IEEE Transactions on Human-Machine Systems最新文献_第3页

Exploring Factors Influencing Human-Autonomy Teams in Automated Driving System Operations 探索自动驾驶系统运行中影响人类自主团队的因素

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-06-25 DOI: 10.1109/THMS.2026.3702567

Camila Correa-Jullian;Marilia Ramos;Ali Mosleh;Jiaqi Ma

{"title":"Exploring Factors Influencing Human-Autonomy Teams in Automated Driving System Operations","authors":"Camila Correa-Jullian;Marilia Ramos;Ali Mosleh;Jiaqi Ma","doi":"10.1109/THMS.2026.3702567","DOIUrl":"https://doi.org/10.1109/THMS.2026.3702567","url":null,"abstract":"Advancing our understanding of human users’ and autonomous systems’ interaction dynamics is critical for the safe operation of complex sociotechnical systems. Defining, modeling, and assessing operational risks arising from human-autonomy interactions are key to evaluating their overall safety. Human-autonomy teams (HATs) emerge as a fundamental concept toward safer designing and evaluating teamwork-related failures and their effect on system-level safety, aiming to evolve from isolated safety analyses toward a holistic perspective of human and machine agents. The adoption of automated driving systems will have a major impact on the transportation environment, where humans will continue to participate as drivers, remote operators, or fellow road users. This article draws from human reliability analysis as well as the cognitive model information, decision, and action in crew context to explore contributing factors shaping tasks and errors across different HATs in automated driving contexts. The impact of organization, agent, scenario, team and other relevant contributing factors on the joint performance of on-board drivers and conditionally automated vehicles are discussed. A candidate selection of factors are proposed to construct a causal HAT model seeking to characterize elements at both design and operation-time performance and for future experimental validation.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"868-876"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694996","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

Evaluating the Performance of Deep-Learning Models in Whole-Body Dynamic 3-D Posture Prediction During Load-Reaching Activities 评估深度学习模型在负荷活动中全身动态三维姿势预测中的性能

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-06-12 DOI: 10.1109/THMS.2026.3697329

Seyede Niloofar Hosseini;Ali Mojibi;Mahdi Mohseni;Navid Arjmand;Alireza Taheri

{"title":"Evaluating the Performance of Deep-Learning Models in Whole-Body Dynamic 3-D Posture Prediction During Load-Reaching Activities","authors":"Seyede Niloofar Hosseini;Ali Mojibi;Mahdi Mohseni;Navid Arjmand;Alireza Taheri","doi":"10.1109/THMS.2026.3697329","DOIUrl":"https://doi.org/10.1109/THMS.2026.3697329","url":null,"abstract":"This article aimed to explore the application of deep neural networks for whole-body human posture prediction during dynamic load-reaching activities. Two time-series models were trained using bidirectional long short-term memory (BLSTM) and transformer architectures. The dataset consisted of three-dimensional (3-D) full-body plug-in gait dynamic coordinates from 20 normal-weight healthy male individuals each performing 204 load-reaching tasks from different load positions while adapting various lifting and handling techniques. The model inputs consisted of the 3-D position of the hand-load position, lifting (stoop, full-squat and semi-squat) and handling (one- and two-handed) techniques, body weight and height, and the 3-D coordinate data of the body posture from the first 25% of the task duration. These inputs were used by the models to predict body coordinates during the remaining 75% of the task period. Moreover, a novel method was proposed to improve the accuracy of the previous and present posture prediction networks by enforcing constant body segment lengths through the optimization of a new cost function. The results indicated that the new cost function decreased the prediction error of the models by approximately 8% and 21% for the arm and leg models, respectively. We indicated that utilizing the transformer architecture, with a root mean square error of 41.4 mm, exhibited approximately 58% more accurate long-term performance than the BLSTM-based model. This article merits the use of neural networks that capture time series dependencies in 3-D motion frames, providing a unique approach for understanding and predicting motion dynamics during manual material handling activities.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"774-783"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694838","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

Efficient CSI-Based Indoor Human Activity Recognition System Optimized for Edge Devices 针对边缘设备优化的高效基于csi的室内人体活动识别系统

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-03-29 DOI: 10.1109/THMS.2026.3693906

Youqin Lin;Shaoxiong Cai;Shumin Yang;Jincheng Xu;Shaojian Zhang;Qingming Wu;Donghai Guo;Zhong Chen;Yuhan Su;Tingzhu Wu

{"title":"Efficient CSI-Based Indoor Human Activity Recognition System Optimized for Edge Devices","authors":"Youqin Lin;Shaoxiong Cai;Shumin Yang;Jincheng Xu;Shaojian Zhang;Qingming Wu;Donghai Guo;Zhong Chen;Yuhan Su;Tingzhu Wu","doi":"10.1109/THMS.2026.3693906","DOIUrl":"https://doi.org/10.1109/THMS.2026.3693906","url":null,"abstract":"Indoor sensing technologies are gaining increasing attention in the development of smart environments. Wi-Fi-based human activity recognition, which exploits channel state information (CSI), enables accurate detection of human movements by analyzing signal fluctuations caused by activity, even in complex indoor settings. This passive, device-free approach leverages the ubiquity of Wi-Fi signals, eliminating the need for wearable devices and improving user convenience. However, current Wi-Fi-based sensing systems face several limitations, including suboptimal real-time performance, inefficient resource utilization, and the absence of dedicated hardware platforms. To address these challenges, this article presents a wireless sensing device based on printed circuit board technology, integrated with a CSI-driven system for recognizing indoor human behavior. Experimental results across diverse scenarios demonstrate high recognition accuracy, underscoring the proposed system's potential to improve the efficiency and practicality of wireless sensing technologies in smart environments.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"897-906"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694843","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

Finite-Time Adaptive Robust Disturbance Observer and Filter-Based Controller for Human–Robot Interaction in Rehabilitation Robots 康复机器人人机交互的有限时间自适应鲁棒干扰观测器和基于滤波器的控制器

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-06-25 DOI: 10.1109/THMS.2026.3701810

Babak Sarani;Rahman Ardakanian;Ghazaleh Dorri;Iman Kardan;A. Akbarzadeh;Aliakbar Akbari

{"title":"Finite-Time Adaptive Robust Disturbance Observer and Filter-Based Controller for Human–Robot Interaction in Rehabilitation Robots","authors":"Babak Sarani;Rahman Ardakanian;Ghazaleh Dorri;Iman Kardan;A. Akbarzadeh;Aliakbar Akbari","doi":"10.1109/THMS.2026.3701810","DOIUrl":"https://doi.org/10.1109/THMS.2026.3701810","url":null,"abstract":"Rehabilitation robots operate under continuous physical human–robot interaction (pHRI). However, many rehabilitation robots lack sensors for directly measuring interaction forces. Therefore, their control strategies must account for interaction dynamics, especially when such forces are unknown or cannot be measured directly. To address this limitation, this article proposes a finite-time adaptive robust disturbance observer integrated with an adaptive finite-time filter-based control strategy for the real-time control of sensorless rehabilitation robots during pHRI. The observer estimates pHRI online using the concept of generalized momentum, while the filter-based controller avoids computationally demanding inertia-matrix inversion and eliminates the need for joint acceleration measurements, thereby reducing sensitivity to noisy signals. Lyapunov-based analysis is used to establish the stability of the integrated observer–controller closed-loop system and to guarantee bounded finite-time convergence of the tracking, parameter-estimation, and observer errors. Numerical simulations in MATLAB/Simulink on a 2-DOF lower-limb exoskeleton model validate the proposed strategy and demonstrate improved trajectory tracking and pHRI estimation compared with competing controllers. Experimental validation is then conducted on a custom-made seated lower-limb rehabilitation robot with ten subjects. The results confirm improved tracking performance and reliable pHRI estimation, highlighting the observer's role in enabling sensorless pHRI-aware control and its potential to improve rehabilitation outcomes.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"917-926"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694990","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

Augmenting Human Hazard Situational Awareness With Haptic Interface for Heterogeneous Autonomous Vehicles 基于触觉界面增强异构自动驾驶车辆的人类危险情境感知

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-03-21 DOI: 10.1109/THMS.2026.3688755

Yang Xing;Ziyue Wang;Xiangqi Kong;Weisi Guo;Antonios Tsourdos

{"title":"Augmenting Human Hazard Situational Awareness With Haptic Interface for Heterogeneous Autonomous Vehicles","authors":"Yang Xing;Ziyue Wang;Xiangqi Kong;Weisi Guo;Antonios Tsourdos","doi":"10.1109/THMS.2026.3688755","DOIUrl":"https://doi.org/10.1109/THMS.2026.3688755","url":null,"abstract":"As vehicle autonomy increases, human operators become more susceptible to distractions and a loss of situational awareness (SA) due to cognitive limitations. Rapidly enhancing human SA in hazardous situations is, therefore, critical for timely hazard perception and collision avoidance, particularly in human-vehicle teaming contexts that demand fast, accurate hazard reasoning. This study evaluates the efficiency of a low-cost vibrotactile interface for enhancing hazard SA of human operators when teaming with heterogeneous autonomous vehicles, including both ground and aerial autonomous vehicles. To do so, we evaluate the effectiveness of a vibrotactile interface in challenging time-critical scenarios considering adversarial attacks to better understand the cognitive constraints faced by human operators. Our quantitative analysis, based on the data collected from 39 participants, demonstrates that: first, haptic cues can significantly enhance human hazard SA across various metrics for the ground and aerial scenarios; second, perception of aerial attacks in a 3-D environment is more challenging than ground risk perception.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"815-825"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694929","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

Deep Learning-Driven Decision Fusion: Spatio-Spectrogram Features for Inner Speech Recognition From Electroencephalogram Signals 深度学习驱动的决策融合：基于脑电图信号的内部语音识别的空间频谱特征

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-06-02 DOI: 10.1109/THMS.2026.3690175

Hussna E. M. Abdalla;Hamidon Basri;Ishak Aris;Abdul Hanif Yusof;Muhammad S. Adha;Hisham Neyaz;Amna Saga;Sadiq H. Abdulhussain;Basheera M. Mahmmod;Nurbek Saparkhojayev;Syed Abdul Rahman Al-Haddad

{"title":"Deep Learning-Driven Decision Fusion: Spatio-Spectrogram Features for Inner Speech Recognition From Electroencephalogram Signals","authors":"Hussna E. M. Abdalla;Hamidon Basri;Ishak Aris;Abdul Hanif Yusof;Muhammad S. Adha;Hisham Neyaz;Amna Saga;Sadiq H. Abdulhussain;Basheera M. Mahmmod;Nurbek Saparkhojayev;Syed Abdul Rahman Al-Haddad","doi":"10.1109/THMS.2026.3690175","DOIUrl":"https://doi.org/10.1109/THMS.2026.3690175","url":null,"abstract":"Inner speech recognition using electroencephalogram (EEG) signals shows strong potential for developing assistive communication technologies. Existing methods often process spatial and temporal features separately, lack interpretability, and are usually tested on a single dataset, limiting their generalization. This study proposes a dual-branch deep learning framework that combines spatial features extracted through common spatial patterns (CSPs) with spectral-temporal features derived from multitaper spectrograms, using convolutional and long short-term memory networks. The model was evaluated on two public datasets, achieving classification accuracies of 89.99% and 92.47% in subject-dependent experiments. Subject-independent evaluation using leave-one-subject-out cross-validation yielded reduced accuracies of 26.20% and 20.47%, reflecting intersubject variability. Interpretability analyses using saliency maps, gradient-weighted class activation mapping, and feature contribution ratios highlighted physiologically meaningful patterns related to model decisions. The proposed method demonstrates strong performance and interpretability for subject-dependent inner speech recognition; while future work will focus on increasing data diversity and improving subject-independent generalization. This study contributes to the development of reliable and explainable EEG-based inner speech decoding for communication applications.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"877-886"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11543475","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694844","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

Embodied Intelligence Robots: Flexible Task Planning Framework and Multimodal Fusion Perception 具身智能机器人：灵活任务规划框架和多模态融合感知

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-08-01 Epub Date: 2026-06-30 DOI: 10.1109/THMS.2026.3703414

Zijian Zhu;Zequn Zhang;Dunbing Tang;Yuchen Ji

{"title":"Embodied Intelligence Robots: Flexible Task Planning Framework and Multimodal Fusion Perception","authors":"Zijian Zhu;Zequn Zhang;Dunbing Tang;Yuchen Ji","doi":"10.1109/THMS.2026.3703414","DOIUrl":"https://doi.org/10.1109/THMS.2026.3703414","url":null,"abstract":"Rapid manufacturing evolution accelerates product iteration, requiring collaborative robots to rapidly adapt and deploy new action programs. Although large language models (LLMs) can generate logically consistent instructions, they lack contextual understanding of human–robot collaborative environments. We propose an understanding and perceiving the environment with requests model that fuses multimodal information to enable embodied robots to interpret user intent within environmental context. In addition, a flexible task planning framework for multiagent systems is introduced, allowing agents to form flexible teams according to task requirements. This framework grants agents reflective capabilities, enabling them to analyze failures and replan accordingly, thus enhancing task planning flexibility. Appropriately designed prompts for embodied intelligence robots are used to mitigate the hallucination effect of LLMs, further improving the accuracy of task planning when using LLMs. In collaborative aerospace component assembly experiments, the proposed system significantly improved natural-language-driven task execution, achieving a 10.80% improvement in final success rate.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 4","pages":"743-752"},"PeriodicalIF":4.4,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148694877","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

IEEE Systems, Man, and Cybernetics Society Information IEEE系统、人与控制论学会信息

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-28 DOI: 10.1109/THMS.2026.3695722

引用次数: 0

APCA-Net: Adaptive Patch-Correlation Attention Network for Vision-Based Human Hand Acupoint Detection in Acupuncture APCA-Net：基于视觉的手部穴位检测的自适应斑块相关注意网络

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-19 DOI: 10.1109/THMS.2026.3670428

Xu Wang;Zhaoshui He;Hao Liang;Jing Guo;Zhijie Lin;Liqiang Zhang;Xingfang Pan

引用次数: 0

Three-Level Pressure-Based Authentication on Touch Screens 基于触摸屏的三级压力认证

IF 4.4 3区计算机科学

IEEE Transactions on Human-Machine Systems Pub Date : 2026-06-01 Epub Date: 2026-03-04 DOI: 10.1109/THMS.2026.3663983

Zhenhua Yang;Tianyi Liang;Jun Kong;Juan Li;Tongxin Shi

{"title":"Three-Level Pressure-Based Authentication on Touch Screens","authors":"Zhenhua Yang;Tianyi Liang;Jun Kong;Juan Li;Tongxin Shi","doi":"10.1109/THMS.2026.3663983","DOIUrl":"https://doi.org/10.1109/THMS.2026.3663983","url":null,"abstract":"Since pressure is invisible in nature, it has been applied to enhance the authentication security. However, previous work focused on only two-level pressure detection, which makes it feasible for an attacker to guess a pressure level from a user's pressing behavior in the shoulder surfing attack. To mitigate the above risk, this article extends pressure-based authentication from two levels to three levels. It systematically evaluates its usability and security with 98 young adults in a mid-west university in two user studies. The first study with 67 participants showed that a three-level pressure-based password did not increase the difficulty of memorization, and it was more resistant to the shoulder surfing attack than a two-level pressure-based password (two-level = 79.39% successful attacks versus three-level = 44.71% successful attacks). However, three-level passwords have a higher false negative rate than two-level passwords, which implies that users lack a consistent pressing pattern on the medium level. To address the above issue, we designed an adaptive training process that assists users in forming a consistent pressing pattern. The training process features an automatic detection of consistent pressing patterns, which potentially reduces the training length. The second user study, with 31 participants, indicated that the false negative rate in three-level passwords is decreased significantly after the training from 59.90% to 2.15%, while maintaining a reasonable false acceptance rate of 20%.","PeriodicalId":48916,"journal":{"name":"IEEE Transactions on Human-Machine Systems","volume":"56 3","pages":"458-468"},"PeriodicalIF":4.4,"publicationDate":"2026-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148504345","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