IEEE Access最新文献

{"title":"Predicting Suspicious Arabic X Accounts Using Stylometric Features","authors":"Taghreed Bagies;Rahaf Alsuhaimi;Miada Almasre;Alaa Bafail","doi":"10.1109/ACCESS.2025.3605126","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605126","url":null,"abstract":"Some users use the X platform to spread negativity, violence, and hatred. These users may initially conceal their true beliefs in order to gain users’ trust, making traditional content-based detection methods not helpful in identifying these accounts as suspicious (i.e., indicate whether an X account belongs to a terrorist). Stylometric features, which analyze writing styles, can reveal behavioral traits and hidden thoughts. In this paper, we propose a novel model that predicts whether an Arabic X account is suspicious (owned by a terrorist) using 85 stylometric features extracted from 1,500 accounts (750 suspicious, 750 non-suspicious). We utilized a variety of AI techniques, such as machine learning and deep learning, to evaluate our approach. We also used NLP techniques for preprocessing and feature extraction. Our results showed that the Random Forest (RF) model achieved the highest accuracy, reaching 98%. This approach can aid cybersecurity efforts by detecting suspicious accounts without relying on content analysis.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153464-153473"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146657","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027931","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 Contribution to the Application of the Phasor Transform for Solving Electric Circuits","authors":"Rubén Romero;César Reynoso;Leonardo H. Macedo;Natalia Alguacil","doi":"10.1109/ACCESS.2025.3605059","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605059","url":null,"abstract":"This paper presents an alternative analysis of the fundamental concepts underlying the use of the phasor transform in electric circuit analysis. Traditionally, the phasor transform is employed to determine the steady-state response of circuits composed of passive elements (resistors, capacitors, and inductors) and active sources (voltage and current sources) operating under sinusoidal excitation. Such circuits are essential for analyzing power systems, telecommunications networks, and similar applications. The primary objective of this study is to develop a comprehensive framework for solving electric circuits in the steady state by leveraging the phasor transform, without explicitly introducing the conventional phasor concept as a rotating vector nor using Euler’s identity. Instead, our approach mirrors the strategy of the Laplace transform, thereby unifying the analysis under a single, consistent methodology without the need for additional new concepts.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"155203-155214"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146791","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027956","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":"Audio-Based Neural Network to Classify Patients With Early Parkinson’s Disease","authors":"Weikang Hou;Changqin Quan;Zhonglue Chen;Sheng Cao;Kang Ren;Wen Su;Zhiwei Luo","doi":"10.1109/ACCESS.2025.3604877","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3604877","url":null,"abstract":"Parkinson’s disease is a progressive neurodegenerative disorder, and identifying patients at the premotor stage enables early intervention and improved treatment outcomes. Dysarthria affects over 90% of Parkinson’s patients, making speech a valuable biomarker. In this study, we propose an end-to-end deep learning model to detect early-stage Parkinson’s disease based on speech signals. The model was trained and evaluated using recordings from 131 early-stage PD patients and 42 healthy controls, including sustained vowels (e.g., /A/, /O/) and repetitive syllables (e.g., /pa/, /ta/). Experimental results demonstrate that our model outperforms various deep learning and ensemble learning classifiers in terms of detection accuracy and F1-score, Among indicators, ACC reached 0.78, and F1-score reached 0.831. Furthermore, we explore the temporal dynamics of speech sequences to reveal their correlation with disease progression.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154283-154294"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146786","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145057455","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":"Advancing Federated Learning: A Systematic Literature Review of Methods, Challenges, and Applications","authors":"Tamanna Zubairi Sana;Shahab Abdulla;Anindya Nag;Ayontika Das;Md. Mehedi Hassan;Zoya Zubairi Fiza;Asif Karim;Sheikh Ridwan Raihan Kabir","doi":"10.1109/ACCESS.2025.3605165","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605165","url":null,"abstract":"Federated Learning (FL) has emerged as a cutting-edge paradigm in machine learning, showcasing remarkable advancements in recent years. This research paper delves into the dynamic landscape of FL by addressing four pivotal research questions. The study investigates the most recent advancements in implementing FL and explores additional applications that could benefit from this decentralized learning paradigm. This inquiry aims to provide an up-to-date overview of the evolving FL field and its potential cross-industry impact. The paper explores the integration of FL with various machine learning approaches to ensure optimal performance, privacy preservation, and scalability. By unraveling the collaborative aspects of FL with other machine learning paradigms, the research seeks to unveil novel strategies for enhancing efficiency in FL scenarios. The third research question focuses on the repercussions of scalability challenges and resource constraints in federated learning. This investigation aims to uncover the practical difficulties of implementing FL across diverse sectors, shedding light on potential barriers to its widespread adoption. The research probes into the future of federated learning by examining how it will be utilized in upcoming technological advancements and industries. This exploration aims to provide insights into the long-term viability and applicability of FL, anticipating its role in shaping the technological landscape across various sectors. Through a comprehensive analysis of these research questions, this paper contributes to the understanding of FL, providing valuable insights for researchers, practitioners, and decision-makers navigating the intricate intersection of FL, machine learning, and emerging technologies. This research paper aspires to provide a holistic overview of the advancements, integration possibilities, challenges, and prospects associated with federated learning, contributing to the ongoing discourse on the intersection of FL and machine learning in contemporary technological landscapes.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153817-153844"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146653","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021191","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":"Machine Learning-Enabled Trajectory Optimization for AUV Relaying in Underwater Communications","authors":"Hyeon Woo Jeon;Duk Kyung Kim","doi":"10.1109/ACCESS.2025.3604805","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3604805","url":null,"abstract":"Underwater communication (UWC) faces significant challenges due to signal attenuation, multipath effects, and complex underwater topography. Deploying an Autonomous Underwater Vehicle (AUV) as a relay node can improve link reliability; however, optimal positioning and trajectory planning remain inadequately explored. Given the dynamic nature of transmission loss with AUV movement, determining an efficient trajectory is crucial for enhancing end-to-end signal quality. While Deep Q-Networks (DQNs) have been applied to this task, their performance degrades in large and complex environments, especially due to difficulty in handling a long-term trajectory optimization. To overcome this, we propose a multi-staged DQN framework that divides the overall path into shorter segments, applying individual DQNs sequentially to identify optimal local paths. These are then concatenated to form a complete trajectory. A reward threshold mechanism guides exploration toward globally optimal solutions. Simulation results demonstrate that the proposed method outperforms conventional approaches in terms of average cumulative signal-to-noise ratio (SNR) gain, achieving rapid convergence, strong generalization across scenarios, and minimal performance loss in challenging conditions.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154251-154266"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146760","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021410","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 Threat-Informed Approach to Malware Evasion Using DRM and TLS Callbacks","authors":"Swayam Tejas Padhy;P. B. Shanthi;Gururaj Bijur;S. Hemalatha","doi":"10.1109/ACCESS.2025.3605020","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605020","url":null,"abstract":"As adversaries refine their techniques to avoid detection, Advanced Persistent Threats (APTs) are increasingly exploring unconventional mechanisms to maintain stealth. This paper introduces a novel approach that leverages Digital Rights Management (DRM) as an anti-analysis shield to prevent reverse engineering and forensic investigation. By binding malware execution to a specific machine through DRM fingerprinting, sandbox, and virtual-machine analysis are effectively thwarted. To harden this mechanism, anti-debugging via Thread Local Storage (TLS) callbacks is implemented to detect debuggers before the main execution begins, rendering any debugging attempt futile by nullifying the malware’s main function. The paper presents a proof-of-concept in the form of a DLL injector, showcasing a stealthy persistence mechanism and anti-analysis measures. To further complicate analysis, Import Address Table (IAT) camouflage introduces whitelisted API noise, misleading defenders and evading static detection. While the current implementation is a minimal loader and persistence mechanism, the techniques outlined here provide a blueprint for more sophisticated operations by advanced threat actors. This paper aims to highlight a unique attack chain that could be utilized to essentially nullify modern defensive mechanisms.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"155195-155202"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146733","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021207","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":"Scale-Free and Phase-Agnostic Detection of Interturn Short-Circuit Faults in Permanent Magnet Synchronous Motors","authors":"Mikyung Hwang;Jonghyeok Kim;Hyuntak Lee;Hyunseok Oh","doi":"10.1109/ACCESS.2025.3605534","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605534","url":null,"abstract":"This study presents a scale-free and phase-agnostic method for detecting interturn short-circuit faults (ISCFs) in the stator windings of permanent magnet synchronous motors (PMSMs). The proposed method integrates denoising and feature extraction with a crest-factor-based health indicator. A wavelet-based denoising method with average peak extraction is devised to enhance the sensitivity to fault-induced current deviations while suppressing external noise. The crest factor is modified to enable phase-agnostic detection across stator windings. To eliminate scale dependency associated with motor capacity, the modified crest factor is further calibrated using baseline data obtained under healthy conditions. The resulting health indicator, namely max-min crest factor, enables consistent and reliable ISCF detection without requiring motor-specific parameters or prior knowledge of the faulty phase. The effectiveness of the proposed method is validated through multiple case studies, including 1) numerical simulations, 2) laboratory-scale testbed experiments on small-capacity PMSMs (100 W and 1 kW), and 3) full-scale testing on an 82.5 kW PMSM under realistic operating conditions. The experimental results demonstrate that the method reliably detects ISCFs regardless of fault location or motor scale.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"154812-154822"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146749","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021201","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 Method and Criterion for Repetitive Surge Current in Silicon Carbide Schottky Diodes","authors":"Jenny Damcevska;Sima Dimitrijev;Daniel Haasmann;Philip Tanner","doi":"10.1109/ACCESS.2025.3604871","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3604871","url":null,"abstract":"The need for efficient power-conversion systems in renewable energy, electric vehicles, and industrial power applications has motivated the development of wide-bandgap power semiconductor devices, such as the SiC Schottky diode. An important parameter that establishes the reliability of these high-power devices is their repetitive forward surge current, which ensures robust circuit designs that can withstand high current conditions without damage or failure. However, there is no consistent measurement method to determine this parameter for SiC Schottky diodes, and manufacturers that provide this parameter have no clear indication of the methodology used to obtain the presented value. In this work, we propose a measurement method and a user-focused criterion for the repetitive peak forward surge current, which also ensures the junction temperature does not exceed the maximum device rating. We demonstrate the need for this criterion by comparing measured surge-current performance of commercially available diodes with two different structures—merged PN Schottky diodes and homogenous Schottky-barrier diodes—designed with three different blocking voltages: 650 V, 1200 V, and 1700 V.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153987-153992"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146654","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021317","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":"Synthetic Network Packet Data Generator With Protocol State and Arrival Timing Awareness","authors":"Yukito Onodera;Erina Takeshita;Tomoya Kosugi;Takashi Nakanishi;Tatsuya Shimada","doi":"10.1109/ACCESS.2025.3604773","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3604773","url":null,"abstract":"Recent advances in network traffic analysis use machine learning (ML) on packet-level data, but obtaining large amount of real data for training ML is becoming a challenge. ML-based generators like Generative Adversarial Networks and Variational Autoencoders are promising candidates for generation the packet-level data but often fail to preserve TCP protocol states and packet arrival time. Without accurately reproducing these characteristics, the synthetic data may fail to reflect real network behavior, potentially leading to erroneous conclusions in the training and evaluation of machine learning models. This paper proposes a new method to synthesize realistic packet-level data with accurate protocol transitions and timing. By separating IP address and port number generation and aligning timing with handshake completion, the model avoids overfitting. Using the CIC-IDS 2017 dataset, our method better replicates headers and timing, producing synthetic data that closely resembles real data features distribution. Visual and statistical comparisons reveal that the synthetic data closely resembles real packet traces, providing a reliable alternative for training and evaluating network analysis.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153398-153405"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146712","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145027986","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":"Assessment of Greenhouse Gas Emissions and Mitigation Strategies for a University in Bangladesh","authors":"Mirza Rasheduzzaman;Md. Sajid Hasan;Nayma Akther Jahan;Atik Jawad;M. Mofazzal Hossain","doi":"10.1109/ACCESS.2025.3605517","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3605517","url":null,"abstract":"Climate change is an urgent global challenge. Higher education institutions (HEIs) have a crucial role in addressing this issue by reducing their environmental impact. This study presents the first comprehensive assessment of greenhouse gas (GHG) emissions at a university in Bangladesh using the GHG Protocol Corporate Standard to categorize emissions into scopes 1, 2, and 3. The total GHG emissions amount to 2498.80 tons of carbon dioxide equivalent (tCO2e) annually, with a per capita carbon footprint of 0.4671 tCO2e. Scope 1 emissions, primarily from university vehicles, generators, cafeterias, and air conditioners, account for 29.73% (742.55 tCO2e). Scope 2 emissions, related to purchased electricity from power grid, are at 18.18% (454.14 tCO2e). The largest contributor is the indirect emissions from commuting in scope 3, accounting for 52.10% (1302.14 tCO2e) of the total. Major emission sources include air conditioners, purchased electricity and commuting of university personnel by cars. To reduce these emissions, the study presents a scenario based mitigation framework consisting of Conventional, Incremental, and Comprehensive Scenarios with targeted interventions for each scope. These include addressing high fugitive emissions from airconditioner by replacing current coolant gases with more efficient alternatives such as R32, transitioning to hybrid or solar-powered electric vehicles, expanding shared transport options, and integrating rooftop and floating solar systems. Although the study is based on one university, the proposed strategies are designed to be broadly applicable to universities across Bangladesh. The study also emphasizes energy efficiency, eco-friendly mobility, and integrating sustainability into the curriculum. This study underscores the need for localized assessments and tailored strategies to effectively address the unique challenges of reducing GHG emissions in HEIs, providing a robust framework for creating a more sustainable university community.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"153741-153763"},"PeriodicalIF":3.6,"publicationDate":"2025-09-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11146783","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145021198","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}