IEEE Access最新文献

{"title":"Intrusion Detection and Prevention System (IDPS) Model for IIoT Environments Using Hybridized Framework","authors":"Manohar Srinivasan;N. C. Senthilkumar","doi":"10.1109/ACCESS.2025.3538461","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538461","url":null,"abstract":"As the Industrial Internet of Things (IIoT) becomes more popular, cyber threats have more places to attack. This is why intrusion detection and prevention systems (IDPS) are so important for keeping industrial environments safe and secure. The main goal of the proposed research is to create a complete Intrusion Detection and Prevention System (IDPS) for IIoT. This system will include detection and protection security models to keep the network safe from cyberattacks and other strange things happening. Convolutional Neural Networks (CNNs) are used in pattern recognition for the detection and protection models in this research. This helps find IIoT networks with strange traffic patterns. Additionally, blockchain-assisted reinforcement learning (RL) uses real-time learning and decision-making to stop or lessen threats on its own. The novelty of this research lies in the combination of deep learning and blockchain-based security for intrusion detection and prevention. While there are already models for finding intrusions, this is the first time that reinforcement learning has been used for dynamic threat prevention along with blockchain to ensure secure communication and data integrity in the IIoT domain. This hybrid approach ensures a higher level of security by continuously learning and adapting to new types of attacks. This approach utilizes a novel Intrusion Detection and Prevention System (IDPS) designed for IIoT environments, which is capable of real-time detection and response to cyber threats. In the simulation parameters, this research shows higher detection accuracy and lower false positive rates using the proposed hybrid model. The integration of deep learning and blockchain technology enhances security for industrial applications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"26608-26621"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870250","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403831","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}

{"title":"Deep Stereo Network With Cross-Correlation Volume Construction and Least Square Aggregation","authors":"Guowei An;Yaonan Wang;Yang Mo;Kai Zeng;Qing Zhu;Xiaofang Yuan","doi":"10.1109/ACCESS.2025.3538762","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538762","url":null,"abstract":"Stereo matching is of great importance in robot operation, autonomous driving and virtual reality. Large textureless regions and depth discontinuity regions are still the error-prone regions of stereo matching tasks. Traditional correlation-based volumes only measure the feature similarity within the same channel of the feature maps, resulting in insufficient feature similarity learning between different channels, which leads to poor performance of stereo networks in large textureless regions with high feature similarity requirements. To address the problems in large textureless regions, we propose the cross-correlation based cost volume construction which adequately learn the feature similarity in different channels of the feature maps. To address the problems in depth discontinuity regions and other gradient sensitive regions, we propose the differentiable least square aggregation module which can sufficiently utilize the gradient information and enhance the aggregation ability of the cost aggregation network for gradient features. Extensive experiments show that the proposed method solves the problems effectively in the above difficult regions and achieves competitive performance on Scene Flow dataset, KITTI 2012 dataset and KITTI 2015 dataset.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"26739-26751"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870210","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403932","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}

{"title":"High Stability Single-Port Dual Band Microwave Sensor Based on Interdigital Capacitor Structure With Asymmetry Branch Feedline","authors":"Syah Alam;Indra Surjati;Lydia Sari;Raden Deiny Mardian;Teguh Firmansyah;Muhammad Iqbal;Slamet Widodo;Mudrik Alaydrus;Zahriladha Zakaria","doi":"10.1109/ACCESS.2025.3538042","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538042","url":null,"abstract":"This paper proposes a single-port interdigital capacitor (IDC) resonator based on asymmetric branch feed line with high stability performance for permittivity detection of solid materials with a permittivity range of 1 - 6.15. The microwave sensor is designed using a single-port resonator operating at two different resonant frequencies <inline-formula> <tex-math>$f_{r1} = 1.61$ </tex-math></inline-formula> GHz and <inline-formula> <tex-math>$f_{r2} = 2.52$ </tex-math></inline-formula> GHz. Dual band frequency was proposed using asymmetric branch feed line. In addition, to confine the electric field concentration of the resonator, an interdigital capacitor (IDC) structure is proposed as a solution. Furthermore, a copper shield was proposed as conducting material to evaluate performance stability of the sensor from disturbance effect with range of <inline-formula> <tex-math>$d = 1$ </tex-math></inline-formula> cm – 2.5 cm. Based on the measurement results, the sensor has high stability both without and with disturbance with an a Frequency Detection Resolution (FDR) of 0.009 - 0.4 GHz/<inline-formula> <tex-math>$Delta varepsilon _{mathrm {r}}$ </tex-math></inline-formula>, a Normalized Sensitivity (NS) of 0.4% - 4.4%, and an average accuracy of 90% - 95% for both resonance frequencies, respectively. Therefore, this sensor can be recommended for several applications such as biomedical industry, pharmaceuticals and material quality control especially for outdoor measurements that are potentially affected by electromagnetic interference and disturbance.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"24576-24586"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870129","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379530","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}

{"title":"A Survey of Deep Learning Techniques for Arabic Aspect-Based Sentiment Analysis","authors":"Dalal Alqusair;Mounira Taileb;and Hassanin Al-Barhamtoshy","doi":"10.1109/ACCESS.2025.3539263","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3539263","url":null,"abstract":"As a valuable tool for comprehending the emotions and perspectives of individuals, the significance of sentiment analysis has risen as a result of the growing of user-generated Arabic content online. Aspect-based sentiment analysis (ABSA) has recently gained significant attention and has become one of the most popular research points. The main objective of ABSA is to extract the aspects and identify their corresponding sentiment polarity from a provided review or text. Compared to generic sentiment analysis, the outcome provides more in-depth information. This paper aims to explore the deep learning (DL) methods employed in Arabic ABSA, and provides a new taxonomy that organizes various ABSA studies depending on the number of tasks processed. Additionally, the models proposed for Arabic ABSA and their contributions and limitations are discussed and summarized to identify gaps in the field. Furthermore, Arabic datasets for ABSA are reviewed as well. Specifically, this article analyzes studies published between 2019 and April 2024. In addition to ascertaining potential future directions that would encourage researchers to contribute to Arabic ABSA studies and generate more effective algorithms.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"25350-25368"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10872945","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396282","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}

{"title":"Federated Reinforcement Learning in Stock Trading Execution: The FPPO Algorithm for Information Security","authors":"Haogang Feng;Yue Wang;Shida Zhong;Tao Yuan;Zhi Quan","doi":"10.1109/ACCESS.2025.3538859","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538859","url":null,"abstract":"Stock trading execution is a critical component in the complex financial market landscape, and the development of a robust trade execution framework is essential for financial institutions pursuing profitability. This paper presents the Federated Proximal Policy Optimization (FPPO) algorithm, an adaptive trade execution framework that leverages joint reinforcement learning. The FPPO algorithm demonstrates significant improvements in model performance across various stocks, with average returns enhanced by 3% to 15%. It also exhibits superior performance in key metrics such as the reward function value, showcasing its effectiveness in different financial contexts. The paper further explores the model’s performance under the FPPO algorithm with varying numbers of client nodes and different risk preferences, underscoring the importance of these factors in model construction. The results substantiate the FPPO algorithm’s capability to safeguard privacy, ensure high performance, and enable the creation of personalized trading models in the optimal trade execution problem. This positions investors to gain a competitive edge in the dynamic and complex financial markets. Although the FPPO algorithm demonstrates significant potential in trade execution optimization, it may need to integrate a broader range of real-world variables and develop advanced privacy-preserving mechanisms to enhance its applicability in diverse financial contexts.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"25074-25086"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10872909","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396349","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}

{"title":"Assessing Driving Risk Level: Harnessing Deep Learning Hybrid Model With Intercity Bus Naturalistic Driving Data","authors":"Wei-Hsun Lee;Che-Yu Chang","doi":"10.1109/ACCESS.2025.3538693","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538693","url":null,"abstract":"Driving risk assessment is crucial for enhancing traffic safety, especially given the severe consequences of highway accidents. This study advances the field by developing a deep learning hybrid model for time series analysis to categorize driving risks into low, moderate, and high levels. By collecting naturalistic driving data from intercity buses, the model is trained on an extensive dataset featuring 27,057 journey-based instances, incorporating dynamic GPS data and static journey background information from over 300 drivers. The model’s effectiveness is highlighted by its outstanding weighted average F1-score of 0.932, indicating exceptional robustness and predictive accuracy. Through comprehensive feature engineering and examinations of three temporal neural models, this research identifies the best parameter configurations. The key finding is that including static journey background information leads to improvements by 8.8% on average in model performance. Additionally, the high-risk level prediction F1-score reaches 0.728 for the proposed model, which is up to 9.3 times better than the performance of the machine learning baseline model. This breakthrough in driving risk prediction not only represents a major advancement in traffic safety management but also has practical implications for fleet scheduling management among transportation companies in the future. By applying this model, companies can enhance passenger safety and comfort, showcasing the significant potential of deep learning in real-world applications.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"25141-25153"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870206","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396352","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}

{"title":"NAVA: A Network-Adaptive View-Aware Volumetric Video Streaming Framework","authors":"Nguyen Long Quang;Truong Thu Huong;Duc Nguyen","doi":"10.1109/ACCESS.2025.3538802","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538802","url":null,"abstract":"Volumetric video is the emerging format for representing real-world dynamic objects such as humans in Extended Reality (XR) applications. However, real-time streaming of volumetric video to user devices is challenging due to the extremely high data rate and low latency requirements. This paper introduces NAVA, a novel network-adaptive view-aware volumetric video streaming framework for XR scenes consisting of multiple volumetric sequences. The proposed framework dynamically adapts the quality of individual volumetric sequences based on network conditions and the user’s viewpoint to optimize streaming performance under network constraints. In our framework, multiple versions with different quality of individual volumetric video are prepared and stored on the server in advance. The rate allocation problem is formulated as a optimization problem by taking into account the visible area of individual sequences as well as the network constraint. We then present two solutions to decide the quality of each volumetric video in real-time. Extensive evaluation shows that the proposed framework can increase the viewport quality by <inline-formula> <tex-math>$0.5sim 1.1$ </tex-math></inline-formula>dB compared to existing methods. The outcome of this study is expected to accelerate the adoption of real-time interactive XR applications, enabling users to experience and interact with dynamic virtual environments seamlessly.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"25223-25238"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870276","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396358","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}

{"title":"Interacting Large Language Model Agents Bayesian Social Learning Based Interpretable Models","authors":"Adit Jain;Vikram Krishnamurthy","doi":"10.1109/ACCESS.2025.3538599","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538599","url":null,"abstract":"This paper discusses the theory and algorithms for interacting large language model agents (LLMAs) using methods from statistical signal processing and microeconomics. While both fields are mature, their application to decision-making involving interacting LLMAs remains unexplored. Motivated by Bayesian sentiment analysis on online platforms, we construct interpretable models and stochastic control algorithms that enable LLMAs to interact and perform Bayesian inference. Because interacting LLMAs learn from both prior decisions and external inputs, they can exhibit bias and herding behavior. Thus, developing interpretable models and stochastic control algorithms is essential to understand and mitigate these behaviors. This paper has three main results. First, we show using Bayesian revealed preferences from microeconomics that an individual LLMA satisfies the necessary and sufficient conditions for rationally inattentive (bounded rationality) Bayesian utility maximization and, given an observation, the LLMA chooses an action that maximizes a regularized utility. Second, we utilize Bayesian social learning to construct interpretable models for LLMAs that interact sequentially with each other and the environment while performing Bayesian inference. Our proposed models capture the herding behavior exhibited by interacting LLMAs. Third, we propose a stochastic control framework to delay herding and improve state estimation accuracy under two settings: 1) centrally controlled LLMAs and 2) autonomous LLMAs with incentives. Throughout the paper, we numerically demonstrate the effectiveness of our methods on real datasets for hate speech classification and product quality assessment, using open-source models like LLaMA and Mistral and closed-source models like ChatGPT. The main takeaway of this paper, based on substantial empirical analysis and mathematical formalism, is that LLMAs act as rationally bounded Bayesian agents that exhibit social learning when interacting. Traditionally, such models are used in economics to study interacting human decision-makers.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"25465-25504"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870230","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396378","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}

{"title":"A Comprehensive Survey of Fake Text Detection on Misinformation and LM-Generated Texts","authors":"Soonchan Kwon;Beakcheol Jang","doi":"10.1109/ACCESS.2025.3538805","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538805","url":null,"abstract":"This paper presents a pioneering and comprehensive analysis of fake text, a pressing issue in the digital age, by categorizing it into two main types: Misinformation and LM-generated texts. It is the first study to systematically dissect and examine the intricate challenges and nuances in distinguishing between genuine and artificial text. Through a meticulous review of various methodologies and technologies in fake text detection, the paper provides an in-depth evaluation of their effectiveness across diverse scenarios. Furthermore, this research delves into the significant societal impacts of both misinformation and LM-generated texts, underlining the urgent need for precise and effective detection mechanisms in our increasingly information-saturated world. This extensive survey not only offers a unique perspective on the current landscape of fake text detection, but also paves the way for future research, highlighting critical areas where further innovation and exploration are essential.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"25301-25324"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870239","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143396382","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}

{"title":"PFRNet: A Small Object Detection Method Based on Parallel Feature Extraction and Attention Mechanism","authors":"Hai Lin;Ji Wang;Jingguo Li","doi":"10.1109/ACCESS.2025.3538608","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3538608","url":null,"abstract":"To address the challenge of detecting small objects in aerial and satellite remote sensing images with low-resolution, we propose a high-precision object detection method based on PFRNet. PFRNet incorporates parallel feature extraction branches and a progressive feature refinement mechanism, significantly enhancing the model’s ability to perceive detailed features. In addition, PFRNet introduces the spatial pyramid pooling fusion with spatial attention (SPPFSPA) module, which integrates multi-scale features with an attention mechanism, enabling the model to better focus on areas of interest, thereby improving detection performance. Results demonstrate that PFRNet achieves outstanding detection accuracy, markedly outperforming other algorithms, particularly in small object detection. Visualization analysis reveals that the PFR module effectively captures richer and more comprehensive visual features in images, providing robust input for subsequent detection tasks, which is crucial for PFRNet’s superior performance. Overall, the proposed PFRNet model makes significant strides in small object detection in UAV aerial and satellite remote sensing images, offering strong support for applications such as intelligent transportation and precision agriculture.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"26727-26738"},"PeriodicalIF":3.4,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10870388","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403931","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}