IEEE Access最新文献

{"title":"Optimized Placement of Distributed Fiber Optic Sensors for Accurate Strain Monitoring of Buried Pipelines in Landslide-Prone Areas","authors":"Alarifi Hamzh;Hisham Mohamad;Phromphat Thansirichaisree","doi":"10.1109/ACCESS.2025.3588181","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588181","url":null,"abstract":"Buried pipelines are vulnerable to damage from geohazards such as landslides, making accurate strain monitoring essential for early hazard detection and integrity management. While conventional strain monitoring tools face limitations in long-distance applications, distributed fibre optic sensing (DFOS) offers continuous strain measurement with high spatial resolution along extended pipeline networks. This study proposes an optimised DFOS placement strategy for early-stage strain detection induced by lateral soil movement. A novel laboratory-scale sandbox model was developed to simulate soil–pipeline interaction, with fibre optic cables installed at varying positions relative to the pipe. Complementary finite element analysis using ABAQUS was conducted to replicate and validate the physical test conditions. Results indicate that placing DFOS cables at a distance of 1.5D to 2D from the pipe (where D is the pipe diameter) provides optimal strain detection. Experimental and numerical results showed strong agreement, with an average strain deviation of less than 11%. The proposed placement approach enhances DFOS performance for buried pipeline monitoring and offers a practical, scalable solution for early-warning applications in geohazard-prone environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124899-124909"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079574","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671167","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":"Hierarchical Cascade Deep Learning for EMG-Based Behavioral Biometrics: Gesture and Subject Classification","authors":"Berke Cansiz;Hatice Vildan Dudukcu;Murat Taskiran;Nihan Kahraman","doi":"10.1109/ACCESS.2025.3588791","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588791","url":null,"abstract":"The integration of electromyography (EMG) signals into biometric recognition has garnered significant attention due to their potential for highly secure and reliable identification. Unlike vision-based methods like cameras, EMG is immune to lighting conditions, clothing, or occlusions. This study presents a hierarchical cascade deep learning framework aimed at simultaneously performing hand gesture recognition and subject-specific biometric classification. Utilizing the publicly available Gesture Recognition and Biometrics ElectroMyogram (GRABMyo) dataset, which encompasses diverse EMG recordings from 43 individuals performing 17 unique gestures, this study proposes a two-staged classification approach. The first stage concentrates on recognizing the hand gesture, succeeded by a gesture-specific model that subsequently categorizes the subject associated with the identified gesture. The experimental results demonstrate the effectiveness of the proposed model, which achieved an average accuracy of 71.62% across gesture and subject classification, representing an improvement of approximately 5% and 21% compared to conventional single-model and multi-task strategies evaluated in this study, highlighting this approach’s effectiveness in handling the variability of EMG signals across different gestures and subjects. The findings underscore the potential of the proposed methodology for enhancing EMG-based biometric recognition systems.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124115-124128"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079587","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671203","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":"GS-GVINS: A Tightly-Integrated GNSS-Visual-Inertial Navigation System Augmented by 3D Gaussian Splatting","authors":"Zelin Zhou;Shichuang Nie;Saurav Uprety;Hongzhou Yang","doi":"10.1109/ACCESS.2025.3589161","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3589161","url":null,"abstract":"Accurate navigation is critical for autonomous vehicles in today’s diverse traffic environments. Integrating Global Satellite Navigation System (GNSS), Inertial Navigation System (INS), and camera has demonstrated significant robustness and high accuracy for navigation in complex environments. However, most integrated systems rely on feature-tracking based visual odometry, which suffers from the problem of feature sparsity, high dynamics, significant illumination changes, etc. Recently, the emergence of 3D Gaussian Splatting (3DGS) has drawn significant attention in the area of 3D map reconstruction and visual SLAM. While extensive research has explored 3DGS for indoor trajectory tracking using visual sensor alone or in combination with Light Detection and Ranging (LiDAR) and Inertial Measurement Unit (IMU), its integration with GNSS for large-scale outdoor navigation remains underexplored. To address these concerns, we propose GS-GVINS: a tightly-integrated GNSS-Visual-Inertial Navigation System augmented by 3DGS. This system leverages 3D Gaussian as a continuous differentiable scene representation in large-scale outdoor environments, enhancing navigation performance through the constructed 3D Gaussian map. Notably, GS-GVINS is the first GNSS-Visual-Inertial navigation application that directly utilizes the analytical jacobians of SE3 camera pose with respect to 3D Gaussians. To maintain the quality of 3DGS rendering in extreme dynamic states, we introduce a motion-aware 3D Gaussian pruning mechanism, updating the map based on relative pose translation and the accumulated opacity along the camera ray. For validation, we test our system under different driving environments: open-sky, suburban, and urban. Both self-collected and public datasets are used for evaluation. The results demonstrate the effectiveness of GS-GVINS in enhancing navigation accuracy across diverse driving environments.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125817-125829"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11080066","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687770","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":"The Rise of Artificial Intelligence Phobia! Unveiling News-Driven Spread of AI Fear Sentiment Using ML, NLP, and LLMs","authors":"Jim Samuel;Tanya Khanna;Julia Esguerra;Srinivasaraghavan Sundar;Alexander Pelaez;Soumitra S. Bhuyan","doi":"10.1109/ACCESS.2025.3588179","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588179","url":null,"abstract":"Contemporary public discourse surrounding artificial intelligence (AI) often displays disproportionate fear and confusion relative to AI’s actual potential. This study examines how the use of alarmist and fear-inducing language by news media contributes to negative public perceptions of AI. Nearly 70,000 AI-related news headlines were analyzed using natural language processing (NLP), machine learning (ML), and large language models (LLMs) to identify dominant themes and sentiment patterns. The theoretical framework draws on existing literature that posits the power of fear-inducing headlines to influence public perception and behavior, even when such headlines represent a relatively small proportion of total coverage. This research applies topic modeling and fear sentiment classification using BERT, LLaMA, and Mistral, alongside supervised ML techniques. The findings show a persistent presence of emotionally negative and fear-laden language in AI news coverage. This portrayal of AI as dangerous to humans or as an existential threat profoundly shapes public perception, fueling AI phobia that leads to behavioral resistance toward AI, which is ultimately detrimental to the science of AI. Furthermore, this can have an adverse impact on AI policies and regulations, leading to a stunted growth environment for AI. The study concludes with implications and recommendations to counter fear-driven narratives and suggests ways to improve public understanding of AI through responsible news media coverage, broad AI education, democratization of AI resources, and the drawing of clear distinctions between AI as a science versus commercial AI applications, to promote enhanced fact-based mass engagement with AI while preserving human dignity and agency.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125944-125969"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079577","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687771","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":"An Intelligent Audio Encryption and Compression Algorithm Inspired by the Encoding of Various Biological Sequences","authors":"Mohammad Nassef","doi":"10.1109/ACCESS.2025.3588764","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588764","url":null,"abstract":"During the last decade, audio streams became an essential and fast means of communication through personal and business applications including social media and telehealth applications. Thus, various research efforts tried to develop robust and secure audio encryption algorithms that keep audio communications secure to the highest extent. Biological sequences retain huge amount of information which present new horizon over legacy encryption algorithms in terms of encoding capacity. This article introduces an intelligent audio encryption and compression framework, namely Audio-to-Peptide (A2P), that mimics the successive generation of biological sequences to successively encrypt and compress sequences of frames in raw WAV audio files. The parameters of the basic encryption key include some general information of the audio file in addition to some technical information that is based on the frequency of the audio to be encrypted. Hence, the proposed framework uses an Artificial Neural Network (ANN) model that was trained to accurately determine these technical parameters of the basic encryption key without any user involvement. The experimental results showed that the proposed algorithm is robust and secure against known security attacks.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"126334-126354"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079586","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687709","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":"TREET: TRansfer Entropy Estimation via Transformers","authors":"Omer Luxembourg;Dor Tsur;Haim Permuter","doi":"10.1109/ACCESS.2025.3588009","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588009","url":null,"abstract":"Transfer entropy (TE) is an information theoretic measure that reveals the directional flow of information between processes, providing valuable insights for a wide range of real-world applications. This work proposes Transfer Entropy Estimation via Transformers (TREET), a novel attention-based approach for estimating TE for stationary processes. The proposed approach employs Donsker-Varadhan representation to TE and leverages the attention mechanism for the task of neural estimation. We propose a detailed theoretical and empirical study of the TREET, comparing it to existing methods on a dedicated estimation benchmark. To increase its applicability, we design an estimated TE optimization scheme that is motivated by the functional representation lemma, and use it to estimate the capacity of communication channels with memory, which is a canonical optimization problem in information theory. We further demonstrate how an optimized TREET can be used to estimate underlying densities, providing experimental results. Finally, we apply TREET to feature analysis of patients with Apnea, demonstrating its applicability to real-world physiological data. Our work, applied with state-of-the-art deep learning methods, opens a new door for communication problems which are yet to be solved.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"126477-126495"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079584","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687712","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 Early Diagnosis: Predicting Mild Cognitive Impairment Progression in Normal Individuals Using Deep Learning on MRI Features","authors":"Abdullah Baktash;Yashar Sarbaz;Saeed Meshgini;Reza Afrouzian","doi":"10.1109/ACCESS.2025.3588801","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588801","url":null,"abstract":"One of the most challenging tasks for neurologists is the early diagnosis of Alzheimer’s disease (AD). Early and accurate diagnosis of the mild cognitive impairment (MCI) stage can enhance efforts to slow down the major consequences linked to this condition. Deep learning systems provide a promising performance in diagnosing the disease through neuroimaging analysis. This research aims to develop a deep learning-based system that efficiently identifies and analyzes the progression from Cognitively Normal (CN) to MCI, addressing the growing need for more accessible, accurate diagnostic tools. The proposed model comprises two distinct feature extraction paths to capture local and global image features. Each path includes advanced modules for feature refinement associated with the channel attention mechanism. The resultant output features are produced using a learned fusion technique from the two paths’ features and applied to the CN vs. MCI binary classifier. Furthermore, the proposed Suspected Subject Classifier (SSC) system applies various machine-learning methods to identify the suspected MCI subjects. The results showed a comparative performance for the binary diagnosis of CN individuals and those with MCI, achieving an accuracy of 91.6% and 88.4% for multi-class diagnoses, including the prediction of progression from normal to confirmed MCI. This study represents an exceptional stride toward predicting early MCI in normal individuals. By enhancing prediction efficiency for early disease progression in normal individuals, our method can potentially advance intervention strategies and improve patient care outcomes.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"122591-122602"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079556","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144657514","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":"Preset-Trajectory-Based Adaptive Neural Autopliot Control for Uncertain Surface Vehicles via Dynamic Event-Triggered Mechanism","authors":"Yongyi Lin;Zonglian Guo","doi":"10.1109/ACCESS.2025.3588820","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588820","url":null,"abstract":"This paper investigates the tracking control problem of autopliot for maritime autonomous surface ships (MASSs) in the presence of the uncertain dynamics and external disturbances, and proposes a dynamic event triggered adaptive mechanism based on a preset-trajectory function. In this paper, to handle the problem of lumped uncertainties, neural netwok and adaptive control technique are employed. A preset-trajectory function is designed, which can guarantee the autopliot error arrive the pre-set accuracy. A dynamic event triggering protocol is established, to reduce the acting frequency of actuators, and decrease the mechanical wear of the MASS actuators. Finally, a new dynamic event-triggered control mechanism is proposed, integrating adaptive neural control and a preset-trajectory function. Based on Lyapunov control theory, all signals in the autopliot control system are proven to be bounded. The numerical simulation results sufficiently demonstrate the effectiveness of the control strategy.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"124932-124940"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079563","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144671178","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":"Road Safety Risk Assessment Approach for Freight Vehicles Using Warning Data","authors":"Cheng Yang;Xiaoling Zhai;Xiaoqin Zhou;Tao Wang;Shiyi Chen;Xiyuan Zhang","doi":"10.1109/ACCESS.2025.3588502","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588502","url":null,"abstract":"Road transport is a vital pillar of the national economy. However, freight vehicles face significant safety challenges during operation due to characteristics such as heavy-load transportation, long-distance travel, and complex cargo types. Traditional accident data analysis methods rely on historical accident statistics, which suffer from strong lagging effects and difficulties in achieving proactive risk identification. To address this, this paper proposes a real-time early-warning-data-based approach for road risk assessment. First, the global Moran’s I index is employed to analyze the spatial clustering characteristics of warning points. Second, an evaluation system is constructed, with the relative occurrence rates of improper driving behavior and abnormal vehicle status warnings as core indicators. The entropy weight method is applied to determine the weights of each indicator, enabling the quantitative calculation of road segment risk values. Finally, cluster analysis is used to determine optimal risk classification thresholds. The method is validated using warning data and historical accident records from 47 road segments across three major roads in Nanning. The results demonstrate that spatial clusters of warning points strongly correlate with high-accident-frequency road segments. The risk classification thresholds exhibit excellent discriminative performance, with boundary values of 0.038 (94.44% accuracy) between low- and medium-risk segments and 0.075 (96.00% accuracy) between medium- and high-risk segments. Significant differences in accident occurrence rates are observed across risk levels: high-risk segments average 7.73 accidents, far exceeding medium-risk (3.53) and low-risk segments (1.35). This study confirms the efficacy of early-warning data in risk assessment, providing transportation authorities with a data-driven risk management tool. The proposed method offers a novel approach for proactive safety control in freight vehicle transportation.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"126769-126779"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079562","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687618","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":"Development of a Torque Sensor for Robot Actuators With Overload Protection","authors":"Kwon-Hui Lee;Bumjoo Lee","doi":"10.1109/ACCESS.2025.3588846","DOIUrl":"https://doi.org/10.1109/ACCESS.2025.3588846","url":null,"abstract":"This study proposes the development of a one-axis torque sensor that can be integrated into robotic joint actuators, featuring an innovative structural design with enhanced overload protection. The developed torque sensor employs a strain gauge-based measurement principle and adopts a binocular structure to induce stress concentration, thereby improving signal sensitivity. In particular, a dedicated stopper mechanism is incorporated into the design to limit deformation and prevent irreversible damage under excessive torque loads. This mechanism plays a critical role in preventing plastic deformation, thereby ensuring long-term structural stability and extending the operational lifespan of the sensor. Finite Element Analysis (FEA) was conducted to simulate the deformation and stress distribution of the torque sensor, leading to the optimization of key design parameters. Based on the simulation results, a physical prototype was fabricated, and experimental validation was performed to evaluate the sensor’s performance. The experimental results showed strong agreement with the FEA outcomes, confirming the validity of the proposed design and demonstrating the effectiveness of the overload protection feature implemented in the sensor. Furthermore, the sensor maintains a compact form factor compatible with CPDS-type high-reduction actuators, while offering enhanced reliability and robustness against unexpected mechanical stress. The findings of this study contribute to the development of high-performance torque sensors suitable for applications in robotics, industrial automation, and precision control systems, and highlight the feasibility of sensor designs with built-in mechanical safety features.","PeriodicalId":13079,"journal":{"name":"IEEE Access","volume":"13 ","pages":"125587-125593"},"PeriodicalIF":3.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11079990","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687753","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}