PeerJ Computer Science最新文献

{"title":"CrossAlignNet: a self-supervised feature learning framework for 3D point cloud understanding.","authors":"Fei Wang, Xingzhen Dong, Jia Wu, Weishi Zhang, Tuo Zhou","doi":"10.7717/peerj-cs.3194","DOIUrl":"10.7717/peerj-cs.3194","url":null,"abstract":"<p><p>We propose a self-supervised point cloud representation learning framework CrossAlignNet based on cross-modal mask alignment strategy, to solve the problems of imbalance between global semantic and local geometric feature learning, as well as cross-modal information asymmetry in existing methods. A geometrically consistent mask region is established between the point cloud patches and the corresponding image patches through a synchronized mask alignment strategy to ensure cross-modal information symmetry. A dual-task learning framework is designed: the global semantic alignment task enhances the cross-modal semantic consistency through contrastive learning, and the local mask reconstruction task fuses the image cues using the cross-attention mechanism to recover the local geometric structure of the masked point cloud. In addition, the ShapeNet3D-CMA dataset is constructed to provide accurate point cloud-image spatial mapping relations to support cross-modal learning. Our framework shows superior or comparative results against existing methods on three point cloud understanding tasks including object classification, few-shot classification, and part segmentation.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3194"},"PeriodicalIF":2.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453720/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132413","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}

{"title":"A method for semantic textual similarity on long texts.","authors":"Omar Zatarain, Juan Carlos González-Castolo, Silvia Ramos-Cabral","doi":"10.7717/peerj-cs.3202","DOIUrl":"10.7717/peerj-cs.3202","url":null,"abstract":"<p><p>This work introduces a method for the semantic similarity of long documents using sentence transformers and large language models. The method detects relevant information from a pair of long texts by exploiting sentence transformers and large language models. The degree of similarity is obtained with an analytical fuzzy strategy that enables selective iterative retrieval under noisy conditions. The method discards the least similar pairs of sentences and selects the most similar. The preprocessing consists of splitting texts into sentences. The analytical strategy classifies pairs of texts by a degree of similarity without prior training on a dataset of long documents. Instead, it uses pre-trained models with any token capacity, a set of fuzzy parameters is tuned based on a few assessment iterations, and the parameters are updated based on criteria to detect four classes of similarity: identical, same topic, concept related, and non-related. This method can be employed in both small sentence transformers and large language models to detect similarity between pairs of documents of random sizes and avoid truncation of texts by testing pairs of sentences. A dataset of long texts in English from Wikipedia and other public sources, jointly with its gold standard, is provided and reviewed to test the method's performance. The method's performance is tested with small-token-size sentence transformers, large language models (LLMs), and text pairs split into sentences. Results prove that smaller sentence transformers are reliable for obtaining the similarity on long texts and indicate this method is an economical alternative to the increasing need for larger language models to find the degree of similarity between two long texts and extract the relevant information. Code and datasets are available at: https://github.com/omarzatarain/long-texts-similarity. Results of the adjustment of parameters can be found at https://doi.org/10.6084/m9.figshare.29082791.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3202"},"PeriodicalIF":2.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453783/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132630","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}

{"title":"Hybrid ARIMA-LSTM for COVID-19 forecasting: a comparative AI modeling study.","authors":"Al Mahmud, Syed Husni Noor Syed Hatim Noor, Kamarul Imran Musa, Firdaus Mohamad Hamzah, Zainab Mat Yudin, Noorshaida Kamaruddin, Ashwini M Madawana, Mohamad Arif Awang Nawi","doi":"10.7717/peerj-cs.3195","DOIUrl":"10.7717/peerj-cs.3195","url":null,"abstract":"<p><p>Pandemics present critical challenges to global health systems, economies, and societal structures, necessitating the development of accurate forecasting models for effective intervention and resource allocation. Classical statistical models such as the autoregressive integrated moving average (ARIMA) have been widely employed in epidemiological forecasting; however, they struggle to capture the nonlinear trends and dynamic fluctuations inherent in pandemic data. Conversely, deep learning models such as long short-term memory (LSTM) networks demonstrate strong capabilities in modeling complex dependencies but often require substantial data and computational resources. To boost forecasting precision, hybrid models such as ARIMA-LSTM integrate the advantages of traditional and deep learning methods. This study evaluates and compares the performance of ARIMA, LSTM, and hybrid ARIMA-LSTM models in predicting pandemic trends, using COVID-19 data from the Malaysian Ministry of Health as a case study. The dataset covers the period from 4 January 2021 to 18 September 2021, and model performance is evaluated using key metrics, including mean squared error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), root mean squared error (RMSE), relative root mean squared error (RRMSE), normalized root mean squared error (NRMSE), and the coefficient of determination (R²). The results demonstrate that ARIMA performs poorly in capturing pandemic trends, while LSTM improves forecasting accuracy. However, the hybrid ARIMA-LSTM model consistently achieves the lowest error rates, confirming the advantage of integrating statistical and deep learning methodologies. All findings support the adoption of hybrid modeling approaches for pandemic forecasting, contributing to more accurate and reliable predictive analytics in epidemiology. Future research should investigate the generalizability of hybrid models across various infectious diseases and integrate additional real-time external variables to improve forecasting reliability.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3195"},"PeriodicalIF":2.5,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453849/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132481","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}

{"title":"Arabic hate speech detection using deep learning: a state-of-the-art survey of advances, challenges, and future directions (2020-2024).","authors":"Mariam Itriq, Mohd Halim Mohd Noor","doi":"10.7717/peerj-cs.3133","DOIUrl":"10.7717/peerj-cs.3133","url":null,"abstract":"<p><p>The proliferation of social media has intensified concerns about the societal and psychological impacts of hate speech, particularly in Arabic-speaking communities, where dialectal diversity, morphological complexity, and sociopolitical factors complicate detection. Despite platform efforts, the automated detection of Arabic hate speech remains challenging owing to limited annotated datasets and linguistic nuances. This survey reviews the advances (2020-2024) in deep learning approaches, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformer-based models (<i>e.g</i>., bidirectional encoder representations from transformers (BERT) and AraBERT), and hybrid architectures for Arabic hate speech detection. It further examines the dataset constraints involving dialectal variation, annotation inconsistencies, and scarcity. The analysis identified critical research gaps and proposed future directions: expanding multilingual datasets, enhancing contextual modeling, and developing ethically grounded frameworks. This review consolidates state-of-the-art methodologies to guide effective countermeasures against Arabic online hate speech.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3133"},"PeriodicalIF":2.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453721/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132529","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}

{"title":"Exploring mHealth interventions for medication management: a scoping review of digital tools, implementation barriers, and patient outcomes.","authors":"Xuye Wang, Beibei Wang, Wan Yin Tew, Xiaoning Yang, Xiangyang Xu, Yifang Gao, Yongjia Chen, Mun Fei Yam","doi":"10.7717/peerj-cs.3190","DOIUrl":"10.7717/peerj-cs.3190","url":null,"abstract":"<p><strong>Background: </strong>Medication non-adherence remains a significant global healthcare challenge, resulting in inadequate disease management, increased hospitalisations, and higher healthcare costs. Mobile health (mHealth) applications have emerged as promising digital health tools for enhancing medication adherence through real-time monitoring, personalised reminders, artificial intelligence (AI)-driven interventions, and improved patient engagement.</p><p><strong>Objectives: </strong>This scoping review examines the effectiveness, key features, and challenges of mHealth applications in promoting medication adherence across diverse patient populations and healthcare settings. It also seeks to identify research gaps and inform future development and implementation strategies for digital therapeutics.</p><p><strong>Eligibility criteria: </strong>Studies published between 2020 and 2024 were included if they investigated the use of mHealth applications to improve medication adherence and reported outcomes related to adherence rates, patient health indicators, or user engagement. Only studies with empirical data, including randomised controlled trials, observational studies, or mixed-methods research, were considered.</p><p><strong>Sources of evidence: </strong>A comprehensive search was conducted across Scopus, Web of Science, PubMed/MEDLINE, Google Scholar, and CINAHL databases. In total, 319 studies met the inclusion criteria following a systematic screening process based on Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) guidelines.</p><p><strong>Charting methods: </strong>Data were extracted on study design, app functionalities, patient demographics, adherence outcomes, and barriers to adoption. The charted data were thematically synthesised to identify trends, success factors, and limitations.</p><p><strong>Results: </strong>Among the included studies, 85% reported improved medication adherence associated with features such as personalised medication reminders, real-time health tracking, and AI-powered adherence prediction. Clinical outcomes were also frequently observed, including improved blood pressure, glucose control, and patient-reported quality of life. Key barriers to adoption included limited digital literacy, concerns about data privacy, socioeconomic disparities, and a lack of integration with electronic health records (EHRs).</p><p><strong>Conclusions: </strong>mHealth applications show significant potential to improve medication adherence and health outcomes, particularly in the management of chronic diseases. However, inclusive design, robust data privacy frameworks, and evidence-based implementation strategies are essential for scalability and sustained impact. Future research should focus on long-term effectiveness, cost-efficiency, and integration of mHealth tools within broader healthcare systems.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3190"},"PeriodicalIF":2.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453750/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132411","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}

{"title":"Bridges in social networks: current status and challenges.","authors":"Jeongseon Kim, Soohwan Jeong, Jungeun Kim, Sungsu Lim","doi":"10.7717/peerj-cs.3122","DOIUrl":"10.7717/peerj-cs.3122","url":null,"abstract":"<p><p>In social network analysis, bridges play a critical role in maintaining connectivity and facilitating the dissemination of information between communities. Despite increasing interest in bridge structures, a systematic classification of their roles across various network types remains unexplored. This study introduces a categorization of bridges into structural and functional types. Structural bridges maintain connectivity by preventing network fragmentation, whereas functional bridges facilitate the flow of information between communities. We conducted a comprehensive literature review and classified existing studies within this framework. The findings clarify the distinct roles of bridges and provide valuable insight for devising effective strategies for network design and analysis.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3122"},"PeriodicalIF":2.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453711/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132588","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}

{"title":"A robust detect and describe framework for object recognition in early childhood education.","authors":"Lan Lv, Suhui Yao","doi":"10.7717/peerj-cs.3080","DOIUrl":"10.7717/peerj-cs.3080","url":null,"abstract":"<p><p>Preschool education plays a vital role in the harmonious development of an individual. Understanding basic shapes, colors, and letters at an early age lays a strong foundation for academic excellence and emotional growth. At an early childhood stage, the skills of spatial reasoning and problem-solving can be developed by recognizing and comprehending the depicted objects. By exploring deep learning technology, this article presents a cognitive enhancement framework for recognizing nested objects. With cutting-edge models, such as You Only Look Once (YOLOv8) and Visual Geometry Group (VGG16), objects and intra-objects are detected. For semantic description, the neural network model, specifically long short-term memory (LSTM), is exploited, preceded by precise object recognition. The framework is implemented in Google Colab with the prominent packages of Ultralytics, PyTorch, and OpenCV. The models are trained and tested by a custom dataset: PreEduDS. The results of the systematic evaluation suggest that the framework has widespread applicability. A promising accuracy score of 94.4% is obtained for object recognition and 96.5% for predicting precise semantic textual description. The proposed system is well-suited for enhancing preschool education and training based on augmented reality (AR) applications.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3080"},"PeriodicalIF":2.5,"publicationDate":"2025-09-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453821/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132434","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}

{"title":"Research on the relationship and prediction model between nighttime lighting data, pm2.5 data, and urban GDP.","authors":"Sen Chen, Junke Li","doi":"10.7717/peerj-cs.3185","DOIUrl":"10.7717/peerj-cs.3185","url":null,"abstract":"<p><p>With the discovery of electricity and the widespread adoption of lighting technology, the extensive application of electricity has greatly increased productivity, making night-time factory production possible. At the same time, the rapid expansion of factories has led to a significant increase in particulate matter 2.5 (PM2.5) in the air. However, economic development heavily relies on lighting and factory production. To address this issue, researchers have focused on predicting urban gross domestic product (GDP) through night-time lights and PM2.5, but current studies often focus on the impact of a single factor on GDP, leaving room for improvement in model accuracy. In response to this problem, this article proposes the Relationship and Prediction Model between Night Light Data, PM2.5, and Urban GDP (R&P-NLPG model). Firstly, night light data, PM2.5 data, and GDP data are collected and preprocessed. Secondly, correlation analysis is conducted to analyze the correlation between data features. Then, data fusion methods are used to integrate features between night-time data and PM2.5 data, forming the third data features. Next, a neural network is constructed to establish a functional relationship between features and GDP. Finally, the trained neural network model is used to predict GDP. The experimental results demonstrate that the predictive capability of the R&P-NLPG model outperforms GDP prediction models constructed with single-feature input and existing multi-feature input.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3185"},"PeriodicalIF":2.5,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453825/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132667","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}

{"title":"Enhancing privacy-preserving brain tumor classification with adaptive reputation-aware federated learning and homomorphic encryption.","authors":"Swetha Ghanta, Prasanthi Boyapati, Sujit Biswas, Ashok K Pradhan, Saraju P Mohanty","doi":"10.7717/peerj-cs.3165","DOIUrl":"10.7717/peerj-cs.3165","url":null,"abstract":"<p><p>Brain tumor diagnosis using magnetic resonance imaging (MRI) scans is critical for improving patient survival rates. However, automating the analysis of these scans faces significant challenges, including data privacy concerns and the scarcity of large, diverse datasets. A potential solution is federated learning (FL), which enables cooperative model training among multiple organizations without requiring the sharing of raw data; however, it faces various challenges. To address these, we propose Federated Adaptive Reputation-aware aggregation with CKKS (Cheon-Kim-Kim-Song) Homomorphic encryption (FedARCH), a novel FL framework designed for a cross-silo scenario, where client weights are aggregated based on reputation scores derived from performance evaluations. Our framework incorporates a weighted aggregation method using these reputation scores to enhance the robustness of the global model. To address sudden changes in client performance, a smoothing factor is introduced, while a decay factor ensures that recent updates have a greater influence on the global model. These factors work together for dynamic performance management. Additionally, we address potential privacy risks from model inversion attacks by implementing a simplified and computationally efficient CKKS homomorphic encryption, which allows secure operations on encrypted data. With FedARCH, encrypted model weights of each client are multiplied by a plaintext reputation score for weighted aggregation. Since we are multiplying ciphertexts by plaintexts, instead of ciphertexts, the need for relinearization is eliminated, efficiently reducing the computational overhead. FedARCH achieved an accuracy of 99.39%, highlighting its potential in distinguishing between brain tumor classes. Several experiments were conducted by adding noise to the clients' data and varying the number of noisy clients. An accuracy of 94% was maintained even with 50% of noisy clients at a high noise level, while the standard FL approach accuracy dropped to 33%. Our results and the security analysis demonstrate the effectiveness of FedARCH in improving model accuracy, its robustness to noisy data, and its ability to ensure data privacy, making it a viable approach for medical image analysis in federated settings.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3165"},"PeriodicalIF":2.5,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453705/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132401","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}

{"title":"A comprehensive approach for waste management with GAN-augmented classification.","authors":"Yashashree Mahale, Nida Khan, Kunal Kulkarni, Shilpa Gite, Biswajeet Pradhan, Abdullah Alamri, Chang-Wook Lee, Nandhini K, Mrinal Bachute","doi":"10.7717/peerj-cs.3156","DOIUrl":"10.7717/peerj-cs.3156","url":null,"abstract":"<p><p>Image processing and computer vision highly rely on data augmentation in machine learning models to increase the diversity and variability within training datasets for better performance. One of the most promising and widely used applications of data augmentation is in classifying waste object images. This research focuses on augmenting waste object images with generative adversarial networks (GANS). Here deep convolutional GAN (DCGAN), an extension of GAN is utilized, which uses convolutional and convolutional-transpose layers for better image generation. This approach helps generate realism and variability in images. Furthermore, object detection and classification techniques are used. By utilizing ensemble learning techniques with <i>DenseNet121, ConvNext, and Resnet101</i>, the network can accurately identify and classify waste objects in images, thereby contributing to improved waste management practices and environmental sustainability. With ensemble learning, a notable accuracy of 99.80% was achieved. Thus, by investigating the effectiveness of these models in conjunction with data augmentation techniques, this novel approach of GAN-based augmentation cooperated with ensemble models aims to provide valuable insights into optimizing waste object identification processes for real-world applications. Future work will focus on better data augmentation methods with other types of GANS architectures and introducing multimodal sources of data to further increase the performance of the classification and detection models.</p>","PeriodicalId":54224,"journal":{"name":"PeerJ Computer Science","volume":"11 ","pages":"e3156"},"PeriodicalIF":2.5,"publicationDate":"2025-09-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12453751/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145132612","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}