IEEE Transactions on Human-Machine Systems最新文献_第6页

WiViHAR: A Deep Learning-Based Human Activity Recognition Method Using WiFi and Vision Multimodal Fusion WiViHAR：一种基于WiFi和视觉多模态融合的深度学习人类活动识别方法

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-15 DOI: 10.1109/THMS.2026.3675889

Xinyu Ma;Yankan Yang;Kun Bian

{"title":"WiViHAR: A Deep Learning-Based Human Activity Recognition Method Using WiFi and Vision Multimodal Fusion","authors":"Xinyu Ma;Yankan Yang;Kun Bian","doi":"10.1109/THMS.2026.3675889","DOIUrl":"https://doi.org/10.1109/THMS.2026.3675889","url":null,"abstract":"Vision-based human activity recognition (HAR) techniques have garnered significant attention and extensive research, with successful applications in many scenarios. However, their recognition accuracy deteriorates significantly under conditions, such as lighting changes and object occlusion. Considering that WiFi-based HAR techniques are unaffected by lighting conditions, we propose WiViHAR, a multimodal HAR method by fusing WiFi and vision information. Specifically, this method first utilizes atrous spatial pyramid pooling (ASPP) module and convolutional block attention module to design a dedicated deep learning network for processing WiFi channel state information. Concurrently, frame images are extracted and resized from vision, and the ASPP is extended to 3-D structure to design a dedicated deep learning network for processing the vision information. Finally, we concatenate the outputs of the two networks and apply the random forest decision fusion method to leverage the advantages of both WiFi and vision, enhancing the environmental adaptability of the method. Extensive experiments conducted in real-world environments demonstrate that the proposed method significantly outperforms single-modal WiFi or vision-based HAR methods, achieving an accuracy of over 98.57% even under lighting changes or occlusions. This highlights the robustness of the proposed method, offering a novel approach for HAR fields.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"582-591"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504709","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

Development and Modeling of a Soft Array Actuator for Elderly Assistive Robotic Exoskeleton 老年辅助机器人外骨骼软阵列驱动器的研制与建模

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-04-01 DOI: 10.1109/THMS.2026.3675670

Yinan Jin;Yixiao Zheng;Junhao Lin;Zetong Li;Shibo Cai;Guanjun Bao;Prashant Jamwal;Shahid Hussain

{"title":"Development and Modeling of a Soft Array Actuator for Elderly Assistive Robotic Exoskeleton","authors":"Yinan Jin;Yixiao Zheng;Junhao Lin;Zetong Li;Shibo Cai;Guanjun Bao;Prashant Jamwal;Shahid Hussain","doi":"10.1109/THMS.2026.3675670","DOIUrl":"https://doi.org/10.1109/THMS.2026.3675670","url":null,"abstract":"The global elderly population is increasing rapidly, and more and more countries are stepping into the aging society. Because of deterioration in gait-related functions, such as muscle activity, most elderly people have difficulty walking, which is one of the most basic activities of daily living. A wearable lower limb robot exoskeleton offers a viable solution to this issue. Rigid exoskeletons usually have fewer degrees of freedom and require a quite big power supply for actuation, resulting in difficulties during wearing and motion. Soft exoskeletons could be an alternative choice for elderly assistance, due to their advantages of lighter weight, simpler mechanism, and compliance. Therefore, this research proposed a soft array actuator for a lower limb assistive exoskeleton for elderly people. The fully compliant actuation mechanism was designed using flexible Thermoplastic Polyurethane fabric to power the soft exoskeleton, making it compact, light, and comfortable to wear. The proposed array actuator was modeled on kinematics, contacting force, output torque, and dynamics. Mechanical performance of the compliant actuation mechanism during inflation/deflation at different air pressures and during static force testing has been evaluated. The internal air pressure of the soft array actuator reaches 100 kPa in 0.2 s and fully deflates in 0.48 s. It can generate 53.7–55.7 N to output 8.1–11.2 N·m of torque at the endpoint, which is 13.5% –18.7% of the maximum human hip joint torque during natural walking. The proposed soft actuation mechanism, with good wearability and performance, could be a good fit for a robot exoskeleton that improves natural gait and reduces human metabolic consumption during walking among the elderly. Its lightweight design, good invisibility, and high power-to-weight ratio enable the proposed soft array actuator to provide compliant, continuous, and consistent gait assistance without imposing a psychological burden on the elderly.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"479-487"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506021","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 Noncontact Tactile Stimulation on Motion-Induced Electrodermal Responses and Subjective Motion Sickness 非接触触觉刺激对运动诱发的皮肤电反应和主观晕动病的影响

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-01-14 DOI: 10.1109/THMS.2025.3644434

Elena N. Schneider;Caroline Lehser;Benedikt Buchheit;Mohamad Alayan;Daniel J. Strauss

引用次数: 0

Hands-Free Mobility Control: A Low-Latency Asynchronous MI-BCI System for Real-Time Robotic Navigation With Cognitive-Ergonomic Enhancement 免提移动控制：一种低延迟异步MI-BCI系统，用于实时机器人导航与认知-人体工程学增强

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-02-18 DOI: 10.1109/THMS.2026.3659708

Qing Li;Qi Huang;Wei Jiang;Zexi Song;Xia Wu

{"title":"Hands-Free Mobility Control: A Low-Latency Asynchronous MI-BCI System for Real-Time Robotic Navigation With Cognitive-Ergonomic Enhancement","authors":"Qing Li;Qi Huang;Wei Jiang;Zexi Song;Xia Wu","doi":"10.1109/THMS.2026.3659708","DOIUrl":"https://doi.org/10.1109/THMS.2026.3659708","url":null,"abstract":"Individuals with severe motor impairments face significant challenges operating conventional interfaces due to reliance on physical movement. While brain–computer interfaces (BCIs) offer alternative control pathways, traditional paradigms (SSVEP/P300) suffer from stimulus dependency, high latency, and cognitive fatigue, limiting real-world deployment. This study presents a novel asynchronous motor imagery-BCI system for hands-free robotic platform navigation, integrating cognitive ergonomics principles to enhance operator experience. We developed an intuitive four-command control paradigm using a cascaded classifier architecture, eliminating dependence on external triggers. Key innovations include: 1) sub-100 ms ultralow-latency pipeline via hybrid feature fusion and ensemble learning; 2) stimulus-independent operation leveraging endogenous sensorimotor cortex activation (μ/β-band); and 3) cognitive load-optimized interaction with ROS-based neurofeedback and NASA-TLX-validated ergonomic design. Evaluated on BCI Competition IV 2a dataset (nine subjects) and self-collected high-resolution electroencephalography data (seven subjects), the system achieved 72.15% offline classification accuracy and 95.36% online command execution success rate with 97ms mean computational latency. NASA-TLX evaluation revealed a 32% reduction in cognitive workload compared to synchronous paradigms. This work establishes a framework for cognitively enhanced mobility assistance, advancing practical brain-controlled assistive technologies.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 2","pages":"291-300"},"PeriodicalIF":4.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505244","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

Real-Time Identification of Personality Traits Based on User Navigation Behavior 基于用户导航行为的人格特征实时识别

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-03-03 DOI: 10.1109/THMS.2026.3663415

Caio Felix de Araujo;Plinio Thomaz Aquino Junior

{"title":"Real-Time Identification of Personality Traits Based on User Navigation Behavior","authors":"Caio Felix de Araujo;Plinio Thomaz Aquino Junior","doi":"10.1109/THMS.2026.3663415","DOIUrl":"https://doi.org/10.1109/THMS.2026.3663415","url":null,"abstract":"Understanding human behavior remains a paramount challenge for artificial intelligence in human–machine interaction. This study introduces an integrated approach for developing efficient and noninvasive adaptive systems tailored to digital environments. The method enables real-time inference of user intent by correlating personality traits with navigation patterns, improving processing accuracy, performance, and cost-efficiency. This research bridges the gap between user psychology and system design by incorporating integration variables, such as task completion time and dynamic interface adjustments. The results reveal significant correlations between psychological profiles and navigation behaviors, highlighting personality traits through user actions and decisions. Applications include personalized recommendation systems, online content curation, and adaptive support services. These findings contribute to the development of intelligent systems that address diverse challenges in digital environments, paving the way for adaptive human–machine systems aligned with individual needs and preferences.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 2","pages":"378-389"},"PeriodicalIF":4.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11420830","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148506069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Error-Correction Enabled Contactless Sedentary Behavior Detection via WiFi Sensing 纠错使非接触式久坐行为检测通过WiFi传感

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-01-19 DOI: 10.1109/THMS.2025.3647500

Linqing Gui;Chuanyue Xie;Zhengxin Guo;Biyun Sheng;Fu Xiao

{"title":"Error-Correction Enabled Contactless Sedentary Behavior Detection via WiFi Sensing","authors":"Linqing Gui;Chuanyue Xie;Zhengxin Guo;Biyun Sheng;Fu Xiao","doi":"10.1109/THMS.2025.3647500","DOIUrl":"https://doi.org/10.1109/THMS.2025.3647500","url":null,"abstract":"Sedentary lifestyle has become a major health risk in modern society. Long sitting time can be detected by accurate recognition of sitting and standing (sit-stand) activities. WiFi-based sitting time detection has the remarkable advantage of low cost, noncontact, and privacy-protection. However, accurate recognition of sit-stand activities via WiFi signal is still facing two challenges. The first and also tougher challenge is inevitable mistakes in recognition results of traditional machine learning methods, while the second challenge is the difficulty of accurate activity segmentation before activity recognition. To the best of the authors' knowledge, few work addresses the above challenges, particularly the first challenge. A new contactless sitting time detection system is designed accordingly. The system first accurately segments all activities and removes in-seat activities. Then, the mistakes in sit-stand activity recognition are effectively corrected by a new recognition error correction method. The proposed method first creates and updates a correction benchmark that can satisfy both successive correlation and waveform symmetry between sit-stand activities. The recognition results of traditional machine learning methods are then corrected based on the latest correction benchmark. Extensive experiment results demonstrate that compared to related work, the designed system has much better accuracy on both sit-stand activity recognition and sitting time estimation. The experiment results also demonstrate the robustness of the designed system.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 2","pages":"366-377"},"PeriodicalIF":4.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504872","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

Virtual Reflections on a Dynamic 2-D Eye Model Improve Spatial Reference Identification 动态二维眼模型的虚拟反射改进空间参考识别

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-01-23 DOI: 10.1109/THMS.2026.3651818

Matti Krüger;Yutaka Oshima;Yu Fang

引用次数: 0

Optimizing Sensor and Data Selection on Lower Limbs via Deep Learning for Real-Time Human Activity Recognition 基于深度学习优化下肢传感器和数据选择，用于实时人体活动识别。

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-01-23 DOI: 10.1109/THMS.2026.3651525

Zihang You;Neethan Ratnakumar;Bo Shen;Hao Su;Xianlian Zhou

{"title":"Optimizing Sensor and Data Selection on Lower Limbs via Deep Learning for Real-Time Human Activity Recognition","authors":"Zihang You;Neethan Ratnakumar;Bo Shen;Hao Su;Xianlian Zhou","doi":"10.1109/THMS.2026.3651525","DOIUrl":"10.1109/THMS.2026.3651525","url":null,"abstract":"Real-time human activity recognition (HAR) is crucial for adaptive control in lower limb exoskeletons, yet achieving an optimal balance between accuracy, latency, and sensor complexity remains challenging. This study’s key idea is to systematically evaluate sensor selection and data modalities for real-time HAR using deep neural networks (DNNs) with ultra-short 50 ms sliding windows. Leveraging a dataset from 21 subjects performing six locomotion activities and employing three deep learning models [multilayer perceptron (MLP), LSTM, CNN-LSTM], we assess multiple sensor combinations, including joint angle data, derived angular velocities, and inertial measurements, and quantify their trade-offs across accuracy, latency, and model complexity. Our analysis reveals that bilateral joint angles from hip, knee, and ankle achieve 98.98% accuracy, significantly outperforming unilateral sensor setups. Adding a thigh-mounted inertial measurement unit further elevates accuracy to 99.23%, highlighting the advantages of multimodal sensor fusion. In addition, incorporating derived joint angular velocities enhances accuracy, with up to 15% increase when using single-joint bilateral inverse kinematics data. Even a minimal configuration, such as bilateral hip joints with derived angular velocities, achieves over 94% accuracy, offering practical solutions for low-power wearable systems. These findings establish actionable design principles for HAR-driven control in assistive robotics and mobile health applications.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 2","pages":"321-330"},"PeriodicalIF":4.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148158628","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

Multimode Assist-As-Needed Adaptive Control for Upper Limb Rehabilitation Exoskeleton 上肢康复外骨骼多模式随需辅助自适应控制

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-03-04 DOI: 10.1109/THMS.2026.3664850

Jiazhen Xu;Haoping Wang;Yang Tian;Yangchun Wei

{"title":"Multimode Assist-As-Needed Adaptive Control for Upper Limb Rehabilitation Exoskeleton","authors":"Jiazhen Xu;Haoping Wang;Yang Tian;Yangchun Wei","doi":"10.1109/THMS.2026.3664850","DOIUrl":"https://doi.org/10.1109/THMS.2026.3664850","url":null,"abstract":"Assist-as-needed (AAN) control for upper-limb rehabilitation exoskeletons is crucial for promoting active patient participation and facilitating neuroplasticity after a stroke. However, a significant challenge lies in designing controllers that can both seamlessly switch assistance levels in response to a patient's fluctuating ability and rigorously enforce safety-critical position constraints across different interaction modes. This study proposes a Multi-Mode Assist-as-Needed (MMAAN) control scheme to address these issues. The proposed framework features an outer loop that uses a virtual tunnel and a novel, continuously differentiable Robot-Assisted Level Metric (RALM) to ensure smooth transitions between Human-Dominated, Human-Robot shared, and Robot-Dominated modes. The inner loop implements a Performance-Varying Barrier Lyapunov Function controller, whose constraint boundaries dynamically adapt based on the RALM to guarantee safety and tracking accuracy. Experimental results with human participants demonstrate that the MMAAN controller automatically adjusts assistive force according to the user's performance while Maintaining tracking errors within prescribed boundaries. This approach offers a robust framework for personalized and safe robotic rehabilitation, potentially enhancing clinical outcomes by adapting to the unique needs of each patient.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 2","pages":"425-434"},"PeriodicalIF":4.4,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148505648","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

TechRxiv: Share Your Preprint Research with the World! techxiv：与世界分享你的预印本研究！

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-04-01 Epub Date: 2026-04-07 DOI: 10.1109/THMS.2026.3679072

引用次数: 0