Peiqi Kang

Peiqi Kang

Auto-generated profile, based on publicly available information

Peiqi Kang

State Key Laboratory of Mechanical System and Vibration, School of Mechanical Engineering, Shanghai Jiao Tong University, Shanghai, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 May 2021 in IEEE Reviews in Biomedical Engineering
Verified
Journal Article
Closed access
SJShuo Jiang
Shuo Jiang
PKPeiqi Kang
Peiqi Kang
XSXinyu Song
Xinyu Song
BLBenny Lo
Benny Lo
PSPeter Shull
Peter Shull
Hands are vital in a wide range of fundamental daily activities, and neurological diseases that impede hand function can significantly affect quality of life. Wearable hand gesture interfaces hold promise to restore and assist hand function and to enhance human-human and human-computer communication. The purpose of this review is to synthesize current novel sensing interfaces and algorithms for hand gesture recognition, and the scope of applications covers rehabilitation, prosthesis control, exoskeletons for augmentation, sign language recognition, human-computer interaction, and user authentication. Results showed that electrical, mechanical, acoustical/vibratory, and optical sensing were the primary input modalities in gesture recognition interfaces. Two categories of algorithms were identified: 1) classification algorithms for predefined, fixed hand poses and 2) regression algorithms for continuous finger and wrist joint angles. Conventional machine learning algorithms, including linear discriminant analysis, support vector machines, random forests, and non-negative matrix factorization, have been widely used for a variety of gesture recognition applications, and deep learning algorithms have more recently been applied to further facilitate the complex relationship between sensor signals and multi-articulated hand postures. Future research should focus on increasing recognition accuracy with larger hand gesture datasets, improving reliability and robustness for daily use outside of the laboratory, and developing softer, less obtrusive interfaces.

21 December 2021 in IEEE Sensors Journal
Verified
Journal Article
Closed access
BFBingfei Fan
Bingfei Fan
QLQingguo Li
Qingguo Li
TTTian Tan
Tian Tan
PKPeiqi Kang
Peiqi Kang
PSPeter Shull
Peter Shull
Accurate joint angle estimation using magneto-inertial measurement units (IMU) is a significant challenge for human movement analysis outside of the lab. Sensor-to-segment misalignment and sensor orientation errors are key factors in joint angle estimation. However, the effects of these factors on 3-D knee joint angle estimation accuracy are not well understood. This paper presents a general model to investigate the effects of sensor-to-segment misalignment and IMU orientation error on 3-D knee joint angle estimation accuracy. An analytical model was built to quantify the effects of sensor-to-segment misalignment and IMU orientation errors for 3-D knee joint angle estimation. Precise outcomes were quantified via simulation analysis and experimental testing in which fourteen healthy subjects performed drop landing and cutting tasks while wearing IMUs and optical motion capture markers for ground truth estimation. Sensor-to-segment misalignment accounted for 52% of the total knee abduction angle error and 40% of the knee internal rotation angle error but did not significantly affect knee flexion angle error. Conversely, IMU orientation error accounted for 55% of the knee flexion angle error but did not significantly affect knee abduction or internal rotation angle errors. These results indicate that sensor-to-segment misalignment significantly affects knee abduction and internal rotation angle estimation while IMU orientation error significantly affects knee flexion angle estimation. This study could serve to inform the development of accurate IMU-based 3-D knee joint angle algorithms for human movement analysis.

27 July 2021 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
PKPeiqi Kang
Peiqi Kang
JLJinxuan Li
Jinxuan Li
BFBingfei Fan
Bingfei Fan
SJShuo Jiang
Shuo Jiang
PSPeter Shull
Peter Shull
Walking, one of the most common daily activities, causes unwanted movement artifacts which can significantly deteriorate hand gesture recognition accuracy. However, traditional hand gesture recognition algorithms are typically developed and validated with wrist-worn devices only during static human poses, neglecting the critical importance of dynamic effects on gesture accuracy. Thus, we developed and validated a signal decomposition approach via empirical mode decomposition to accurately segment target gestures from coupled raw signals during dynamic walking and a transfer learning method based on distribution adaptation to enable gesture recognition through domain transfer between dynamic walking and static standing scenarios. Ten healthy subjects performed seven hand gestures during both walking and standing experiments while wearing an IMU wrist-worn device. Experimental results showed that the signal decomposition approach reduced the gesture detection error by 83.8%, and the transfer learning approach (20% transfer rate) improved hand gesture recognition accuracy by 15.1%. This ground-breaking work demonstrates the feasibility of hand gesture recognition while walking via wrist-worn sensing. These findings serve to inform real-life and ubiquitous adoption of wrist-worn hand gesture recognition for intuitive human-machine interaction in dynamic walking situations.

3 June 2022 in Frontiers in Physiology
Verified
Journal Article
Open access
XSXinyu Song
Xinyu Song
SVShirdi Shankara van de Ven
Shirdi Shankara van de Ven
SCShugeng Chen
Shugeng Chen
PKPeiqi Kang
Peiqi Kang
QGQinghua Gao
Qinghua Gao
PSPeter Shull
Peter Shull
Stroke often leads to hand motor dysfunction, and effective rehabilitation requires keeping patients engaged and motivated. Among the existing automated rehabilitation approaches, data glove-based systems are not easy to wear for patients due to spasticity, and single sensor-based approaches generally provided prohibitively limited information. We thus propose a wearable multimodal serious games approach for hand movement training after stroke. A force myography (FMG), electromyography (EMG), and inertial measurement unit (IMU)-based multi-sensor fusion model was proposed for hand movement classification, which was worn on the user’s affected arm. Two movement recognition-based serious games were developed for hand movement and cognition training. Ten stroke patients with mild to moderate motor impairments (Brunnstrom Stage for Hand II-VI) performed experiments while playing interactive serious games requiring 12 activities-of-daily-living (ADLs) hand movements taken from the Fugl Meyer Assessment. Feasibility was evaluated by movement classification accuracy and qualitative patient questionnaires. The offline classification accuracy using combined FMG-EMG-IMU was 81.0% for the 12 movements, which was significantly higher than any single sensing modality; only EMG, only FMG, and only IMU were 69.6, 63.2, and 47.8%, respectively. Patients reported that they were more enthusiastic about hand movement training while playing the serious games as compared to conventional methods and strongly agreed that they subjectively felt that the proposed training could be beneficial for improving upper limb motor function. These results showed that multimodal-sensor fusion improved hand gesture classification accuracy for stroke patients and demonstrated the potential of this proposed approach to be used as upper limb movement training after stroke.

26 July 2022 in IEEE Journal of Biomedical and Health Informatics
Verified
Journal Article
Closed access
HWHong Wang
Hong Wang
PKPeiqi Kang
Peiqi Kang
QGQinghua Gao
Qinghua Gao
SJShuo Jiang
Shuo Jiang
PSPeter Shull
Peter Shull
Wrist-based hand gesture recognition has the potential to unlock naturalistic human-computer interaction for a vast array of virtual and augmented reality applications. Photoplethysmography (PPG), force myography (FMG), and accelerometry (ACC) have generally been proposed as isolated single sensing modalities for gesture recognition, but any of these alone is inherently limited in the amount of biological information it can collect during finger and hand movements. We thus propose a novel, wrist-based, PPG-FMG-ACC combined sensing approach based on a multi-head attention mechanism fusion convolutional neural network (CNN-AF) for gesture recognition. Nine subjects performed twelve hand gestures involving various wrist and finger postures. Experimental results showed that multi-modal fusion improved classification performance significantly ( $p$ $< $ 0.01) compared to any single sensing modality, and the F1-score of the combined PPG-FMG-ACC approach was 40.1% higher than PPG alone, 27.4% higher than ACC alone, and 11.9% higher than FMG alone. To the best of our knowledge, this paper is the first to combine wrist-based PPG, FMG, and ACC signals for hand gesture recognition. These results could serve to inform wrist-based gesture recognition design (e.g., via a smartwatch) and thus expand the capabilities of intuitive and ubiquitous human-machine interaction.

26 December 2022 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
PKPeiqi Kang
Peiqi Kang
JLJinxuan Li
Jinxuan Li
SJShuo Jiang
Shuo Jiang
PSPeter Shull
Peter Shull
Multi-modal sensor fusion can improve the performance of human-machine interfaces (HMI). However, increased sensing modalities and sensor count often causes excess redundancies, and when applying deep learning approaches, the recognition system can become overly complex and difficult for humans to understand. In this paper, we propose an explainable artificial intelligence (XAI) approach to reduce redundancies in inertial measurement units (IMU) and electromyography (EMG) multi-modal systems and optimize sensor disposition in prosthetic hand control. Four attribution algorithms and four quantitative evaluation algorithms were used on an open-source dataset of seventeen hand gestures from sixty healthy subjects and eleven amputees to explore the working mechanism behind the multi-modal system. Using an XAI approach, we reduced the total number of required sensors by 40% while maintaining the same level of accuracy. These results could enable optimized HMI system design with reduced sensor costs and manufacturing costs. The proposed approach lays the foundation for improving HMI systems by reducing complexity and revealing explainable information that is typically hidden within deep neural networks, thereby facilitating patients in the daily use of prosthetic hands and helping improve their quality of life.