JXJiaqi Xue

Jiaqi Xue

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Jiaqi Xue has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Agile human-robot collaboration through movement anticipation: multi-task sEMG learning for knee tracking in older adults with possible sarcopenia

    by Jiaqi Xue, Ziqi Li, Alex Chit Yuen Cheng, Xiaoting Li, Xiaoyang Zou, Zijia Qu, Clio Yuen Man Cheng, Wenbo Yuan, Vivian Weiqun Lou, Ning Xi, et al.

  • Assessing Lower Limb Movement Performance in Elderly Individuals Using a Nanocomposite E-Textile Sensor

    by Xiaoyang Zou, Xiaoting Li, Jiaqi Xue, Colin Pak Yu Chan, Ziqi Li, Jing Zhang, King Wai Chiu Lai

    The knee joint is one of the most important joints in our lower body, affecting humans’ lower limb activities. For instance, the knee joint can even bear three to four times the human body’s weight when running and climbing. The knee joint is prone to degenerative lesions for older people as they age, which significantly affects their daily lives. Therefore, long-term and real-time assessment of lower-limb motions in older people is crucial for their lower-limb health detection. In this work, we developed wearable knee sensors based on nanocomposite e-textile strain sensors for detecting knee joints’ range of motion (ROM) while older people perform lower-limb activities. A total of ten features were extracted to characterize their STS performance by detecting their knee joint range of motion through normal speed and fast speed sit-to-stand (STS). The elderly subjects were grouped by their age, gender, and body mass index (BMI) to assess the relationship of these three parameters with the extracted features. As a result, the stability, ROM, and gender of elderly subjects while performing fast speed STS had a significant relationship with age and BMI (P<0.05). The result demonstrates the generalizability of e-textile sensors for assessing lower-limb motions, which shows great potential for long-term and real-time detection of lower-limb health in older people.


  • Wrist Motion Classification Using Flexible sEMG Sensors in Different Feature Conditions Based on Machine Learning

    by Jiaqi Xue, Xiaoyang Zou, Ziqi Li, King Wai Chiu Lai

    Electromyography (EMG) is a bioelectrical signal to reflect human intention before actual motion occurs. EMG has been widely used in human-machine interaction such as robot control, rehabilitation and health monitoring. In this work, we have designed an intelligent approach for wrist motion classification based on EMG signals. Since commercial electrodes cannot maintain good contact with skin during deformation, we have utilized a new type of fabricated flexible electrodes. With these electrodes, high-quality signals can be acquired. And the machine learning methods have been utilized to classify the extracted feature sets. Four different feature conditions have been compared. In the condition of six EMG features, we have identified four wrist gestures including wrist flexion, extension, radial deviation, and ulnar deviation with the best accuracy of 92.26%.

  • Open Access

    Continuous Lower Limb Multi‐Intent Prediction for Electromyography‐Driven Intrinsic and Extrinsic Control

    by Jiaqi Xue, King Wai Chiu Lai

    Currently, electromyography (EMG)‐driven lower limb control can be divided into computational intrinsic control and interactive extrinsic control based on the participation of neural information in the controllers. However, the former method lacks detailed measurements of the expected motion, whereas the latter is prone to errors in diverse movement situations. Based on this problem, a multi‐intent prediction scheme is proposed that analyzes both rhythmic locomotion and volitional movement intent for AI‐based intrinsic and extrinsic hybrid control (AIEC). A 1D residual shrinkage convolutional network is designed to extract EMG features. The motion state is continuously predicted with an accuracy of 91.66% and the angle completion is also estimated with of 0.9540 and 0.9456 for left and right knee angles, respectively. Additionally, the comparison test further indicates that the motion state classification is significantly improved in the multitask analysis compared with the single‐task approach. This work demonstrates and verifies a novel method in EMG studies that multi‐intent recognition not only compensates for the lack of information in the analysis of single rhythmic or volitional movement, but also enhances the comprehensive performance and makes AIEC feasible, which optimizes the current EMG‐driven control for ampler intent collection and more practical robotic control.


  • The Force Classification Based on EMG Signals for Intelligent Wearable Systems

    by Jiaqi Xue, Xiaoyang Zou, Colin Pak Yu Chan, King Wai Chiu Lai

    In recent years, the development of flexible and stretchable sensors has shown considerable potential in human information collection for wearable applications. With skin-fitting film electrodes, Electromyography (EMG) signals can be monitored stably and detected for effective control actuation in wearable systems. Traditionally in EMG-based activation, researchers usually focused on the design of EMG features, which is time-costing and difficult to always find the optimal combination. In this work, we have proposed a scheme to use convolutional neural network for complicated EMG feature extraction and accurate force classification. Four force levels were recognized by our model. The experimental result stated that the accuracy in each force level has reached 90.64%, 89.94%, 84.21% and 95.24%, respectively. In addition, the performance of our deep learning model has outperformed the traditional manual-feature-based methods, which utilized mean absolute value (MAV), waveform length (WL) and Willison amplitude (WAMP) for force identification. Actually, this work has verified the excellent effect of intelligent methods in EMG feature learning, and can be further applied in a real-time wearable system to promote its convenience and practicality.


  • High-Fidelity sEMG Signals Recorded by an on-Skin Electrode Based on AgNWs for Hand Gesture Classification Using Machine Learning

    by Xiaoyang Zou, Jiaqi Xue, Xiaoting Li, Colin Pak Yu Chan, Ziqi Li, Pengyu Li, Zhengbao Yang, King Wai Chiu Lai

    The human forearm is one of the most densely distributed parts of the human body, with the most irregular spatial distribution of muscles. A number of specific forearm muscles control hand motions. Acquiring high-fidelity sEMG signals from human forearm muscles is vital for human-machine interface (HMI) applications based on gesture recognition. Currently, the most commonly used commercial electrodes for detecting sEMG or other electrophysiological signals have a rigid nature without stretchability and cannot maintain conformal contact with the human skin during deformation, and the adhesive hydrogel used in them to reduce skin-electrode impedance may shrink and cause skin inflammation after long-term use. Therefore, developing elastic electrodes with stretchability and biocompatibility for sEMG signal recording is essential for developing HMI. Here, we fabricated a nanocomposite hybrid on-skin electrode by infiltrating silver nanowires (AgNWs), a one-dimensional (1D) nano metal material with conductivity, into polydimethylsiloxane (PDMS), a silicone elastomer with a similar Young's modulus to that of the human skin. The AgNW on-skin electrode has a thickness of 300 μm and low sheet resistance of 0.481 ± 0.014 Ω/sq and can withstand the mechanical strain of up to 54% and maintain a sheet resistance lower than 1 Ω/sq after 1000 dynamic strain cycles. The AgNW on-skin electrode can record high signal-to-noise ratio (SNR) sEMG signals from forearm muscles and can reflect various force levels of muscles by sEMG signals. Besides, four typical hand gestures were recognized by the multichannel AgNW on-skin electrodes with a recognition accuracy of 92.3% using machine learning method. The AgNW on-skin electrode proposed in this study has great potential and promise in various HMI applications that employ sEMG signals as control signals.