PeerJ Computer SciencePub Date : 2025-03-04eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2692
Xinxin Kang, Yong Nie
{"title":"Design and analysis of teaching early warning system based on multimodal data in an intelligent learning environment.","authors":"Xinxin Kang, Yong Nie","doi":"10.7717/peerj-cs.2692","DOIUrl":"10.7717/peerj-cs.2692","url":null,"abstract":"<p><p>In online teaching environments, the lack of direct emotional interaction between teachers and students poses challenges for teachers to consciously and effectively manage their emotional expressions. The design and implementation of an early warning system for teaching provide a novel approach to intelligent evaluation and improvement of online education. This study focuses on segmenting different emotional segments and recognizing emotions in instructional videos. An efficient long-video emotional transition point search algorithm is proposed for segmenting video emotional segments. Leveraging the fact that teachers tend to maintain a neutral emotional state for significant portions of their teaching, a neutral emotional segment filtering algorithm based on facial features has been designed. A multimodal emotional recognition model is proposed for emotional recognition in instructional videos. It begins with preprocessing the raw speech and facial image features, employing a semi-supervised iterative feature normalization algorithm to eliminate individual teacher differences while preserving inherent differences between different emotions. A deep learning-based multimodal emotional recognition model for teacher instructional videos is introduced, incorporating an attention mechanism to automatically assign weights for feature-level modal fusion, providing users with accurate emotional classification. Finally, a teaching early warning system is implemented based on these algorithms.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2692"},"PeriodicalIF":3.5,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888907/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143587809","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-03-04eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2466
Chao Fang, Nazir Ullah, M Batumalay, Waleed Mugahed Al-Rahmi, Fahad Alblehai
{"title":"Blockchain technology and its impact on sustainable supply chain management in SMEs.","authors":"Chao Fang, Nazir Ullah, M Batumalay, Waleed Mugahed Al-Rahmi, Fahad Alblehai","doi":"10.7717/peerj-cs.2466","DOIUrl":"10.7717/peerj-cs.2466","url":null,"abstract":"<p><p>The COVID-19 pandemic has had a significant impact on small and medium-sized enterprises (SMEs), leading to disruptions in supply chains, financial losses, and closures. To overcome these challenges, organizations, including those in developing economies like Malaysia, are turning to blockchain technology as a solution to enhance traditional supply chain management frameworks. This study aims to identify the factors that influence the acceptance of blockchain technology among SMEs. By drawing on established adoption theories such as the technology acceptance model (TAM), diffusion of innovation (DOI) theory, and theory of planned behavior (TPB), the researchers developed a research framework. They utilized partial least square structural equation modeling (PLS-SEM) to analyze the causal relationships between different constructs and test their hypotheses. The findings confirmed that the constructs of the technology acceptance model, specifically perceived usefulness, perceived ease of use and attitude were significantly associated with the intention to use blockchain technology. Additionally, the constructs of the diffusion of innovation theory, relative advantage and compatibility, showed significant associations with perceived ease of use, while complexity had a negligible relationship with perceived usefulness and perceived ease of use. The construct of subjective norms from the theory of planned behavior exhibited a significant relationship with perceived usefulness and an insignificant relationship with intention to use. Finally, perceived behavioral control demonstrated a positive relationship with intention to use. The study's findings provide valuable insights for blockchain developers and organizations aiming to make informed decisions regarding the application of blockchain technology as a process innovation in SMEs.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2466"},"PeriodicalIF":3.5,"publicationDate":"2025-03-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888871/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-03-03eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2742
Fengjin Ye, Yuchao Zhao, Zohaib Latif
{"title":"Research on sports activity behavior prediction based on electromyography signal collection and intelligent sensing channel.","authors":"Fengjin Ye, Yuchao Zhao, Zohaib Latif","doi":"10.7717/peerj-cs.2742","DOIUrl":"10.7717/peerj-cs.2742","url":null,"abstract":"<p><p>Sports behavior prediction requires precise and reliable analysis of muscle activity during exercise. This study proposes a multi-channel correlation feature extraction method for electromyographic (EMG) signals to overcome challenges in sports behavior prediction. A wavelet threshold denoising algorithm is enhanced with nonlinear function transitions and control coefficients to improve signal quality, achieving effective noise reduction and a higher signal-to-noise ratio. Furthermore, multi-channel linear and nonlinear correlation features are combined, leveraging mutual information estimation <i>via</i> copula entropy for feature construction. A stacking ensemble learning model, incorporating extreme gradient boosting (XGBoost), K-nearest network (KNN), Random Forest (RF), and naive Bayes (NB) as base learners, further enhances classification accuracy. Experimental results demonstrate that the proposed approach achieves over 95% prediction accuracy, significantly outperforming traditional methods. The robustness of multi-channel correlation features is validated across diverse datasets, proving their effectiveness in mitigating channel crosstalk and noise interference. This work provides a scientific basis for improving sports training strategies and reducing injury risks.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2742"},"PeriodicalIF":3.5,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888918/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588038","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-03-03eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2725
Meizhen Liu, Anis Salwa Mohd Khairuddin, Khairunnisa Hasikin, Weitong Liu
{"title":"Novel cross-dimensional coarse-fine-grained complementary network for image-text matching.","authors":"Meizhen Liu, Anis Salwa Mohd Khairuddin, Khairunnisa Hasikin, Weitong Liu","doi":"10.7717/peerj-cs.2725","DOIUrl":"10.7717/peerj-cs.2725","url":null,"abstract":"<p><p>The fundamental aspects of multimodal applications such as image-text matching, and cross-modal heterogeneity gap between images and texts have always been challenging and complex. Researchers strive to overcome the challenges by proposing numerous significant efforts directed toward narrowing the semantic gap between visual and textual modalities. However, existing methods are usually limited to computing the similarity between images (image regions) and text (text words), ignoring the semantic consistency between fine-grained matching of word regions and coarse-grained overall matching of image and text. Additionally, these methods often ignore the semantic differences across different feature dimensions. Such limitations may result in an overemphasis on specific details at the expense of holistic understanding during image-text matching. To tackle this challenge, this article proposes a new Cross-Dimensional Coarse-Fine-Grained Complementary Network (CDGCN). Firstly, the proposed CDGCN performs fine-grained semantic alignment of image regions and sentence words based on cross-dimensional dependencies. Next, a Coarse-Grained Cross-Dimensional Semantic Aggregation module (CGDSA) is developed to complement local alignment with global image-text matching ensuring semantic consistency. This module aggregates local features across different dimensions as well as within the same dimension to form coherent global features, thus preserving the semantic integrity of the information. The proposed CDGCN is evaluated on two multimodal datasets, Flickr30K and MS-COCO against state-of-the-art methods. The proposed CDGCN achieved substantial improvements with performance increment of 7.7-16% for both datasets.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2725"},"PeriodicalIF":3.5,"publicationDate":"2025-03-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888920/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-02-28eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2738
Darie Moldovan
{"title":"A majority voting framework for reliable sentiment analysis of product reviews.","authors":"Darie Moldovan","doi":"10.7717/peerj-cs.2738","DOIUrl":"10.7717/peerj-cs.2738","url":null,"abstract":"<p><p>This article presents a tailored majority voting approach for enhancing the consistency and reliability of sentiment analysis in online product reviews. The methodology addresses discrepancies in sentiment classification by leveraging sentiment labels from multiple automated tools and implementing a robust majority decision rule. This consensus-based approach significantly enhances the trustworthiness and consistency of sentiment analysis outcomes, serving as a dependable foundation for training more precise sentiment analysis models. The data labeled with our method was utilized to train deep learning models, achieving competitive accuracy with significantly less data. The findings demonstrate the effectiveness of the method in producing results comparable to commercial tools while ensuring data consistency for model training.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2738"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888917/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-02-28eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2740
Jia Xu
{"title":"Leveraging LLaMA2 for improved document classification in English.","authors":"Jia Xu","doi":"10.7717/peerj-cs.2740","DOIUrl":"10.7717/peerj-cs.2740","url":null,"abstract":"<p><p>Document classification is an important component of natural language processing, with applications that include sentiment analysis, content recommendation, and information retrieval. This article investigates the potential of Large Language Model Meta AI (LLaMA2), a cutting-edge language model, to enhance document classification in English. Our experiments show that LLaMA2 outperforms traditional classification methods, achieving higher precision and recall values on the WOS-5736 dataset. Additionally, we analyze the interpretability of LLaMA2's classification process to reveal the most pertinent features for categorization and the model's decision-making. These results emphasize the potential of advanced language models to enhance classification outcomes and provide a more profound comprehension of document structures, thereby contributing to the advancement of natural language processing methodologies.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2740"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888901/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588207","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-02-28eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2723
Yang Xu, Yueyi Zhang, Yefang Sun, Hanting Zhou
{"title":"An adaptive method for determining the optimal number of topics in topic modeling.","authors":"Yang Xu, Yueyi Zhang, Yefang Sun, Hanting Zhou","doi":"10.7717/peerj-cs.2723","DOIUrl":"10.7717/peerj-cs.2723","url":null,"abstract":"<p><p>Topic models have been successfully applied to information classification and retrieval. The difficulty in successfully applying these technologies is to select the appropriate number of topics for a given <i>corpus</i>. Selecting too few topics can result in information loss and topic omission, known as underfitting. Conversely, an excess of topics can introduce noise and complexity, resulting in overfitting. Therefore, this article considers the inter-class distance and proposes a new method to determine the number of topics based on clustering results, named average inter-class distance change rate (AICDR). AICDR employs the Ward's method to calculate inter-class distances, then calculates the average inter-class distance for different numbers of topics, and determines the optimal number of topics based on the average distance change rate. Experiments show that the number of topics determined by AICDR is more in line with the true classification of datasets, with high inter-class distance and low inter-class similarity, avoiding the phenomenon of topic overlap. AICDR is a technique predicated on clustering results to select the optimal number of topics and has strong adaptability to various topic models.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2723"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888909/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-02-28eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2703
Samet Memiş, Ferhan Şola Erduran, Hivda Aydoğan
{"title":"Adaptive machine learning approaches utilizing soft decision-making <i>via</i> intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices.","authors":"Samet Memiş, Ferhan Şola Erduran, Hivda Aydoğan","doi":"10.7717/peerj-cs.2703","DOIUrl":"10.7717/peerj-cs.2703","url":null,"abstract":"<p><p>The exponential data growth generated by technological advancements presents significant challenges in analysis and decision-making, necessitating innovative and robust methodologies. Machine learning has emerged as a transformative tool to address these challenges, especially in scenarios requiring precision and adaptability. This study introduces two novel adaptive machine learning approaches, <i>i.e</i>., AIFPIFSC1 and AIFPIFSC2. These methods leverage the modeling ability of intuitionistic fuzzy parameterized intuitionistic fuzzy soft matrices (<i>ifpifs</i>-matrices). This state-of-the-art framework enhances the classification task in machine learning by employing soft decision-making through <i>ifpifs</i>-matrices. The proposed approaches are rigorously evaluated against leading fuzzy/soft-based classifiers using 15 widely recognized University of California, Irvine datasets, including accuracy and robustness, across six performance metrics. Statistical analyses conducted using Friedman and Nemenyi tests further substantiate the reliability and superiority of the proposed approaches. The results consistently demonstrate that these approaches outperform their counterparts, highlighting their potential for solving complex classification problems. This study contributes to the field by offering adaptable and effective solutions for modern data analysis challenges, paving the way for future advancements in machine learning and decision-making systems.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2703"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888911/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588153","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-02-28eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2701
M Anandaraj, Naganandhini S
{"title":"An optimal peer selection for peer-to-peer video content distribution using fuzzy linear programming approach.","authors":"M Anandaraj, Naganandhini S","doi":"10.7717/peerj-cs.2701","DOIUrl":"10.7717/peerj-cs.2701","url":null,"abstract":"<p><p>The problem of peer selection in peer-to-peer (P2P) video content distribution network is significant to solve since it affects the performance and efficiency of the network widely. In this article, a novel framework is introduced that uses fuzzy linear programming (FLP) to address the inherent uncertainties in peer selection. The primary motivation for the use of FLP lies in its capability to handle the imprecision and vagueness that are characteristic of dynamic P2P environments. Factors such as peer reliability, bandwidth, and proximity are often uncertain in this environment. By using fuzzy logic, the proposed framework models these criteria as fuzzy sets and then integrates uncertainty into the decision-making process. FLP is then applied to optimize peer selection, improving download speed, reducing download time, and enhancing peer reliability. The proposed method is evaluated and analyzed using extensive simulation with SciPy. The result reveals that proposed technique works better compared to some of the traditional methods in terms of download time, download speed and also reliability measure. It also exhibits approximately 20% of increase in download speed as well as a 15% decrease in download time compared to traditional approaches. It leads to faster content retrieval and enhanced the efficiency in content distribution. Also, in selection of reliable peers for content distribution, there is a notable 20% of increase in peer reliability with result of enhanced robustness. The proposed method provides efficient and robust solution to the problem of peer selection. It can be implemented in a broad range of P2P content distribution networks.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2701"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888916/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
PeerJ Computer SciencePub Date : 2025-02-28eCollection Date: 2025-01-01DOI: 10.7717/peerj-cs.2722
Mohammed A El-Shorbagy, Anas Bouaouda, Laith Abualigah, Fatma A Hashim
{"title":"Atom Search Optimization: a comprehensive review of its variants, applications, and future directions.","authors":"Mohammed A El-Shorbagy, Anas Bouaouda, Laith Abualigah, Fatma A Hashim","doi":"10.7717/peerj-cs.2722","DOIUrl":"10.7717/peerj-cs.2722","url":null,"abstract":"<p><p>The Atom Search Optimization (ASO) algorithm is a recent advancement in metaheuristic optimization inspired by principles of molecular dynamics. It mathematically models and simulates the natural behavior of atoms, with interactions governed by forces derived from the Lennard-Jones potential and constraint forces based on bond-length potentials. Since its inception in 2019, it has been successfully applied to various challenges across diverse fields in technology and science. Despite its notable achievements and the rapidly growing body of literature on ASO in the metaheuristic optimization domain, a comprehensive study evaluating the success of its various implementations is still lacking. To address this gap, this article provides a thorough review of half a decade of advancements in ASO research, synthesizing a wide range of studies to highlight key ASO variants, their foundational principles, and significant achievements. It examines diverse applications, including single- and multi-objective optimization problems, and introduces a well-structured taxonomy to guide future exploration in ASO-related research. The reviewed literature reveals that several variants of the ASO algorithm, including modifications, hybridizations, and multi-objective implementations, have been developed to tackle complex optimization problems. Moreover, ASO has been effectively applied across various domains, such as engineering, healthcare and medical applications, Internet of Things and communication, clustering and data mining, environmental modeling, and security, with engineering emerging as the most prevalent application area. By addressing the common challenges researchers face in selecting appropriate algorithms for real-world problems, this study provides valuable insights into the practical applications of ASO and offers guidance for designing ASO variants tailored to specific optimization problems.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e2722"},"PeriodicalIF":3.5,"publicationDate":"2025-02-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11888905/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143588281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}