Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013012

Authors: Wessam F. Abouzaid Ebrahim A. Ramadan Nermeen G. Rezk

This study explores the use of traditional machine learning and deep learning algorithms to develop efficient Intrusion Detection Systems (IDSs). It evaluates data using the NSL-KDD dataset, which contains both normal and attack traffic. The research compares the performance of various classifiers, including Random Forest, Extreme Gradient Boosting, LightGBM, and Prototypical Networks. Recursive Feature Elimination is used for feature selection to enhance decision-making and model performance. The models are assessed using multiple metrics, such as accuracy, precision, recall, F-score, ROC curves, and confusion matrices. In addition, Explainable AI techniques like SHAP and LIME are employed to interpret predictions, making the IDS more transparent and reliable. Results indicate that few-shot learning models, particularly Prototypical Networks, combined with Recursive Feature Elimination techniques, outperform traditional models, achieving up to 98% accuracy. This approach enhances IDS applications in IoT by enabling more accurate threat detection, improving decision-making, and identifying key intrusion parameters.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013011

Authors: Deepa Sonal Md Alimul Haque Sultan Ahmad Sultan Alqahtani A. E. M. Eljialy

Humans have always been curious about what animals are trying to communicate, especially our closest companions—dogs and cats. While we often rely on instinct and observation to understand their needs and feelings, this method can be inaccurate or limited. This research introduces a new computational model designed to translate the behaviors of dogs and cats into simple, human-readable messages. By combining data from their body language, sounds, facial expressions, and movements, the model uses advanced machine learning and deep learning techniques to identify what the animal might be feeling or trying to express. We collect and analyze real-world behavioral data from pets, then train the system to interpret signals like barking, meowing, tail movements, or posture changes. The final output could be a sentence or voice alert that helps pet owners understand things like “I’m hungry,” “I’m scared,” or “I want to play.” This approach not only improves how we care for pets but also enhances emotional connection and communication between humans and animals. It opens new doors for technology in pet care, training, and veterinary support.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013010

Authors: Nwadher S. Alblihed Dina M. Ibrahim

A range of sensors are used by human activity recognition (HAR) to identify the activities that people complete each day. The recognition of human activities has benefited greatly from machine learning (ML), as it has made many human activities more easily recorded. Unfortunately, a centralized approach is used in many HAR applications, which might compromise user privacy. One must use deep learning (DL) using different algorithms and models to analyze the data generated from ML. Another kind of ML is distributed ML, called federated learning (FL), which tries to distribute ML models across edge devices. Thus, this study presents an FL model to support HAR by building a generic model and using user-based training data without data sharing. Through developing heterogeneous local models, each client takes the most suitable DL model to the client. This study uses three different DL models to develop the local model: Convolutional Neural Network (CNN), Residual Network (ResNet), and Long Short-term Memory (LSTM). Moreover, different numbers of clients are experimented with: two, five, and ten clients. The UniMiB SHAR dataset is used to apply the experiments. As a result, using five clients with three mixed DL models gives the highest Accuracy of 90.8%.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013007

Authors: Rana Albelaihi

Federated learning (FL) enables distributed IoT devices to train machine learning models collaboratively without sharing raw data. However, energy heterogeneity among devices significantly challenges efficient and equitable participation, particularly in resource-constrained networks. This paper introduces BEAF (Bid-based Energy-Aware Federated Learning), a client selection strategy that incorporates the availability of energy and the training utility of the device into a unified selection criterion. Each client independently computes a bid score based on its remaining energy and the relative improvement in local training loss. Clients with the highest utility-per-joule scores are selected to participate in each round. The approach operates without centralized profiling or historical coordination and is compatible with synchronous FL protocols. The evaluation of standard benchmarks shows that BEAF enhances the precision of the global model, reduces total energy consumption, and improves fairness in client participation compared to baseline methods, such as random sampling and selection based on energy thresholds. The method is suitable for deployment in energy-limited environments, including agricultural monitoring and other distributed sensing applications.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013008

Authors: Abdulnaser Rashid

This paper explores the relationship between random matrix theory (RMT) and the use of weight conditioning for training deep neural networks by employing an integrated framework. It has been shown that trained neural networks produce singular value distributions that follow universal distributions prescribed by RMT; however, the presence of non-universal outliers in the distribution can contain significant information particular to the task being performed. In addition, this research investigates how the application of diagonal row equilibration as a form of conditioning affects spectral behavior and optimization stability within deep neural networks. The results show that through conditioning, the random bulk of the singular value decomposition (SVD) spectrum is effectively compressed into a narrow band about the value 1, significantly reducing the Marchenko–Pastur bounds. The results also support the claim that weight conditioning retains the informative nature of the spectral outliers. The experimental results show that weight condition numbers (κ(W)) decreased from extremely ill-conditioned regimes of approximately 103 to 104 to almost 1.0, producing smoother training landscapes, a quicker convergence rate, and an improved ability for gradients to propagate. These results suggest that conditioning weights can be thought of as an implicit spectral regularize linking RMT evidence and concepts to the practical optimization of deep learning methods.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013006

Authors: Leidi M. Saleh Aouto Lin M. Saleh Aouto Rawan Khaled Flifel Dina M. Ibrahim

The brain is the most complex organ in the human body, and neurological disorders pose significant diagnostic challenges. This study focuses on three prevalent conditions—Alzheimer’s disease, brain tumors, and Parkinson’s disease—collectively referred to as Encephalon Diseases. We propose a three-level deep learning-based framework, termed the Encephalon Diseases Classifier, for automated diagnosis from magnetic resonance imaging (MRI) scans. In Level 1, MRI images are classified as normal or diseased. Level 2 further categorizes diseased cases into one of the three targeted conditions. Level 3 performs stage or subtype classification for Alzheimer’s disease and brain tumors. The framework employs four convolutional neural network (CNN) architectures, namely ResNet152-V2, EfficientNet-B0, DenseNet121, and VGG16, trained on a preprocessed dataset. Experimental results show that ResNet152-V2 achieves the highest accuracy of 100%, while EfficientNet-B0 and DenseNet121 yield comparable performance across all levels. The proposed method demonstrates the potential of multi-level deep learning strategies for precise and scalable Encephalon disease classification.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013005

Authors: Rawan Abdulaziz AlRumaih Tarek Moulahi Dina M. Ibrahim

The rise of the Internet of Medical Things (IoMT) has transformed healthcare through real-time monitoring and improved outcomes but also introduced critical security and privacy challenges. This paper presents a focused survey of Explainable AI (XAI) approaches for intrusion detection in IoMT, emphasizing methods that are lightweight, transparent, and deployable under resource constraints. We first clarify XAI terminology and taxonomy (global vs. local scope; ante hoc vs. post hoc; model-agnostic vs. model-specific) and then systematize recent works from the past five years across cybersecurity sub-domains relevant to eHealth. Representative pipelines span classical ML (e.g., LR, RF, SVM, and XGBoost) and deep models (e.g., DNNs and SRU/LSTM), with post hoc explainers, especially SHAP and LIME, dominating practice on benchmark datasets such as CICIDS2017, NSL-KDD, ToN-IoT, WUSTL-EHMS, and CICIoMT2024. Our comparative analysis highlights consistent gains from model ensembling and interpretable feature selection while uncovering key gaps: limited real-world validation, inconsistent explainability metrics, adversarial brittleness, and the computing cost of explanations at the edge.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013009

Authors: Ghida Almusned Lama Almutairi Emna Benmohamed Rana Albelaihi

Malware remains a major threat to computer systems, posing serious risks to security and privacy by stealing sensitive data, disrupting services, and compromising system integrity. Traditional detection methods are often ineffective against rapidly evolving malware. In response, data-driven deep learning has emerged as a powerful alternative. Recent models have demonstrated promising performance in detecting malicious behavior by learning from these behavioral traces. Behavior-based detection represents a significant advancement in the fight against malware. This paper introduces a deep stacked Graph Convolutional Network (GCN) for effective malware behavioral analysis. The aggregation of multiple GCN layers and blocks results in dynamically performed Jumping Knowledge (JK) method, especially Long Short-Term Memory (LSTM). LSTM-based JK dynamically selects and weights the most informative GCN layers for each node to improve the model’s ability. Experimental results demonstrate the superior performance of our deep stacked Graph Convolutional Network with Dynamic Aggregation (DSGCN-DA) model, achieving an accuracy of 98.93% on the API-Call-Sequences dataset, outperforming the state-of-the-art approaches.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013004

Authors: Shefa Alkhowaiter Mohamed Tahar Ben Othman

This study addresses the challenge of DNA sequence similarity analysis by combining deep learning with DNABERT embeddings. Traditional alignment methods based on direct pairwise comparisons often fail to detect deeper biological relationships beyond nucleotide matching. However, DNABERT, a large transformer-based language model, captures contextual and functional patterns within genomic data. We initially used a dataset of 20 human DNA sequences and later expanded it to 70 sequences to enhance statistical reliability. The results showed that DNABERT recovered functional similarities even between sequences with low identity percentages, revealing previously overlooked structural relationships that were hidden by traditional alignments. Quantitative evaluation using precision, recall, and F1 score confirmed the robustness and consistency of the DNABERT-based approach. Overall, this study demonstrates that combining traditional and deep learning-based methods yields a more accurate and interpretable framework for DNA sequence alignment, thereby paving the way for enhanced genomic analysis.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013003

Authors: Abdulsalam Ibrahim Almirdasi Mohamed Tahar Ben Othman

Cloud storage systems require strong and efficient encryption methods to ensure data security and reliability. However, selecting the most suitable encryption algorithm remains a challenge due to variations in performance, overhead, and reliability. This study aims to introduce a comparative analysis of five encryption algorithms—Advanced Encryption Standard (AES), Blowfish, Rivest-Shamir-Adleman (RSA), Elliptic Curve Cryptography (ECC), and Advanced Encryption Standard one-time password AES-OTP with RSA hybrid model (AES-OTP with RSA)—to identify the most suitable algorithm to protect sensitive data in cloud storage systems. The evaluation of these algorithms was based on encryption/decryption time, data size overhead, encryption/decryption throughput, performance metrics (accuracy, precision, recall, and F1-score), and error metrics mean square error and mean absolute error (MSE and MAE), using datasets of various sizes. The results indicated that AES provided the fastest encryption and decryption time, minimal overhead, and the highest throughput and accuracy, while Blowfish also performed efficiently but with slightly higher error rates. RSA and ECC, although secure, were slower and demonstrated more overhead. The hybrid AES-OTP with RSA model achieved a good balance between speed and secure key management. This study highlights the trade-offs between speed, security, and storage efficiency, offering guidance in selecting appropriate encryption algorithms for cloud-based data protection.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013002

Authors: Raneem Khaled AlFadhel Mohammad Ali A. Hammoudeh

With the growing volume of sensitive data stored and processed in cloud environments, conventional security models are no longer sufficient to guarantee privacy, integrity, and trust. This paper proposes a blockchain-based framework that integrates Zero-Knowledge Proofs (ZKPs) and homomorphic encryption (HE) to enable secure and privacy-preserving data sharing. ZKPs are employed to verify user access rights without exposing identities or underlying information, while HE allows computations to be performed directly on encrypted data, ensuring confidentiality is preserved throughout the data lifecycle. The proposed framework addresses the limitations of existing approaches that either lack encrypted computation capabilities or expose sensitive data during processing. Formal and informal analyses demonstrate the feasibility of the model in terms of encryption time, ZKP verification latency, and computation overhead. The framework is designed to be applied initially in the healthcare sector and aligns with national digital transformation initiatives such as Saudi Vision 2030.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2026013001

Authors: Dina M. Ibrahim Jamal Alotaibi

n/a

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012019

Authors: Sameena Pathan Saad Hassan Kiani

n/a

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012018

Authors: Marios Vardalachakis Manos Vasilakis Manolis Tampouratzis

Businesses need good defenses against any number of incidents in the continually evolving area of cybersecurity. SIEM (Security Information and Event Management) systems are now important tools for them. The current study offers a comprehensive analysis of SIEM solutions, such as their key features, benefits, installation issues, and suggested procedures. SIEM systems effectively store security event data, giving continuous tracking, interaction, and examination to recognize and deal with threats rapidly. The advantages of this technology include enhanced operating efficiency, streamlined compliance with laws, expedited response to events, and heightened threat detection capabilities. However, the implementation of SIEM systems has many challenges that must be overcome, including intricacies, cognitive exhaustion, data integration complications, and restrictions. To effectively handle these issues, businesses are advised to develop objectives, properly schedule, attend school, and periodically review and enhance their SIEM goals. In addition, organizations may use the complete capabilities of SIEM systems to enhance their cybersecurity stance and mitigate the risks posed by cyberattacks by staying updated with the most recent developments. This study aims to provide a comprehensive examination of Security Information and Event Management (SIEM) systems, with a specific emphasis on important features, benefits, implementation challenges, and suggestions.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012017

Authors: Parth Patil Karthik Kamaldinni Sanjana Patil Sakshi Gaitonde

Attention Deficit/Hyperactivity Disorder (ADHD) is a neurodevelopmental disorder that is found in both children and adults. While this disorder often continues in adulthood, diagnosis can be challenging, particularly in females. Unlike males, who are often diagnosed with ADHD due to their externalizing behaviors (i.e., impulsive nature), most females show inattentive symptoms (i.e., in focusing, disorganization), which makes this disorder hard to detect. This paper proposes a machine learning approach to detect ADHD among females. The Wids Datathon 2025 provides three datasets: categorical data, quantitative data, and function connectomes. It contains information on 1213 participants who are seeking to take a test to detect ADHD. Categorical data includes 10 attributes, quantitative data has 19 attributes, and functional connectomes contain 19,901 attributes which are relevant to studying the participants’ overall condition. By combining both XGBoost and Random Forest, an accuracy of 79.42% was achieved. The results show that machine learning algorithms can help in improving ADHD detection in females, leading to better diagnoses in future.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011038

Authors: Olga Valenzuela Fernando Rojas Luis Javier Herrera Hector Pomares Ignacio Rojas

n/a

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012016

Authors: Monika Sharma Navneet Sharma Priyanka Verma

To demonstrate the interrelation of fashion elements for design forecasting, the research examines classification and sentiment analysis methodologies. The study combines survey data with information from social media and e-commerce sites to find important emotional and behavioral patterns that affect how people make buying decisions. The research employs deep learning, Logistic Regression, and Random Forest models to predict design trends and user preferences. The research methodology focuses on improving fashion analytics through feature selection and user segmentation and visual storytelling methods to enhance strategic decision-making.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012015

Authors: Bhanu Prakash Jayanth Sidlaghatta Muralidhar Mohammed Zaman Pasha Vijay Kumar Harapanahalli Kulkarni Shridhar B. Devamane N. Rana Pratap Reddy

Flooding in Bengaluru areas such as Kodigehalli, Hebbal, and Nagavara has led to severe disruptions, including traffic congestion, infrastructure damage, and health risks. To address this issue, we have proposed a smart flood alert and communication system, integrating Internet of things (IoT), artificial intelligence (AI), and smart infrastructure solutions. The system helps by giving information about real-time water level sensors, AI-driven flood prediction models, automated emergency coordination, and a mobile-based citizen reporting platform. Through cloud-based data processing, predictive analytics, and smart drainage management, this solution aims to enhance early warnings, reduce emergency response time, and improve urban flood resilience. It yields up to an 80% reduction in alert delays, a 50% faster emergency response, and improved community safety. This project seeks collaboration with government agencies, technology firms, and community stakeholders to implement a pilot plan, ensuring a scalable and sustainable flood mitigation strategy for Bengaluru.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012014

Authors: Kajal Mungase Shwetambari Chiwhane Priyanka Paygude

The need to automate the disease identification processes is frequent because manual identification is time-consuming and needs professional skills to be performed; hence, it may improve effectiveness and precision. This paper has resolved the problem by using image classification with deep learning to detect silkworm diseases. A Kaggle-sourced dataset of work of 492 labelled samples (247 diseased and 245 healthy) was used with a stratified division into 392 training and 100 testing samples. The transfer learning method was performed on two Residual Network models, ResNet-18 and ResNet-50, in which pretrained convolutional layers were frozen and the last fully connected layer was trained to conduct binomial classification. Performance was measured by standard evaluation metrics such as accuracy, precision, recall, F1-score, and confusion matrices.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012013

Authors: Mudiduddi Lova Kumari P. S. G. Aruna Sri Rajapraveen Kumar Nakka Sonal Sharma Swaminathan Balasubramanian Preeti Gupta

In the past, health records were primarily on paper and were essential for recording the results of patient information and treatments. The deployment of “electronic health records” (EHRs) is a new development in healthcare that enables authenticated data storage, reliability when accessing data, and the establishment of easy communication centralized across healthcare service providers. This change enhances the quality of operations for medical environment decision-making using clinical data and patient involvement. Nevertheless, ensuring the authenticity of “EHRs” is a challenging task as a result of the weaknesses of centralized systems. We, therefore, suggest the implementation of (ABE), particularly (CP-ABE) using the blockchain technique, to overcome this problem. CP-ABE maintains data confidentiality and accuracy by encrypting access policies and smart contracts, thus allowing authorized users to decrypt information based on predetermined attributes. In this way, EHRs are ensured to be unaltered as patients’ privacy is preserved, and healthcare providers are not allowed to evaluate people records without consent. The machine learning techniques (“SVM, RF and Naïve Bayes”) used with datasets like “Cleveland Heart Disease” explain the cause risk factors for speed diagnosis and for cardiac disorders. Such a system not only fortifies the security of EHRs but also provides healthcare professionals with the necessary tools to improve patient care. The use of state-of-the-art encryption methods together with predictive analytics allows healthcare providers to protect patient privacy and at the same time make healthcare delivery more efficient through the use of a clinically informed final judgment of patient and personalized wellness plans.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012012

Authors: Krishnamurthy Nayak Supreetha Balavalikar Shivaram Sumukha K. Nayak

Present financial markets are characterized by great volatility and nonlinear dynamics since they are driven by both quantitative forces and qualitative mood. Traditional trading practices cannot capture such nuance. This study proposes an automated trading system based on machine learning that uses technical analysis as well as sentiment factors for better decision-making. Historical OHLCV stock price data from 2000 to 2025 was augmented with financial indicators such as SMA, EMA, RSI, and Bollinger Bands, as well as sentiment scores based on real-time news via natural language processing. LightGBM regression for predicting the price range and Histogram-Based Gradient Boosting classification for directional prediction were employed. Signals were generated with volatility-adjusted thresholds and classifier confirmation, and a risk management layer enforced position sizing, stop-loss triggering, and drawdown constraint. Back testing demonstrated improved Sharpe ratio, Sortino ratio, and win rates versus baseline strategies. The findings emphasize that the combination of machine learning and sentiment analysis with risk-conscious design improves predictive accuracy, dependability, and preservation of capital in automated trading systems.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012011

Authors: Anagha Kulkarni Priyanka Pawar Bhavana Pansare Harshal Raje

For psoriatic lesions, automatic segmentation is crucial to perform objective assessment, monitoring, and medication planning in dermatology. This study proposes a Multiscale Convolutional Neural Network (MSCNN) framework for precise segmentation of psoriatic lesions from medical images. The model was evaluated using the ISIC 2017 dataset and demonstrated robust performance in lesion localization. By analyzing the predicted masks, it has been observed that the boundaries closely match ground truth annotations. Metrics for quantitative evaluation are Dice Coefficient, Intersection over Union (IoU), used with high precision and slightly lower recall, reflecting occasional under-segmentation of fine-scale lesion details. The findings focus on the proposed MSCNN’s capability to produce reliable lesion masks, while also detecting areas for advancement in capturing irregular lesion boundaries. Future work involves integrating multimodal imaging, attention mechanisms, and larger, diverse datasets to improve segmentation accuracy and clinical applicability.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012010

Authors: Utham Kumar Anugula Sethupathy Vijayanand Ananthanarayan

The rapid expansion of digital payment channels has significantly widened the financial transaction attack surface, exposing ecosystems to sophisticated, polymorphic threat vectors. This study introduces an AI-powered cybersecurity mesh that unites Generative AI (GenAI), federated reinforcement learning, and zero-trust principles, with a forward-looking architecture designed for post-quantum readiness. The architecture ingests high-velocity telemetry, coordinates self-evolving agent collectives, and anchors model provenance in a permissioned blockchain to guarantee verifiability and non-repudiation. Empirical evaluations across two production-scale environments—a mobile wallet processing two million transactions per day and a high-throughput cross-border remittance rail—demonstrate a 95.1% threat-detection rate, a 62% reduction in false positives, and a 35.7% latency decrease compared to baseline systems. These results affirm the feasibility of a generative cybersecurity mesh as a scalable, future-proofed blueprint for next-generation payment security.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012005

Authors: Sameena Pathan Saad Hassan Kiani

n/a

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012009

Authors: Priyanka Pawar Anagha Kulkarni Bhavana Pansare Prajakta Pawar Prachi Bahekar Madhavi Kapre

Depigmented patches are the result of vitiligo, a skin condition brought on by the slow breakdown of melanocytes. High variability, complex lesion morphology, and subtle differences between affected and unaffected skin make accurate diagnosis difficult. In these situations, conventional supervised image analysis techniques have trouble generalizing. By allowing models to acquire significant representations from unlabeled data, self-supervised learning (SSL) presents a viable substitute. The new SSL-based framework for vitiligo skin image analysis proposed in this study uses contrastive learning with augmentation-based pretext tasks to capture complex visual patterns such as patch distribution, texture loss, and border irregularity. The SSL-enhanced model achieved a validation accuracy of 0.83 after fine-tuning on a small, labeled subset. This suggests that SSL could support accurate and labeled efficient vitiligo assessment in clinical and research settings. Direct comparisons with existing supervised model were not performed and were left for future research.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012008

Authors: Yusra Rafat Potu Narayana R. Madana Mohana Kolukuluri Srilatha

A substantial amount of data is generated day-to-day, to which news articles are a major contributor. Most of this data is not well-structured, highlighting the need for efficient ways to manage, process, and analyze said data. One useful approach involves the categorization of the data. The work “News Article Category Classification” develops a Long Short-Term Memory (LSTM) model for classifying news articles into 14 categories. LSTM networks are suitable for text classification tasks, as they efficiently capture contextual and sequential dependencies. They have a special ability to retain long-term information which makes them perfect for understanding the meaning of news articles.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012007

Authors: Ankur Goyal Vikas Honmane Kumarsagar Dange Shiv Kant

Millions of people suffer from chronic venous disease (CVD), a common vascular condition that frequently causes pain, edema, and skin ulcers. For treatment to be effective, its stages must be accurately and promptly classified. This study offers a deep learning-based framework for classifying CVD stages using medical images, such as limb photos or ultrasound scans. For training and assessment, convolutional neural networks (CNNs) are used in conjunction with pre-trained models like ResNet, VGG, and Efficient Net. Metrics like accuracy, precision, recall, and F1-score are used to evaluate the model’s performance. The encouraging findings suggest that deep learning tools can greatly facilitate the diagnosis of CVD and may be integrated into clinical decision support systems for quicker, more precise evaluations.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012006

Authors: Srushti Honnangi Anushri Kajagar Shashank Shetgeri Tanvi Korgaonkar Salma Shahapur Rajashri Khanai

A machine learning architecture is introduced to predict attention deficit hyperactivity disorder (ADHD) and biological sex from multimodal inputs. The problem sidesteps the clinical task of early ADHD detection and adds prediction of sex as a meta-feature to enhance robustness. The architecture is applied to demographic profiles, quantitative tests, and functional brain connectomes as 200 × 200 matrices. Preprocessing includes data harmonization, matrix symmetrization, graph-based descriptor extraction, including total strength, mean, and standard deviation, categorical encoding, variance thresholding, and imputation of missing values using k-nearest neighbors. Sex classification is performed using XGBoost with stratified cross-validation to generate probability outputs that enhance the ADHD model. ADHD classification is tuned using FLAML’s automatic hyperparameter search for XGBoost and class-weighting to address imbalance. Findings show that combining imaging-derived features and automated model selection yields a robust method of ADHD detection, underscoring the utility of multimodal data fusion in neuropsychiatric studies.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012004

Authors: K. Rama Krishna B. B. Shabarinath

This paper proposes a fast epileptic seizure detection method to allow for early clinical intervention. The primary goal is to enhance computational and predictive performance to make the method viable for online implementation. An advanced Line Spectral Estimation (LSE)-based method for EEG analysis was developed with Bayesian inference and Toeplitz structure-based fast inversion with Capon and non-uniform Fourier transforms to reduce computational requirements. XGBoost classifier with parallel boosting was employed to increase prediction performance. The method was tested with patients’ EEG data using multiple embedded Graphic Processing Unit (GPU) platforms and achieved 95.5% accuracy, and 23.48 and 33.46 min average and maximum lead times before a seizure, respectively. The sensitivity and specificity values (92.23% and 93.38%) show the method to be reliable. The integration of LSE and XGBoost can be extended to create an efficient and practical online seizure detection and management tool.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012003

Authors: Bhavana Santosh Pansare Anagha Deepak Kulkarni Priyanka Prabhakar Pawar

Across the world, asthma is a prominent and widespread respiratory disorder that has a substantial clinical and socioeconomic influence. The classification of asthma subtypes should be performed precisely and effectively, with objectives such as personalized treatments, improved rehabilitation outcomes, and preventing tragic exacerbations. Typical screening approaches are primarily based on spirometry measures, immunologic assessments, and individual clinical diagnoses, and they are commonly affected by limitations such as uncertainty, crossover disparities, and restricted generalizability among various groups of patients. This study utilizes machine learning (ML) methodologies as a Data-Driven Approach (DDA)-based framework for asthma classification to overcome the mentioned challenges. Methodically constructed and evaluated classifiers, such as Random Forest and XGBoost, use the Asthma Disease Dataset from Kaggle, which consists of demographic data, lung function metrics (FEV1, FVC, FEV1/FVC ratio, and PEFR), and immunoglobulin E (IgE) biomarkers. A wide range of metrics such as accuracy, precision, recall, F1-score, receiver operating characteristic area under the curve (ROC-AUC), and average precision (AP) are used exhaustively to assess the performance of the model. The results indicate that though each model exhibits outstanding forecasting abilities, XGBoost has an enhanced classification capability, especially in recall and AP, which minimizes the proportion of false negatives, resulting in a clinically noteworthy result. The significance of the FEV1/FVC ratio, IgE levels, and PEFR as key indicators is recognized by feature interpretability analysis. These results emphasize the ability of ML-powered evaluation in advancing personalized healthcare and revolutionizing the clinical management of asthma.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012002

Authors: Bharti Singh Anand Pandey Timsy Kakkar

The research is centered on how India’s top-tier IT companies—the “Big Six” of TCS, Infosys, HCLTech, Wipro, Cognizant, and Tech Mahindra—are integrating sustainability in their digitally driven operations, platforms, and business models. The study employs a mixed methodology, combining critical case study analysis with Fuzzy Delphi validation to assess triangular fuzzy numbers, centroid-based defuzzification, and consensus thresholds. The study explores how AI, big data, analytics, and digital marketing influence environmentally sustainable consumption behaviors within global ecosystems. Results show that, despite limited consumer control, these companies shape sustainability-related behavior indirectly through backend systems, digital platforms, and algorithmic logic—known as “invisible architecture”. This study confirms six main sustainability factors through expert consensus. Noteworthy among those are Digital Infrastructure for Sustainability, Platform Logic for Behavioral Change, and AI-Enabled Analytics and Recommendations. Thematic cross-case results reveal both the promise and ethical challenges of digital sustainability, including the prevalence of greenwashing and risks of overconsumption.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025012001

Authors: Sourav Yallur Jiya Patil Tanvi Shikhari Prajwal Dabbanavar Rajashri Khanai Salma Shahpur

More reliable and intelligent detection systems are required because of the rise in fraudulent activities brought on by the volume of digital financial transactions. In this work, the data used is from a publicly accessible dataset with more than a million transaction records to investigate a machine learning strategy to identify hidden patterns in the fraud transaction. Data preprocessing included applying Z-score normalization, eliminating outliers using the IQR method, and handling missing values according to the skewness of each attribute. The selection of important features was guided by correlation analysis using Chi-square tests and Pearson coefficients. This study implemented multiple supervised learning techniques, comprising Random Forest, Logistic Regression, K-Nearest Neighbors, and Gradient Boost to evaluate and compare their effectiveness in accurately detecting fraudulent transactions.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011033

Authors: James Ming Chen Giusy Chesini

This paper focuses on one specific aspect of a larger project evaluating three measures of banking risk. It emphasizes the overarching question of comparative regulatory policy: Do the European Union and the United States constitute two distinct and separate banking cultures? To answer such a question, conventional econometrics often prescribes fixed effects regression. This paper pursues an alternative approach. It directly asks whether banks on those separate continents can be distinguished using exactly the same design matrix to evaluate the proposed risk measures. The successful completion of that classification task permits the bifurcation of the overall dataset into distinct subsets, one for each continent. Parameter estimates and fitted values produced by separate regressions supply far more reliable and accurate insights into the distinct business and regulatory cultures of European and American banking.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011032

Authors: Frédéric Montet Benjamin Pasquier Beat Wolf

Recently, time-series forecasting foundation models trained on large, diverse datasets have demonstrated robust zero-shot and few-shot capabilities. Given the ubiquity of time-series data in IoT, finance, and industrial applications, rigorous benchmarking is essential to assess their forecasting performance and overall value. In this study, our objective is to benchmark foundational models from Amazon, Salesforce, and Google against traditional statistical and deep learning baselines on both public and proprietary industrial datasets. We evaluate zero-shot, few-shot, and full-shot scenarios using metrics such as sMAPE and NMAE on fine-tuned models, ensuring reliable comparisons. All experiments are conducted with onTime, our dedicated open-source library that guarantees reproducibility, data privacy, and flexible configuration. Our results show that foundation models often outperform traditional methods with minimal dataset-specific tuning, underscoring their potential to simplify forecasting tasks and bridge performance gaps in data-scarce settings. Additionally, we address non-performance criteria, such as integration ease, model size, and inference/training time, which are critical for real-world deployment.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011031

Authors: James Ming Chen Thomas Poufinas Angeliki C. Panagopoulou

Two-stage least squares (2SLS) regression undergirds much of contemporary geospatial econometrics. Walk-forward validation in time-series forecasting constitutes a special instance of iterative local regression. Two-stage least squares and iterative regression supply distinct approaches to isolating the drift and diffusion terms in data containing deterministic and stochastic components. To demonstrate the benefits of these methods outside their native contexts, this paper applies 2SLS correction of residuals and iterative local regression to panel data on passenger railway traffic in Europe. Goodness of fit improved from r2 ≈ 0.685 to r2 ≈ 0.723 through 2SLS and to r2 ≈ 0.825 through iterative local regression. Two-stage least squares provides strong evidence of geopolitical and temporal influences. Iterative local regression produces implicit vectors of coefficients and p-values that reinforce some causal inferences of the unconditional model for rail passenger traffic while simultaneously undermining others.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011030

Authors: Pierre Bouny Eric Grivel Roberto Diversi Veronique Deschodt Arsac

In this paper, interpersonal coordination is studied by analyzing physiological synchronization between individuals. To this end, a four-phase protocol is proposed to collect biosignals from the participants in each dyad. Then, the time evolution of the low-frequency (LF) power of the heart rate variability process for each participant is deduced. Finally, an approach based on a bivariate autoregressive model and Granger causality is proposed to determine whether a dependency exists between the biosignals. The approach is first applied to synthetic data and then to real data. This method has the advantage of providing explicit modeling of the dependency, which can help physiologists achieve better interpretation.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011029

Authors: S M Ahasanul Karim Bahram Zarrin Niels Buus Lassen

Generative models are being used in all domains. While primarily built for processing texts and images, their reach has been further extended towards data-driven forecasting. Whereas there are many statistical, machine learning and deep learning models for predictive forecasting, generative models are special because they do not need to be trained beforehand, saving time and computational power. Also, multivariate forecasting with the existing models is difficult when the future horizons are unknown for the regressors because they add mode uncertainties in the forecasting process. Thus, this study experiments with TimeGPT(Zeroshot) by Nixtla where it tries to identify if the generative model can outperform other models like ARIMA, Prophet, NeuralProphet, Linear Regression, XGBoost, Random Forest, LSTM, and RNN. To determine this, the research created synthetic datasets and synthetic signals to assess the individual model performances and regressor performances for 12 models. The results then used the findings to assess the performance of TimeGPT in comparison to the best fitting models in different real-world scenarios. The results showed that TimeGPT outperforms multivariate forecasting for weekly granularities by automatically selecting important regressors whereas its performance for daily and monthly granularities is still weak.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011027

Authors: Polycarp Shizawaliyi Yakoi Xiangfu Meng Danladi Suleman Adeleye Idowu Victor Adeyi Odeh Chunlin Yu

This study re-examines the balance between architectural intricacy and generalization in Transformer models for long-term time series predictions. We perform a systematic comparison involving a lightweight baseline (iTransformer) and two enhanced versions: MiTransformer, which incorporates an external memory component for extending context, and DFiTransformer, which features dual-frequency decomposition along with Learnable Cross-Frequency Attention. All models undergo training using the same protocols across eight standard benchmarks and four forecasting periods. Findings indicate that both MiTransformer and DFiTransformer do not reliably surpass the baseline. In many instances, the increased complexity leads to greater variance and decreased accuracy, especially with unstable or inconsistent datasets. These results imply that architectural minimalism, when effectively refined, can match or surpass the effectiveness of more complex designs—challenging the prevailing trend toward increasingly intricate forecasting architectures.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011020

Authors: Paridhi Talwar Aman Jain Eugene Pinsky

Dramatic price swings and the possibility of extreme returns have made Bitcoin a hot topic of interest for investors and researchers alike. With the help of advanced neural network models including CNN, RCNN, and LSTM networks, this paper has delved deep into the intricacies of Bitcoin price behavior. We will study different time intervals—close-to-close, close-to-open, open-to-close, and day-to-day—to find a pattern that we can use to develop an investment strategy. The average volatility over a year, six months, and three months is compared with the predictive power of volatility versus a traditional buy-and-hold strategy. Our findings point out the strengths and weaknesses of each neural network model and provide useful insights into optimizing cryptocurrency portfolios. This study contributes to the literature on the price prediction and volatility analysis of cryptocurrencies, thus providing useful information to both researchers and investors to execute strategic steps within the volatile cryptocurrency market.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011019

Authors: Alina Timmermann Ananya Pal

Accurate forecasts play a crucial role in various industries, where enhancing forecast accuracy has been a major focus of research. However, for volatile data and industrial applications, ensuring the reliability and interpretability of forecast results is equally important. This study shifts the focus from predicting future values to estimating forecast accuracy with confidence when no future validation data is present. To achieve this, we use time series characteristics calculated by statistical tests and estimate forecast accuracy metrics. For this, two methods are applied: Estimation by the euclidean distances between time series characteristic values, and second, estimation by clustering of time series characteristics. In-sample forecast accuracy serves as a benchmark method. A diverse, industrial data set is used to evaluate the methods. The results demonstrate that there is significant correlation between certain time series characteristics and estimation quality of forecast accuracy metrics. For all forecast accuracy metrics, the two proposed methods outperform the in-sample forecast estimation. These findings contribute to improving the reliability and interpretability of forecast evaluations, particularly in industrial applications with unstable data.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011026

Authors: Julio Losada-Rodríguez Pedro A. Castillo Antonio Mora Pablo García-Sánchez

Video games, especially competitive ones such as Dota 2, have gained great relevance both as entertainment and in e-sports, where predicting the outcome of games can offer significant strategic advantages. In this context, machine learning (ML) is presented as a useful tool for analysing and predicting performance in these games based on data collected before the start of the games, such as character selection information. Thus, in this work, we have developed and tested ML models, including Random Forest and Gradient Boosting, to predict the outcome of Dota 2 matches. This study is innovative in that it incorporates explainability techniques using Shapley Additive Explanations (SHAP) graphs, allowing us to understand which specific factors influence model predictions. Data extracted from the OpenDota API were preprocessed and used to train the models, evaluating them using metrics such as accuracy, precision, recall, F1-score, and cross-validated accuracy. The results indicate that predictive models, particularly Random Forest, can accurately predict game outcomes based only on pregame information, also suggesting that the explainability of machine learning techniques can be effective for analysing strategic factors in competitive video games.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011025

Authors: Luciano Cabral Luam Santos Jário Santos Júnior Thyago Oliveira Dalgoberto Pinho Júnior Nicholas Cruz Joana Lobo Breno Duarte Lenardo Silva Rafael Silva Bruno Pimentel

The accurate forecasting of student disability trends is essential for optimizing educational accessibility and resource distribution in the context of Brazil’s oldest public policy, the National Textbook Program (PNLD). This study applies machine learning (ML) and time series forecasting models (TSF) to predict the number of visually impaired students in Brazil using educational census data from 2021 to 2023, with the aim of estimating the amount of Braille textbooks to be acquired in the PNLD’s context. By performing a comparative analysis on various ML models (e.g, Naive Bayes, ElasticNet, gradient boosting) and TSF techniques (e.g., ARIMA and SARIMA models, as well as exponential smoothing) to predict future enrollment trends, we identify the most effective approaches for school-level and long-term disability enrollment predictions. Results show that ElasticNet and gradient boosting excel in forecasting enrollment estimations over TSF models. Despite challenges related to data inconsistencies and reporting variations, incorporating external demographic and health data could further improve predictive accuracy. This research contributes to AI-driven educational accessibility by demonstrating how predictive analytics can enhance policy decisions and ensure an equitable distribution of resources for students with disabilities.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011024

Authors: James Ming Chen

Economic data is highly dependent on its arrangement within space and time. Perhaps the most obvious and important definition of space is geospatial configuration on the Earth’s surface. Consideration of geospatial effects produces a dramatic improvement in the prediction of median housing prices across 20,640 districts in California. Unconditional regression with engineered variables, two-stage least squares regression (2SLS), and iterative local regression approach r2 ≈ 0.8536, the goodness of fit attained in the original California study. Geospatial methods can be generalized to panel data analysis and time-series forecasting. Distance-sensitive analysis reveals the value of treating time-variant data as potentially discrete and discontinuous. This insight highlights the value of methodologies that suspend the assumption that data varies in a continuous or even linear fashion across space and time.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011023

Authors: Ayauzhan Arystambekova Eugene Pinsky

This paper applies hierarchical clustering and Hamming Distance to analyze the temporal trends of infectious diseases across different regions of Uzbekistan. By leveraging hierarchical clustering, we effectively group regions based on disease similarity without requiring predefined cluster numbers. Hamming Distance further quantifies disease trajectory similarities, helping assess epidemiological patterns over time. Binary tree visualizations enhance the interpretability of clustering results, offering a novel method for identifying regional trends. The dataset includes yearly incidence rates of seven infectious diseases from 2012 to 2019, along with population, healthcare infrastructure, and geographic attributes for each region. This approach provides an interpretable framework for public health analysis and decision-making.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011022

Authors: Hao Niu Guillaume Habault Huy Quang Ung Roberto Legaspi Zhi Li Yanan Wang Donghuo Zeng Julio Vizcarra Masato Taya

Anomaly detection in time series data is crucial across various domains. Traditional methods often struggle with continuously evolving time series requiring adjustment, whereas large language models (LLMs) and multi-modal LLMs (MLLMs) have emerged as promising zero-shot anomaly detectors by leveraging embedded knowledge. This study expands recent evaluations of MLLMs for zero-shot time series anomaly detection by exploring newer models, additional input representations, varying input sizes, and conducting further analyses. Our findings reveal that while MLLMs are effective for zero-shot detection, they still face limitations, such as effectively integrating both text and vision representations or handling longer input lengths. These challenges unveil diverse opportunities for future improvements.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011021

Authors: Leonard Dervishi Antonios Raptakis Gerald Bieber

Effective forecasting is vital in various domains as it supports informed decision-making and risk mitigation. This paper aims to improve the selection of appropriate forecasting methods for univariate time series. We propose a systematic categorization based on key characteristics, such as stationarity and seasonality and analyze well-known forecasting techniques suitable for each category. Additionally, we examine how forecasting horizons, the time periods for which forecasts are generated, affect method performance, thus addressing a significant gap in the existing literature. Our findings reveal that certain techniques excel in specific categories and demonstrate performance progression over time, indicating how they improve or decline relative to other techniques. By enhancing the understanding of method effectiveness across diverse time series characteristics, this research aims to guide professionals in making informed choices for their forecasting needs.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011017

Authors: Kárel García-Medina Daniel Estevez-Moya Ernesto Estevez-Rams Reinhard B. Neder

Natural dynamical systems can often display various long-term behaviours, ranging from entirely predictable decaying states to unpredictable, chaotic regimes or, more interestingly, highly correlated and intricate states featuring emergent phenomena. That, of course, imposes a level of generality on the models we use to study them. Among those models, coupled oscillators and cellular automata (CA) present a unique opportunity to advance the understanding of complex temporal behaviours because of their conceptual simplicity but very rich dynamics. In this contribution, we review the work completed by our research team over the last few years in the development and application of an alternative information-based characterization scheme to study the emergent behaviour and information handling of nonlinear systems, specifically Adler-type oscillators under different types of coupling: local phase-dependent (LAP) coupling and Kuramoto-like local (LAK) coupling. We thoroughly studied the long-term dynamics of these systems, identifying several distinct dynamic regimes, ranging from periodic to chaotic and complex. The systems were analysed qualitatively and quantitatively, drawing on entropic measures and information theory. Measures such as entropy density (Shannon entropy rate), effective complexity measure, and Lempel–Ziv complexity/information distance were employed. Our analysis revealed similar patterns and behaviours between these systems and CA, which are computationally capable systems, for some specific rules and regimes. These findings further reinforce the argument around computational capabilities in dynamical systems, as understood by information transmission, storage, and generation measures. Furthermore, the edge of chaos hypothesis (EOC) was verified in coupled oscillators systems for specific regions of parameter space, where a sudden increase in effective complexity measure was observed, indicating enhanced information processing capabilities. Given the potential for exploiting this non-anthropocentric computational power, we propose this alternative information-based characterization scheme as a general framework to identify a dynamical system’s proximity to computationally enhanced states. Furthermore, this study advances the understanding of emergent behaviour in nonlinear systems. It explores the potential for leveraging the features of dynamical systems operating at the edge of chaos by coupling them with computationally capable settings within machine learning frameworks, specifically by using them as reservoirs in Echo State Networks (ESNs) for time series forecasting and predictive modeling. This approach aims to enhance the predictive capacity, particularly that of chaotic systems, by utilising EOC systems’ complex, sensitive dynamics as the ESN reservoir.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011016

Authors: Ciaran O’Connor Andrea Visentin Steven Prestwich

Time series forecasting is a cornerstone of decision-making in energy and finance, yet many studies fail to rigorously analyse the underlying dataset characteristics, leading to suboptimal model selection and unreliable outcomes. This paper addresses these shortcomings by presenting a comprehensive framework that integrates fundamental time series diagnostics—stationarity tests, autocorrelation analysis, heteroscedasticity, multicollinearity, and correlation analysis—into forecasting workflows. Unlike existing studies that prioritise pre-packaged machine learning and deep learning methods, often at the expense of interpretable statistical benchmarks, our approach advocates for the combined use of statistical models alongside advanced machine learning methods. Using the Day-Ahead Market dataset from the Irish electricity market as a case study, we demonstrate how rigorous statistical diagnostics can guide model selection, improve interpretability, and improve forecasting accuracy. This work offers a novel, integrative methodology that bridges the gap between statistical rigour and modern computational techniques, improving reliability in time series forecasting.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011015

Authors: S M Ahasanul Karim Bahram Zarrin Niels Buus Lassen

Demand forecasting is different from traditional forecasting because it is a process of forecasting multiple time series collectively. It is challenging to implement models that can generalise and perform well while forecasting many time series altogether, based on accuracy and scalability. Moreover, there can be external influences like holidays, disasters, promotions, etc., creating drifts and structural breaks, making accurate demand forecasting a challenge. Again, these external features used for multivariate forecasting often worsen the prediction accuracy because there are more unknowns in the forecasting process. This paper attempts to explore effective ways of leveraging the exogenous regressors to surpass the accuracy of the univariate approach by creating synthetic scenarios to understand the model and regressors’ performances. This paper finds that the forecastability of the correlated external features plays a big role in determining whether it would improve or worsen accuracy for models like ARIMA, yet even 100% accurately forecasted extra regressors sometimes fail to surpass their univariate predictive accuracy. The findings are replicated in cases like forecasting weekly docked bike demand per station every hour, where the multivariate approach outperformed the univariate approach by forecasting the regressors with Bi-LSTM and using their predicted values for forecasting the target demand with ARIMA.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011014

Authors: José Gerardo Covarrubias Xuedong Liu

This study analyzes the evolution of the Mexico–U.S. trade balance as a seasonally adjusted time series, comparing the Hodrick–Prescott (HP) filter and wavelet analysis. The HP filter allowed the trend and cycle to be extracted from the series, while wavelets decomposed the information into different time scales, revealing short-, medium-, and long-term fluctuations. The results show that HP provides a simplified view of the trend, while wavelets more accurately capture key events and cyclical dynamics. It is concluded that wavelets offer a more robust tool for studying the volatility and persistence of economic shocks in bilateral trade.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011011

Authors: Natasya Liew Sreeya R. K. Haninatha Sarthak Pattnaik Kathleen Park Eugene Pinsky

Selective voter mobilization dominates U.S. elections, with campaigns prioritizing swing voters to win critical states. While effective for a short-term period, this strategy deepens policy polarization, marginalizes minorities, and undermines representative democracy. This paper investigates voter turnout disparities and policy manipulation using advanced time series forecasting models (ARIMA, LSTM, and seasonal decomposition). Analyzing demographic and geographic data, we uncover significant turnout inequities, particularly for marginalized groups, and propose actionable reforms to enhance equitable voter participation. By integrating data-driven insights with theoretical perspectives, this study offers practical recommendations for campaigns and policymakers to counter polarization and foster inclusive democratic representation.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011037

Authors: Ajmal Shahbaz Syed U. Yunas Emma M. Baxter Mark F. Hansen Melvyn L. Smith Lyndon N. Smith

Stress, being an inherent trait, is a major driver of farm animal disease, leading to significant antimicrobial use (AMU). AMU is the recognized source of antimicrobial resistance (AMR). Among other ways, AMR spread can be controlled by selective breeding. To address this, stress susceptibility among daughters (gilts) of stressed mothers (sows) is tracked using AI and computer vision techniques. A deep learning-based model is trained and validated on the ground truth labels (through behaviour testing during recording of the videos) of stress susceptibility (SS) of mothers (sows). Then, this trained model is employed as a feature extractor for clustering techniques, such as K-means, Agglomerative, etc. This leads to the conclusion that more than 90% of stress-susceptible (SS) mothers had SS daughters. This result is crucial, as it can ease the process of selective breeding, where low stress-susceptible (LS) mothers could further be used for the breeding of the new generation.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011036

Authors: Khalil Mhadhbi Yossr Ghanmi

This study examines volatility transmission between major European indices (CAC 40, DAX, FTSE MIB, IBEX 35, EURO STOXX 50) and Tunisia’s TUNINDEX amid global crises (2008 financial crisis, COVID-19, Russo-Ukrainian war). Using GARCH(1,1) and BEKK models, the analysis reveals low correlation and weak volatility spillovers between the TUNINDEX and European markets, indicating relative decoupling. ARCH-LM tests confirm conditional heteroskedasticity, while GARCH models show persistent volatility. The BEKK model underscores marginal shock transmission, affirming the TUNINDEX’s independence. These findings suggest diversification benefits for investors but highlight local risk considerations. Practical recommendations are provided for stakeholders, with future research directions including asymmetric effects and high-frequency data analysis.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011035

Authors: Yuvraj Sunecher Naushad Mamode Khan Paulo Canas Rodrigues

The city of Pittsburg, Pennsylvania, remains -the epicenter of aggravated assaults this year. Compared to its pre-pandemic figures, violent crimes saw an upsurge with theft topping the city crime list. This study assessed the trend of crime series, particularly thefts, robberies, and burglaries, in two specific periods, namely from January 1990 to December 2001 and from 1 July 2023 to 30 September 2023, in Pittsburg using the discrete valued time series processes, with some popular innovation distributions that have recently emerged. The upward trend in thefts, robberies, and burglaries was affiliated with a shortage of police, existing police officers’ low morale, the latter’s anti-police demeanours, weak crime laws, gun proliferation, falling inflation rates, a rise in the consumers’ price index, uncomfortable homes, life insecurity, poverty, alcohol, drugs, and a devalued society. Thus, the implications include a need to strengthen existing crime laws, to create a diversion judiciary system offering alternatives to high-cost incarcerations provided that culprits adhere to the programs, and to establish evidence-based policies rooted in effective approaches.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011034

Authors: Yuvraj Sunecher Naushad Mamode Khan Muhammed Rasheed Irshad Hendrik Willem Pretorius

This paper proposes a family of first order bivariate integer-valued autoregressive (BINAR(1)) with Poisson Lindley innovations (BINAR(1)PL). The model parameters are estimated using the conditional maximum likelihood (CML) estimation approach. The proposed models are applied on some real life crime data.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011018

Authors: Saeed Varasteh Yazdi

Reliable demand forecasting is crucial for effective supply chain management, where inaccurate forecasts can lead to frequent out-of-stock or overstock situations. While numerous statistical and machine learning methods have been explored for demand forecasting, reinforcement learning approaches, despite their significant potential, remain little known in this domain. In this paper, we propose a multi-agent deep reinforcement learning solution designed to accurately predict demand across multiple stores. We present empirical evidence that demonstrates the effectiveness of our model using a real-world dataset. The results confirm the practicality of our proposed approach and highlight its potential to improve demand forecasting in retail and potentially other forecasting scenarios.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011012

Authors: Martin Chanza Modisane Seitshiro

This study investigates the behavior of South African stock prices during divestment periods using mixture distributions. Divestment often triggers significant market reactions, necessitating a deeper understanding of stock return distributions in such events. Given the complexities of emerging markets like South Africa, this research models stock price behavior to assess associated risks. A mixture distribution approach is employed to capture the return dynamics of stocks listed on the Johannesburg Stock Exchange (JSE) between 2015 and 2024. Gaussian Mixture Models (GMMs), Lognormal Mixture, and Student’s t mixture models are applied to financial, technology, and energy stocks affected by divestment. Statistical tests including AIC and BIC assess the model performance. Mixture distributions outperform single-distribution models, effectively capturing heavy tails, volatility clustering, and asymmetry in stock returns. The GMM and Student’s t mixture models provide the best fit, revealing increased volatility and extreme negative returns following divestment events. Mixture distributions offer a robust framework for modeling South African stock prices during divestment periods. These models enhance the understanding of market dynamics, supporting better financial modeling and risk management in emerging markets.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011007

Authors: Sami Diaf Rachid Toumache

Oil, as a key commodity in international markets, bears an importance for both producers and consumers. For oil-exporting countries, periodic fluctuations have a considerable impact on the economic status and the way monetary and fiscal policies should be conducted in the future. While most of academic efforts tried to link low-frequency real exchange rate with macroeconomic fundamentals for medium-/long-term inference, they omitted to gauge the volatile and complex high-frequency linkage between oil prices and exchange rate fluctuations. The inherent non-linear characteristics of such time series preclude the use of traditional tools or aggregated schemes based on lower frequencies for inference purposes. This work investigates the scale-based volatile linkage between daily international oil fluctuations and nominal exchange rate variations of an oil-exporting country, namely Algeria, by adopting a fractal regression approach to uncover the power-law, time-varying transmission and track its incidence in the short and long runs. Results show the absence of any short-term transmission mechanism from oil prices to the exchange rate, as the two variables remain decoupled but exhibit an increasing negative correlation when long scales are considered. Furthermore, the multiscale regression analysis confirms the existence of a scale-free, two-state Markov switching regime process generating short- and long-term impacts with sizeable amplitudes. The findings confirm the usefulness of monetary policy interventions to stabilize the local currency, as the source of Dollar–Dinar multifractality was found to be the probability distribution of observations rather than long-range correlations specific to oil prices.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011013

Authors: Krzysztof Drachal Joanna Jędrzejewska

This paper explores the forecasting of aluminum prices using various predictive models dealing with variable uncertainty. A diverse set of economic and market indicators is considered as potential price predictors. The performance of models including LASSO, RIDGE regression, time-varying parameter regressions, LARS, ARIMA, Dynamic Model Averaging, Bayesian Model Averaging, etc., is compared according to forecast accuracy. Despite the initial expectations that Bayesian dynamic mixture models would provide the best forecast accuracy, the results indicate that forecasting by futures prices and with Dynamic Model Averaging outperformed all other methods when monthly average prices are considered. Contrary, when monthly closing spot prices are considered, Bayesian dynamic mixture models happen to be very accurate compared to other methods, although beating the no-change method is still a hard challenge. Additionally, both revised and originally published macroeconomic time-series data are analyzed, ensuring consistency with the information available during real-time forecasting by mimicking the perspective of market players in the past.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011010

Authors: Alexander Tyrsin Michail Gerasimov Michael Beer

In economics, risk analysis is often associated with certain difficulties. These include the presence of several correlated risk factors, non-stationarity of economic processes, and small data samples. A mathematical model of multidimensional risk is described which satisfies the main features of processes in the economy. In the task of risk monitoring, we represent the analyzed factors as a set of correlated non-stationary time series. The method allows us to assess the risk at each moment using small data samples. For this purpose, risk factors are locally described in the form of parabolic or linear trends. An example of monitoring the risk of reducing the level of socio-economic development of Russia in 2000–2023 is considered. The monitoring results showed that the proposed multivariate risk model was generally sensitive to all the most significant economic shocks and adequately responded to them.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011009

Authors: Minfei Liang Yu Gao Eugene Pinsky

Since the 19th century, the development of metallurgical technology has been influenced by various factors, such as materials, casting technology, political policies, and the economic development of different countries. This paper aims to analyze the time-series evolution trend in medal issues in different countries and explore their historical and commemorative significance. Taking the characteristics of medal production places, types, compositions, diameters, weights, shapes, compositions, and thicknesses between 1850 and 2025 as indicators, data analysis methods such as time series, hierarchical cluster analysis (HCA), logistic regression, and random forests are used to study the process of medal development and influencing factors in the past 175 years. The results show that compared with the pre-World War II period, the weight and diameter of all medals of major countries changed significantly in different periods. Moreover, before and after World War II, there was a shift from traditional materials to cost-effective and convenient alternatives.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011008

Authors: Diana Alejandra Godoy Pulecio César Andrés Ojeda Echeverri

This research focuses on the study of stochastic processes with irregularly spaced time intervals, which is present in a wide range of fields such as climatology, astronomy, medicine, and economics. Some studies have proposed irregular autoregressive (iAR) and moving average (iMA) models separately, and moving average autoregressive processes (iARMA) for positive autoregressions. The objective of this work is to generalize the iARMA model to include negative correlations. A first-order moving average autoregressive model for irregular discrete time series is presented, being an ergodic and strictly stationary Gaussian process. Parameter estimation is performed by Maximum Likelihood, and its performances are evaluated for finite samples through Monte Carlo simulations. The estimation of the autocorrelation function (ACF) is performed using the DCF (Discrete Correlation Function) estimator, evaluating its performance by varying the sample size and average time interval. The model was implemented on real data from two different contexts; the first one consists of the two-week measurement of star flares of the Orion Nebula in the development of the COUP and the second pertains to the measurement of sunspot cycles from 1860 to 1990 and their relationship to temperature variation in the northern hemisphere.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011028

Authors: Mariem Bouattour Malek Abaab Hajer Chibani Hamdi Becha Kamel Helali

This study examines the synchronization of economic and growth cycles between China and the United States of America amid ongoing economic and geopolitical tensions. Using a Markov-Switching–Vector Autoregression (MS-VAR) model, the analysis applies the Hodrick–Prescott and Baxter–King filters to monthly data from January 2000 to December 2024, capturing trends and cyclical fluctuations. The findings reveal asymmetries in economic synchronization, with differences in recession and expansion durations influenced by trade disputes, financial integration, and external shocks. As the rivalry between the two nations intensifies, marked by trade wars, technological competition, and geopolitical conflicts, understanding their economic co-movement becomes crucial. This study contributes to the literature by providing empirical insights into their evolving interdependence and offers policy recommendations for mitigating asymmetric shocks and promoting global economic stability.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011006

Authors: Zibo Wang Weiqi Zhang Eugene Pinsky

Accurate and concise temperature prediction models have important applications in meteorological science, agriculture, energy, and electricity. This study aims to compare the performance of simple models and deep learning models in temperature prediction and explore whether simple models can replace deep learning models in specific scenarios to save computing resources. Based on 37 years of daily temperature time series data from 10 cities from 1987 to 2024, the Simple Moving Average (SMA), Seasonal Average Method with Lookback Years (SAM-Lookback), and Long Short-Term Memory (LSTM) models are fitted to evaluate the accuracy of simple models and deep learning models in temperature prediction. The performance of different models is intuitively compared by calculating the RMSE and Percentage Error of each city. The results show that LSTM has higher accuracy in most cities, but the prediction results of SMA and LSTM are similar and perform equally well, while SAM-Lookback is relatively weak.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011005

Authors: Luis Fernando Alvarez-Velasquez Eduardo Giraldo

In this work, we propose a nonlinear dynamic inverse solution to the diffusion problem based on Krylov Subspace Methods with spatiotemporal constraints. The proposed approach is applied by considering, as a forward problem, a 1D diffusion problem with a nonlinear diffusion model. The dynamic inverse problem solution is obtained by considering a cost function with spatiotemporal constraints, where the Krylov subspace method named the Generalized Minimal Residual method is applied by considering a linearized diffusion model and spatiotemporal constraints. In addition, a Jacobian-based preconditioner is used to improve the convergence of the inverse solution. The proposed approach is evaluated under noise conditions by considering the reconstruction error and the relative residual error. It can be seen that the performance of the proposed approach is better when used with the preconditioner for the nonlinear diffusion model under noise conditions in comparison with the system without the preconditioner.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011004

Authors: Konstantinos Mavrogiorgos Athanasios Kiourtis Argyro Mavrogiorgou Dimitrios Apostolopoulos Andreas Menychtas Dimosthenis Kyriazis

The formulation of touristic policies is a time-consuming process that consists of a wide range of steps and procedures. These policies are highly dependent on the number of tourists and visitors to an area to be as effective as possible. The estimation of this number is not always easy to achieve, since there is a lack of the corresponding data (i.e., number of visitors per day). Hence, this estimation must be achieved by utilizing alternative data sources. To this end, in this paper, the authors propose a neural network architecture that is trained on waste management data to estimate the number of visitors and tourists in the highly touristic municipality of Vari-Voula-Vouliagmeni, Greece.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011003

Authors: Omid M. Ardakani

This paper develops a novel entropy-based framework to quantify tail risk and detect speculative bubbles in financial markets. By integrating extreme value theory with information theory, I introduce the Tail-Weighted Entropy (TWE) measure, which captures how information scales with extremeness in asset price distributions. I derive explicit bounds for TWE under heavy-tailed models and establish its connection to tail index parameters, revealing a phase transition in entropy decay rates during bubble formation. Empirically, I demonstrate that TWE-based signals detect crises in equities, commodities, and cryptocurrencies days earlier than traditional variance-ratio tests, with Bitcoin’s 2021 collapse identified weeks prior to the peak. The results show that entropy decay—not volatility explosions—serves as the primary precursor to systemic risk, offering policymakers a robust tool for preemptive crisis management.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010018

Authors: Hicham Gibet Tani Mohamed Kouissi Mohamed Ben Ahmed Anouar Boudhir Abdelhakim Lotfi Elaachak

n/a

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011002

Authors: Marta Ferreira Liliana Monteiro

Extreme value theory comprises a set of techniques for inference at the tail of distributions, where data are scarce or non-existent. The tail index is the main parameter, with risk measures such as value at risk or expected shortfall depending on it. In this study, we will analyze a method for estimating the tail index through a simulation study. This will allow for an application using real data including the estimation of the mentioned risk measures.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010017

Authors: Anouar El Mourabit Ibrahim Hadj Baraka

This manuscript investigates the feasibility of Four-In-Wheel Electronic Differential Systems (4 IW-EDSs) within contemporary electric vehicles (EVs), emphasizing their benefits for stability regulation predicated on steering angles. Through an extensive literature review, we conduct a comparative analysis of various in-wheel-motor models in terms of power output, efficiency, and torque characteristics. Furthermore, we explore the distinctions between IW-EDSs and steer-by-wire systems, as well as conventional systems, while evaluating recent research findings to determine their implications for the evolution of electric mobility. Moreover, this paper addresses the necessity for fault-tolerant methodologies to boost reliability in practical applications. The findings yield valuable insights into the challenges and impacts associated with the implementation of differential steering control in four-wheel independent-drive electric vehicles. This study aims to explore the interaction between these systems, optimize torque distribution, and discover the most ideal control strategy that will improve maneuverability, stability, and energy efficiency, thereby opening up new frontiers in the development of next-generation electric vehicles with unparalleled performance and safety features.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025011001

Authors: Marius Syberg Lucas Polley Jochen Deuse

Sales forecasting in make-to-order (MTO) production is particularly challenging for small- and medium-sized enterprises (SMEs) due to high product customization, volatile demand, and limited historical data. This study evaluates the practical feasibility and accuracy of statistical and machine learning (ML) forecasting methods in MTO settings across three manufacturing sectors: electrical equipment, steel, and office supplies. A cross-industry benchmark assesses models such as ARIMA, Holt–Winters, Random Forest, LSTM, and Facebook Prophet. The evaluation considers error metrics (MAE, RMSE, and sMAPE) as well as implementation aspects like computational demand and interpretability. Special attention is given to data sensitivity and technical limitations typical in SMEs. The findings show that ML models perform well under high volatility and when enriched with external indicators, but they require significant expertise and resources. In contrast, simpler statistical methods offer robust performance in more stable or seasonal demand contexts and are better suited in certain cases. The study emphasizes the importance of transparency, usability, and trust in forecasting tools and offers actionable recommendations for selecting a suitable forecasting configuration based on context. By aligning technical capabilities with operational needs, this research supports more effective decision-making in data-constrained MTO environments.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010014

Authors: Mohamed Ben jouad Lotfi Elaachak

Large language models (LLMs) are developing at a rapid pace, which has made it necessary to better understand how they train, especially when faced with resource limitations. This paper examines in detail how various state-of-the-art LLMs train on a single Graphical Processing Unit (GPU), paying close attention to crucial elements like throughput, memory utilization and training time. We find important trade-offs between model size, batch size and computational efficiency through empirical evaluation, offering practical advice for streamlining fine-tuning processes in the face of hardware constraints.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010013

Authors: Lamiae Eloutouate Hicham Gibet Tani Lotfi Elaachak Fatiha Elouaai Mohammed Bouhorma

The application of machine learning (ML) to medical datasets offers significant potential for improving disease prediction and patient outcomes. However, challenges such as feature redundancy, overfitting, and suboptimal model performance limit the practical effectiveness of ML algorithms. This study focuses on optimizing ML techniques for cardiovascular disease prediction using the Kaggle Cardiovascular Disease dataset. We systematically apply feature selection methods, including correlation analysis and regularization techniques (L1/L2), to identify the most relevant attributes and address multicollinearity. Advanced ensemble models such as Random Forest, XGBoost, and LightGBM are employed to mitigate overfitting and enhance predictive performance. Through hyperparameter tuning and stratified k-fold cross-validation, we ensure model robustness and generalizability. The results demonstrate that ensemble methods, particularly gradient boosting algorithms, outperform traditional models, achieving superior predictive accuracy and stability. This study highlights the importance of algorithm optimization in ML applications for healthcare, offering a replicable framework for medical datasets and paving the way for more effective diagnostic tools in cardiovascular health.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010012

Authors: Anass Roman Chaymae Taib Ilham Dhaiouir Haimoudi El Khatir

Machine learning is revolutionizing healthcare by enhancing diagnosis and treatment personalization. This study explores ML applications in medical imaging, analyzing data from X-rays, CT, MRI, and ultrasound for early disease detection. It reviews key ML models, including SVM, ANN, RF, CNN, and other methods, demonstrating their effectiveness in detecting cancers such as lung and prostate cancer and other diseases. Despite their accuracy, these methods face challenges such as a reliance on large datasets and significant computational requirements. This study highlights the need for further research to integrate ML into clinical practice, addressing its limitations and unlocking new opportunities for improved patient care.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010011

Authors: Ikram Lefhal Lalaoui Essaid El Haji Mohamed Kounaidi

The importance of real-time big data has become crucial in the digital revolution of modern society, in the context of increasing data flows from multiple sources, including social media, internet connected devices (IOT) and financial systems, real-time analysis and processing is becoming a strategic tool for fast and accurate decision making, we find applications in different domains such as healthcare, finance, and digital marketing, which is revolutionizing traditional business models. In this article, we explore the recent advances and future prospects of real-time big data. Our research is based on recent work published between 2020 and 2025, examining the technological advances, the difficulties encountered and suggesting ways of optimizing the efficiency of these technologies.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010010

Authors: Merouane Mouadili El Mokhtar En-Naimi Mohamed Kouissi

Numerous studies in the healthcare field conducted in recent years have highlighted the impact of stress on health and its role in the development of several critical illnesses. Stress monitoring using wearable technologies, such as smartwatches and biosensors, has shown promising results in improving the management of this issue. Data from both physical and mental health can be leveraged to enhance medical decision-making, support research on new treatments, and deepen our understanding of complex diseases. However, traditional machine learning (ML) systems often face limitations, particularly in real-time processing and resource optimization, which restrict their application in critical situations. In this article, we present the development of a deep learning-based approach that leverages models such as 1D CNN (Convolutional Neural Networks), LSTM (Long Short-Term Memory), and Time-Series Transformers, alongside classical deep learning techniques. We then highlight the transformative potential of TinyML for real-time, low-power health monitoring, focusing on Heart Rate Variability (HRV) analysis. This approach aims to optimize personalized health interventions and enhance the accuracy of medical monitoring.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010009

Authors: Arshad Jamal R. Kanesaraj Ramasamy Junaidi Abdullah

The separation of respiratory and cardiac sounds is a significant challenge in biomedical signal processing due to their overlapping frequency and time characteristics. Traditional methods struggle with accurate extraction in noisy or diverse clinical environments. This study explores the application of machine learning, particularly convolutional neural networks (CNNs), to overcome these obstacles. Advanced machine learning models, denoising algorithms, and domain adaptation strategies address challenges such as frequency overlap, external noise, and limited labeled datasets. This study presents a robust methodology for detecting heart and lung diseases from audio signals using advanced preprocessing, feature extraction, and deep learning models. The approach integrates adaptive filtering and bandpass filtering as denoising techniques and variational autoencoders (VAEs) for feature extraction. The extracted features are input into a CNN, which classifies audio signals into different heart and lung conditions. The results highlight the potential of this combined approach for early and accurate disease detection, contributing to the development of reliable diagnostic tools for healthcare.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010007

Authors: Reshma Sreejith R. Kanesaraj Ramasamy Wan-Noorshahida Mohd-Isa Junaidi Abdullah

The accurate and early detection of respiratory diseases is vital for effective diagnosis and treatment. This study presents a new approach for classifying lung sounds using a double denoising method combined with a 1D Convolutional Neural Network (CNN). The preprocessing uses Fast Fourier Transform to clean up sounds and High-Pass Filtering to improve the quality of breathing sounds by eliminating noise and low-frequency interruptions. The Short-Time Fourier Transform (STFT) extracts features that capture localised frequency variations, crucial for distinguishing normal and abnormal respiratory sounds. These features are input into the 1D CNN, which classifies diseases such as bronchiectasis, pneumonia, asthma, COPD, healthy, and URTI. The dual denoising method enhances signal clarity and classification performance. The model achieved 96% validation accuracy, highlighting its reliability in detecting respiratory conditions. The results emphasise the effectiveness of combining signal augmentation with deep learning for automated respiratory sound analysis, with future research focusing on dataset expansion and model refinement for clinical use.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010002

Authors: Fatima Zahrae Chentouf Mohamed El Alami Hasoun Said Bouchkaren

Rapid urbanization and the rising demand for sustainable living have encouraged the growth of smart cities, which incorporate innovative technologies to ameliorate environmental sustainability, optimize resource management, and improve living standards. The convergence of blockchain (BC) technology and the Internet of Things (IoT) presents transformative convenience for managing smart cities and achieving sustainability goals. In fact, blockchain technology combined with IoT devices provides a decentralized, transparent, and safe framework for managing massive volumes of data produced by networked sensors and systems. By guaranteeing accountability, minimizing fraud, and maximizing resource use, blockchain not only facilitates the smooth operation of smart city infrastructures but also encourages sustainable habits. The various uses of blockchain technology in smart city management and its contribution to sustainability objectives are examined in this study. Through an examination of important domains like energy distribution, waste management, transportation systems, healthcare, and governance, the research shows how blockchain promotes effective data exchange and data security, builds stakeholder trust, and makes it possible to establish decentralized organizations to improve decision-making.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010001

Authors: Hicham Gibet Tani Mohamed Kouissi Mohamed Ben Ahmed Anouar Boudhir Abdelhakim Lotfi Elaachak

n/a

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010016

Authors: Camara Alseny Dhaiouir Ilham Haimoudi El Khatir

The digital age has transformed education, making distance learning essential. With rapid knowledge evolution, flexible and personalized learning is crucial. This article examines how ontology and semantic web technologies enhance e-learning. Ontology structures knowledge in specific domains, while the semantic web enables data automation and integration. Their adoption revolutionizes content organization and personalization. This study explores key concepts, applications, benefits, challenges, and future implications. By analyzing innovations and obstacles, it provides recommendations for educators. Ultimately, it highlights the need for a collaborative approach to leverage these technologies for a more inclusive and adaptive educational environment.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010015

Authors: Abdellah Dardour Essaid El Haji Mohamed Achkari Begdouri

The rapid growth of information and communication technologies, in particular big data, artificial intelligence (AI), and the Internet of Things (IoT), has made it possible to make smart cities a tangible reality. In this context, real-time video surveillance plays a crucial role in improving public safety. This article presents a systematic review of studies focused on the detection of acts of aggression and crime in these cities. By studying 100 indexed scientific articles, dating from 2018 to 2024, we examine the most recent methods and techniques, with an emphasis on the use of machine learning and deep learning for the processing of real-time video streams. The works examined cover several technological axes such as convolutional neural networks (CNNs), fog computing, and integrated IoT systems while also addressing issues such as the challenges related to the detection of anomalies, frequently affected by their contextual and uncertain nature. Finally, this article offers suggestions to guide future research, with the aim of improving the accuracy and efficiency of intelligent monitoring systems.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010008

Authors: Oumayma Berraadi Hicham Gibet Tani Mohamed Ben Ahmed

The rapid expansion of IoT in smart cities has improved traffic management but increased security risks. Traditional IDS struggle with advanced threats, prompting adaptive solutions. This work proposes a framework combining machine learning (ML), Zero Trust Architecture (ZTA), and blockchain authentication. Supervised models (XGBoost, RF, SVM, LR) detect known anomalies, while a CNN Autoencoder identifies novel threats. Blockchain ensures identity integrity, and compromised devices are isolated automatically. Tests on the IoT-23 dataset demonstrate superior accuracy, fewer false positives, and better scalability than conventional methods. The integration of AI, Zero Trust, and blockchain significantly boosts IoT traffic system security and resilience.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010006

Authors: Jalal El Bahri Mohamed Kouissi Mohammed Achkari Begdouri

This study investigates the energy consumption and carbon footprint of two prominent automatic speech recognition (ASR) systems: OpenAI’s Whisper and Google’s Speech-to-Text API. We evaluate both local and cloud-based speech recognition approaches using a public Kaggle dataset of 20,000 short audio clips in Urdu, utilizing CodeCarbon, PyJoule, and PowerAPI for comprehensive energy profiling. As a result of our analysis, we expose some substantial differences between the two systems in terms of energy efficiency and carbon emissions, with the cloud-based solution showing substantially lower environmental impact despite comparable accuracy. We discuss the implications of these findings for sustainable AI deployment and minimizing the ecological footprint of speech recognition technologies.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010005

Authors: Mohamed Toufik Ailane Carolin Rubner Andreas Rausch

In the era of digital transformation, the environmental impact of software development has become a pressing concern, necessitating the integration of sustainability into software development processes. This paper addresses how DevOps, traditionally celebrated for enhancing efficiency and speed in software delivery, can integrate sustainability principles to mitigate environmental impacts. We propose guidelines for integrating sustainability throughout the DevOps life cycle, aiming for significant carbon footprint reduction without compromising quality. Using a Life Cycle Assessment (LCA) approach, this study enables stakeholders to incorporate green guidelines at various software development and operation stages, enhancing software environmental friendliness. Our model supports sustainable software development and encourages proactive environmental impact minimization.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010004

Authors: Chaymae Abdellaoui Youssef Lagmich

The performance degradation of photovoltaic (PV) systems, comprising solar panels and DC-DC converters, is often caused by various anomalies related to manufacturing defects, operational conditions, or environmental factors. These faults significantly reduce energy output, preventing the system from reaching its nominal power and expected production levels. Given the demonstrated impact of such faults on PV system efficiency, an effective diagnostic method is essential for proactive maintenance and optimal performance. This paper presents a fault detection algorithm based on a Mamdani-type fuzzy logic approach. The proposed method utilizes three key inputs—panel current, panel voltage, and converter voltage—to assess system health. By computing the distortion ratios of these electrical parameters and processing them through a fuzzy logic controller, the algorithm accurately identifies fault conditions. Simulation results validate the effectiveness of this approach, demonstrating its capability to detect and classify 12 distinct faults in both the PV array and the DC-DC converter. The study highlights the potential of fuzzy logic-based diagnostics in enhancing the reliability and maintenance of photovoltaic systems.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2025010003

Authors: Najlae Abarghache Younès Alaoui Soulimani Lotfi Elaachak Abderrahim Ghadi

Digitalization has shaped every part of our world, from education to healthcare, from finance to entertainment, and from manufacturing to social interactions. This digital transformation has put tremendous power in the hands of individuals and delivered even better results than sticking to old, traditional ways. Such effective digitalization cannot be achieved easily; a good digitized system is the product of a lot of effort. In this paper, we explore the state-of-the-art advancements in smart education technologies, analyze existing digital solutions, and outline considerations for developing a tailored system to digitalize the Teaching at the Right Level (TaRL) assessment for Moroccan primary education. Our approach aims to bridge skill gaps by integrating serious games, adaptive learning techniques, and real-time analytics to enhance assessment effectiveness and ease educators’ workloads.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008099

Authors: Hongjian Wang Shan Ouyang Xunlei Chen Yi Jin

Current encryption technologies mostly rely on complex algorithms or difficult mathematical problems to improve security. Therefore, it is difficult for these encryption technologies to possess both high security and high efficiency, which are two properties that people desire. Trying to solve this dilemma, we built a new encryption technology, called configurable encryption technology (CET), based on the typical structure of reconfigurable quaternary logic operator (RQLO) that was invented in 2018. We designed the CET as a block cipher for symmetric encryption, where we use four 32-quit RQLO typical structures as the encryptor, decryptor, and two key derivation operators. Taking advantage of the reconfigurability of the RQLO typical structure, the CET can automatically reconfigure the keys and symbol substitution rules of the encryptor and decryptor after each encryption operation. We found that a chip containing about 70,000 transistors and 500 MB of nonvolatile memory could provide all the CET devices and generalized keys needed for any user’s lifetime, to implement a practical one-time pad encryption technology. We also developed a strategy to solve the current key distribution problem with prestored generalized key source data and on-site appointment codes. The CET is expected to provide a theoretical basis and core technology for using the RQLO to build a new cryptographic system with high security, fast encryption/decryption speed, and low manufacturing cost.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2024009006

Authors: Keying Zhang Ruirui Cai Xinqiao Wu Jiguang Zhao Ping Qin

Three-dimensional semantic segmentation is crucial for comprehending transmission line structure and environment. This understanding forms the basis for a variety of applications, such as automatic risk assessment of line tripping caused by wildfires, wind, and thunder. However, the performance of current 3D point cloud segmentation methods tends to degrade on imbalanced data, which negatively impacts the overall segmentation results. In this paper, we proposed an imBalanced-Aware Long-Range 3D Semantic Segmentation framework (iBALR3D) which is specifically designed for large-scale transmission line segmentation. To address the unsatisfactory performance on categories with few points, an Enhanced Imbalanced Contrastive Learning module is first proposed to improve feature discrimination between points across sampling regions by contrasting the representations with the assistance of data augmentation. A structural Adaptive Spatial Encoder is designed to capture the distinguish measures across different components. Additionally, we employ a sampling strategy to enable the model to concentrate more on regions of categories with few points. This strategy further enhances the model’s robustness in handling challenges associated with long-range and significant data imbalances. Finally, we introduce a large-scale 3D point cloud dataset (500KV3D) captured from high-voltage long-range transmission lines and evaluate iBALR3D on it. Extensive experiments demonstrate the effectiveness and superiority of our approach.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008098

Authors: Xiaoli Yang Songbai Wang

This paper explains that setting up artificial intelligence courses can clearly enhance students’ interest in high technology, boost learning confidence and promote students’ overall development in the following three aspects: the significance of artificial intelligence education to students, the confusion regarding artificial intelligence teaching in this stage, especially in rural middle schools, and some related suggestions.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2024009004

Authors: Girolamo Macaluso Alessandro Sestini Andrew D. Bagdanov

Offline reinforcement learning leverages pre-collected datasets of transitions to train policies. It can serve as an effective initialization for online algorithms, enhancing sample efficiency and speeding up convergence. However, when such datasets are limited in size and quality, offline pre-training can produce sub-optimal policies and lead to a degraded online reinforcement learning performance. In this paper, we propose a model-based data augmentation strategy to maximize the benefits of offline reinforcement learning pre-training and reduce the scale of data needed to be effective. Our approach leverages a world model of the environment trained on the offline dataset to augment states during offline pre-training. We evaluate our approach on a variety of MuJoCo robotic tasks, and our results show that it can jumpstart online fine-tuning and substantially reduce—in some cases by an order of magnitude—the required number of environment interactions.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2024009005

Authors: Matthias Reuse Karl Amende Martin Simon Bernhard Sick

Autonomously driving vehicles in car factories and parking spaces can represent a competitive advantage in the logistics industry. However, the real-world application is challenging in many ways. First of all, there are no publicly available datasets for this specific task. Therefore, we equipped two industrial production sites with up to 11 LiDAR sensors to collect and annotate our own data for infrastructural 3D object detection. These form the basis for extensive experiments. Due to the still limited amount of labeled data, the commonly used ground truth sampling augmentation is the core of research in this work. Several variations of this augmentation method are explored, revealing that in our case, the most commonly used is not necessarily the best. We show that an easy-to-create polygon can noticeably improve the detection results in this application scenario. By using these augmentation methods, it is even possible to achieve moderate detection results when only empty frames without any objects and a database with only a few labeled objects are used.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008096

Authors: Hailong Ji

In this paper, the author starts with a critique of Wiener’s advocated concept of information and provides new definitions for a series of fundamental concepts in the fundamentals of information science. Furthermore, a fresh interpretation of several fundamental issues in information science is presented, thereby establishing a distinct and innovative foundation for information science.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008097

Authors: Yanfang Hou

This paper summarizes the problems existing in cross-border higher education through the analysis of the development status and characteristics of virtual reality technology and cross-border higher education, and puts forward the important significance and enlightenment of the application of virtual reality technology in cross-border higher education in the new era for solving the practical problems of cross-border education. It also points out that the new mode and situation of online and offline joint development created by the integration of virtual reality technology and cross-border higher education will have an important impact on accelerating the opening up of Chinese education and improving the quality and efficiency of cross-border higher education.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2024009003

Authors: Bhargav Dodla Kartik Hegde A. N. Rajagopalan

Vision-language models (VLMs) have demonstrated increasing potency in solving complex vision-language tasks in the recent past. Visual question answering (VQA) is one of the primary downstream tasks for assessing the capability of VLMs, as it helps in gauging the multimodal understanding of a VLM in answering open-ended questions. The vast contextual information learned during the pretraining stage in VLMs can be utilised effectively to finetune the VQA model for specific datasets. In particular, special types of VQA datasets, such as OK-VQA, A-OKVQA (outside knowledge-based), and ArtVQA (domain-specific), have a relatively smaller number of images and corresponding question-answer annotations in the training set. Such datasets can be categorised as data-scarce. This hinders the effective learning of VLMs due to the low information availability. We introduce SemIAug (Semi-Supervised Implicit Augmentation), a model and dataset agnostic strategy specially designed to address the challenges faced by limited data availability in the domain-specific VQA datasets. SemIAug uses the annotated image-question data present within the chosen dataset and augments it with meaningful new image-question associations. We show that SemIAug improves the VQA performance on data-scarce datasets without the need for additional data or labels.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008095

Authors: Jian Zheng Yuting Xie Yaqi Ni

With the development of modern network technology, human beings have constructed a development model of digital society. Human social practice has been given a unique digital color. Digital society determines the existence and development of a digital socialist ideology. At the same time, digital socialist ideology also promotes the development of the Chinese path to modernization in the new era. In the complex era of digital socialization, it is of great practical significance to elaborate on the determinacy of digital socialist ideology, analyze the impact areas of safeguarding digital socialist ideological security, and explore ways to safeguard digital socialist ideological security from multiple perspectives.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2024009002

Authors: Samira Zare Hien Van Nguyen

Standard training via empirical risk minimization may result in making predictions that overly rely on spurious correlations. This can degrade the generalization to out-of-distribution settings where these correlations no longer hold. Invariant learning has been shown to be a promising approach for identifying predictors that ignore spurious correlations. However, an important limitation of this approach is that it assumes access to different “environments” (also known as domains), which may not always be available. This paper proposes a simple yet effective strategy for discovering maximally informative environments from a single dataset. Our frustratingly easy environment discovery (FEED) approach trains a biased reference classifier using a generalized cross-entropy loss function and partitions the dataset based on its performance. These environments can be used with various invariant learning algorithms, including Invariant Risk Minimization, Risk Extrapolation, and Group Distributionally Robust Optimization. The results indicate that FEED can discover environments with a higher group sufficiency gap compared to the state-of-the-art environment inference baseline and leads to improved test accuracy on CMNIST, Waterbirds, and CelebA datasets.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2024009001

Authors: Kuan-Chuan Peng Abhishek Aich Ziyan Wu

In submitting conference proceedings to the Computer Sciences & Mathematics Forum, the volume editors of the proceedings certify to the publisher that all papers published in this volume have been subjected to peer review administered by the volume editors [...]

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008093

Authors: Rafal Maciag

Discourses can be treated as instances of knowledge. The dynamic space in which the trajectories of these discourses are described can be regarded as a model of knowledge. Such a space is called a discursive space. Its scope is defined by a set of discourses. The procedure of constructing such a space is a serious problem, and so far, the only solution has been to identify the dimensions of this space through the qualitative analysis of texts on the basis of the discourses that were identified. This paper proposes a solution by using an extended variant of the embedding technique, which is the basis of neural language models (pre-trained language models and large language models) in the field of natural language processing (NLP). This technique makes it possible to create a semantic model of the language in the form of a multidimensional space. The solution proposed in this article is to repeat the embedding technique but at a higher level of abstraction, that is, the discursive level. First, the discourses would be isolated from the prepared corpus of texts, preserving their order. Then, from these discourses, identified by names, a sequence of names would be created, which would be a kind of supertext. A language model would be trained on this supertext. This model would be a multidimensional space. This space would be a discursive space constructed for one moment in time. The described steps repeated in time would allow one to construct the assumed dynamic space of discourses, i.e., discursive space.

Computer Sciences & Mathematics Forum doi: 10.3390/cmsf2023008094

Authors: Rafal Maciag

Spectacular achievements of the so-called large language models (LLM), a technical solution that has emerged within natural language processing (NLP), are a common experience these days. In particular, this applies to the artificial text generated in various ways by these models. This text represents a level of semantic perfection comparable to that of or even equal to a human. On the other hand, there is extensive and old research on the role and meaning of the text in human culture and society, with a very rich philosophical background gathered in the field of hermeneutics. The paper justifies the necessity of using the research background of hermeneutics to study artificial texts and also proposes the first conclusions about these texts in the context of this background. It is the formulation of foundations of the research area that can be called the hermeneutics of artificial text.