planes.

Precipitation downscaling is widely employed for enhancing the resolution and accuracy of precipitation products from general circulation models (GCMs). In this study, we propose a novel statistical downscaling method to foster GCMs’ precipitation prediction resolution and accuracy for monsoon region. We develop a deep neural network composed of convolution and Long Short Term Memory (LSTM) recurrent module to estimate precipitation based on well-resolved atmospheric dynamical fields. The proposed model is compared against GCM precipitation product and classical downscaling methods in the Xiangjiang River Basin in South China. Results show considerable improvement compared to the ECMWF-Interim reanalysis precipitation. Also, the model outperforms benchmark downscaling approaches, including 1) quantile mapping, 2) support vector machine, and 3) convolutional neural network. To test the robustness of the model and its applicability in practical forecast, we apply the trained network for precipitation prediction forced by retrospective forecasts from ECMWF model. Compared to ECMWF precipitation forecast, our model makes better use of the resolved dynamical field for more accurate precipitation prediction at lead time from 1 day up to 2 weeks. This superiority decreases along forecast lead time, as GCM’s skill in predicting atmospheric dynamics being diminished by the chaotic effect. At last, we build a distributed hydrological model and force it with different sources of precipitation inputs. Hydrological simulation forced with the neural network precipitation estimation shows significant advantage over simulation forced with the original ERA-Interim precipitation (with NSE value increases from 0.06 to 0.64), and the performance is just slightly worse than the observed precipitation forced simulation (NSE=0.82). This further proves the value of the proposed downscaling method, and suggests its potential for hydrological forecasts.

Efficiently solving the problem of computing, in a distributed fashion, the shortest paths of a graph whose topology dynamically changes over time is a core functionality of many today’s digital infrastructures, probably the most prominent example being communication networks. Many solutions have been proposed over the years for this problem that can be broadly classified into two categories, namely Distance-Vector and Link-State algorithms. Distance-Vector algorithms are widely adopted solutions when scalability and reliability are key issues or when nodes have either limited hardware resources, as they result in being very competitive approaches in terms of both the memory and the computational point of view. In this paper, we first survey some of the most established solutions of the Distance-Vector category. Then, we discuss some recent algorithmic developments in this area. Finally, we propose a new experimental study, conducted on a prominent category of network instances, namely generalized linear preference (GLP) power-law networks, to rank the performance of such solutions.

When extract building from high resolution remote sensing image with meter/sub-meter accuracy, the shade of trees and interference of roads are the main factors of reducing the extraction accuracy. Proposed a Bayesian Convolutional Neural Networks(BCNET) model base on standard fully convolutional networks(FCN) to solve these problems. First take building with no shade or artificial removal of shade as Sample-A, woodland as Sample-B, road as Sample-C. Set up 3 sample libraries. Learn these sample libraries respectively, get their own set of feature vector; Mixture Gauss model these feature vector set, evaluate the conditional probability density function of mixture of noise object and roofs; Improve the standard FCN from the 2 aspect:(1) Introduce atrous convolution. (2) Take conditional probability density function as the activation function of the last convolution. Carry out experiment using unmanned aerial vehicle(UVA) image, the results show that BCNET model can effectively eliminate the influence of trees and roads, the building extraction accuracy can reach 97%.

This study uses machine learning to predict the convergence results of the Duffing equation with and without damping. The Duffing equation represents a nonlinear second-order differential equation with interesting behavior in undamped free vibration and forced vibration with damping. Convergence alternates randomly between 1 and -1 in undamped free vibration, depending on initial conditions. For forced vibration with damping, multiple factors influence vibration patterns. We utilize the fourth-order Runge-Kutta method to collect convergence results for both conditions. Machine learning techniques, specifically the long short term memory (LSTM) and LSTM-Neural Network (LSTM-NN) method, are employed to predict these convergence values. The LSTM-NN model is a hybrid approach that combines the LSTM method with the addition of hidden layers of neurons. Both the LSTM and LSTM-NN models are thoroughly explored and analyzed in this research. The research process involves three stages: data preprocessing, training, and verification. The results show that the LSTM-NN model becomes more adept at predicting binary datasets, boasting an impressive accuracy of up to 98%. However, when it comes to predicting multiple solutions, the traditional LSTM method outperforms the LSTM-NN approach.

Deep learning techniques, such as convolutional neural networks (CNN), generative adversarial networks (GAN), and graph neural networks (GNN), have over the past decade changed the ac-curacy of prediction in many diverse fields. In recent years, the application of deep learning tech-niques in computer vision tasks in pathology demonstrated extraordinary potential in assisting clinicians, automating diagnosis, and reducing costs for patients. Formerly unknown pathologi-cal evidence, such as morphological features related to specific biomarkers, copy number varia-tions, and other molecular features, were also able to be captured by deep learning models. In this paper, we review popular deep learning methods and some recent publications about their appli-cations in pathology.

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

in our increasingly interconnected world, sensor networks are critical in gathering and sending data for various applications, from environmental monitoring and industrial automation to healthcare and smart cities. However, as sensor networks expand in importance, so does the need to solve the multidimensional concerns of security, privacy, and forensics. This article explores the complex world of sensor network security, the delicate balance between data privacy and utility, and the emerging area of sensor network forensics. This article focuses on risk assessment of a network.

In computer vision and image analysis, Convolutional Neural Networks (CNNs) and other deep learning models are at the forefront of research and development. These advanced models have proven to be highly effective in tasks related to computer vision. One technique that has gained prominence in recent years is the construction of ensembles using Deep CNNs. These ensembles typically involve combining multiple pre-trained CNNs to create a more powerful and robust network. The purpose of this study is to evaluate the effectiveness of building CNN ensembles by combining several advanced techniques. Tested here are CNN ensembles constructed by replacing ReLU layers with different activation functions, employing various data augmentation techniques, and utilizing several algorithms, including some novel ones, that perturb network weights. Experimental results performed across many data sets representing different tasks demonstrate that our proposed methods for building deep ensembles produces superior results. All the resources required to replicate our experiments are available at https://github.com/LorisNanni.

We present a simplified computational rule for the back-propagation formulas for artificial neural networks. In this work, we provide a generic two-step rule for the back-propagation algorithm in matrix notation. Moreover, this rule incorporates both the forward and backward phases of the computations involved in the learning process. Specifically, this recursively computing rule permits the propagation of the changes to all synaptic weights in the network, layer by layer, efficiently. In particular, we use this rule to compute both the up and down partial derivatives of the cost function of all the connections feeding into the output layer.

Social networks have become the scenario with the greatest potential for the circulation of disinformation, hence there is a growing interest in understanding how this type of information is spread, especially in relation to the mechanisms used by disinformation agents such as bots, trolls, among others. In this scenario, the potential of bots to facilitate the spread of disinformation is recognised, however, the analysis of how they do this is still in its initial stages. Taking into consideration what was previously stated, this paper aimed to model and simulate scenarios of disinformation propagation in social networks caused by bots based on the dynamics of this mechanism documented in the literature. For achieving the purpose, System dynamics was used as the main modelling technique. The results present a mathematical model, as far as disinformation by this mechanism is concerned, and the simulations carried out against the increase in the rate of activation and deactivation of bots. Thus, the preponderant role of social networks in controlling disinformation through this mechanism, and the potential of bots to affect citizens, is recognised.

Optical artificial neural networks (ONNs) have significant potential for ultra-high computing speed and energy efficiency. We report a novel approach to ONNs that uses integrated Kerr optical micro-combs. This approach is programmable and scalable and is capable of reaching ultra-high speeds. We demonstrate the basic building block ONNs — a single neuron perceptron — by mapping synapses onto 49 wavelengths to achieve an operating speed of 11.9 x 10⁹ operations per second, or Giga-OPS, at 8 bits per operation, which equates to 95.2 gigabits/s (Gbps). We test the perceptron on handwritten-digit recognition and cancer-cell detection — achieving over 90% and 85% accuracy, respectively. By scaling the perceptron to a deep learning network using off-the-shelf telecom technology we can achieve high throughput operation for matrix multiplication for real-time massive data processing.

This article presents a forecast model that uses a hybrid architecture of recurrent neural networks (RNN) with surface neural networks (ANN), based on historical records of exported active energy (EAE) and weather data. Two types of models were developed: the first type includes six models that use EAE records and weather variables as inputs, while the second type includes eight models that use only weather variables. Different metrics were applied to assess the performance of these models, and the best model of each type was selected. Finally, a comparison of the performance between the selected models of both types is presented, and they are validated with real data provided by a solar plant, achieving acceptable levels of accuracy. The selected model of the first type has an RMSE of 0.19, MSE of 0.03, MAE of 0.09, a correlation coefficient of 0.96, and a determination coefficient of 0.93. The other selected model of the second type showed lower precision in the metrics (RMSE = 0.24, MSE = 0.06, MAE = 0.10, Corr. Coef. = 0.95, and Det. Coef. = 0.90). Both models demonstrated good performance and acceptable accuracy in forecasting the weekly photovoltaic energy production of the solar plant.

Sense element engagement theory explains how neural networks produce cortical prosthetic vision. A major prediction of the theory can be tested by developing a device which is expected to enable perception of continuous forms in altered visual geometries. The research reported here completes several essential steps in developing this device: (1) replication of simulations that are consistent with the theory using the NEST simulator, which can also be used for full-scale network emulation by a neuromorphic computer; (2) testing whether results consistent with the theory survive increasing the scale and duration of simulations; (3) establishing a method that uses numbers of spikes produced by network neurons to report the number of phosphenes produced by cortical stimulation; and (4) simulating essential functions of the prosthetic device. NEST simulations replicated early results and increasing their scale and duration produced results consistent with the theory. A decision function created using multinomial logistic regression correctly classified the expected number of phosphenes for 2080 spike number distributions for each of three sets of data, half of which arise from simulations expected to yield continuous visual forms on an altered visual geometry. A process for modulating electrical stimulation amplitude based on intermittent population recordings that is predicted to produce continuous visual forms was successfully simulated. The classification function developed using logistic regression will be used to tune this process as the scale of simulations is further increased.

Deep learning models are part of the family of artificial neural networks and, as such, it suffers of catastrophic interference when they learn sequentially. In addition, most of these models have a rigid architecture which prevents the incremental learning of new classes. To overcome these drawbacks, in this article we propose the Self-Improving Generative Artificial Neural Network (SIGANN), a type of end-to-end Deep Neural Network system which is able to ease the catastrophic forgetting problem when leaning new classes. In this method, we introduce a novelty detection model to automatically detect samples of new classes, moreover an adversarial auto-encoder is used to produce samples of previous classes. This system consists of three main modules: a classifier module implemented using a Deep Convolutional Neural Network, a generator module based on an adversarial autoencoder; and a novelty detection module, implemented using an OpenMax activation function. Using the EMNIST data set, the model was trained incrementally, starting with a small set of classes. The results of the simulation show that SIGANN is able to retain previous knowledge with a gradual forgetfulness for each learning sequence. Moreover, SIGANN can detect new classes that are hidden in the data and, therefore, proceed with incremental class learning.

We consider a general problem of optimal allocation of limited resources in a wireless telecommunication network. The users are divided into several different groups (or classes), which correspond to different levels of service. The network manager must satisfy these different users requirements. This approach leads to a convex optimization problem with balance and capacity constraints. We present several decomposition type methods to find a solution of this problem, which exploit its special features. We suggest to apply first the dual Lagrangian method with respect to the total capacity constraint, which gives the one-dimensional dual problem. However, calculation of the value of the dual cost function requires solution of several optimization problems. Our methods differ in approaches of solution of these auxiliary problems. We compare the performance of the suggested methods on several series of test problems. They show rather satisfactory convergence. Nevertheless, proper decomposition technique enhance the convergence essentially.

Attackers are perpetually modifying their tactics to avoid detection and frequently leverage legitimate credentials with trusted tools already deployed in a network environment, making it difficult for organizations to proactively identify critical security risks. Network traffic analysis products have emerged in response to attackers’ relentless innovation, offering organizations a realistic path forward for combatting creative attackers. Additionally, thanks to the widespread adoption of cloud computing, Device Operators (DevOps) processes, and the Internet of Things (IoT), maintaining effective network visibility has become a highly complex and overwhelming process. What makes network traffic analysis technology particularly meaningful is its ability to combine its core capabilities to deliver malicious intent detection. In this paper, we propose a novel darknet traffic analysis and network management framework to real-time automating the malicious intent detection process, using a weight agnostic neural networks architecture. It is an effective and accurate computational intelligent forensics tool for network traffic analysis, the demystification of malware traffic, and encrypted traffic identification in real-time. Based on Weight Agnostic Neural Networks (WANNs) methodology, we propose an automated searching neural net architectures strategy that can perform various tasks such as identify zero-day attacks. By automating the malicious intent detection process from the darknet, the advanced proposed solution is reducing the skills and effort barrier that prevents many organizations from effectively protecting their most critical assets.

The escalation of climate change and the increasing frequency of extreme weather events have amplified the importance of precise and timely lightning prediction. This predictive capability is pivotal for the preservation of life, protection of property, and maintenance of crucial infrastructure safety. Recently, the rapid advancement and successful application of data-driven deep learning across diverse sectors, particularly in computer vision and spatio-temporal data analysis, have opened up innovative avenues for enhancing both the accuracy and efficiency of lightning prediction. This article presents a comprehensive review of the broad spectrum of existing lightning prediction methodologies. Starting from traditional numerical forecasting techniques, we traverse the path to the most recent breakthroughs in deep learning research. We encapsulate these diverse methods, shedding light on their progression and summarizing their capabilities, while also predicting their future development trajectories. This exploration is designed to enhance our understanding of these methodologies, allowing us to better utilize their strengths, navigate their limitations, and potentially integrate these techniques to create novel and powerful lightning prediction tools. Through such endeavors, our aim is to bolster our preparedness against the growing unpredictability of our climate and ensure a proactive stance towards lightning prediction.

In this paper, we continue the research cycle on the properties of convolutional neural network-based image recognition systems and ways to improve noise immunity and robustness [1]. Currently, a popular research area related to artificial neural networks is adversarial attacks. The effect of adversarial attacks on the image is not highly perceptible to the human eye, also it drastically reduces the neural network accuracy. Image perception by a machine is highly dependent on the propagation of high frequency distortions throughout the network. At the same time, a human efficiently ignores high-frequency distortions, perceiving the shape of objects as a whole. The approach proposed in this paper can improve the image recognition accuracy in the presence of high-frequency distortions, in particular, caused by adversarial attacks. The proposed technique makes it possible to measure up the logic of artificial neural network to that of a human, for whom high-frequency distortions are not decisive in object recognition.

The Physics-Informed Neural Networks (PINNs) improve the efficiency of data utilization by combining physical principles with neural network algorithms and ensure that the predictions are consistent and stable with the physical laws. PINNs opens up a new approach to address inverse problems in fluid mechanics. Based on the single-relaxation-time lattice Boltzmann method (SRT-LBM) with the Bhatnagar-Gross-Krook (BGK) collision operator, the PINN-SRT-LBM model is proposed in this paper for solving the inverse problem in fluid mechanics. The PINN-SRT-LBM model consists of three components. The first component involves a deep neural network that predicts the equilibrium control equations in different discrete velocity directions within SRT-LBM. The second component employs another deep neural network to predict non-equilibrium control equations, enabling inference of the fluid's non-equilibrium characteristics. The third component, a physics informed function translates the outputs of the first two networks into physical infor-mation. By minimizing the residuals of the physical partial differential equations (PDEs), the physics informed function infers relevant macroscopic quantities of the flow. The model evolves two sub-models applicable to different dimensions, named PINN-SRT-LBM-I and PINN-SRT-LBM-II models according to the construction of the physical informed function. The innovation of this work is the introduction of SRT-LBM and discrete velocity models as physical drivers into the neural network through the interpretation function. Therefore, PINN-SRT-LBM allows the neural network to handle inverse problems of various dimensions and focus on problem-specific solving. Experimental results confirm the accurate prediction of flow infor-mation at different Reynolds numbers within the computational domain. Relying on the PINN-SRT-LBM models, inverse problems in fluid mechanics can be solved efficiently.

The basic challenges of this work are twofold: demonstrating the dependence between the functional and topological qualities of partition networks and finding the simplest—with respect to algorithmic complexity—network elements. The study of these problems is based on finding the solution to an appropriate antagonistic vertex game. The results of the numerical simulations of antagonistic partition games demonstrate that the winner’s graphs are “almost always” dense and hyperenergetic compared to the loser’s graphs. These observations reveal that successful evolutionary mechanisms can be realized, in principle, by the simplest objects (such as viruses).

Adaptive mechanisms, such as channel hopping and packet replication, are used in low-power wireless networks to deal with the spatial and temporal variations in the link quality, and meet the reliability requirements of industrial applications (i.e., PDR>99%). However, the benefits of such mechanisms are limited and may have a large impact on end-to-end latency and energy consumption. Hence, in this paper we propose using adaptive modulation diversity, which allows to dynamically select different modulations, to improve link reliability. We present three adaptive modulation diversity selection strategies and validate them using the data derived from a real-world deployment using the IEEE 802.15.4g SUN modulations (i.e., SUN-FSK, SUN-OQPSK and SUN-ODFM) in an industrial environment. The results show that by using adaptive modulation diversity it is possible to improve link reliability regardless of node conditions.

The explosive emergence of wireless technologies and standards, covering licensed and unlicensed spectrum bands has triggered the appearance of a huge amount of wireless technologies, with many of them coexisting in the same band. Unfortunately, the wireless spectrum is a scarce resource, and the available frequency bands will not scale with the foreseen demand for new capacity. Certain parts of the spectrum, in particular the license-free ISM bands, are overcrowded, while other parts, mostly licensed bands, may be significantly underutilized. As such, there is a need to introduce more advanced techniques to access and share the wireless medium, either to improve the coordination within a given band, or to explore the possibilities of intelligently using unused spectrum in underutilized (e.g., licensed) bands. Therefore, in this paper, we present an open source SDR-based framework that can be employed to devise disruptive techniques to optimize the sub-optimal use of radio spectrum that exists today. Additionally, we describe three use cases where the proposed framework can be employed along with intelligent algorithms to achieve improved spectrum utilization.

In this paper, a special recurrent neural network (RNN) called \emph{Long Short-Term Memory (LSTM)} is used to design a virtual load sensor that estimates the mass of heavy vehicles. The estimation algorithm consists of a two-layer LSTM network, with the two layers based on sequence-to-sequence and sequence-to-one logic, respectively. The network estimates the vehicle mass based on the vehicle speed, longitudinal acceleration, engine speed, engine torque, and the accelerator pedal position. The network is trained and tested with a data set collected in a high-fidelity simulation environment called Truckmaker. Training data is generated in acceleration maneuvers in a range of speeds whereas test data is obtained by simulating the vehicle in a Worldwide harmonized light vehicles test cycle (WLTC). Preliminary results show that, with the proposed approach, the heavy-vehicle mass can be estimated as accurately as commercial load sensors in a range of load mass as wide as four tons.

Intelligent Transportation Systems (ITS) encompasses technologies, services, and applications facilitating communication between vehicles (V2V) and between vehicles and fixed infrastructure (V2I and I2V). This mutual interaction constitutes a Vehicular Ad-Hoc Network (VANET) which supports a plethora of applications targeting critical transportation aspects, such as safety, mo-bility, and environmental considerations. Dedicated Short Range Communications (DSRC), op-erating on the 5.9 GHz band, is pivotal for such exchanges. We introduced an innovative algorithm designed to identify jamming attacks and transition the Safety Application to a secure fail-safe mode. This algorithm leverages a dual-metric strategy, incorporating both distance and PDR measurements. Field tests confirm that our algorithm adeptly recognizes the activities of deceptive jammers, ensuring a prompt shift of the safety application into its fail-safe state. This paper delves into these countermeasures, evaluating their efficiency via mathematical modelling, simulations, and on-ground testing. Findings acknowledge that these strategies bolster the reliability of safety applications in jamming scenarios. Furthermore, the approaches propounded align with ongoing standardization endeavours by relevant authorities, ensuring communication mediums remain unhindered.

Artificial neural networks are widely established models of computational intelligence that have been tested for effectiveness in a variety of real-world applications. These models require fitting a set of parameters through the use of some optimization technique. However, an issue that researchers often face is finding an efficient range of values for the parameters of the artificial neural network. This paper proposes an innovative technique of generating a promising range of values for the parameters of the artificial neural network. Finding the value field is done by a series of rules for partitioning the original set of values or expanding it, which rules are generated using Grammatical Evolution. After finding a promising interval of values, any optimization technique such as a genetic algorithm can be used to train the artificial neural network on that interval of values. The new technique was tested on a wide range of problems from the relevant literature and the results were extremely promising.

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

The Necessity of Human resources beyond perception of human understanding towards the Evaluation of video quality or Data screening methodology is conducted based on human perception level since it is concerned with how visual content is perceived by a observer based on observations with his/ her perception on a particular video sequence. Therefore, we considered that the subject has to grade the encoded video sequences under certain test environment conditions based on ITU-Recommendations. Since Human perception is considered as the true judgment and precise measurement of visual content, data screening has became quite essential and quite comfortable to general public due to introduction of User Experience(UX) concept by User Experience community. The translations of A recurrent neural network is based on certain principles, for instance we considered natural language processing which is certainly adaptable towards understanding sequential data and use patterns to predict the consistency within observers. In our research, we adapted principles based on Recurrent Neural Networks while assuming consistency within observers for predicting video quality within data screening environment towards subjective experiments. Moreover,this research work explores the trade offs between Human perception on visual content and consistency of observations within individual observer.

This article explores the transformative role of neural networks in the realm of biology, particularly within microscopy image processing and illustrations. Neural networks have revolutionized cell segmentation and analysis, enabling precise delineation of cell boundaries and tracking of cellular behaviours. They excel in detecting subcellular structures, unravelling intricate organelle interactions. In 3D image reconstruction, neural networks navigate volumetric datasets, enhancing our understanding of spatial cellular architecture. These networks enhance disease diagnosis by identifying anomalies and irregularities, potentially revolutionizing early detection and classification. Moreover, neural networks restore and enhance microscopy images, unveiling hidden details. Lastly, they bridge art and science, fostering captivating biological art and enriching science communication. As neural networks evolve, they promise a future of limitless possibilities, weaving together technology, science, and art to illuminate the microscopic realm in unprecedented ways.

Mucus is a critical part of the human body’s immune system which traps and carries away various particulates such as anthropogenic pollutants, pollen, viruses etc. Various synthetic hydrogels have been developed to mimic mucus, using different polymers as their backbones. Common to these simulants is a three-dimensional gel network which is physically crosslinked and is capable of loosely entrapping water within. Two of the challenges in mimicking mucus using synthetic hydrogels include the need to mimic the rheological properties of the mucus and its ability to capture particulates (its adhesion mechanism). In this paper, we review the existing mucus simulants and discuss their rheological, adhesive and tribological properties. We show that most, but not all, simulants indeed mimic the rheological properties of the mucus but only one mimics the ability of mucus to capture particulates.

Oral squamous cell carcinoma often arises from an oral potentially malignant disorder called oral leukoplakia (OL). With this work we aimed to develop a novel data-driven predictive model based on gene expression profiles to distinguish OL patients who underwent malignant transformation from those who did not. We used the Tree Augmented Naïve (TAN) Bayes classifier to predict the posterior probability of having oral cancer given the data. 86 patients were included with a median follow-up of 7.11 years. Fifty-one patients (51/86; 59%) underwent malignant transformation. We found that 16 genes were predictors of oral cancer in patients with OL and these included SLC7A11, SPINK6, SERPINA12, VIT, ATP1B3, CST6, FLRT2, ELMOD1, AZGP1, RNASE13, DIO2, ECM1, CYP4F11, SYTL4, AKR1C1, and AKR1C3. In conclusion, we showed that Bayesian gene networks are a data-driven approach which could be used also in other predictor models in oncology.

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

Many real complex systems present multilayer structure where high-order metadata on one layer refers to dyadic data on a lower layer. Significant progresses to analyse high-order metadata under the assumption of community organization have been done. However, there are no planted communities in real-world networks, and the necessity of new frameworks to analyze high-order metadata regardless of community organization has been raised.Here, we propose to adopt hyperedge organization. Predicting ‘entanglements’ between a hyperedge and nodes scattered in the rest of the network might suggest structural or functional liaisons, without assumption of any community organization. We introduce a novel concept: hyperedge entanglement (HE), which associates to each hyperedge an entangled hyperedge, by means of a network operator that predicts significant ‘interactions at distance’ between network nodes and existing hyperedges. We also introduce a new challenge termed hyperedge entanglement prediction (HEP), and an algorithm to perform this task. We evaluated HEP performance on social, biological and synthetic data where, given only topology and hyperedges (such as communities or functional modules), the goal is to predict whether nodes not connected to a certain hyperedge might be candidates for a significant entanglement. Finally, as real application in diseasome systems biomedicine, we perform HEP on the human protein interactome to predict unknown gene entanglements with the COPD disease gene hyperedge. HEP predictions are validated by biological experiments, enlarging our understanding of molecular mechanisms behind COPD/aneurysm comorbidity.

In the last years, we have witnessed a remarkable progress of algorithms solving Boolean satisfiability (SAT). The success of these algorithms has been especially relevant in a large number of industrial or real-world applications, for which these SAT solvers are nowadays an essential core part of their solving processes. Interestingly enough, these applications include a very diverse and heterogeneous range of domains, such as hardware verification, planning, and cryptography, among others. Unfortunately, the reasons of the good performance of these solvers on this variety of industrial benchmarks are not completely understood yet. Since SAT solvers’ efficiency is fundamental in various domains, obtaining a better understanding of these algorithms and the reasons of their good performance is crucial. In order to shed light on this question, SAT solvers are often viewed as complex systems with many interconnected components (e.g., conflict analysis and learning mechanism, database management, search restarts) interacting in many unpredictable ways. There is the common belief that the resulting emergent behavior of these complex systems takes advantage of a certain underlying structure of the SAT formula, which is shared by the majority of these industrial problems regardless the domain they come from. Recently, there have been some attempts of characterizing this structure under the lens of complex networks, with the purpose of better understanding the success of the solvers, and potentially improving them. In this paper, we analyze the structure of industrial SAT instances under the lens of self-similarity, and study how the execution of SAT solvers affect that structure. Many real-world graphs exhibit self-similar structure (with small fractal dimension), which means that after rescaling (replacing groups of nodes by a single node), the same kind of structure can be observed. In our analysis, in which we represent SAT instances as graphs, we observe that many industrial SAT formulas exhibit the same kind of structure. Moreover, we analyze how this structure evolves by effects of learning new clauses during the search. In particular, we observe that learned clauses usually contain variables that are close in the graph representation of the formula. This is, the learning mechanism tends to work locally. On the contrary, this learning mechanism on random SAT formulas –which do not exhibit any structure at all– is unable to generate these local clauses. This difference contributes to explain the success of modern SAT solvers on industrial problems.

A good recommender system can infer customers’ preferences based on their historical purchase records, and recommend products that the customers may be interested in, saving them a lot of time and energy. For enterprises, it is difficult to recommend accurately to each customer, and the bad recommendation may be counterproductive. Customer loyalty is an indicator that measures the preference relationship between customers and products in the field of marketing. A hypothesis is proposed in this study: if companies can divide customers into different groups based on customer loyalty, the recommendation effect on certain groups is better than that on overall customers. In this study, customer loyalty is measured by four features of the RFML model. All customers are viewed as points on a four-dimensional space, which are clustered by the k-means model. Two recommendation algorithms based on complex networks are tested: recommendation algorithm based on bipartite graph and PersonalRank (BGPR), and recommendation algorithm based on a single vertex set network and DeepWalk (SVDW). The experimental results show that customer loyalty has improved the effectiveness of the two algorithms over 14%, and the recommendation effect is the best on customer groups with a loyalty level of 4 (the highest level is 5). The recommendation algorithms with customer loyalty are better than using them alone.

The Hennovation project, an EU H2020 funded thematic network, aimed to explore the potential value of practice-led multi-actor innovation networks within the laying hen industry. The project proposed that husbandry solutions can be practice-led and effectively supported to achieve durable gains in sustainability and animal welfare. It encouraged a move away from the traditional model of science providing solutions for practice, towards a collaborative approach where expertise from science and practice were equally valued. During the 32-month project, the team facilitated 19 multi-actor networks in 5 countries through 6 critical steps in the innovation process: problem identification, generation of ideas, planning, small scale trials, implementation and sharing with others. The networks included farmers, processors, veterinarians, technical advisors, market representatives and scientists. The interaction between the farmers and the other network actors, including scientists, was essential for farmer innovation. New relationships emerged between the scientists and farmers, based on experimental learning and the co-production of knowledge for improving laying hen welfare. The project demonstrated that a practice-led approach can be a major stimulus for innovation with several networks generating novel ideas and testing them in their commercial context. The Hennovation innovation networks not only contributed to bridging the science-practice gap by application of existing scientific solutions in practice but more so by jointly finding new solutions. Successful multi-actor, practice-led innovation networks appeared to depend upon the following key factors: active participation from relevant actors, professional facilitation, moderate resource support and access to relevant expertise. Farmers and processors involved in the project were often very enthusiastic about the approach, committing significant time to the network’s activities. It is suggested that the agricultural research community and funding agencies should place greater value on practice-led multi-actor innovation networks alongside technology and advisor focused initiatives to improve animal welfare and embed best practices.