IEEE Transactions on Human-Machine Systems最新文献_第5页

Smartphone-Based Telerehabilitation for Low Back Pain: A Randomized Controlled Trial on Pain, Disability, Fear-Avoidance, and Trunk Muscle Endurance 基于智能手机的腰痛远程康复：疼痛、残疾、恐惧回避和躯干肌肉耐力的随机对照试验

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-01 DOI: 10.1109/THMS.2026.3682700

Cheng-Yen Liao;Bor-Shing Lin;Huey-Wen Liang;Po-Yao Wang;Tzu-Jung Huang;Si-Huei Lee

{"title":"Smartphone-Based Telerehabilitation for Low Back Pain: A Randomized Controlled Trial on Pain, Disability, Fear-Avoidance, and Trunk Muscle Endurance","authors":"Cheng-Yen Liao;Bor-Shing Lin;Huey-Wen Liang;Po-Yao Wang;Tzu-Jung Huang;Si-Huei Lee","doi":"10.1109/THMS.2026.3682700","DOIUrl":"https://doi.org/10.1109/THMS.2026.3682700","url":null,"abstract":"Low back pain (LBP) is a widespread global health problem associated with a significant economic burden. Compared with traditional treatment, telerehabilitation may enhance exercise adherence and execution. This randomized controlled trial evaluated the efficacy of a smartphone-based mHealth platform for telerehabilitation (SMPT) in individuals with LBP. Participants were randomly assigned to either the SMPT group (<italic>n = 23) or a control group (<italic>n = 19) for a 12-week home-based program. Outcomes included pain assessed by the visual analogue scale (VAS), disability by the Roland–Morris disability questionnaire (RMDQ), fear-avoidance beliefs by the fear-avoidance beliefs questionnaire (FABQ), and trunk endurance tests. After the 12-week intervention, the SMPT group showed significantly lower postintervention VAS scores compared with the control group (19.0 [11.5–31.5] vs. 27.0 [20.0–45.5]; <italic>p = 0.036; <italic>r = 0.35). A greater median reduction in pain intensity was observed in the SMPT group (−29.0 [−44.5 to −17.5]) than in the control group (−11.0 [−33.5 to −4.0]) (<italic>p = 0.044; Hodges–Lehmann Δ = 15.0 [95% CI −60.1, 64.3]). Within the SMPT group, disability and fear-avoidance outcomes also improved significantly, with RMDQ scores decreasing from 7.0 [5.0–9.5] to 4.0 [3.0–6.5] (<italic>p = 0.013) and FABQ total scores from 34.0 [27.5–41.5] to 27.0 [19.5–34.5] (<italic>p = 0.005). These results suggest that the SMPT is effective in reducing pain, disability, and fear-avoidance beliefs, while improving trunk endurance. The SMPT may serve as a practical adjunct to conventional rehabilitation in patients with LBP.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"488-497"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505817","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-01 DOI: 10.1109/THMS.2026.3684013

Jaeryoung Lee;Dimitar Stefanov

{"title":"Task-Related Electrodermal Activity Dynamics in Robot-Mediated Interaction: A Six-Case Study of Children With Neurodevelopmental Disorders","authors":"Jaeryoung Lee;Dimitar Stefanov","doi":"10.1109/THMS.2026.3684013","DOIUrl":"https://doi.org/10.1109/THMS.2026.3684013","url":null,"abstract":"Socially assistive robots have been explored as platforms to support structured interaction with children with neurodevelopmental disorders; however, most systems are designed for individuals with autism spectrum disorder (ASD) and may not be generalizable to other conditions. Emotional engagement and physiological arousal often differ across diagnostic categories and symptom severities, highlighting the challenge of capturing heterogeneous arousal patterns observed in small, diverse participant samples. This study presents a six case exploratory analysis of electrodermal activity (EDA) responses during four task-based emotional interaction sessions in robot-assisted training involving children diagnosed with ASD, pervasive developmental disorder, developmental coordination disorder, and intellectual disability. A multimodal platform integrating a NAO robot, an E4 wristband, facial expression tracking, and therapist control was used to synchronize behavioral and physiological data streams using unified timestamps; physiological signals were recorded for offline analysis. EDA signals were interpreted as task-related arousal dynamics rather than discrete emotional states. Descriptive time series inspection and vector autoregressive impulse response visualization were applied to characterize individual variability. The findings revealed heterogeneous arousal trajectories shaped by task type and individual characteristics, reflecting pronounced individual differences in task-related arousal dynamics. Overall, this study presents a timestamp synchronized multimodal data logging platform and an exploratory six-case analysis of task-related EDA arousal dynamics during robot-mediated interaction, emphasizing pronounced individual variability.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"552-561"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Impact of Retail Collaborative Robots on Surrounding Human Neuromuscular Responses: An EMG Analysis 零售协作机器人对周围人类神经肌肉反应的影响：肌电图分析

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-17 DOI: 10.1109/THMS.2026.3668974

Xiangrui Wang;Yue Luo;Yu Gu;Jason Gross;Chizhao Yang;Boyi Hu

{"title":"Impact of Retail Collaborative Robots on Surrounding Human Neuromuscular Responses: An EMG Analysis","authors":"Xiangrui Wang;Yue Luo;Yu Gu;Jason Gross;Chizhao Yang;Boyi Hu","doi":"10.1109/THMS.2026.3668974","DOIUrl":"https://doi.org/10.1109/THMS.2026.3668974","url":null,"abstract":"Retail robots have increasingly become popular in retail stores, serving as collaborative assistants by completing tedious and repetitive tasks. As key participants in a retail environment, understanding how these robots influence the movements and behaviors of nearby customers can provide valuable insights to improve robot ergonomics. This article examined neuromuscular information changes with and without the presence of a retail robot. Sixteen participants were recruited to perform item picking and sorting tasks in a high-fidelity retail setting. Surface electromyography (EMG) signals were collected from four muscles—biceps brachii, brachioradialis, upper trapezius and erector spinae (ES), to measure muscle activity and EMG-EMG coherence. A global decrease in power spectral density (PSD) was observed across all monitored muscles with the robot's presence, indicating a reduction in overall muscular energy expenditure. The introduction of the retail robot also led to a significant reduction in the peak values and waveform length of the ES muscle. These findings not only highlight the potential of retail robots to enhance the overall shopping experience but also provide crucial insights for enhancing ergonomics during robotic design.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"438-447"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fast Decision Making in Human–Machine Interaction Through Estimation of Human Reaching Intent 基于人达到意图估计的人机交互快速决策

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-10 DOI: 10.1109/THMS.2026.3675918

Jasper Van der Auwera;Erwin Aertbeliën;Wilm Decré;Herman Bruyninckx

{"title":"Fast Decision Making in Human–Machine Interaction Through Estimation of Human Reaching Intent","authors":"Jasper Van der Auwera;Erwin Aertbeliën;Wilm Decré;Herman Bruyninckx","doi":"10.1109/THMS.2026.3675918","DOIUrl":"https://doi.org/10.1109/THMS.2026.3675918","url":null,"abstract":"This article proposes intent-based decision-making approaches for operator assistance in manipulation tasks, where the intent of the human operator is defined by the target of an ongoing reaching motion. These approaches start from a motion model database, which contains multiple motion models learned using Trajectory parameterized Probabilistic Principal Component Analysis. Often, such a database is constructed offline using supervised learning. Instead, this article proposes a semi-supervised and unsupervised online learning approach, able to encode new motion styles observed during execution. Then, the intended target of an ongoing reaching motion is predicted based on this motion model database, for which three probabilistic intent estimation approaches are proposed: 1) classification intent estimation; 2) prediction intent estimation; and 3) mixture intent estimation. In addition, a decision-making approach is introduced which determines whether the human operator will deviate from the task’s high-level plan based on the target probabilities obtained from intent estimation, such that an early intervention in the human’s task execution can be provided. This decision-making approach directly considers the target probabilities in its decision-making process, instead of only considering the most probable target, which makes it more adaptable to different situations and better at dealing with large uncertainties. The proposed methods were validated on the publicly available HA4M dataset.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"498-512"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human–Machine Shared Steering in Driving via Integration of Driver Fatigue in a Fuzzy Logic-Based System 基于模糊逻辑的驾驶员疲劳集成驾驶人机共享转向系统

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-10 DOI: 10.1109/THMS.2026.3677428

Qinhan Hu;Xixia Sun;Zhenyang Yan;Xiangpeng Xie;Yang Liu

{"title":"Human–Machine Shared Steering in Driving via Integration of Driver Fatigue in a Fuzzy Logic-Based System","authors":"Qinhan Hu;Xixia Sun;Zhenyang Yan;Xiangpeng Xie;Yang Liu","doi":"10.1109/THMS.2026.3677428","DOIUrl":"https://doi.org/10.1109/THMS.2026.3677428","url":null,"abstract":"As traffic environments become increasingly complex, the workload of drivers continues to intensify, and fatigue driving has been recognized as a major hidden danger affecting traffic safety. To improve driving performance under different fatigue states, this article proposes a human–machine shared steering control scheme employing the homogeneous polynomials parameter-dependent technology. First, the real-time driver fatigue assessment model is established, in which the Gaussian interval type-2 fuzzy logic systems with higher interpretability are employed to infer driver fatigue through multiple sets of facial feature points. Second, a more reasonable authority allocation strategy between the human driver and machine is developed based on accurately assessed fatigue level. Then, to mitigate the impact of time-varying nonlinear parameter disturbance on driving performance, a homogeneous matrix polynomial gain scheduling scheme is proposed. Through developing multiple groups of controller gains containing deep system information, the feasible stabilization region of the shared controller design under different fatigue states is effectively expanded. Finally, the superiority of the proposed shared controller is validated through the human–machine shared driving experimental platform. The results show that the proposed controller can effectively improve the vehicle performance. With the adjustment of the controller's homogeneous polynomial order, the vehicle performance is further optimized.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"662-671"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human–Machine Fitness While Driving: Evaluating Human Acceptance of Autonomous Driving Styles Through EEG Signal Analysis 驾驶时的人机适应性：通过脑电图信号分析评估人类对自动驾驶风格的接受程度

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-10 DOI: 10.1109/THMS.2026.3676889

Geqi Qi;Zhentao Dong;Wei Guan;Ailing Huang;Ya’ning An

{"title":"Human–Machine Fitness While Driving: Evaluating Human Acceptance of Autonomous Driving Styles Through EEG Signal Analysis","authors":"Geqi Qi;Zhentao Dong;Wei Guan;Ailing Huang;Ya’ning An","doi":"10.1109/THMS.2026.3676889","DOIUrl":"https://doi.org/10.1109/THMS.2026.3676889","url":null,"abstract":"Autonomous driving (AD) systems often exhibit driving styles that differ considerably from those of human drivers. When users engage with AD systems, they are essentially passengers in a vehicle controlled by an unseen operator. This lack of fitness can lead to unexpected driving behaviors, which may significantly undermine user trust. Evaluating human–machine fitness is essential for ensuring safety, efficiency, and user satisfaction in AD systems. However, evaluating human acceptance of AD styles is challenging due to their subjective nature and context-dependent variability. In this study, we utilize electroencephalography (EEG) signals collected from the same individuals during both autonomous and manual driving (MD) to analyze AD acceptance, capturing subtle human responses during human–machine interactions. By examining the differences between MD and AD styles in car-following segments, we quantify AD acceptance. We build a prediction model using EEG-based brain functional networks with various similarity metrics and thresholding methods. The results show that our model outperforms baseline methods, achieving an R2 of 0.824, with the combination of phase-locking value and density-based thresholding being the most effective. Cognitive analysis indicates that brain networks exhibit greater efficiency during MD than AD, and this difference diminishes with increased acceptance of AD. Furthermore, high-order connectivity matrices indicate that different acceptance levels are linked to distinct coupling patterns between brain networks across various task states. This research provides insights for continuously assessing AD acceptance, aiding in the development of reliable systems tailored to diverse users.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"636-649"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504919","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effects of Time and Posture Factors on Handwriting Features of Dynamic Signature 时间和姿势因素对动态签名笔迹特征的影响

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-10 DOI: 10.1109/THMS.2026.3666775

Linqi Jiang;Peter Xiaoping Liu

{"title":"Effects of Time and Posture Factors on Handwriting Features of Dynamic Signature","authors":"Linqi Jiang;Peter Xiaoping Liu","doi":"10.1109/THMS.2026.3666775","DOIUrl":"https://doi.org/10.1109/THMS.2026.3666775","url":null,"abstract":"The reliability of signature verification systems and the accuracy of forensic signature comparison are affected by factors, such as time and writing posture. Current work on posture-induced variations relies mainly on qualitative classification methods, which lack objective quantitative metrics. To understand the underlying patterns of dynamic signature handwriting under various time and postural conditions, this study collected 12 000 signature samples across five sessions, incorporating six postures. A signature posture dataset was defined using four joint angles (wrist, elbow, hip, and ankle) to quantify signing postures. Different statistical methods were applied to analyze the static and dynamic features of signature handwriting in order to evaluate the significance of time and posture influences on signature features. For the signature posture dataset, the generalized linear model and structural equation model were employed to assess the extent of joint angle effects. Principal component analysis was further utilized to identify the features that are the most significantly affected by posture. The results show that time and posture have statistically significant effects on different signature features. Posture-induced variations predominantly (80% ) arise from differences between sitting and nonsitting postures, with 69.5% of these variations attributable to changes in hip and ankle joint angles. Among the posture-sensitive features, area exhibits the highest sensitivity to postural variations. These results provide important insights for research in the fields of signature verification and forensic handwriting.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"592-601"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Vision-Driven End-User Robot Programming Method Based on the Alignment Between Body Language and Motion Commands 一种基于肢体语言和运动指令对齐的视觉驱动终端用户机器人编程方法

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-20 DOI: 10.1109/THMS.2026.3679132

Shipeng Lyu;Shenzeng Huo;Wanyu Ma;Guodong Guo;David Navarro-Alarcon

{"title":"A Vision-Driven End-User Robot Programming Method Based on the Alignment Between Body Language and Motion Commands","authors":"Shipeng Lyu;Shenzeng Huo;Wanyu Ma;Guodong Guo;David Navarro-Alarcon","doi":"10.1109/THMS.2026.3679132","DOIUrl":"https://doi.org/10.1109/THMS.2026.3679132","url":null,"abstract":"This work is motivated by the complexity of conventional robot programming methods, which require a deep understanding of both robotics and software development. This situation presents significant challenges for nontechnical end-users who need to program a new robotic task. To address this issue, we propose a new robot programming method that enables humans to specify robot motion tasks using simple and intuitive body-language commands. To this end, we propose a triadic task decomposition framework to decompose complex robot motion tasks into three basic task units, i.e., location, operation, and motion. These units are paired with a set of body-language cues that enable end-users to specify a variety of actions and motions, providing an intuitive alternative to traditional robot programming methods. To program these units, we develop a multimodal fusion-based instruction-parsing algorithm with a dual-phase visual architecture, enabling temporally aware body-language recognition and high-accuracy cross-modal object localization. Furthermore, a semantics-adaptive task execution system is proposed, which incorporates an intent reasoning module that dynamically handles end-users' nonstandard programming sequences and incomplete task logic, enhancing programming success rates and system usability. We evaluate the proposed method on a dual-arm robotic platform and a humanoid robot through various pick-and-place tasks, and compare its performance with that of several baselines from the literature.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"448-457"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148508389","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing Auditory Brainstem Response Extraction From Noised EEG With Adaptive Kalman Denoising Technique 基于自适应卡尔曼去噪技术的脑电听觉脑干响应提取

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-20 DOI: 10.1109/THMS.2026.3681602

Xin Wang;Junyu Ji;Haoshi Zhang;Xiaobei Jing;Xu Yong;Yangjie Xu;Hongguan Pan;Yuan Tao;Mingxing Zhu;Michael Chi Fai Tong;Poly Z. H. Sun;Guanglin Li;Shixiong Chen

{"title":"Enhancing Auditory Brainstem Response Extraction From Noised EEG With Adaptive Kalman Denoising Technique","authors":"Xin Wang;Junyu Ji;Haoshi Zhang;Xiaobei Jing;Xu Yong;Yangjie Xu;Hongguan Pan;Yuan Tao;Mingxing Zhu;Michael Chi Fai Tong;Poly Z. H. Sun;Guanglin Li;Shixiong Chen","doi":"10.1109/THMS.2026.3681602","DOIUrl":"https://doi.org/10.1109/THMS.2026.3681602","url":null,"abstract":"Auditory brainstem response (ABR) is a weak evoked EEG signal that provides an objective measure for assessing auditory function. However, the traditional extraction method, namely, averaging is noise-sensitive and needs thousands of trials, which places high demands on the subjects and the experimental environment. Kalman weighted (KW) technique has the potential to extract ABR with high quality but relies heavily on expert experience for precise parameter tuning. In this article, an adaptive Kalman denoising technique, which can adaptively adjust the parameter, was developed. A comprehensive investigation was carried out on different noise types (pink noise/Gaussian white noise/uniform noise), proportions (20%/40%/60%/80%/100%), amplitudes (20/40/60/80 <italic>μV), and integrated manners (early-noised/intermittent-noised/late-noised). Multiple metrics, such as Pearson correlation coefficient, root mean square error, latency and amplitude of characteristics wave, and the wave recognition rate were calculated for evaluation. The simulation results showed that the proposed method outperformed the averaging and KW techniques over these evaluation metrics. Also, these evaluation metrics of the proposed method were much more stable than those of averaging the KW. Finally, we verified the proposed method in the real scenario. It is believed that the proposed method opens a window for daily ABR-based auditory health condition screening, which can benefit the early detection and diagnosis of auditory diseases.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"562-571"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504279","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated Parkinson’s Disease Detection System Using FBSE-FAWT-Based Time-Frequency Representation of Speech Signals 基于fbse - faw语音信号时频表示的帕金森病自动检测系统

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-25 DOI: 10.1109/THMS.2026.3667216

Amishi Vijay;Ram Bilas Pachori;Nitya Tiwari;Balasubramanyam Appina

{"title":"Automated Parkinson’s Disease Detection System Using FBSE-FAWT-Based Time-Frequency Representation of Speech Signals","authors":"Amishi Vijay;Ram Bilas Pachori;Nitya Tiwari;Balasubramanyam Appina","doi":"10.1109/THMS.2026.3667216","DOIUrl":"https://doi.org/10.1109/THMS.2026.3667216","url":null,"abstract":"Parkinson’s disease (PD) detection from speech signals attracts significant attention from researchers due to the effectiveness of speech impairment symptoms in PD diagnosis in its early phase. The short-time Fourier transform (STFT)-based analysis suffers from fixed resolution. The discrete wavelet transform (DWT) provides multiresolution analysis. However, an analytic wavelet transform with a flexible time-frequency covering (AWTFTFC) is a generalized form of DWT with flexible selection of redundancy, dilation factor, and Q-factor. The Fourier-Bessel series expansion (FBSE)-based flexible analytic wavelet transform (FAWT) (FBSE-FAWT) is an improved version of AWTFTFC with the replacement of the Fourier-based spectrum by the FBSE-based spectrum to have better frequency resolution. In this article, FBSE-FAWT-based time-frequency representation (TFR) is used to detect PD from speech signals. In the FBSE-FAWT-based TFR method, the FBSE-FAWT technique has been used to obtain subband signals and Hilbert spectral analysis is applied to compute TFR of speech signals. Seven different pretrained networks, namely, AlexNet, GoogleNet, SqueezeNet, DenseNet-101, InceptionNet-v3, VGG-16, and ResNet-50 are trained using the obtained TFRs to detect PD. The proposed framework with ResNet-50 demonstrates the highest performance with an accuracy of 98.05%, an F1-score of 98.27%, a specificity of 98.61%, a precision of 98.93%, and a recall of 97.62%. The robustness of the proposed framework is verified in cross-task situations where the framework has been trained on spontaneous dialogue task and tested on read text task. Further, the proposed framework achieves better performance as compared with its variant, where the FBSE-FAWT-based TFR is replaced with a spectrogram, as well as compared with other existing methods in the literature.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"532-541"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0