IEEE Access最新文献_第8页

PatchTSFL: Patch Fourier Enhanced Linear for Long-Term Time-Series Forecasting 补丁傅里叶增强线性长期时间序列预测

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-15 DOI: 10.1109/ACCESS.2025.3588672

Ling Li;Xianyun Wen;Weibang Li;Chengjie Li;Chengfang Zhang

{"title":"PatchTSFL: Patch Fourier Enhanced Linear for Long-Term Time-Series Forecasting","authors":"Ling Li;Xianyun Wen;Weibang Li;Chengjie Li;Chengfang Zhang","doi":"10.1109/ACCESS.2025.3588672","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588672","url":null,"abstract":"Long-term time series forecasting presents a critical challenge across numerous application domains. Recently, various transformer-based models have been employed for this task; however, these methods face two key challenges: difficulty in retaining local series information and failure to fully capture the overall trend of time series. To address these limitations, we propose a novel model called Patch Time Series Fourier-former Linear (PatchTSFL), which incorporates three innovative features: 1) A patching operation that splits long-term series into multiple patches, using the number of patches as the input length of the encoder, which preserves local sequence information while reducing model complexity; 2) A Fourier-enhanced block that replaces the traditional transformer’s multi-attention mechanism, capturing important information by converting time domain data into frequency domain mapping, further reducing computational complexity; 3) A Mixture Of Experts Decomposition block (MOEDecomp) that decomposes the series, enabling comprehensive capture of the overall time series trend. We conducted extensive experiments on nine widely-used long-term time series datasets, comparing PatchTSFL with state-of-the-art transformer-based models. Results demonstrate that PatchTSFL significantly improves forecasting accuracy (31.9% reduction in MSE and 19.0% reduction in MAE on average) while maintaining the lowest model complexity and runtime (4.3 times faster than FEDformer). These findings establish PatchTSFL as an effective and efficient solution for long-term time series prediction. The source code is available at: <uri>https://github.com/WESTBROOK-0/PatchTSFL</uri>.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124651-124664"},"PeriodicalIF":3.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079599","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Task-Ready PanNuke and NuCLS Datasets: Reorganization, Synthetic Data Generation, and Experimental Evaluation 任务就绪PanNuke和NuCLS数据集：重组，合成数据生成和实验评估

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-15 DOI: 10.1109/ACCESS.2025.3589477

Sai Chandana Koganti;Siri Yellu;Jihoon Yun;Sanghoon Lee

{"title":"Task-Ready PanNuke and NuCLS Datasets: Reorganization, Synthetic Data Generation, and Experimental Evaluation","authors":"Sai Chandana Koganti;Siri Yellu;Jihoon Yun;Sanghoon Lee","doi":"10.1109/ACCESS.2025.3589477","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589477","url":null,"abstract":"Automating nuclei analysis in histopathology is essential for enhancing disease diagnosis; however, training reliable models necessitates well-structured datasets. This paper addresses the gap in standardized data preparation workflows for two critical histopathology datasets: PanNuke and NuCLS. First, we organize histopathology images and masks into training-validation splits, extract subsets specific to cell types, and generate multi-scale patches to enable robust model training across various resolutions using the PanNuke dataset. Second, we curate task-specific subsets for object detection and semantic segmentation, ensuring consistency across splits while addressing annotation inconsistencies with the NuCLS dataset. Third, we conduct experiments on two reorganized datasets, including cell-type-specific binary classification, multi-task evaluation, and extension to synthetic datasets. Our workflows address common histopathology data challenges, including fragmented annotations, class imbalance, and mismatched metadata. The processed datasets are shared in standardized formats, allowing researchers to train models directly for critical tasks such as detecting cancerous nuclei or segmenting inflammatory cells in histopathology images.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125275-125286"},"PeriodicalIF":3.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080424","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Speaker-Independent Phoneme-Based Automatic Quranic Speech Recognition Using Deep Learning 基于深度学习的独立说话人音素自动古兰经语音识别

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-15 DOI: 10.1109/ACCESS.2025.3589252

Samah Al-Zaro;Mahmoud Al-Ayyoub;Osama Al-Khaleel

{"title":"Speaker-Independent Phoneme-Based Automatic Quranic Speech Recognition Using Deep Learning","authors":"Samah Al-Zaro;Mahmoud Al-Ayyoub;Osama Al-Khaleel","doi":"10.1109/ACCESS.2025.3589252","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589252","url":null,"abstract":"An automatic speech recognition system is important to help Muslims recite the Holy Quran accurately. Most existing research ignores a wide range of potential users (reciters) in their systems by focusing on professional adult male reciters due to the abundance of this group’s recordings and the lack of annotated data for other groups. This work bridges this gap by developing a speaker-independent system that recognizes Quranic recitations of different genders, ages, accents, and Tajweed levels. Our recognizer is designed on the phoneme level to offer Tajweed detection. Using a private dataset, rich of non-transcribed recitations, we propose training the DeepSpeech model with Transfer Learning and semi-supervised learning techniques. The performance of our model is evaluated using several proposed language models and evaluation metrics, including Word Error Rate (WER) and Phoneme Error Rate (PER). The goal is to show how our model would perform in regard to diverse reciter groups. Starting with a typical test set of unseen professional adult male recitations, the WER/PER of our model are 3.11% and 6.18%, respectively. More interestingly, our model achieves a WER of 25.39% and 17.93% when tested on recitations of non-professional (normal) females and children, respectively. The results are very promising and ensure the ability of our model to recognize recitations of various groups of normal reciters. Moreover, the latter results were done on the public “in-the-wild” Tarteel dataset, hoping this will be useful for comparison with future research and building more practical recitation teaching applications. In fact, a major limitation of existing systems (including ours) is the ability to handle diverse in-the-wild scenarios, such as when the reciter is reciting the verses in a very high tempo (common for those trying to memorize the Quran.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125881-125896"},"PeriodicalIF":3.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080439","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Multi-Scale Venation Pattern Analysis for Medicinal Plant Species Recognition 药用植物物种识别的多尺度脉化模式分析

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-15 DOI: 10.1109/ACCESS.2025.3589278

Arnav Sanjay Karnik;Nikhil Nair;Yashas Sagili;P. B. Shanthi

{"title":"Multi-Scale Venation Pattern Analysis for Medicinal Plant Species Recognition","authors":"Arnav Sanjay Karnik;Nikhil Nair;Yashas Sagili;P. B. Shanthi","doi":"10.1109/ACCESS.2025.3589278","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589278","url":null,"abstract":"This research addresses the challenge of medicinal plant species recognition based on leaf images by focusing on venation patterns as discriminative features. Venation patterns—defined by the hierarchical arrangement of veins within a leaf—carry significant taxonomic information that is often overlooked by conventional plant classification approaches. We propose a novel, venation-aware methodology that combines specialized image preprocessing techniques with both transfer learning and custom-designed deep learning architectures. Our method extracts and analyzes venation patterns at multiple spatial scales, capturing both global and fine-grained structural details to improve classification performance. To validate the effectiveness of our approach, we developed and evaluated three distinct model architectures: 1) a modified ResNet-50 model utilizing transfer learning with an adapted input pipeline for venation-aware channels; 2) a custom-built convolutional neural network, VenationNet, explicitly designed for multi-scale venation analysis; and 3) a Dual-Stream CNN architecture that processes leaf texture and venation maps independently before merging via attention-based fusion. Preprocessing involves contrast enhancement, Frangi filtering for venation extraction, and edge detection to create a three-channel input comprising RGB, venation, and edge maps. Experimental evaluation using the Indian Medicinal Plants Dataset demonstrates that our venation-centric strategy significantly outperforms traditional CNN-based approaches, achieving higher accuracy, precision, recall, and F1-scores across diverse plant categories. This research contributes a practical and scalable solution for reliable medicinal plant identification, which is crucial for pharmacological research, biodiversity monitoring, and traditional medicine practices. Moreover, our approach is well-suited for deployment in real-time mobile and edge computing environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125526-125536"},"PeriodicalIF":3.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080426","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Microservices-Driven Automation in Full-Stack Development: Bridging Efficiency and Innovation With FSMicroGenerator 全栈开发中的微服务驱动自动化：用FSMicroGenerator桥接效率和创新

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-15 DOI: 10.1109/ACCESS.2025.3589285

Samira Khalfaoui;Hafida Khalfaoui;Abdellah Azmani

{"title":"Microservices-Driven Automation in Full-Stack Development: Bridging Efficiency and Innovation With FSMicroGenerator","authors":"Samira Khalfaoui;Hafida Khalfaoui;Abdellah Azmani","doi":"10.1109/ACCESS.2025.3589285","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589285","url":null,"abstract":"The development of modern web applications presents major challenges due to increasingly complex architectures, scalability requirements, and the need to reduce time to market. These challenges are exacerbated by the shortage of talent, making the implementation of modern architectures more difficult for many companies. In response, this article presents FSMicroGenerator, an innovative code generation tool based on a low-code approach, which exploits UML class diagrams and templates to generate multilingual, full-stack web applications based on a microservices architecture. FSMicroGenerator automates the entire process of creating IT solutions, from development to deployment, reducing technical barriers and technical debt, and enabling teams to focus on business innovation while ensuring compliance with industry standards and best practices. By facilitating the adoption of DevSecOps practices, it improves collaboration between the development and operations teams, ensuring that security is integrated at every stage of the development process. This enables continuous management of the application lifecycle, faster and more reliable releases, and proactive identification and mitigation of security vulnerabilities. FSMicroGenerator also stands out for its ability to create a catalog of ready-to-use functional blocks, enabling their reuse and integration into other solutions. In addition, it offers a secure ecosystem, protecting companies’ assets against the risks of data exposure and leakage thanks to a robust architecture and integrated security mechanisms. As part of our open innovation approach, we plan to make FSMicroGenerator open source, to broaden its adoption and enable the community to contribute to its continuous improvement.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125131-125156"},"PeriodicalIF":3.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080431","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680876","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Deep Learning for Time Series Prediction of Strata Pressure in Coal Mining 深度学习在煤矿开采地层压力时间序列预测中的应用

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-15 DOI: 10.1109/ACCESS.2025.3589493

Xinyu Gu;Khay See;Xiuze Zhou

{"title":"Deep Learning for Time Series Prediction of Strata Pressure in Coal Mining","authors":"Xinyu Gu;Khay See;Xiuze Zhou","doi":"10.1109/ACCESS.2025.3589493","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589493","url":null,"abstract":"Hydraulic support plays a vital role in maintaining the structural integrity and safety of underground coal mines. We analyze a six-month dataset (May 1-October 31) of strata pressure from ten hydraulic supports (No. 65-74) in a 5966m <inline-formula> <tex-math>$times 280$ </tex-math></inline-formula>m longwall face, preprocessed into one-minute intervals, to predict strata pressure in underground coal mines, which is critical for ensuring safety and structural integrity. Using Pearson Correlation Coefficient (PCC), Fourier Transform (FT), and change point detection, we uncover strong intra-support correlations (PCC > 0.9), non-periodic patterns, and frequent abrupt shifts (3-5 events/hour). For short-term (one-minute) prediction, we propose a novel CNN-DLinear hybrid model that integrates DLinear’s interpretable trend-residual decomposition, tailored to strata pressure dynamics, with CNN’s localized spike detection for abrupt geological events. For long-term (30-minute) forecasting, we employ a smoothing technique to mitigate abrupt fluctuations and a sliding window approach to capture evolving trends. Experimental results show that our CNN-DLinear model achieves superior performance compared to ARIMA, LSTM, and Transformer models, with average reductions of 67% in MAE, 71% in MAPE, and 62% in RMSE, and an average <inline-formula> <tex-math>$R^{2}$ </tex-math></inline-formula> of 0.96 across ten supports. Our approach excels in capturing non-periodic, noisy strata pressure dynamics with lower computational complexity (<inline-formula> <tex-math>$O(L)$ </tex-math></inline-formula> vs. <inline-formula> <tex-math>$O(L^{2})$ </tex-math></inline-formula> for Transformers), enabling real-time safety monitoring. This work addresses the urgent need for accurate, efficient strata pressure forecasting in dynamic underground environments, thereby advancing operational safety and decision-making in coal mining.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124068-124085"},"PeriodicalIF":3.4,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080498","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Modeling Purposes of Public Transportation Trips for Human Need-Responsive Urban Mobility Efficiency 基于人类需求响应的城市交通效率的公共交通出行建模目的

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-14 DOI: 10.1109/ACCESS.2025.3587994

Lan Zhang;Kaijian Liu

{"title":"Modeling Purposes of Public Transportation Trips for Human Need-Responsive Urban Mobility Efficiency","authors":"Lan Zhang;Kaijian Liu","doi":"10.1109/ACCESS.2025.3587994","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3587994","url":null,"abstract":"Public transportation (PT) systems are the artery systems for urban residents to access resources essential for fulfilling their daily needs. Enhancing the operational efficiency of PT systems is thus of critical importance in urban mobility improvement and sustainable city development. However, current PT system operations do not account for the impact of operation decisions on the satisfaction of diverse needs of riders, irresponsive to the fundamental human needs driving mobility behaviors of PT riders. To address this limitation, it is imperative to model and infer the purposes of PT trips to understand the types of human needs that these trips aim to satisfy. As such, this paper presents a Bayesian probabilistic method for station-level, hourly PT trip purpose modeling and inference. The proposed method integrates 1) the gravity model for modeling spatial trip purpose distributions and 2) a temporal variation model for modeling temporal trip purpose distributions to enable station-level, hourly PT trip purpose modeling and inference. The method was validated by comparing the modeled PT trip purpose distributions to those obtained from established mobility surveys. The validation results showed a strong alignment of the two types of distributions, with a Kullback-Leibler divergence score of 0.061 and a Jensen-Shannon divergence score of 0.014. Building upon the validation, this paper further implemented and demonstrated the proposed method in modeling and analyzing shifts in PT trip purposes during the COVID-19 pandemic in New York City. Temporal-spatial analysis revealed distinct patterns in the trip purpose shifts across time and space.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124413-124428"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079554","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

The Evolution of Global and Local Scientist Mobility Network: Evidence From ORCID Profiles 全球和地方科学家流动网络的演变：来自ORCID档案的证据

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-14 DOI: 10.1109/ACCESS.2025.3588744

Ziyang Lin;Huiming Gu

{"title":"The Evolution of Global and Local Scientist Mobility Network: Evidence From ORCID Profiles","authors":"Ziyang Lin;Huiming Gu","doi":"10.1109/ACCESS.2025.3588744","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588744","url":null,"abstract":"The global and local mobility of scientists are two critical aspects influencing national innovation systems. However, existing research primarily analyzes the scientist mobility network at either a global or local scale, failing to capture the structure and dynamic of networks at the coupled global-local scale. To address this gap, we develop a conceptual model of the global and local scientist mobility network. Empirically, based on a dataset containing approximately two million profiles from ORCID, we construct a mobility network encompassing 206 countries and 16,049 universities. Using social network analysis methods and the core-periphery profile algorithm, we analyze the structural evolution of the network. Furthermore, we employ community detection algorithms and a random network null model to examine the driving role of the proximity in this evolution. The main findings are as follows: (1) Over time, the size of the scientist mobility network has expanded significantly, with increasingly small-world properties and network centralization, which are more evident at the global scale; (2) Geographical and institutional proximity play a crucial role in the evolution of the scientist mobility network, with geographical proximity primarily influencing local networks. The findings of this study provide more robust and generalizable empirical evidence for universities, local governments, and national policymakers to better understand the competitive dynamics of domestic and international talent, and also offer important implications for optimizing talent management policies.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124010-124024"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079595","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

On the Causal Relationship Between Music Virality and Success 论音乐病毒式传播与成功的因果关系

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-14 DOI: 10.1109/ACCESS.2025.3589173

Gabriel P. Oliveira;Ana Paula Couto Da Silva;Mirella M. Moro

{"title":"On the Causal Relationship Between Music Virality and Success","authors":"Gabriel P. Oliveira;Ana Paula Couto Da Silva;Mirella M. Moro","doi":"10.1109/ACCESS.2025.3589173","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589173","url":null,"abstract":"Songs going viral is not a new phenomenon in the music industry. Still, this phenomenon has reached new heights with the popularization of the Web and social platforms, which allow songs to achieve worldwide hit status almost instantly. Although interconnected, musical virality and commercial success are distinct concepts, and platforms such as TikTok have had significant power in amplifying music virality and creating successful hits. In this work, we analyze the temporal connection between musical virality and success. Specifically, our goal is to investigate the causal relationship between such concepts. By using global chart data from streaming platforms, we model time series to represent songs’ viral and success evolution over time and then perform two distinct analyses over them. First, we use Granger Causality to assess whether musical virality can forecast success and vice versa. Then we address the causal discovery task to qualitatively uncover the underlying causal relationships between them. The results suggest there is potential for using music virality to forecast future success and vice versa, although this does not apply to all songs. Despite their symbiotic relationship influenced by social platforms, our findings reinforce the contrast between music virality and success as different facets of music popularity.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"122782-122791"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079973","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0

Efficient IDS for IoT Networks Using Host-Based Data Aggregation and Multi-Entropy Analysis 基于主机数据聚合和多熵分析的物联网网络高效入侵检测

IF 3.4 3区计算机科学

IEEE Access Pub Date : 2025-07-14 DOI: 10.1109/ACCESS.2025.3589057

Yusei Katsura;Arata Endo;Ismail Arai;Kazutoshi Fujikawa

{"title":"Efficient IDS for IoT Networks Using Host-Based Data Aggregation and Multi-Entropy Analysis","authors":"Yusei Katsura;Arata Endo;Ismail Arai;Kazutoshi Fujikawa","doi":"10.1109/ACCESS.2025.3589057","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589057","url":null,"abstract":"IoT devices have limited computational resources, posing challenges to implementing adequate security measures. As a result, numerous attacks targeting vulnerabilities in IoT devices have been observed. Against this backdrop, research on Intrusion Detection Systems (IDSs) leveraging machine learning in IoT environments has been actively conducted. However, packet-based and flow-based IDSs proposed in existing studies are vulnerable to attacks such as DoS and DDoS, which involve numerous packet or flow combination patterns. These methods also face challenges related to computational resource burdens caused by the increased volume of input data. This study proposes a lightweight IDS with the host-based approach, representing communication behaviors with multiple entropies. The host-based approach aggregates features from different communications sent by the same host, enabling a reduction in input data. Additionally, the method captures host-level communication behaviors by leveraging multiple entropies, focusing on characteristic patterns of IoT devices, such as periodic communication with specific servers during normal operation. This enables the reduction of computational resources during detection processing while maintaining detection accuracy, even when using fewer features and lightweight machine learning algorithms. The evaluation results demonstrate that the proposed method achieves a maximum reduction of 99.7% (2916 milliseconds) in processing time and 86.4% (633 MiB) in memory usage while maintaining an intrusion detection accuracy of 99.97%, proving its feasibility in constrained environments comparable to IoT gateways.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125406-125419"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080017","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"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}

引用次数: 0