We conducted a topological analysis of the novel, non-associative, and unital algebraic structure known as Bermejo Algebras, developed by Alejandro Bermejo, which includes the Algebra B and Treon Algebra. This algebras can define Lie and Malcev algebras when their product operations are derived from the Bermejo Algebras product. Central to this study are treons, complex entities that arise as isomorphisms of Algebra B when the field is real. We define the vector spaces associated with Bermejo Algebras to establish equivalence classes and a quotient topology, resulting in Hausdorff spaces that do not depend on traditional norms, inner products, or metrics. Our findings lay the groundwork for constructing new types of differential manifolds, opening new avenues for advanced mathematical research.

In This paper we introduce the integration of Renormalization Group (RG) methods with Deep Q-Networks (DQNs) to improve reinforcement learning in high-dimensional state spaces. RG methods provide multi-scale analysis, enhancing state representation, learning stability, and exploration. The proposed RG-DQN algorithm uses hierarchical Q-value estimation and multi-scale representations, demonstrating superior performance on synthetic genomic data compared to traditional DQNs.}

Multimodal emotion classification (MEC) involves analyzing and identifying human emotions by integrating data from multiple sources, such as audio, video, and text. This approach leverages the complementary strengths of each modality to enhance the accuracy and robustness of emotion recognition systems. However, one significant challenge is effectively integrating these diverse data sources, each with unique characteristics and levels of noise. Additionally, the scarcity of large, annotated multimodal datasets in Bangla limits the training and evaluation of models. In this work, we unveiled a pioneering multimodal Bangla dataset, MAViT-Bangla (Multimodal Audio Video Text Bangla dataset). This dataset, comprising 1002 samples across audio, video, and text modalities, is a unique resource for emotion recognition studies in the Bangla language. It features emotional categories such as anger, fear, joy, and sadness, providing a comprehensive platform for research. Additionally, we developed a framework for emotion recognition that employs a cross-modal attention mechanism among unimodal features. This mechanism fosters the interaction and fusion of features from different modalities, enhancing the model’s ability to capture nuanced emotional cues. The effectiveness of this approach was demonstrated by achieving an F1-score of 0.64, a significant improvement over unimodal methods.

This paper highlights the importance of one-shot learning from prototype SKU images for efficient product recognition in retail and inventory management. Traditional methods require large supervised datasets to train deep neural networks, which can be costly and impractical. One-shot learning techniques mitigate this issue by enabling classification from a single prototype image per product class, thus reducing data annotation efforts. We introduce the variational prototyping-encoder (VPE), a novel deep neural network for one-shot classification. Utilizing a support set of prototype SKU images, VPE learns to classify query images by capturing image similarity and prototypical concepts. Unlike metric learning-based approaches, VPE pre-learns image translation from real-world object images to prototype images as a meta-task, facilitating efficient one-shot classification with minimal supervision. Our research demonstrates that VPE can significantly reduce the need for large datasets while accurately classifying query images into their respective categories, providing a practical solution for product classification tasks.

The paper addresses the energy consumption minimization problem in wireless powered communication networks (WPCNs) and proposes a DT-SWIPT-assisted time allocation scheme, named DaTA, such that the wireless station can share the remaining energy after transmission to the HAP to those who have not transmitted to the HAP to minimize the energy consumption of the network. In addition to proposing a new frame structure, the paper also considers the SNR (Signal-to-Noise) constraint to guarantee that the HAP can successfully receive data from wireless stations. In the paper, the energy consumption minimization problem is formulated as a nonlinear programming model. We employ the SQP (Sequential Quadratic Programming) algorithm to figure out the optimal solution. Moreover, a heuristic method is proposed as well to obtain a near-optimal solution in a shorter time. Simulation results showed that the proposed scheme can have better performance than the related work in terms of energy consumption and energy efficiency.

Physics-informed neural networks can be trained to serve as surrogate models by learning how spatial physical fields develop with change of parameters. This is an advantage over traditional numerical methods that can only be used to calculate a single solution field for a single discrete setting of a parameter. While many studies report accurate results of physics-informed deep learning of laminar flows, evaluations of surrogate modeling of high Reynolds number flows remain sparse. To contribute to this question, we here explore the capabilities and limits of physics-informed deep learning to solve the Reynolds-averaged Navier-Stokes equations for the flow around two airfoils under variable angles of attack. No labeled training data were provided and a single network was trained to simultaneously learn several solution fields in a single training run. The network captured essential flow features such as boundary layers and high and low pressure regions. Moreover, the qualitative correlations of lift and drag with the angle of attack and the higher drag of the thicker airfoil were captured. However, comparisons with reference simulations revealed an underestimation of the shear layer gradients as well as deviations of the fields' extrema. Thus, we also debate potential future improvements to increase the accuracy of the predicted flow. This work offers a prospect on the capabilities and current limitations of physics-informed neural networks for surrogate modeling of high Reynolds number flows. We argue that the method is promising and this work is aimed to encourage further research and development of the method when applied to Reynolds-averaged flows at high Reynolds numbers.

It is discovered that writing an odd integer as $2^m - 1$ for $m \geq 1$ helps in understanding the dynamics of the Collatz-type sequences. Starting with the original Collatz sequence $3n + 1$, it is found that when the odd step is applied to an odd integer $2^m - 1$, an even integer $2^{m+1} + 2^m - 2$ is obtained, which is exactly once divisible by 2. This implies that the sequence alternates between odd and even steps $m$ times. This governs the dynamics of the Collatz-type sequences because: (i) for the sequence to diverge to infinity, $m$ must be infinite, and (ii) the value of $m$ determines the number of times the integer can be divided by 2 in each even step. This formulation allows construction of odd integers like $\sum 2^m - 1$ to follow specific patterns of odd and even steps. Applying this understanding to the modified Collatz sequence $5n + 1$ reveals that for $m = 3$, the integer $2^{m + 1} + 2^m - 1$ is obtained, indicating that any integer formulation ending with $2^3 - 1$ in $5n + 1$ will diverge to infinity.

This study investigates the impact of AI regulations and adoption on labor markets and employment in the USA. In order to achieve the study's objective, a robust econometric approach was employed using Principal Components Analysis (PCA) to address multicollinearity among the variables. The regression analysis incorporated principal components representing overall AI adoption and education (PC1), AI innovation and academic output (PC2), economic growth (PC3), and unemployment and AI strategies (PC4). The analysis utilized heteroskedasticity-robust standard errors to ensure reliable coefficient estimates and tested for stationarity to confirm the stability of the time series data. Data were collected from 2010 to 2022, encompassing key AI-related and economic indicators. The results reveal that higher AI adoption and education levels initially lead to job displacement, negatively impacting labor market metrics. Similarly, AI innovation and economic growth driven by AI do not immediately translate into job creation, reflecting transitional challenges. However, the strategic implementation of AI significantly mitigates these adverse effects and enhances employment conditions. The study finds that comprehensive AI strategies, robust regulatory frameworks, and effective workforce retraining and upskilling programs are essential for supporting labor market stability and promoting employment growth. Based on the findings, the study recommended that there is the need to develop and implement comprehensive AI strategies that include robust regulatory frameworks to support workforce transitions. Policies should focus on retraining and upskilling programs to help displaced workers adapt to new AI-driven roles.

This paper explores the application of machine learning in financial time series analysis, focusing on predicting trends in financial enterprise stocks and economic data. It begins by distinguishing stocks from stocks and elucidates risk management strategies in the stock market. Traditional statistical methods such as ARIMA and exponential smoothing are discussed in terms of their advantages and limitations in economic forecasting. Subsequently, the effectiveness of machine learning techniques, particularly LSTM and CNN-BiLSTM hybrid models, in financial market prediction is detailed, highlighting their capability to capture nonlinear patterns in dynamic markets. The study demonstrates the advancements in predictive accuracy and robustness achieved by deep learning methods through empirical analysis and model validation. The findings contribute significantly to academic discourse and offer practical insights for investors, financial analysts, and policymakers navigating market volatility and optimizing investment strategies. Finally, the paper outlines prospects for machine learning in financial forecasting, laying a theoretical foundation and methodological framework for achieving more precise and reliable economic predictions.

The persistent security challenges in Industry 4.0 due to resource-constrained IoT devices necessitate innovative solutions. Addressing this, a study introduces the ASCON algorithm for lightweight Authenticated Encryption with Associated Data, enhancing confidentiality, integrity, and authenticity within IoT limitations. By integrating Digital Twins, the framework emphasizes the need for robust security in Industry 4.0, with ASCON ensuring secure data transmission, bolstering system resilience against cyber threats. Practical validation using MQTT protocol confirms ASCON’s efficacy over AES-GCM, highlighting its potential for enhanced security in Industry 4.0. Future research should focus on optimizing ASCON for microprocessors and developing secure remote access tailored to resource-constrained devices, ensuring adaptability in the digital era

Background: The key objective of this research was to identify the dominant parameters and determine the patient status of pediatric patients with congenital heart disease in the ICU. The data we collected from the Congenital Heart Disease (CHD) Surgery Unit (ICU) in the National Heart Foundation Hospital and Research Institute, Dhaka, Bangladesh. Data from 300 ICU patients was collected and analyzed. We choose patients who are less than 12 years old at the time of ICU admission and whose ICU stay is longer than 24 hours. (2) Methods: According to the doctor’s advice, the dependent and independent variables are selected. The relationship between these parameters in the ICU was selected by linear modeling, which is associated with mortality risk. These parameters are used in the linear regression model and the ARIMA model for prediction. The prediction model is used for pediatric congenital heart disease patients in the ICU. (3) Results: The relation between CVP and BP (95% CI=0.2113,0.353 r=0.2841249), PEEP, and FiO2 (95% CI=0.6992,0.770 r=0.7367744) is statistically significant (p value<0.001). pH and PO2 were statistically significant, but there were correlations (95% CI=0.161,0.308 r=0.2362575). The statistically significant (p < 0.001) parameters were selected for prediction. In this study, BP, FiO2, and PO2 parameters were used in the linear regression model and the ARIMA model for prediction. We predict the next-hour patient’s status. The ARIMA model was found to have less error than the linear regression model. (4) Conclusions: This study helps identify the important parameters that are measured in the ICU to monitor patient status and predict the future value of those parameters, with the ultimate goal of providing physicians with an early signal of future patient conditions.

This survey provides a comprehensive overview of in-context learning (ICL) in large language models (LLMs), a phenomenon where models can adapt to new tasks without parameter updates by leveraging task-relevant information within the input context. We explore the definition and mechanisms of ICL, investigate the factors contributing to its emergence, and discuss strategies for optimizing and effectively utilizing ICL in various applications. Through a systematic review of recent literature, we first clarify what ICL is, distinguishing it from traditional fine-tuning approaches and highlighting its unique characteristics. We then delve into the underlying causes of ICL, examining theories ranging from implicit meta-learning during pre-training to the emergence of task vectors in LLMs. The survey also covers various approaches to enhance ICL performance, including prompt engineering techniques, demonstration selection strategies, and methods for improving generalization across diverse tasks. Additionally, we discuss the limitations and challenges of ICL, such as its sensitivity to demonstration ordering and potential biases. By synthesizing findings from numerous studies, we aim to provide researchers and practitioners with a clear understanding of the current state of ICL research, its practical implications, and promising directions for future investigation. This survey serves as a valuable resource for those seeking to leverage ICL capabilities in LLMs and contributes to the ongoing discourse on the remarkable adaptability of these models.

This research addresses the challenge of integrating fairness considerations into optimization problems, focusing on the development of multi-objective optimization techniques that balance traditional efficiency metrics with fairness constraints. In many algorithmic decision-making processes, optimizing for efficiency alone can inadvertently perpetuate or exacerbate biases, leading to inequitable outcomes. This study explores how data analysis and machine learning can be leveraged to identify and mitigate these biases, ensuring that optimization models yield both efficient and fair solutions. The research presents a framework for incorporating fairness constraints into multi-objective optimization, utilizing various fairness metrics such as demographic parity, equal opportunity, and disparate impact. It investigates the application of this framework across different domains, including resource allocation in healthcare systems, loan approvals in finance, and personalized learning platforms in education. By analyzing real-world data sets, the study demonstrates how fairness-aware optimization can lead to more equitable outcomes without significantly compromising efficiency. Empirical results from case studies show that multi-objective optimization with fairness constraints can effectively balance the trade-off between efficiency and equity. The research also discusses the computational challenges and ethical considerations associated with implementing fairness constraints in optimization models. Strategies for addressing these challenges, such as regularization techniques and fairness-aware machine learning algorithms, are evaluated and presented. Findings highlight the importance of incorporating fairness into optimization processes to prevent algorithmic biases and promote social equity. The study concludes with practical recommendations for policymakers, practitioners, and researchers on adopting fairness-aware optimization techniques to ensure that algorithmic decision-making processes are both efficient and just.

The rapid advancement of large language models (LLMs), such as ChatGPT, has revolutionized natural language processing, enabling these models to generate coherent and contextually relevant text. These capabilities hold significant potential for various applications, particularly in the medical field. LLMs can assist healthcare professionals by providing accurate information, supporting diagnostic processes, and enhancing medical education. However, the implementation of LLMs in clinical settings faces several barriers, including technical limitations, ethical concerns, regulatory constraints, and practical challenges. Ensuring accuracy, reliability, and interpretability is crucial, along with addressing biases, ensuring data privacy, and establishing ethical guidelines. Future research should focus on improving training techniques, developing explainable AI methods, and creating efficient, resource-saving models. Expanding applications through domain-specific models and multi-modal integration can further unlock the potential of LLMs. By addressing these challenges and prioritizing responsible development, LLM technology can be safely and effectively integrated into various domains, driving innovation and improving outcomes. This paper explores the current state of LLM technology, its medical applications, barriers to implementation, and directions for future research and development

This article develops duality principles and numerical results for a large class of non-convex variational models. The main results are based on fundamental tools of convex analysis, duality theory and calculus of variations. More specifically the approach is established for a class of non-convex functionals similar as those found in some models in phase transition. Finally, in some sections we present concerning numerical examples and the respective softwares.

Large Language Models (LLMs) have demonstrated promising capabilities to solve complex tasks in critical sectors such as healthcare. However, LLMs are limited by their training data which is often outdated, the tendency to generate inaccurate ("hallucinated") content and a lack of transparency in the content they generate. To address these limitations, retrieval augmented generation (RAG) grounds the responses of LLMs by exposing them to external knowledge sources. However, in the healthcare domain there is currently a lack of systematic understanding of which datasets, RAG methodologies and evaluation frameworks are available. This review aims to bridge this gap by assessing RAG-based approaches employed by LLMs in healthcare, focusing on the different steps of retrieval, augmentation and generation. Additionally, we identify the limitations, strengths and gaps in the existing literature. Our synthesis shows that proprietary models such as GPT-3.5/4 are the most used for RAG applications in healthcare. Also, there is a lack of standardized evaluation frameworks for RAG-based applications. In addition, the majority of the studies do not assess or address ethical considerations related to RAG in healthcare. It is important to account for ethical challenges that are inherent when AI systems are implemented in the clinical setting. Lastly, we highlight the need for further research and development to ensure responsible and effective adoption of RAG in the medical domain.

For better solving both fuzziness and reliability occurring in practical issues simultaneously, Z-number deserves further exploration under uncertainty environment. Based on the credibility distribution and conversion rules, we define its expected value, variance, and semi-variance, and realize the feasibility of calculation by deriving calculation formulas. Moreover, we delve into three characteristics inherent in symmetrical Z-numbers. The link that followed between the variance and the semi-variance of Z-numbers is discovered and proved. Furthermore, we apply the formulas of expected value and variance on Z-numbers to examples, whose consequences validate our proposed formulas. The findings indicate the significance of our study in applying the expected value and variance of fuzzy sets across diverse fields.

This paper presents a repository of image databases where the image features are augmented with embedded vector field (VF) features to enhance the machine learning (ML) and increase classification statistics. Six VFs are formulated and used for the purpose of embedding. Three of them generate real shaped singular points (SPs): springing, sinking and saddle. The other three VFs generate seven kinds of SPs which include the real shaped SPs and four complex shaped SPs: repealing and attracting (out and in) spirals; clockwise and counterclockwise orbits (center). Also, the paper describes the VF singularities, their shapes, and locations according to the image objects. Then, the present work defines the mappings between the SPs’ shapes if the VFs are separately embedded into the same image. Thus, the paper infers which VFs are most appropriate for embedding into a particular image database such that the augmented SPs shapes enhance the ML classification. Examples of images with different embedded VFs are shown, in the text, to support and validate the theoretical conclusions. The contributions of the paper are: a description of the SPs location in an image; the mappings between the SPs of the different VFs; the definition of an imprint of an image in a VF; the generation of databases’ imprints. The advantage of classifying an image database with embedded VFs is that the new database enhances ML and improves the classification statistics if compared to the classification of the original image database with the same ML classifier. Furthermore, images with embedded SPs create a useful augmentation to the original image databases.

Article explores participant specific study of muscle inherehit dynamics hidden inside the diognostic electromyography (D-EMG) signals during load pull exercises, aiming to uncover underlying patterns and nonlinear behaviors. Employing a multi-step analytical framework, the study first evaluates signal stationarity through Quantile-Quantile (Q-Q) plot and surrogate data analyses, revealing insights into signal stability. Subsequent use of phase space reconstruction techniques exposes intrinsic dynamics within the EMG signals, visualized through Poincar´e maps, elucidating attractor geometry and system dynamics. Histogram analysis further dissects the Poincar´e maps, offering insights into signal behavior relative to physiological processes. Additionally, the study quantifies the largest Lyapunov exponent from the Poincar´e maps, providing a measure of dynamical complexity within the muscle EMG signals during load pull exercises. By integrating these methods, this research sheds light on the nuanced interplay between EMG signals and muscle activity during dynamic exercises, offering valuable insights for rehabilitation strategies.

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

Traditional 3D reconstruction models have consistently encountered a challenge: attaining high recall of object edges while preserving precision. In this paper, we introduce a post-processing method Multi-Head Attention Refiner (MA-R) aimed at tackling this challenge by integrating a multi-head attention mechanism within the U-Net style refiner module. The 3D reconstruction model applying this method demonstrates excellence in parsing intricate image details, resulting in significant enhancement of boundary predictions and increased recall rates. In our experiments, our method significantly enhances the reconstruction performance of Pix2Vox++ when multiple images are utilized as input. Specifically, it achieves an enhanced Intersection Over Union score of approximately 1.1% compared to the original Pix2Vox++ model when 16-view images are employed.

This study explores the limitations of current AI systems, which predominantly function in the digital realm, and investigates the transformative potential of embodied AI. Embodied AI involves AI agents equipped with physical bodies, enabling them to interact directly with the physical world. This research focuses on how embodied AI can bridge the "embodiment gap" and enhance human-machine collaboration and learning in dynamic environments. The research examines the fundamental differences between traditional AI systems and embodied AI, emphasizing the importance of physical interaction for contextual understanding, adaptive learning, and intuitive human-machine collaboration. It explores various applications of embodied AI, including robotics, autonomous vehicles, and assistive technologies, demonstrating how physical embodiment can improve performance, safety, and user experience. Through experimental studies and real-world case analyses, the study highlights the advantages of embodied AI in tasks requiring situational awareness, dexterity, and real-time decision-making. It also addresses the challenges associated with developing and deploying embodied AI systems, such as sensor integration, real-time processing, and human-machine interface design. Findings indicate that embodied AI can significantly improve the efficacy of AI systems in dynamic and unpredictable environments. By leveraging physical embodiment, AI agents can better understand and respond to their surroundings, facilitating more natural and effective interactions with humans. The research concludes with recommendations for advancing embodied AI, including interdisciplinary collaboration, investment in sensor and actuator technologies, and the development of standardized frameworks for embodied intelligence.

Accurate segmentation of skin lesions from dermoscopic images is crucial for early skin cancer detection, yet variations in lesion appearance and image artifacts present challenges. This study proposes two deep learning models, UCM-NetV2 and BNN-UCM-NetV2, to improve accuracy and computational efficiency. UCM-NetV2 enhances the UCM-Net architecture with a novel "cyber-structure" combining Multilayer Perceptron and CNN layers, improving prediction accu-racy without increasing the model's parameter count. BNN-UCM-NetV2 further optimizes for mobile deployment by binarizing activations and weights into 1-bit values, reducing computa-tional complexity and model size. Evaluations on the ISIC2017 and ISIC2018 datasets demonstrate that UCM-NetV2 outperforms existing methods in both accuracy and computational efficiency, achieving this with less than 0.04 GFLOPs. These models have the potential to make skin lesion analysis accessible to a broader population, particularly in resource-limited settings, allowing for proactive skin health monitoring and facilitating teledermatology. To foster further innovation in mobile health diagnostics, the source code for UCM-NetV2 will be available on GitHub: https://github.com/chunyuyuan/UCMV2-Net.

The integration of Artificial Intelligence (AI) into education has the potential to revolutionize traditional teaching and learning methods. AI can offer personalized learning experiences, streamline administrative tasks, enhance feedback mechanisms, and provide robust data analysis. Numerous studies have demonstrated the positive impact of AI on both student outcomes and teacher efficiency. However, caution must be exercised when implementing AI in education, considering potential risks and ethical dilemmas. It is essential to use AI as a tool to support human educators rather than replace them entirely. The adoption of AI in education holds the promise of creating more inclusive and effective learning environments, catering to students of diverse backgrounds and abilities. As AI technology continues to advance, the education sector can anticipate even more innovative applications, further shaping the future of learning. This abstract provides an overview of the multifaceted landscape of AI in education, highlighting its potential benefits, associated challenges, and the importance of responsible integration.

The revolutionary idea of complementary intelligence involves a unique strategy in which artificial intelligence (AI) works with human cognitive abilities embodied by natural intelligence (NI), creating a harmonious partnership instead of engaging in a competitive relationship. This innovative concept can potentially revolutionize how we approach scientific research and discovery. This cutting-edge process capitalizes on pooling the vast information from various distinct and autonomous sources to generate forecasts that frequently outshine human perspectives by significant margins, leading to groundbreaking advancements in scientific development based on hybrid intelligence. Multilayer networks extend traditional network theory to adjacent layers linked through copula nodes. Artificial intelligence, with its retrieval capacity to collect and interpret big data, sharply increases the number of nodes and their linking interpretation. This process, amplified by multilayer networks, dramatically improves the scalability of the networked ecosystem. Multilayer networks can represent NI and AI in complementary hyperplanes, connecting them with copula nodes and edge properties. Thus, it is possible to measure the interaction of NI and AI, assessing their scalable value co-creation properties. This study examines the interaction of NI and AI with an innovative and multidisciplinary approach. A theoretical framework of these related concepts precedes practical insights for possible applications in future research.

Strip steel surface defect recognition research has important research significance in industrial production. Aiming at the problems of defect feature extraction difficulty, slow detection speed and insufficient dataset, YOLOv5 is improved on the basis of YOLOv5, and YOLO-LFPD (Lightweight fine particle detection) model is proposed. By introducing the RepVGG (Re-param VGG) module, the robustness of the model to the surface defect features of strip steel is enhanced, and the expressive ability of the model is improved. FasterNet is used to replace the backbone network, which ensures the accuracy and accelerates the inference speed, making the model more suitable for real-time monitoring. The use of pruning, GA genetic algorithm with OTA loss function method further reduces the model size while better learning the strip steel defect feature information, thus improving the generalisation ability and accuracy of the model. The experimental results show that the introduction of the RepVGG module and the use of FasterNet can well improve the model performance, with a reduction of 48% in the number of parameters, a reduction of 13% in the number of GFLOPs, an inference time of 77% of the original, and an optimal accuracy compared with the network models in recent years. The experimental results on the NEU-DET dataset show that the accuracy of YOLO-LFPD is improved by 3% to 81.2%, which is better than other models, and provides new ideas and references for the lightweight strip steel surface defect detection scenarios and application deployment.

Incorporating knowledge graphs as auxiliary information to enhance recommendation systems can improve the representations learning of users and items. Recommendation methods based on knowledge graph can introduce user-item interaction learning into the item graph, focusing only on learning the node vector representations within a single graph; alternatively, they can treat user-item interactions and item graphs as two separate graphs and learn from each graph individually. Learning from two graphs has natural advantages in exploring original information and interaction information, but faces two main challenges: 1) in complex graph connection scenarios, how to adequately mine the self-information of each graph, and 2) how to merge interaction information from the two graphs while ensuring that user-item interaction information predominates. Existing methods do not thoroughly explore the simultaneous mining of self-information from both graphs and effective interaction information, leading to the loss of valuable insights. Considering the success of contrastive learning in mining self-information and auxiliary information, this paper proposes a dual-graph contrastive learning recommendation method based on knowledge graphs (KGDC) to explore a more accurate representations of users and items in recommendation systems based on external knowledge graphs. In the learning process within the self-graph, KGDC has strengthened and represented the information of different connecting edges in both graphs, and extracted the existing information more fully. In interactive information learning, KGDC reinforces the interaction relationship between users and items in the external knowledge graph, realizing the leading role of the main task. We have conducted a series of experiments on three standard datasets, and the results show that the proposed method can achieve better results.

Detecting cracks in structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features, suitable for deployment on drone platforms with limited computational power and memory. CrackScopeNet features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead and a stripe-wise context attention mechanism to enhance the capture of long-range contextual information, mitigating the interference from complex backgrounds. Experimental results on CrackSeg9k dataset demonstrate that CrackScopeNet leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, while maintaining a lightweight architecture with only 1.05M parameters and 1.58G floating point operations (FLOPs). Besides, CrackScopeNet excels in inference speed on edge devices without GPU because of its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks, suitable for practical structural health monitoring applications using drone platforms.

This study involves the development of a hybrid forecasting framework that integrates two different models in a framework to improve prediction capability. Although the concept of hybridization is not a new issue in forecasting, our approach presents a new structure that combines two standard simple forecasting models uniquely for superior performance. Hybridization is significant for complex data sets with multiple patterns. Such data sets do not respond well to simple models, and hybrid models based on the integration of various forecasting tools often lead to better forecasting performance. The proposed architecture includes serially connected ARIMA and ANN models. The original data set is first processed by ARIMA. The error (i.e., residuals) of the ARIMA is sent to the ANN for secondary processing. Between these two models, there is a classification mechanism where the raw output of the ARIMA is categorized into three groups before they are sent to the secondary model. The algorithm is tested on well-known forecasting cases from the literature. The proposed model performs better than existing methods in most cases.

Digital recruitment systems have revolutionized the hiring paradigm, imparting exceptional efficiencies and extending the reach for both employers and job seekers. This investigation scrutinizes the efficacy of classical machine learning methodologies alongside advanced large language models (LLMs) in aligning resumes with job categories. Traditional matching techniques, such as Logistic Regression, Decision Trees, Naïve Bayes, and Support Vector Machines, are constrained by the necessity of manual feature extraction, limited feature representation, and performance degradation, particularly as dataset size escalates, rendering them less suitable for large-scale applications. Conversely, LLMs like GPT-4, GPT-3, and LLAMA, adeptly process unstructured textual content, capturing nuanced language and context with greater precision. We evaluate these methodologies utilizing two datasets comprising resumes and job descriptions to ascertain accuracy, efficiency, and scalability. Our results reveal that while conventional models excel with structured data, LLMs significantly enhance the interpretation and matching of intricate textual information. This study highlights the transformative potential of LLMs in recruitment, offering insights into their application and future research avenues.

Mobile devices (MD) are used by mobile cloud computing (MCC) customers users because of their 11 portability and robust connectivity and the ability to house and operate third-party applications 12 (apps). However, the apps installed on a MD may pose data security risks to the MD owner and to 13 other MCC users, especially when the requested permissions include access to sensitive data (e.g., 14 user’s location and contacts). Calculating the risk score of an app or quantifying its potential 15 harmfulness based on user input or on data gathered while the app is actually running may not 16 provide reliable and sufficiently accurate results to avoid harmful consequences. This study 17 develops and evaluates a risk assessment framework for Android-based MDs that does not depend 18 on user input or on actual app behaviour. Rather, an app risk evaluator assigns a risk category to 19 reach resident app based on the app’s classification (benign or malicious) and the app’s risk score. 20 The app classifier (a trained machine learning model) considers the permissions and the intents 21 requested by the app. The apps risk score is calculated by a probabilistic function based on the 22 app’s use of a set of selected dangerous permissions. The results from the testing of an instance of 23 the framework on a MD with real-life resident apps indicated that the proposed security solution 24 was effective and feasible.

Introduction: In Traditional Chinese Medicine (TCM), tongue diagnosis plays an important role. Besides shape, colour and textural attributes of tongue regions have significance due to their association with different organs (viz. heart, lung, kidney-bladder, liver-gallbladder and stomach-spleen) in health and disease. Although numerous quantitative methods have been proposed to reduce inter and intra observer variability in tongue diagnosis, almost all of them considered only global colour/ textural features i.e. from entire body of tongue. In this work, regional colour and texture information of tongue have been analysed for healthy subjects (NOM) and patients suffering from chronic acidity-indigestion (ACD). Methods: Tongue boundaries are marked manually in each image and then tongue bodies are automatically partitioned into five regions linked with said internal organs. Rough assessments of regions’ boundaries are obtained from literature and then they are fine-tuned according to experts’ advice. As boundaries are not well defined, regions near the common boundary of two or more organs, are not assigned to any organ. Several first and second order statistical features based on grey scale intensities and a* values of LAB colour space (indicative of redness) have been extracted from five different regions of tongue images. Intragroup analysis using Wilcoxon signed rank test compared different regions within individual study group. Additionally, intergroup analysis using Wilcoxon rank sum test compared tongues of NOM with ACD for each region separately. Results: Intragroup analysis reveals a* values are statistically different (p<0.01) between stomach-spleen and liver-gallbladder regions for ACD while no significant change of a* are noted between these regions of normal tongue. It was found from intergroup analysis that correlation (one of the second order texture features extracted from grey scale images) of heart region has significantly decreased while correlation of kidney, liver-gallbladder and stomach-spleen regions significantly increased from NOM to ACD. Conclusion: This study sheds light on importance of inclusion of regional textural analysis of tongue in quantitative studies and can be applied to automated tongue diagnosis for other diseases.

The emerging and promising paradigm of the Internet of Vehicles (IoV) employ vehicle-to-everything communication for facilitating vehicles to not only communicate with one another but also with the supporting roadside infrastructure, vulnerable pedestrians, and the backbone network in a bid to primarily address a number of safety-critical vehicular applications. Nevertheless, owing to the inherent characteristics of IoV networks, in particular, of being (a) highly dynamic in nature and which results in a continual change in the network topology and (b) non-deterministic owing to the intricate nature of its entities and their interrelationships, they are susceptible to a number of malicious attacks. Such sort of attacks, if and when materializes, jeopardizes the entire IoV network, thereby putting the human lives at risk. Whilst the cryptographic-based mechanisms are capable of mitigating the external attacks, the internal attacks are extremely hard to tackle. Trust, therefore, is an indispensable tool since it facilitates in the timely identification and eradication of malicious entities responsible for launching internal attacks in an IoV network. To date, there is no dataset pertinent to trust management in the context of IoV networks and the same has proven to be a bottleneck for conducting an in-depth research in this domain. The manuscript-at-hand, accordingly, presents a first of its kind trust-based IoV dataset encompassing 96,707 interactions amongst 79 vehicles at different time instances. The dataset involves 9 salient trust parameters, i.e., packet delivery ratio, similarity, external similarity, internal similarity, familiarity, external familiarity, internal familiarity, reward / punishment, and context, which play a considerable role for ascertaining the trust of a vehicle within an IoV network.

Synthetic Aperture Radar has been extensively used in numerous fields and can gather a wealth of information about the area of interest. This large-scene data-intensive technology puts a high value on automatic target recognition (ATR) which can free the utilizers and boost the efficiency. Recent advances in artificial intelligence have made it possible to create a deep learning-based SAR ATR that can automatically identify target features from massive input data. In the last 6 years, intensive research has been conducted in this area, however, most papers in the current SAR ATR field used recurrent neural network (RNN) and convolutional neural network (CNN)-varied models to deepen the regime’s understanding of the SAR images. To equip SAR ATR with updated deep learning technology, this paper tries to apply a lightweight vision transformer (LViT)-based model to classify SAR images. The entire structure was verified by an open- accessed SAR data set and recognition results show that the final classification outcomes are robust and more accurate in comparison with referred traditional network structures without even using any convolutional layers.

Some business license commitments in online single submission (OSS) currently only consist of an independent statement from the business actor, and there is no time limit for fulfilling the license, especially for low-risk bio-business licenses. Therefore, a system design is needed to monitor the fulfillment of business license commitments and to provide confidence to the public regarding the business provided. The system design started with discussing the importance of smart governance tools, defining the requirements for monitoring the commitment of bio-business licenses, selecting documents, determining important words and document types, and proposing a design. This research produces a prototype of a business license monitoring system. This smart governance tool checks the validity of business license documents. The proposed smart governance tool will overcome the complexity of the integration process for fulfilling business licenses from the Indonesian government units or agency systems with the OSS system. Apart from that, it is also very effective by looking at the thousands of government applications that currently exist and the desire to become one application solution that contains many functions that can fulfill the many needs of business actors for simple and transparent business licenses.

The rapid proliferation of Internet of Things (IoT) technology has ushered in a new era of connectivity, allowing billions of devices to produce extensive data. Significant challenges in software engineering need to be addressed for full utilization of Internet of Things (IoT) applications. This article examines the challenges in Internet of Things, software engineering and discusses current developments aimed at addressing these issues and seizing new opportunities. We examine the challenges associated with Internet of Things software development, including resource constraints, device diversity, security vulnerabilities, and data management concerns. New studies have indicated the use of advanced techniques like as containerization, model-driven development, AI and ML integration, and robust security frameworks. Moreover, the significance of system architecture is explained, including the device, network, and cloud layers, with an emphasis on the principles of reusability, scalability, and modularity. Results and conversations explore the complexities of security measures, emerging opportunities, and scaling solutions made possible by simulation tools, penetration testing, and cross-domain development platforms. The study expects IoT system evolution and emphasises the need for continual software and firmware changes, testing, and deployment.

There is a lot of pressures from organizations to continually redesign the business processes and the technology infrastructure to support the organization, but to also help organizations manage competing stakeholder needs, changing objectives and behaviour, and so on. A key part of this is making sure that all their activities in the different components of the business are interconnected and that they are moving in the same direction. Enterprise Architecture (EA) is an effective way of dealing with the challenge of designing business activities and supporting IT. This paper will summarize the organization of EA and look more closely at some major components of EA: governance architecture, business architecture, information architecture and technical architecture and consider the overlap and constructive interaction involved. Enterprise Architecture can be best understood through business process redesign. So, it is useful to briefly review the leading frameworks for business process redesign, including COBIT from ISACA, LEAN from the Toyota Group, TOGAF from the Object-Management Group, and the Capgemini Integrated Architecture Framework (IAF). All these frameworks allow us to more successful transformation, to return to the central idea of this paper.

This research article provides an unconditional proof of an inequality proposed by \textit{Srinivasa Ramanujan} involving the Prime Counting Function $\pi(x)$, \begin{align*} (\pi(x))^{2}<\frac{ex}{\log x}\pi\left(\frac{x}{e}\right) \end{align*} for every real $x\geq \exp(1486)$, using specific order estimates of the \textit{Mertens Function}, $M(x)$. The proof primarily hinges upon investigating the underlying relation between $M(x)$ and the \textit{Second Chebyshev Function}, $\psi(x)$, in addition to applying the meromorphic properties of the \textit{Riemann Zeta Function}, $\zeta(s)$ with an intention of deriving an improved approximation for $\pi(x)$.

Dams significantly impact the environment, industry, residential areas, and agriculture. Efficient dam management can mitigate negative impacts and enhance benefits such as flood and drought reduction, energy efficiency, water access, and improved irrigation. This study tackles the critical issue of predicting dam occupancy levels precisely within the framework of Integrated Water Resource Management (IWRM). Our research proposes that combining the physical model of evapotranspiration using the Penman–Monteith equation with data-driven models based on historical reservoir data, weather data, and consumption data is essential for accurately predicting occupancy levels. We implemented various prediction models, including Random Forest, Extra Trees, Long Short-Term Memory, Orthogonal Matching Pursuit CV, and Lasso Lars CV. To strengthen our proposed model with robust evidence, we conducted a statistical test on the MAPE values. We achieved a remarkable accuracy in predicting the occupancy level one month ahead, with an error margin of just 1% using Extra Trees. This study represents a pioneering effort in providing guidance and proposing a hybrid model in this field.

This study presents extended Immunity Agent-Based Model (IABM) simulations to evaluate vaccination strategies in controlling the spread of infectious diseases. The application of IABM in the analysis of vaccination configurations is innovative, as a vaccinated individual can be infected depending on how their immune system acts against the invading pathogen, without a pre-established infection rate. Analysis at the microscopic level demonstrates the impact of vaccination on individual immune responses and infection outcomes, providing a more realistic representation of how the humoral response caused by vaccination affects the individual’s immune defense. At the macroscopic level, the effects of different population-wide vaccination strategies are explored, including random vaccination, targeted vaccination of specific demographic groups, and spatially focused vaccination. The results indicate that increased vaccination rates are correlated with decreased infection and mortality rates, highlighting the importance of achieving herd immunity. Furthermore, strategies focused on vulnerable populations or densely populated regions prove to be more effective in reducing disease transmission compared to randomly distributed vaccination. The results presented in this work show that vaccination strategies focused on highly crowded regions are more efficient in controlling epidemics and outbreaks. Results suggest that applying vaccination only in the densest region resulted in the suppression of infection in that region, with less intense viral spread in areas with lower population densities. Strategies focused on specific regions, in addition to being more efficient in reducing the number of infected and dead people, reduce costs related to transportation, storage, and distribution of doses compared to the random vaccination strategy. Considering that, despite scientific efforts to consolidate the use of mass vaccination, the accessibility, affordability, and acceptability of vaccines are problems that persist, investing in the study of strategies that mitigate such issues is crucial in the development and application of government policies that make immunization systems more efficient and robust.

This work considers the existence of heteroclinic solutions for second order differential equations with ϕ-Laplacians and generalized impulsive conditions on the real line. For the construction of the results, it was only imposed that ϕ is a homeomorphism and the Schauder’s fixed point theorem allied with the concepts of L1-Carathéodory functions and sequences together with the equiconvergence on infinity and on each impulsive moments. Finally, a practical part illustrates the main theorem.

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

The importance of XAI is undeniable in the current scenario and thus it's importance in considerable. Unfortunately, there are a couple of scenarios where the current XAI models fail. Additionally, attackers seek vulnerabilities in these models. This review paper is intended to cover some of the important scenarios where the existing XAI models may fail and some progresses made which shows their vulnerabilities and how to secure them.

The application of deep learning in autonomous vehicles has surged over the years with the advances in technologies. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows that deep learning, which as a part of machine learning, mimics the human brain's neural networks, enabling advancements in perception, decision-making, localization, mapping, and overall navigation. Techniques like convolutional neural networks are used for image detection and steering control, while deep learning is crucial for path planning, automated parking, and traffic maneuvering. Localization and mapping are essential for AVs' navigation, with deep learning-based object detection mechanisms like Faster R-CNN and YOLO proving effective in real-time obstacle detection. Apart from the roles, the study also revealed that integration of deep learning in AVs faces challenges such as dataset uncertainty, sensor challenges, and model training intricacies. However, these issues can be addressed through increased standardization of sensors, real-life testing for model training, and advancements in model compression technologies can optimize the performance of deep learning in AVs. The study concludes that deep learning plays a crucial role in enhancing the safety and reliability of AV navigation. This study contributes to the ongoing discourse on the optimal integration of deep learning in AVs, aiming to foster their safety, reliability, and societal acceptance.

Stress has various impacts on the health of human beings. Recent success in wearable sensor development, combined with advancements in deep learning to automatically detect features from raw data, opens several interesting applications related to detecting emotional states. Being able to accurately detect stress-related emotional arousal in an acute setting can positively impact the imminent health status of humans, i.e., through avoiding dangerous locations in an urban traffic setting. This work proposes an explainable deep learning methodology for the automatic detection of stress in physiological sensor data, recorded through a non-invasive wearable sensor device, the Empatica E4 wristband. We propose an Long-Short Term-Memory (LSTM) network, extended through a Deep Generative Ensemble of conditional GANs (LSTM DGE) , to deal with the low data regime of sparsely labeled sensor measurements. As explainability is often a main concern of deep learning models, we leverage Integrated Gradients (IG) to highlight the most essential features used by the model for prediction and to compare the results to state-of-the-art expert-based stress detection methodologies in terms of precision, recall and interpretability. Results show that our LSTM DGE outperforms the state-of-the-art algorithm by 3 percentage points in terms of recall, and 7.18 percentage points in terms of precision. More importantly, through the use of Integrated Gradients as a layer of explainability, we show that there is a strong overlap between model-derived stress features for electrodermal activity, and existing literature, which current state-of-the-art stress detection systems in medical research and psychology are based on.

We consider a system of two coupled parallel queues, queue 1 and queue 2, with infinite waiting rooms. The time setting is discrete. In either queue, the service of a customer requires exactly one discrete time slot. Arrivals of new customers occur independently from slot to slot, but the numbers of arrivals of both types within a slot may be mutually interdependent. Their joint probability generating function (pgf) is indicated as A(z1, z2) and characterizes the whole model. It is well-known that, in general, determining the steady-state joint probability mass function (pmf) u(m, n), m, n ≥ 0 or the corresponding joint pgf U(z1, z2) of the system contents (i.e., numbers of customers present) in both queues is a formidable task. Only in a number of isolated cases, for very specific choices of the arrival pgf A(z1, z2), explicit results are known in the literature. In this paper, we identify a multiparameter, generic class of arrival pgfs A(z1, z2), for which we can explicitly determine the system-content pgf U(z1, z2). We find that, for arrival pgfs of this class, U(z1, z2) has a denominator which is a product, say r1(z1)r2(z2) of two univariate functions. This property allows a straightforward inversion of U(z1, z2), resulting in a pmf u(m, n) which can be expressed as a finite linear combination of bivariate geometric terms. We also observe that our generic model encompasses most of the previously known results as special cases.

Fusing data from many sources helps to achieve higher results of analysis. In this work, we present a new algorithm to fuse data from multiple cameras with data from multiple lidars. This algorithm was developed to increase the sensitivity and specificity of autonomous vehicle perception systems, where the most accurate sensors measuring the vehicle’s surroundings are cameras and lidar devices. Perception systems based on data from one type of sensor do not use complete information and have lower quality. The camera provides two-dimensional images; lidar produces three-dimensional point clouds. We developed a method for matching pixels on a pair of stereoscopic images using dynamic programming inspired by an algorithm to match sequences of amino acids used in bioinformatics. We improve the quality of the basic algorithm using additional data from edge detectors. We also improve the algorithm performance by reducing the size of matched pixels determined by available car speeds. We perform point cloud densification in the final step of our method, fusing lidar output data with stereovision output. We implemented our algorithm in C++ with Python API, and we provided the open-source library named Stereo PCD. This library very efficiently fuses data from multiple cameras and multiple lidars. In the article, we present the results of our approach to benchmark databases in terms of quality and performance. We compare our algorithm with other popular methods.

Training artificial intelligence (AI) for reasoning presents significant challenges due to the lack of clear objectives and reward functions. In structured environments such as chess and Go, objectives are well-defined, and the optimal moves can be determined through search algorithms that maximize the reward function. This clarity enables AI to learn and improve autonomously through random trials and recursive calculation of rewards, mirroring human learning processes that depend on prior experiences and state-dependent actions. However, in real-world applications, AI lacks access to direct interaction and feedback, making it difficult to define proper reward functions. This limitation is particularly evident in the training of large language models (LLMs), where the quality of the output is constrained by the training data and the absence of a dynamic reward system. Simulated environments offer some utility but are inherently limited by their design and scope. Achieving artificial general intelligence (AGI) requires AI to function and receive feedback in real-world settings, similar to human cognitive and strategic development through interactive experiences. This paper explores the critical role of clear objectives and reward functions in AI training, the limitations posed by the current lack of real-world interaction, and the implications for future advancements in AI reasoning capabilities.

We will try to use the approach of labeled cycle cover sum to count the number of hamiltonian cycles in a special type of bipartite graphs, with 4k + 2 vertices which can also be considered as an alternative method to check hamiltonicity in such bipartite graphs. This graph is such that, there exists at least 1 vertex which is not a part of any cycle of size 4m + 2 where m < k, in O∗(1.414n) time. The algorithm is inspired by Bjorklund’s approach where instead of working on the field of GF(2k), we will be working on C.

The rapid growth of the global population is causing a significant increase in waste production, leading to serious environmental and public health challenges. To address these issues, waste management systems are incorporating advanced technologies. Machine learning and computer vision are used to predict waste patterns, optimize collection schedules, and improve sorting accuracy. Deep learning automates the sorting process, provides predictive analytics, and enhances recycling rates. Robotics, combined with AI and computer vision, improves sorting efficiency, while the Internet of Things (IoT) monitors waste levels and optimizes collection routes. Despite these benefits, challenges such as data scarcity, high computational demands, and the need for substantial infrastructure investments must be addressed. This research explores the integration of advanced technologies into waste management and evaluates their effectiveness using waste datasets. It highlights the potential to tackle environmental challenges and lay the groundwork for more intelligent waste management solutions.

In the fast-evolving landscape of web services, success relies on optimizing efficiency, reliability, and user satisfaction. Decision-making in real-world applications demands a blend of quantitative (numerical values of quality of Service factors) and qualitative data of experts’ ratings of the quality of service factors. This paper proposes an optimization technique that integrates Hesitant and Intuitionistic Fuzzy Linguistic Terms with TOPSIS, leveraging Entropy Objective weights. There is limited research on Hesitant Intuitionistic Fuzzy Linguistic terms and the need to model fuzziness, haste and intuition in data precisely from experts rating. Thus, this article introduces an Entropy-based model tailored for web service optimization. Using the WS-DREAM dataset, quantitative data was extracted and objective weights were determined through the Entropy algorithm and qualitative evaluations from five experts, employing Hesitant Intuitionistic Fuzzy Linguistic Terms, were integrated. The process involved computing criteria weights and experts' assessment of Quality of Service factors for four services (S1, S2, S3, and S4) to form the Fuzzy Decision Matrix using modified Online output software. Applying the proposed technique to a web service optimization problem validated its effectiveness. The results indicated optimal selection of S1 as the best web service, supported by Coefficient Index values (0.785). This study introduces a novel approach, Entrop – Hesitationistic - Fuzz-TOPSIS, for web service optimization, integrating quantitative and qualitative data through an Entropy-based model. The effectiveness of the proposed technique, validated through application on the WS-DREAM dataset, underscores its potential in addressing real-world decision-making challenges. The optimal selection of S1 as the best web service suggests practical utility. The study encourages further exploration of this technique's applicability to diverse Multiple Criteria Decision Making (MCDM) problems, opening avenues for future research and application.

In the fast-changing world of software development, the protection of software products has emerged as an imperative requirement. This paper presents a new way to increase the maturity of development teams to reach the highest level of software security. Based on these, the framework uses the Fuzzy Analytic Hierarchy Process (Fuzzy-AHP) to systematically evaluate and enhance the people maturity of software development projects. The essence of the fuzzy logic and AHP technique interaction is to handle the uncertainty and complexity of human factors and team dynamics in the evaluation framework. Using the decision-making model allows the project managers and stakeholders to determine the appropriate areas for improvement and develop the right strategies and actions to nurture a secure and mature development culture. The paper identifies 24 human success factors (HSFs) and human security vulnerabilities (HSVs) and 38 practices for addressing these HSFs and HSVs. Furthermore, we discuss the local and global ranks of each HSF and HSV practice and categorize the identified practices into 9 categories to determine the ranks and weight of each category. Based on collected data, FAHP prioritized these practices; the category “C4: Skill Development and Stakeholder Engagement” is ranked highest at rank-1 and possesses the most significant weight of 0.12435. Similarly, the highest global weight is 0.051506, and the global ranked (rank-1) HSF and HSV practice is “P15: Hands-On Practice and Stakeholder Communication”. Research evidence and case discussions show how the described framework assists in building secure software development (SSD) practices, which can be considered evidence of the application of team maturity to improve cybersecurity in organizations. Additional research directions include improving the framework, especially using highly developed learning techniques and applying the framework to other forms of development.

This paper presents Double Database Decomposition Framework, which integrates vertical and horizontal table decompositions to minimize data leakage due to intrusions. Vertical decompositions segregate sensitive attributes, while horizontal ones partition data based on user access patterns. In this way, the framework ensures that users access only the data necessary for their operations, adhering to the principle of least privilege. This double decomposition approach improves the robustness of the original database against impersonation attacks and limits the blast radius of potential intrusions. Furthermore, the framework significantly mitigates the risks associated with data breaches by confining unauthorized access to specific data subsets and restricting the exposure of sensitive information. Performance analysis highlights the trade-offs between robustness and overhead offered by distinct allocation strategies of the output of the decompositions to, among other, physical machines, virtual machines, and containers, to balance security and resource efficiency. We present a case study in a healthcare environment that confirms both the effectiveness of the framework and its applicability in complex systems where data security is paramount. By integrating advanced security measures and optimising data access, the framework results in a scalable and adaptable solution for enhancing database security and performance in various domains.

This project aims to simulate and analyze population dynamics in evolutionary systems, using stochastic differential equations and probabilistic rules for crossbreeding and benefits. The study employs advanced computational techniques to model the evolution of populations over an extended period. Specifically, we explore a scenario with ten distinct groups, each starting with an equal population and evolving under defined genetic and cooperative behaviors. The simulation spans 1000 years, incorporating individual lifespans, stochastic updates, and probabilistic interactions. To ensure robustness and reliability, the study includes detailed statistical analysis, encompassing descriptive statistics, confidence intervals, and ANOVA tests. We further visualize the temporal behavior of populations and subpopulations, providing insights into the evolutionary dynamics and stability of the system. The results demonstrate the effectiveness of balanced cooperation and genetic diversity in maintaining stable population distributions. The project showcases the integration of mathematical modeling, statistical analysis, and computational simulations, contributing valuable insights into evolutionary biology and complex systems. It highlights the importance of interdisciplinary approaches in understanding and predicting population behaviors, with implications for both theoretical research and practical applications in fields such as ecology, genetics, probability and social sciences.

Experiential learning, defined as the result, source, or context of knowledge obtained from direct experience, is increasingly bolstered by technology and human-computer interaction (HCI) principles and protocols. This article will describe how technology-based human-computer interaction (HCI) has been used in experiments to enhance direct knowledge experience. In this paper, immersive technologies (such as Virtual Reality, Augmented Reality, and haptics) will be described based on cognitive learning theory, empirical research and practical experience gained from implementing cutting-edge technology and maximizing HCI principles in constructive learning. Additionally, this article will describe how AI can be used to create individualized learning environments according to a student's needs in the future. While cost, technical issues and specialised trainings are the obstacle to deliver personalized learning experiences especially to economically disadvantaged students, technological change opportunities are projected, and these technologies will take educational outcomes to the next level.

This study evaluates the effectiveness of Darknet53 and VGG16 pretrained models to develop a hybrid ensemble model named HybridPlantNet23 deep learning model for effective plant disease classification, using the publicly available dataset ‘A Dataset of Leaf Images’ from Mendeley webpage. The preprocessing of the dataset involved resizing the images to the respective requirements of the pretrained models to develop a combined datastore which served as the input. All experiments were conducted using MATLAB R2023b deep network designer interface. Model performances were evaluated based on the conventional accuracy, precision, recall, and F1-score. VGG16 achieved the highest accuracy (97.25%), precision (96.30%), recall (96.96%), and F1-score (96.55%), outperforming both Darknet53 and the ensemble HybridPlantNet23 model. Despite the advanced architecture of the ensemble model, its performance (accuracy: 95.37%, precision: 93.56%, recall: 94.20%, F1-score: 93.74%) was not significantly superior, thus highlighting scientific reasons behind this development. Recommendations for future works were provided accordingly.

The complex network is an abstract modeing of complex systems in the real world, which plays an important role in analyzing the function of complex systems. Community detection is an important tool for analyzing network structure. In this paper, we propose a new community detection algorithm (RWBS) based on different seed nodes aims to understand the community structure of the network, which provides a new idea for the allocation of resources in the network. RWBS provides a new centrality metric ($MC$) to calculate node importance, which calculates the ranking of nodes as seed nodes. Furthermore, two algorithms are proposed for determining seed nodes on networks with and without ground-truth, respectively. We set the number of steps for the random walk to 6 according to the six degrees of separation theory to reduce the running time of the algorithm. Since some traditional community detection algorithms may detect smaller communities, e.g., two nodes become one community, this may make the resource allocation unreasonable. Therefore, modularity ($ Q $) is chosen as the optimization function to combine communities, which can improve the quality of detected communities. Final experimental results on real-world and synthetic networks show that the RWBS algorithm can effectively detect communities.

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, through the review of traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to effectively improve abnormal traffic detection's accuracy and efficiency. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

Recent research underscores the potential hazards that Backdoor Attacks pose to natural language processing (NLP) models. A thorough exploration of these attack methodologies is critical for comprehending the susceptibility of such models. Under normal circumstances, a model compromised by a backdoor attack will produce standard outputs; however, the presence of a specific trigger within the input leads to erroneous results. This paper focuses on the vulnerability of BERT, a widely recognized model in numerous NLP applications, by introducing a novel backdoor attack strategy that effectively compromises it. We manipulate the attention heads in BERT to enhance the backdoor attack. The efficacy of this method is demonstrated through experiments conducted on clean-label attack and a Sentiment Analysis task.

This study investigates anomaly detection of IoT device traffic using Convolutional Neural Networks (CNN) and Variational Autoencoders (VAE) to enhance the detection capability of security threats in IoT environments. A series of hardware configurations, software environments, and hyperparameters were utilized to optimize the training and testing processes of the models. The CNN model demonstrates robust classification performance, achieving an accuracy rate of 95.85% on the test dataset, effectively distinguishing between different types of IoT device traffic. Meanwhile, the VAE model exhibits proficient anomaly detection capabilities by effectively capturing abnormal patterns in the data using reconstruction loss and KL divergence. The combined use of CNN and VAE models offers a comprehensive solution to cybersecurity challenges in IoT environments. Future research directions include exploring diverse IoT traffic data, practical deployment for validation, and further optimization of model structures and parameters to improve performance and applicability.

This study introduces a novel method that combines Generative Adversarial Networks (GANs) with conformal prediction to revolutionize the domain of stock ticker forecasting. Our approach enhances prediction accuracy and offers dependable prediction intervals to gauge uncertainty, surpassing current GAN-based techniques in unpredictable market scenarios. We made a validation using AAPL stock data, showing the ability of our model to generate accurate forecasts and reliable assessments of prediction uncertainty. The prediction intervals generated provide investors and risk managers with a powerful tool to make informed decisions. Our approach represents a notable advancement in financial prediction as it improves the clarity and reliability of forecasts. By incorporating conformal prediction into the GAN framework, the reliability of forecasts is improved, providing a thorough evaluation of uncertainty that is crucial for successful risk management. This framework has the potential to transform the field of predictive analytics in finance. It shows a solution that balances accuracy and uncertainty quantification. The results clearly show the effectiveness of this method, paving the way for its potential application in a wide range of financial prediction scenarios.

Gastric cancer is the fifth most common and fourth deadliest cancer worldwide, with a bleak 5-year survival rate of about 20%. Despite significant research into its pathobiology, prognostic predictability remains insufficient due to pathologists’ heavy workloads and the potential for diagnostic errors. Consequently, there is a pressing need for automated and precise histopathological diagnostic tools. This study leverages Machine Learning and Deep Learning techniques to classify histopathological images into healthy and cancerous categories. By utilizing both handcrafted and deep features and shallow learning classifiers on the GasHisSDB dataset, we conduct a comparative analysis to identify the most effective combinations of features and classifiers for differentiating normal from abnormal histopathological images without employing fine-tuning strategies. Our methodology achieves an accuracy of 95% with the SVM classifier, underscoring the effectiveness of feature fusion strategies. Additionally, cross-magnification experiments produced promising results with accuracies close to 80% and 90% when testing the models on unseen testing images with different resolutions.

With the widespread application of artificial intelligence technology in various industries, users' attention to privacy and data security has increased significantly. Federated learning, as a new technology paradigm combining privacy-enhanced computing and artificial intelligence, resolves the contradiction between data security and open sharing. This paper presents the benefits of federated learning in terms of privacy, real-time processing, model robustness, compliance and cross-industry applications. At the same time, when combined with Edge AI technology, federated learning promotes the decentralisation of intelligent systems, improving data privacy protection and model accuracy. This paper also discusses the application cases of federated learning in the medical field, through local data processing and model training, effectively protecting user privacy, realizing medical data sharing and model optimization, and promoting the development of artificial intelligence.

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

Conventional tutoring approaches are confronted with limitations such as restricted availability, inconsistent pedagogical quality, and scalability con-straints. Furthermore, the exclusive use of Large Language Models (LLMs) like ChatGPT in education has its shortcomings, including the potential for incorrect responses and the lack of customized guidance aligned with specific course con-tent. This research proposes an innovative intelligent chatbot tutoring system, in-tegrating the Retrieval Augmented Generation (RAG) approach with a custom LLM. The developed system aims to overcome the limitations of traditional tu-toring and general-purpose LLMs by providing accurate, contextually relevant, and personalized assistance, thereby enhancing student understanding and en-gagement. The system, powered by an intelligent agent, retrieves relevant information from curated academic sources, incorporates interactive features for user feedback, and utilizes machine learning algorithms for ongoing performance enhancement, ensuring a robust and effective tutoring experience. The anticipated outcome is an enriched educational experience for university students, advance-ment in personalized learning, and improved student engagement, retention, and academic performance. Through continuous research and refinement, it is expected that the intelligent chatbot tutor will assume an important role in enhancing and supporting the educational journey of students.

Public safety and intelligent surveillance systems critically depend on anomaly behavior detection for effective monitoring. In real-world pedestrian detection scenarios, prevalent challenges such as missed detections, complex background interference, and small target sizes hinder accurate anomaly identification. To address these issues, this study introduces YOLO-ABD, a lightweight method for anomaly behavior detection that integrates small target detection and channel shuffling. This method employs YOLOv8n as the baseline model, incorporating a small target detection mechanism in the Head part and utilizing GSConv convolution in the Backbone to enhance perceptual capability. Additionally, the SimAM attention mechanism is integrated to mitigate complex background interference, thereby improving target detection performance. Evaluation on the IITB-Corridor dataset demonstrated mAP50 and mAP50-95 scores of 89.3% and 60.6%, respectively. Generalization testing on the street-view-gdogo dataset further highlighted the superiority of YOLO-ABD over advanced detection algorithms, underscoring its effectiveness and generalizability. With a relatively small parameter count, YOLO-ABD presents an excellent lightweight solution for pedestrian anomaly behavior detection.

Transportation plays an important role in urban development. Population growth and environmental burden have turned the efforts of cities globally towards smarter and greener mobility. Cooperative and Connected Automated Mobility (CCAM) serves as a concept with the power and potential to help achieve these goals building upon technological fields like Internet of Things, computer vision and distributed computing. However, its implementation is hindered by various challenges covering technical parameters such as performance and reliability in tandem with other issues, such as safety, accountability and trust. To overcome these issues, new distributed and decentralized approaches like blockchain and smart contracts are needed. This paper aims at identifying a comprehensive inventory of CCAM challenges and use it as a framework to describe methodologies using blockchain and smart contracts to address them. It provides a comparative analysis of the findings to draw useful conclusions and discuss future directions in CCAM and relevant blockchain applications. The paper contributes to intelligent transportation systems’ research by offering an integrated view of the difficulties in substantiating CCAM and providing insights on the most prominent blockchain and smart contract technologies that tackle them.

A mathematical procedure enabling the transformation of an arbitrary tessellation of a surface into a bi-colored complete graph is introduced. Polygons constituting the tessellation are represented by vertices of the graphs. Vertices of the graphs are connected by two kinds of links/edges, namely, by a green link, when polygons have the same number of sides, and by a red link, when the polygons have a different number of sides. This procedure gives rise to a semi-transitive, complete, bi-colored Ramsey graph. The Ramsey number was established as R_trans (3,3)=5. Shannon entropies of the tessellation and graphs are introduced. Ramsey graphs emerging from random Voronoi and Poisson Line tessellations were investigated. The limits ζ=lim┬(N→∞)⁡〖N_g/N_r 〗, where N is the total number of green and red seeds, N_g and N_r, were found ζ=0.272±0.001 (Voronoi) and ζ= 0.47±0.02 (Poisson Line). The Shannon Entropy for the random Voronoi tessellation was calculated as S= 1.690±0.001 and for the Poisson line tessellation as S =1.265±0.015.

Multimodal knowledge graph completion necessitates the integration of information from multiple modalities (such as images and text) into the structural representation of entities to improve link prediction. However, most existing studies have overlooked the interaction between different modalities. To address this issue, this paper proposed a Transformer-based knowledge graph link prediction model (MM-Transformer) that fuses multimodal features. Different modal encoders are employed to extract structural, visual and textual features, and hybrid key-value calculations are performed on features from different modalities based on the Transformer architecture. The similarities of textual tags to structural tags and visual tags are calculated and aggregated respectively, and multimodal entity representations are modeled and optimized to reduce the heterogeneity of the representations. Experimental results demonstrate that, compared to the current multimodal state-of-the-art methods, the proposed method achieves significant performance improvements in knowledge graph link prediction tasks. This proves that the proposed method effectively addresses the problem of multimodal feature fusion in knowledge graph link prediction tasks.

Finite-time control theory has been widely used as a mathematical tool to design robust controllers. By manipulating the finite-time convergence proof of this theory, we developed a new control design appropriately tuned for the finite-time control of the chaotic logistics system. In our experimental setup, the logistic equation is programmed into a PIC microcontroller, and a part of the controller was conceived using analog electronics. Because the system to be controlled is in the discrete-time domain, and the finite-time stability proof is stated in the continuous-time representation, our finite-time control approach is a good example for designing control algorithms in both time domain schemes. Hence, our experimental results support our main contribution. Pulse Width Modulation (PWM) is the signal format used to translate digital signals into continuous-time fields.

This study investigates the implementation and performance benefits of using a MongoDB replica set compared to a single node setup. The primary objective was to evaluate the efficiency and reliability improvements provided by replication in a NoSQL database cluster. The research involved configuring a single node and a three-node replica set, followed by conducting performance tests using CRUD operations on both setups. The results indicated that while the single node exhibited faster write operations, the replica set significantly improved read performance and provided high availability and fault tolerance. The findings highlight the advantages of using a replica set for applications requiring robust data access and consistent performance under varying workloads.

The use of Retrieval-augmented generation (RAG) using large language models (LLMs) has shown potential for addressing issues such as hallucinations and inadequately contextualized responses. A pivotal stage in the RAG process involves a retriever for retrieving chunks based on semantic similarity with the query. In this study, we advocate for and provide experimental evidence supporting integrating and maintaining questions and answers (QA) formatted databases to improve retrieved-context representations and response quality. Our experiments evaluate our approach on benchmark RAG datasets using standard evaluation metrics and provide comparative analyses against state-of-the-art retrieval methods, showing the potential of our approach.

The present work deals with the study of the gravitational collapsing phenomenon of spherically symmetric massive stars with a Λ parameterization A collapsing model with a cosmological constant of the form Λ=β(θ ̇/3+θ^2/9) has been considered. In this model, exact solutions of the Einstein field equations (EFEs) are obtained using the $\Lambda$ parametrization and the junction conditions. All the physical and geometrical quantities are calculated in terms of the Schwarzschild mass M and areal radius R of spherically symmetric stars. Consequently, we have approximated the masses and radii of different stars to estimate the value of the model parameter β. We discuss the collapsing process and singularity formation for these stars and observe that all the physical and geometrical parameters of the model heavily depend on the model parameter β. We further discuss spacetime singularity through the development of apparent horizons.

With the global objectives of achieving a ‘carbon peak’ and ‘carbon neutrality’, along with the implementation of carbon reduction policies, China’s industrial structure has undergone significant adjustments, resulting in constraints on high-energy consumption and high-emission industries while promoting the rapid growth of green industries. Consequently, these changes have led to an increasingly complex power system structure and presented new challenges for electricity demand forecasting. To address this issue, this study proposes a 24-step multivariate time series short-term load forecasting algorithm model based on KNN data imputation and BiTCN bidirectional temporal convolutional networks combined with BiGRU bidirectional gated recurrent units and attention mechanism. The Kepler adaptive optimization algorithm (KOA) is employed for hyperparameter optimization to effectively enhance prediction accuracy. Furthermore, using real load data from a wind farm in Xinjiang as an example, this paper predicts the electricity load from January 1st to December 30th in 2019. Experimental results demonstrate that our comprehensive short-term load forecasting model exhibits lower prediction errors and superior performance compared to traditional methods, thus holding great value for practical applications.

The widespread adoption of IoT networks has revolutionized modern life thanks to their diverse range of applications. With their increased usage, the need to transfer data securely has never been more vital. Often IoT devices are battery-driven and possess limited processing and storage capabilities. In response to those limitations, there has been a shift towards the implementation of resource-efficient and lighter protocols. This research aims to evaluate how lightweight key establishment through Object Security for Constrained RESTful Environments (OSCORE) and Ephemeral Diffie-Hellman Over COSE (EDHOC) can enhance cybersecurity in IoT networks where resources are limited. The study aims to explore different key management approaches and the effects of certificates on security, efficiency, and power consumption. The research methodology consists of the practical implementation of the protocols in a physical system where factors such as the impact of hardware acceleration on computational overhead and overall power consumption will be assessed. Furthermore, the study will verify the cost of resources and overall efficiency, evaluating them against real-world scenarios. The expected contributions of this study are insights into the tradeoffs between security, power consumption, and efficiency in resource-limited IoT environments.

This study builds on our previous Systematic Literature Review (SLR) that assessed the applications and performance of zk-SNARK, zk-STARK, and Bulletproof Non-Interactive Zero-Knowledge Proof (NIZKP) protocols. To address identified research gaps, we designed and implemented a benchmark comparing these three protocols using a dynamic MiMC hash application. We evaluated performance across four general-purpose programming libraries and two programming languages. Our results show that zk-SNARK produced the smallest proofs, while zk-STARK generated the largest. In terms of proof generation and verification times, zk-STARK was the fastest, and Bulletproof the slowest. Interestingly, zk-SNARK proofs verified marginally faster than zk-STARK, contrary to other findings. These insights enhance our understanding of the functionality, security, and performance of NIZKP protocols, providing valuable guidance for selecting the most suitable protocol for specific applications.

In this paper, we analyze the generalized Ulam-Hyers stability of affine type AQ Functional Equation in various Banach Spaces using Direct and Fixed Methods

Linear Hashing is an important algorithm for many key-value stores. Spiral Storage was invented to overcome the poor fringe behavior of Linear Hashing, but after an influential study by Larson, seems to have been discarded. Since almost 50 years have passed, we repeat Larson’s comparison with in-memory implementation of both to see whether his verdict still stands. Our study shows that Spiral Storage has slightly better look-up performance, but slightly poorer insert performance.

This paper systematically discusses the application and development of federated learning in data privacy protection and data value sharing. With the rapid development of global information technology, especially the explosive growth of data from Internet of Things devices, data security and privacy protection are facing unprecedented challenges. This paper first analyzes the growth trend of global data volume and its importance to next generation technologies such as artificial intelligence technologies such as deep learning. Second, the paper provides an in-depth look at the impact of current data privacy regulations on data flows and value creation, particularly the EU's GDPR and China's Data Security and Personal Information Protection Law. Then, this paper introduces in detail federated learning, as a new distributed machine learning paradigm, which effectively solves the contradiction between existing data sharing and privacy protection by protecting individual data privacy and realizing global model collaborative construction. Finally, this paper discusses the combination of blockchain technology and federated learning, and proposes BeFL architecture as a new secure, decentralized and trusted federated learning system, which is expected to provide a comprehensive solution for large-scale data processing and value creation in multi-party scenarios. The research in this paper not only deepens the understanding of federation learning in theory, but also provides important reference and enlightenment for future research and application in related fields.

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

Investigation into a modified deterministic rumour spread model using mathematical epidemiology approach as an extension of Daley and Kendall (D-K) model was carried out. It is proven that the spread of a rumour is fairly comparable to a contagious disease transmission, except that the spread depends solely on the fraction of individuals who are aware of the rumour at the early stage as well as the intrinsic rumour spread rate . Model simulation reveals a rumour diminishing strategy so far as is maintained.

Despite significant advancements in Artificial Intelligence (AI) and Large Language Models (LLMs), detecting and mitigating bias remains a critical challenge, particularly within social media platforms like X (formerly Twitter) and in addressing cyberbullying present on them. This research investigates the effectiveness of leading LLMs in generating synthetic biased and cyberbullying data and evaluates the proficiency of Transformer AI models in detecting bias and cyberbullying within both authentic and synthetic contexts. The study involves semantic analysis and feature engineering on a dataset of over 48,000 sentences related to cyberbullying collected from Twitter (before it became X). Leveraging state-of-the-art LLMs such as ChatGPT-4o, Pi AI, Claude 3 Opus, and Gemini-1.5, synthetic biased, cyberbullying, and neutral data were generated to deepen the understanding of bias in human-generated data. AI models including DeBERTa, Longformer, BigBird, HateBERT, MobileBERT, DistilBERT, BERT, RoBERTa, ELECTRA, and XLNet were initially trained to classify Twitter cyberbullying data and subsequently fine-tuned, optimized, and quantized for multilabel classification (detecting both biases and cyberbullying). The study's outcomes include a prototype of a hybrid application that combines a Bias Data Detector and a Bias Data Generator, validated through extensive testing.

The teaching of mathematics at the Faculty of Military Technology of the University of Defense in the first two years of the five-year Military master’s degree is divided into the teaching of students in four specializations: Military Technologies – Mechanical, Military Technologies – Electrical, Military Geography and Cartography, and Cybersecurity. The article discusses the previous five-year experience in teaching the subjects Mathematics I, Mathematics II, Mathematics III, and Graph theory for the specialization in Cybersecurity, that the author of the paper gained while teaching, as a guarantor of these four subjects. The article provides an overview of the topics that are covered, typical exam assignments, and an evaluation of the results of the semester exams in the five years since the accreditation of the Cybersecurity specialization was granted.

This paper presents a comprehensive comparative analysis of four different computational vision algorithms for implementing an unpalleting system in a factory environment, under typical edge computing constraints. The primary objective is to automate the process of detecting and locating specific variable-shaped objects on a pallet, enabling a robotic system to accurately unstack them. The four algorithms evaluated are Pattern Matching, Scale-Invariant Feature Transform, Oriented FAST and Rotated BRIEF, and Haar cascade classifiers. Each technique is described in detail in this paper, and their implementations are outlined. Experimental results are thoroughly analyzed, assessing the algorithms’ performance based on accuracy, robustness to variability, computational speed, detection sensitivity, and resource consumption. The findings reveal the strengths and limitations of each algorithm, providing valuable insights for selecting the most appropriate technique based on the specific requirements of the unpalleting system. This research contributes to the advancement of automated object detection and localization in industrial environments, paving the way for more efficient and reliable unpalleting systems.

We address weighted composition operators between Bers-type spaces on generalized Hua-Cartan-Hartogs domains and provide necessary and sufficient conditions for their boundedness and compactness. We then apply our results to study the boundedness and the compactness of weighted composition operators between Bers-type spaces on five different domains: generalized Hua domains, Cartan-Hartogs domains, generalized Cartan-Hartogs domains, generalized Cartan-Hartogs domains over different Cartan domains and generalized ellipsoidal-type domains.

Brain-Computer Interface (BCI) processes and converts brain signals to provide 20 commands to output devices to carry out certain tasks. The main purpose of BCI is to replace or 21 restore missing or damaged functions of disabled people including neuromuscular disorders like 22 Amyotrophic Lateral Sclerosis (ALS), cerebral palsy, stroke, or spinal cord injury. Hence, BCI does 23 not use neuromuscular output pathways. Scientists have used several techniques like 24 Electroencephalography (EEG), intracortical, and Electrocorticographic (ECoG) to collect brain 25 signals which are used to control robotic arms, prosthetics, wheelchairs, and several other devices. 26 The non-invasive method of EEG is used for collecting and monitoring the signals of the brain. 27 Implementing EEG-based BCI technology in home automation systems may facilitate a wide range 28 of tasks for people with disabilities. It is important to assist and empower individuals with paralysis 29 to engage with existing home automation systems and gadgets in this particular situation. This 30 paper proposed a home security system to control a door and a light using EEG-based BCI. The 31 system prototype consists of the EMOTIV Insight™ headset, Raspberry PI 4, servo motor to 32 open/close the door, and LED. The system can be very helpful for disabled people including arm 33 amputees who cannot close/open doors or use remote control to turn on/turn off doors. The system 34 includes an application made in Flutter to receive notifications on the smartphone related to the 35 status of the door and the LEDs. The disabled person can control the door as well as the LED using 36 his/her brain signals detected by the EMOTIV Insight™ headset.

The Internet of Things (IoT) is a promising technology for sensing and monitoring the environment to reduce disaster impact. Energy is one of the major concerns for IoT devices, as sensors used in IoT devices are battery-operated. Thus, it is important to reduce energy consumption, especially during data transmission in disaster-adverse situations. Clustering-based communication helps reduce a node’s energy decay during data transmission and enhances the network’s lifetime. Many hybrid combination algorithms are proposed for clustering and the routing protocol to improve the network lifetime in disaster scenarios. However, the performance of these protocols is widely varied based on the underlying network configuration and the optimisation parameters considered. In this research, we have used the clustering parameters that are most relevant to disaster scenarios, such as the node’s residual energy, distance to sink, and network coverage. Then, we proposed a bio-inspired hybrid (BAO-PSO) algorithm where the Butterfly Optimisation Algorithm (BOA) is used for clustering and Particle Swarm Optimisation (PSO) is used for the routing protocol. The performance of the proposed algorithm is compared with the benchmark protocols LEACH, DEEC, PSO, PSO-GA, and PSO-HAS. Residual energy, network throughput, and network lifetime are considered performance matrices. The simulation result showed that the proposed algorithm increases network lifetime by 10%-20% by comparison with the benchmark algorithm.

This paper presents two novel bio-inspired particle swarm optimisation (PSO) variants: biased eavesdropping PSO (BEPSO) and altruistic heterogeneous PSO (AHPSO). These algorithms are inspired by types of group behaviour found in nature that have not previously been exploited in search algorithms. The primary search behaviour of the BEPSO algorithm is inspired by eavesdropping behaviour observed in nature coupled with a cognitive bias mechanism that enables particles to make decisions on cooperation. The second algorithm, AHPSO, conceptualises particles in the swarm as energy-driven agents with bio-inspired altruistic behaviour which allows the formation of lending-borrowing relationships. The mechanisms underlying these algorithms provide new approaches to maintaining swarm diversity which contributes to preventing premature convergence. The new algorithms were tested on the 30, 50 and 100-dimensional CEC'13, CEC'14 and CEC'17 test suites, and various constrained real-world optimisation problems, against 13 well-known PSO variants and the CEC competition winner, differential evolution algorithm L-SHADE. The experimental results show that both algorithms, BEPSO and AHPSO, provide very competitive performance on the unconstrained test suites and the constrained real-world problems. They were significantly better than most other PSO variant on most problem sets and no other comparator algorithm was significantly better than either of them on any of the 50 and 100-d problem sets.

The article evaluates the use of machine learning methods to predict valve plate failures in hydraulic pumps. To conduct this assessment, a laboratory setup was developed that allowed the creation of a training dataset containing both the normal operating state of the pump and the operating state with three different valve plate damages. Five different predictive models were evaluated, including three composite models based on decision trees: Random Forest, Gradient-Boosted Trees, and Rotation Forest, as well as the kNN algorithm and a neural network. The analysis showed that neural networks achieved the highest prediction accuracy, enabling a prediction accuracy level of 89%. The kNN algorithm ranked second, and tree-based algorithms performed 4% worse than the neural network. Additionally, the attribute importance analysis revealed that leak flow, pressure output together with output flow, are the most important parameters for accurate prediction.

Accurate prostate volume estimation is crucial for effective prostate disease management. Ultrasound (US) imaging, particularly transrectal ultrasound, offers a cost-effective and rapid assessment. However, US images often suffer from artifacts and poor contrast, making prostate volume estimation challenging. This review explores recent advancements in deep learning (DL) techniques for automatic prostate segmentation in US images as a primary step for prostate volume estimation. We examine various DL architectures, including traditional U-Net modifications and innovative designs incorporating residual connections, multi-directional image data, and attention mechanisms. Additionally, we discuss pre-processing methods to enhance image quality, the integration of shape information, and strategies to improve the consistency and robustness of DL models. The effectiveness of these techniques is evaluated through metrics such as Dice Similarity Coefficient, Jaccard Index, and Hausdorff Distance. The review highlights the potential of DL in improving prostate volume estimation accuracy and reducing clinical workload, while also identifying areas for future research to enhance model performance and generalizability.

With the advance of generative AI, the text-to-image (T2I) model has the ability to generate various contents. However, the generated contents cannot be fully controlled. There is a potential risk that text-to-image model can generate unsafe images with uncomfortable contents. In our work, we focus on eliminating the NSFW (not safe for work) content generation from text-to-image model while maintaining the high quality of generated images by fine-tuning the pretrained diffusion model via reinforcement learning by optimizing the well-designed content-safe reward function. The proposed method leverages a customized reward function consisting of the CLIP (Contrastive Language-Image Pre-training) and nudity rewards to prune the nudity contents that adhere to the pretrained model and keep the corresponding semantic meaning on the safe side. In this way, the text-to-image model is robust to unsafe adversarial prompts since unsafe visual representations are mitigated from latent space. Extensive experiments conducted on different datasets demonstrate the effectiveness of the proposed method in alleviating unsafe content generation while preserving the high-fidelity of benign images as well as images generated by unsafe prompts. Our method surpasses existing state-of-the-art (SOTA) baseline methods and achieves better performance on sexual content removal (14.5% higher than SafeGen) and image quality retention. In terms of robustness, our method outperforms Safe Latent Diffusion and SafeGen under the SOTA black-box attacking model SneakyPrompt by approximately 2x and 5.6x, respectively. Furthermore, our constructed method can be a benchmark for other methods aiming for anti-NSFW generation, high-level prompt-image safe alignment.

The proliferation of Internet of Things (IoT) devices on Linux platforms has heightened concerns regarding vulnerability to malware attacks. This paper introduces a novel approach to investigating the behavior of Linux IoT malware by examining syscalls and library syscall wrappers extracted through static analysis of binaries, as opposed to the conventional method of using dynamic analysis for syscall extraction. We rank and categorize Linux system calls based on their security significance, focusing on understanding malware intent without execution.Feature analysis of the assigned syscall categories and risk ranking is conducted with statistical tests to validate their effectiveness and reliability in differentiating between malware and benign binaries. Our findings demonstrate that potential threats can be reliably identified with an F1 score of 96.86%, solely by analyzing syscalls and library syscall wrappers. This method can augment traditional static analysis, providing an effective preemptive measure to enhance Linux malware analysis. This research highlights the importance of static analysis in strengthening IoT systems against emerging malware threats.

Artificial intelligence provides a new research concept for digital image processing. However, at present, artificial intelligence is rarely introduced into the teaching of digital image processing in colleges and universities, and there are problems such as obsolete teaching content, single teaching methods, and simple course experiments, which affect the teaching effect and are not conducive to the cultivation of comprehensive and innovative talents. Digital image processing technology brings more possibilities to communication engineering and makes communication more convenient. For example, video calls and photo transmission make people's communication methods in daily life more and more diversified. Time and space limitations allow people to meet online, creating more communication possibilities. However, there are still many problems and methods worthy of in-depth exploration. Therefore, this paper has a comprehensive understanding and mastery of the traditional and deep learning methods of digital image processing to improve the relevant project practice and scientific research exploration ability and refer for similar research conclusions.

With the rapid development of intelligent logistics and network environment, it has become an urgent problem to efficiently and accurately handle and analyse the huge amount of uncertain decision information. Traditional decision making methods often fail to make the best use of complex and incomplete information, especially in the field of cyber defence. To address these problems, this paper introduces a new mathematical tool, discrete multidimensional Z-numbers (MZs), for expressing and dealing with uncertainty and reliability in network defence decisions. In this paper, we first introduce the synthesis method of discrete multidimensional Z-numbers, which allows us to consider the uncertainty and reliability of multi-source information in network defence strategy. Then, the hidden probability of MZs is calculated by using the hidden probability model, and the multidimensional Z+−number is proposed, which improves the expressiveness of the model in dealing with information uncertainty. Based on MZs, we define a variety of utility functions and build a multi-attribute group decision framework for network defence around these functions. The MZs provides a novel perspective for analysing and designing response strategies, especially against highly adaptive and covert attacks. The method in this paper is verified by a case of network security assessment of an intelligent logistics company. The results show that this method can significantly improve the accuracy and efficiency of decision making, demonstrating its unique advantages and wide application potential in network defence. This integrated discrete multidimensional Z-number group decision method is not only suitable for intelligent logistics decision making, but also provides an efficient decision support tool for network defence, which helps to improve the intelligence and adaptability of network security defence.

In this paper, we present a multi-task model that predicts disparities and confidence levels in deep stereo matching simultaneously. We do this by combining its successful model for each separate task and obtaining a multitask model that can be trained with a proposed loss function. We show the advantages of this model compared to training and predicting disparity and confidence sequentially. This method enables an improvement of 15% to 30% in the area under the curve (AUC) metric when trained parallel rather than sequential. In addition, the effect of weighting the components in the loss function on the stereo and confidence performance is investigated. By improving the confidence estimate, the practicality of stereo estimators for creating distance images is increased.

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

The advanced industrial systems are characterized by complex event-driven processes. The specification and computer analysis are illustrated by the common problem of a servo drive with the PWM controller. A mathematical model from the class of Cauchy problems with non-liner control logic is presented to resolve the task discussed. The designed model is performed in two stages: the mathematical model specification (modeling) and implementation (simulation). Two approaches to make a model specification are considered, the first one is the traditional structural technique, and the advanced method is based on the finite state machine paradigm. Structural and finite state software models are built in progressive simulation tools. Computer implementation of the software models of hybrid systems is performed using platform built-in libraries with numerical methods and algorithms for correct event detection. The results of computational experiments for transient processes of phase variables are qualitatively identical, that proves the adequacy of the developed models. The algorithm for asymptotic event detection is considered in detail. This technique demonstrated the best results by the one-sidedness criterion, which is explained by using the author’s algorithm for the integration step determining and the event function dynamics monitoring in the vicinity of the event limits.

Aiming at the problems of inaccurate segmentation of long object and information loss of small object in real-time semantic segmentation algorithm, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment and fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model’s awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses NVIDIA GeForce RTX 3080 Laptop GPU experiment, on the road street view data set Cityscapes and CamVid average occurring simultaneously ratio reached 77.1% and 78.4% respectively, with running speed of 127 frames/s respectively and 112 frames/s. The experimental results show that the proposed algorithm can achieve real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance

In the era of Big Data and the Internet of Things (IoT), ensuring the security and privacy of patient data within distributed health systems is paramount. This research delves into the challenges posed by these advancements and explores viable solutions, focusing notably on blockchain technology, data encryption methods, and access control mechanisms. Employing a comprehensive literature review approach, the study synthesizes current research findings, complemented by analyses of existing frameworks and case studies from healthcare organizations, offering practical insights. Interviews with cybersecurity experts and healthcare IT professionals provide nuanced perspectives on current security issues and emerging trends. Through qualitative and quantitative data analyses, the study generates recommendations aimed at enhancing patient data security. These include the adoption of new frameworks and innovative technologies to fortify healthcare data systems. By addressing these critical aspects, this research aims to significantly contribute to the advancement of a more secure and efficient healthcare ecosystem in today's digital landscape.

RNA sequencing techniques, like bulk RNA-seq and Single Cell (sc) RNA-seq, are critical tools for the biologist looking to analyze the genetic activity/transcriptome of a tissue or cell during an experimental procedure. Platforms like Illumina's next-generation sequencing (NGS) are used to produce the raw data for this experimental procedure. This raw FASTQ data must then be prepared via a complex series of data manipulations by bioinformaticians. This process currently takes place on an unwieldy textual user interface like a terminal/command line that requires the user to install and import multiple program packages, preventing the untrained biologist from initiating data analysis. Open-source platforms like Galaxy have produced a more user-friendly pipeline, yet the visual interface remains cluttered and highly technical, remaining uninviting for the natural scientist. To address this, SeqMate is a user-friendly tool that allows for one-click analytics by utilizing the power of a large language model (LLM) to automate both data preparation and analysis (differential expression, trajectory analysis, etc). Furthermore, by utilizing the power of generative AI, SeqMate is also capable of analyzing such findings and producing written reports of upregulated/downregulated/user-prompted genes with sources cited from known repositories like PubMed, PDB, and Uniprot.