Systems and Soft Computing最新文献

{"title":"Parameter efficient vs full fine-tuning for building children’s myopia prediction models","authors":"Elena Ros-Sánchez ,&nbsp;César Domínguez ,&nbsp;Jónathan Heras ,&nbsp;David Oliver-Gutiérrez ,&nbsp;Didac Royo ,&nbsp;Anna Boixadera Espax ,&nbsp;Miguel Ángel Zapata","doi":"10.1016/j.sasc.2026.200452","DOIUrl":"10.1016/j.sasc.2026.200452","url":null,"abstract":"<div><h3>Background and objective:</h3><div>The prevalence of myopia is increasing globally, with projections suggesting that by 2050, half of the population could be affected and 10% may experience high myopia. High myopia significantly increases the risk of irreversible vision loss due to complications such as myopic macular degeneration, retinal detachment, and glaucoma. Early detection in childhood is therefore crucial to implement timely interventions and prevent progression. However, identifying myopia in clinical practice remains challenging, as current methods often rely on subjective recall or require specialized tests that may not be widely available. This highlights the need for faster, more accessible, and reliable detection methods. Artificial intelligence, particularly deep learning, offers a promising alternative for quickly and accurately identifying myopia in children. This study presents the first application of deep learning methods to predict myopia in children.</div></div><div><h3>Methods:</h3><div>We conducted a comprehensive analysis of different families of deep learning architectures – namely convolutional neural networks, transformers, and state-based models – along with training strategies including Low-Rank Adaptation (LoRA) and full fine-tuning. These models were trained to predict spherical equivalent from retinal fundus images of children.</div></div><div><h3>Results:</h3><div>Our experiments demonstrated that transformer- and state-based architectures outperformed convolutional models. Additionally, full fine-tuning yielded better results compared to LoRA, although the latter is more resource-efficient. The best-performing model, based on the Mamba architecture, achieved a mean absolute error (MAE) of 0.74 diopters in estimating spherical equivalent, a similar result to those obtained in the literature for adult cohorts.</div></div><div><h3>Conclusions:</h3><div>Deep learning models, particularly those based on transformer and Mamba architectures, show strong potential for predicting myopia in children using retinal fundus images. These findings are a step towards the development of scalable and accessible tools for early myopia detection and intervention.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200452"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MoistViT: A vision transformer model for moisture content prediction of wood chips","authors":"Daniel E. Marulanda ,&nbsp;Abdur Rahman ,&nbsp;Jason Street ,&nbsp;Mohammad Marufuzzaman ,&nbsp;Haifeng Wang ,&nbsp;Veera G. Gude ,&nbsp;Randy Buchanan","doi":"10.1016/j.sasc.2025.200429","DOIUrl":"10.1016/j.sasc.2025.200429","url":null,"abstract":"<div><div>Moisture content in wood chips is a critical parameter for industries such as pelleting mills, bio-refineries, paper mills, and renewable energy production. The moisture level significantly influences both the quality of the final product and the efficiency of the production process. Consequently, accurate knowledge of moisture content is of substantial importance to wood chip-reliant industries. However, current methods for determining moisture content are either time-consuming or require costly equipment and specialized setups. Therefore, developing a quick and reliable method for assessing wood chip moisture content is imperative. To address this need, we evaluate fourteen Vision Transformer (ViT) architectures and introduce an optimized model, MoistViT, developed using Bayesian Optimization Hyperband (BOHB) for efficient hyperparameter tuning. Experiments on two wood chip image datasets (1600 total images) show that MoistViT achieves 91% accuracy and 92% F1-score on Source 1 and 93% accuracy and 93% F1-score on Source 2, outperforming all baseline models. Subsequently, a thorough analysis of failure cases has been carried out, including the identification of the most challenging groups of moisture levels. These analyses provide valuable insights into the complex task of determining moisture content from inherently heterogeneous wood chips. The proposed MoistViT demonstrates significant potential for real-time applications in relevant industries, which could ultimately lead to a streamlined production process.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200429"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145792135","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic panel regression with fuzzy outputs: A two-stage estimation framework","authors":"Gholamreza Hesamian ,&nbsp;Arne Johannssen","doi":"10.1016/j.sasc.2026.200454","DOIUrl":"10.1016/j.sasc.2026.200454","url":null,"abstract":"<div><div>Traditional panel data models, while effective in managing longitudinal and cross-sectional variations, are not suitable for handling imprecise data in real-world scenarios caused by vagueness, subjectivity or measurement limitations. To address these issues, this paper introduces a fuzzy linear dynamic panel data model that incorporates fuzzy response variables. Unlike existing approaches, the proposed model accounts for temporal dynamics through lagged fuzzy responses and enables accurate modeling of imprecise data. A two-stage estimation procedure utilizing the least absolute error criterion is proposed for parameter estimation. The method is validated using two real-world data sets, demonstrating superior predictive accuracy compared to existing fuzzy panel models. Thus, this work extends the applicability of panel regression to fuzzy environments and offers a robust framework for analyzing uncertain longitudinal data.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200454"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid data balancing with MLP probabilities-based categorical boosting model for robust intrusion detection system in IoT environment","authors":"A. Mallikarjun,&nbsp;Pramoda Patro","doi":"10.1016/j.sasc.2026.200443","DOIUrl":"10.1016/j.sasc.2026.200443","url":null,"abstract":"<div><div>The rapid expansion of the Internet of Things (IoT) has led to an estimated 29.3 billion connected devices by 2030, generating over 79.4 zettabytes of data annually. However, IoT networks remain highly vulnerable, with nearly 57% of IoT devices susceptible to cyber threats, including Denial-of-Service (DoS) and data spoofing attacks. Existing Intrusion Detection Systems (IDS) often suffer from class imbalance, leading to biased models and reduced detection accuracy for minority attack classes. To address these challenges, a novel Data-Balanced Machine Learning IDS (DBML-IDS) is proposed, integrating data preprocessing, Support Vector Machine (SVM) Weights-based Synthetic Minority Over-sampling Technique (SVWS) for improved data balancing, and a Multi-Layer Perceptron (MLP) Probabilities-based Categorical Boosting (MLPP-CB) classifier. The CICIoT2023 dataset, consisting of two classes (Normal and Attack), is used for evaluation. The proposed DBML-IDS framework ensures optimal feature distribution, mitigates overfitting, and enhances generalization for real-world IoT threat detection. Experimental results demonstrate that DBML-IDS achieves a superior classification performance with accuracy, precision, recall, and an F1-score of 0.9973, outperforming existing IDS models. These findings highlight the effectiveness of the proposed methodology in securing IoT environments against emerging cyber threats.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200443"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146026099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent matching methods for educational resources under a multimodal deep learning framework","authors":"Jing Zhou","doi":"10.1016/j.sasc.2026.200470","DOIUrl":"10.1016/j.sasc.2026.200470","url":null,"abstract":"<div><div>The rapid development of artificial intelligence (AI) and sensor technologies has enabled personalized and adaptive learning experiences. However, traditional educational resource-matching systems struggle to process multimodal data and capture complex semantic relationships, limiting their effectiveness in diverse learning environments. To address these challenges, this study proposes the Attentive Extreme Gradient Sequential Bidirectional Memory Net (AEGSBMN), a novel multimodal deep learning framework that integrates Bidirectional Long Short-Term Memory (Bi-LSTM) networks with an attention mechanism for contextual feature weighting, and an Extreme Gradient Boosting (XGBoost) classifier for final decision-making. The framework was evaluated using a multimodal educational dataset containing textual content, annotated images, and synchronized speech data. Preprocessing included spectral gatingfor audio denoising, histogram equalization for image enhancement, and tokenization withstop-word removalfor text normalization. Feature extraction employed BERT embeddings for text, ResNet-50 for visual data, and Wav2Vec for acoustic signals. Extracted features were fused through Bi-LSTM layers with attention to capture temporal dependencies and highlight salient multimodal features, followed by XGBoost for classification. Experimental results demonstrate that AEGSBMN achieves a matching accuracy of 97%<strong>,</strong> with improved recall, ranking metrics (Recall@1: 88%, Recall@5: 94%, MRR: 91%), and reduced error rates (15.01%). These findings indicate that AEGSBMN effectively enhances semantic alignment, learner comprehension, and adaptive resource retrieval in multimodal educational environments. The framework was implemented in Python<strong>,</strong> using PyTorch and Hugging Face Transformers for deep learning, and XGBoost for classification.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200470"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Applying hidden markov models for user and entity behavioural analytics model","authors":"Bolat Tynymbayev","doi":"10.1016/j.sasc.2026.200467","DOIUrl":"10.1016/j.sasc.2026.200467","url":null,"abstract":"<div><div>Methods and means of illegal infiltration into computer systems of companies have become more intelligent and multi-layered. Consequently, since a complex password is no longer a guarantee of security, the user and entity behaviour analytics increase the security of the company’s computer system. The article proposes a model based on Hidden Markov Model to investigate and formulate the behavioural profile of an attacker in order to increase the accuracy of predicting their future actions. This research assesses the effectiveness of implementing Hidden Markov Model in the entity behaviour analytics system based on the real user activity logs were collected from the SIEM platform deployed in a company with about 1000 employees over a 30 days period (1,2 million events). The logs included authentication events, process creation, registry modification, and network communication data. All events were normalized and correlated using predefined SIEM correlation rules. Hidden Markov Model is used to predict a set of hidden states based on existing observations. The results of the experiments clearly indicate the advantages of using the suggested technique to model discrete time data as it offers significantly less learning time and better performance compared to existing methods. The true positive rate (TPR) score confirms the author’s hypotheses and gives it practical application to avoid missing suspicious events.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200467"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative adversarial networks: A comprehensive survey","authors":"Abdullah Al-Yaari,&nbsp;Youjun Deng","doi":"10.1016/j.sasc.2026.200460","DOIUrl":"10.1016/j.sasc.2026.200460","url":null,"abstract":"<div><div>Generative adversarial networks have become a central framework for learning implicit generative models and producing high-fidelity synthetic data, yet their training dynamics remain fragile, and their design space has expanded rapidly. This survey provides a focused, method-oriented synthesis of the field, organizing key advances by architectural families, objective functions, regularization, optimization, stabilization techniques, and evaluation practice. We summarize representative models from the early formulation to recent large-scale and transformer-based variants, highlight how design choices influence stability, fidelity, diversity, and computational cost, and connect methodological developments to major application areas. We also discuss current limitations and open research directions, including data efficiency, reproducibility, safety, and misuse risks, and the emerging interaction between adversarial learning and other modern generative paradigms.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200460"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mathematical Analysis of Real-Time Data Processing Methods for IoT Applications Based on Hesitant Bipolar Fuzzy Dombi Power Operators","authors":"Tahir Mahmood ,&nbsp;Hafiz Muhammad Waqas ,&nbsp;Ubaid ur Rehman ,&nbsp;Dragan Pamucar","doi":"10.1016/j.sasc.2026.200444","DOIUrl":"10.1016/j.sasc.2026.200444","url":null,"abstract":"<div><div>The rapid growth of Internet of Things (IoT) technologies has made real-time data processing a critical component for efficient monitoring, analysis, and intelligent decision-making in dynamic and large-scale environments. IoT systems continuously generate massive volumes of heterogeneous data that must be processed with minimal latency to ensure timely responses and reliable system performance. Effective real-time data processing enables IoT applications to adapt to changing conditions, enhance operational efficiency, improve safety and reliability, and support time-sensitive services in domains such as smart cities, healthcare monitoring, industrial automation, and intelligent transportation systems. This study presents a comprehensive mathematical framework for the analysis of real-time data processing methods for IoT applications based on hesitant bipolar fuzzy (HBF) Dombi power operators. The proposed model is designed to effectively capture uncertainty, hesitation, and bipolar information that naturally arise in real-world IoT environments due to incomplete, imprecise, and conflicting data sources. By incorporating a multi-criteria decision-making (MCDM) approach, multiple real-time data processing techniques are systematically evaluated and prioritized with respect to several performance-related attributes. The proposed HBF Dombi power-based framework offers a reliable and transparent mechanism for comparing competing real-time data processing strategies and selecting the most suitable method for specific IoT scenarios. The results indicate that the proposed approach improves decision accuracy and supports better alignment between data processing methods and the complex operational requirements of modern IoT systems. This work contributes both theoretical insights and practical guidance for the design and evaluation of efficient, adaptive, and intelligent real-time IoT data processing architectures.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200444"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146078470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A deep learning approach for early prediction of task failures in cloud computing environments","authors":"Saba Aldomi ,&nbsp;Husam Suleiman ,&nbsp;Ali Shatnawi ,&nbsp;Luay Alawneh","doi":"10.1016/j.sasc.2026.200442","DOIUrl":"10.1016/j.sasc.2026.200442","url":null,"abstract":"<div><div>Prediction of task failures in cloud computing is of great importance due to its critical impact on task execution and resource utilization. Potential risks associated with failure events of tasks can lead to dissatisfaction among clients relying on cloud services. Therefore, it is crucial to comprehend properties and attributes of task failures to prevent them, or at least, to develop the capability to tolerate them. While there has been research conducted on failure analysis, there is a notable lack of emphasis on the application of Artificial Intelligence (AI) in characterizing and predicting task failures. This study aims to address this gap by developing a failure prediction framework capable of early identification of failed tasks and predicting the type of failure events that represent task states throughout their life cycle. We present a hybrid feature extraction and classification framework that uses SelectKBest for feature pre-selection and a GRU network as a sequence-level feature extractor. The extracted features are utilized by the GRU to train machine learning classifiers for the multi-class prediction phase including Random Forest (RF), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). The framework presents several benefits, including reducing resource wastage and Service Level Agreement (SLA) violations. The framework is evaluated based on the analysis of Google cluster traces in which the task states are Enable, Evict, Lost, Finish, Kill, Fail, Queue, Schedule, Update Pending, and Update Running. The findings show that a GRU model trained with the top 14 features achieves a test accuracy of 97.7% for feature extraction and that the combined GRU-RF yields the best predictive performance (overall <span><math><mrow><mtext>RMSE</mtext><mspace></mspace><mo>=</mo><mspace></mspace><mn>0</mn><mo>.</mo><mn>1415</mn></mrow></math></span>, Fail-class <span><math><mrow><mtext>F1</mtext><mspace></mspace><mo>=</mo><mspace></mspace><mn>0</mn><mo>.</mo><mn>99</mn><mtext>%</mtext></mrow></math></span>, average AUC per <span><math><mrow><mtext>class</mtext><mspace></mspace><mo>&gt;</mo><mspace></mspace><mn>0</mn><mo>.</mo><mn>98</mn></mrow></math></span>).</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200442"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145977955","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Formal verification of time-bounded BPMN model with message broker using timed automata","authors":"Kittisak Khetkarn,&nbsp;Nuengwong Tuaycharoen,&nbsp;Wiwat Vatanawood","doi":"10.1016/j.sasc.2026.200453","DOIUrl":"10.1016/j.sasc.2026.200453","url":null,"abstract":"<div><div>Modern business processes are growing their complexity due to concurrency and parallelism of both digital and manual processes with synchronous and asynchronous communications. Therefore, their timing behaviors are hard to predict and verify. Business Process Model and Notation (BPMN) is widely used for business process modeling. However, BPMN is still lacking support for incorporating time constraints that are crucial properties for real-world applications where the execution times of tasks vary but are critical to business competitiveness. In this article, an extension to the standard BPMN is proposed to specify lower and upper bounds of execution times on the task elements, called Time-Bounded BPMN (TBBP), along with transformation rules to timed automata, which can be automatically transformed using the TBBPTA Tool developed in this work. This extension enables the use of the UPPAAL model checking tool to verify properties in terms of time constraints, including deadlock, safety, liveness, and reachability. To demonstrate the practical applicability of our approach, several small test cases were used to validate transformation and verification with sample TCTL queries. In addition, four case studies of complex systems are presented to illustrate how TBBP can be applied to asynchronous communications involving multiple systems, including message brokers. These case studies serve as sample prototypes for verifying asynchronous processes in distributed systems using our TBBP. Our approach bridges the gap between business process modeling and formal verification and demonstrates the potential of applying time-bounded analysis to asynchronous systems in distributed environments.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"8 ","pages":"Article 200453"},"PeriodicalIF":3.6,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147385226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}