Wen Jung Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Wen Jung Li has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Ning Xi
The University of Hong Kong
2 shared publications - Yuzhao Zhang
Shanghai University
2 shared publications - Aleksandra Vuckovic
James Watt School of Engineering, University of Glasgow, Scotland, UK, G12 8QE5
1 shared publication Arul Lenus Roy Vellaisamy
Hong Kong Metropolitan University, Hong Kong, China
1 shared publication- Calvin Kalun Or
Department of Data and Systems Engineering, The University of Hong Kong, Hong Kong, China
1 shared publication - Chao Wang
Shanghai University, Shanghai, China
1 shared publication
Latest Publications
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
Graph Rotation Network: Equivariant Graph Neural Network for Efficient Inverse Design in 4-D Printing
Four-dimensional printed structures transform shape under external stimuli, and designing these structures to achieve desired deformation outcomes is crucial for 4-D printing technology. Current machine-learning (ML)-assisted methods can design 4-D-printed structures rapidly and accurately, but often overlook the E(3) equivariance required for the model, leading to inconsistent prediction structure between different coordinate representations of the same structure. Consequently, many ML-assisted design approaches rely on data augmentation techniques such as rotation to improve the model’s generalization across different coordinate representations, but the method through data augmentation is inefficient. We observe that equivariant graph neural networks (GNNs), due to their equivariant properties, can address the inefficiencies associated with the aforementioned training augmentation. Therefore, we propose utilizing an equivariant GNN to improve these efficiencies. Nonetheless, existing equivariant GNNs struggle to balance computational efficiency with expressive power, which will impact their effectiveness in 4-D printing structure design. In response, we introduce a novel equivariant GNN, the graph rotation network (GRN), which approximates arbitrary E(3) equivariant functions by constructing a 3-D equivariant basis through rotations. This approach enhances the model’s performance with trainable rotational angles. We theoretically analyze the E(3) equivariance of our model as well as its computational complexity and empirically demonstrate the improved training efficiency introduced by equivariance. Finally, we apply GRN to both forward prediction and inverse design of 4-D-printed meshes. Our equivariant GNN significantly outperforms nonequivariant GNNs and other equivariant GNNs in forward prediction tasks. For inverse design, our method achieves an accuracy of 98.8% (relative to the mesh size), providing an effective tool for the design of 4-D-printed structures.
- 8 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. PP (2162237X) , 1-15
Graph Rotation Network: Equivariant Graph Neural Network for Efficient Inverse Design in 4-D Printing
Four-dimensional printed structures transform shape under external stimuli, and designing these structures to achieve desired deformation outcomes is crucial for 4-D printing technology. Current machine-learning (ML)-assisted methods can design 4-D-printed structures rapidly and accurately, but often overlook the E(3) equivariance required for the model, leading to inconsistent prediction structure between different coordinate representations of the same structure. Consequently, many ML-assisted design approaches rely on data augmentation techniques such as rotation to improve the model’s generalization across different coordinate representations, but the method through data augmentation is inefficient. We observe that equivariant graph neural networks (GNNs), due to their equivariant properties, can address the inefficiencies associated with the aforementioned training augmentation. Therefore, we propose utilizing an equivariant GNN to improve these efficiencies. Nonetheless, existing equivariant GNNs struggle to balance computational efficiency with expressive power, which will impact their effectiveness in 4-D printing structure design. In response, we introduce a novel equivariant GNN, the graph rotation network (GRN), which approximates arbitrary E(3) equivariant functions by constructing a 3-D equivariant basis through rotations. This approach enhances the model’s performance with trainable rotational angles. We theoretically analyze the E(3) equivariance of our model as well as its computational complexity and empirically demonstrate the improved training efficiency introduced by equivariance. Finally, we apply GRN to both forward prediction and inverse design of 4-D-printed meshes. Our equivariant GNN significantly outperforms nonequivariant GNNs and other equivariant GNNs in forward prediction tasks. For inverse design, our method achieves an accuracy of 98.8% (relative to the mesh size), providing an effective tool for the design of 4-D-printed structures.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 4375-4387
Feature-Aligned Cell Detection for Heterogeneous Microscopic Images With Focal Attenuated Distance Transform
Accurate and robust cell detection in microscopic images is a fundamental yet challenging task due to diverse imaging conditions, dense cell distributions, and morphological variability. In this study, we propose FACellDet, a novel dual-branch hierarchical encoder-decoder framework that integrates adaptive feature alignment and a new supervisory signal to enhance cell detection. Specifically, a Coordinate-Attention-based Feature Alignment (CAFA) module is introduced to address spatial misalignment during multi-scale feature fusion, substantially improving cell detection precision. Furthermore, we design a Focal Attenuated Distance (FAD) map as an intermediate representation, providing highly discriminative and spatially informative cues, particularly in crowded regions. FACellDet features a dual-branch architecture, with the main branch predicting FAD maps for cell detection, while the auxiliary branch generates density maps to estimate cell counts for suppressing false detections. Extensive experiments on diverse cell types and imaging modalities from multiple public and in-house datasets demonstrate that our approach outperforms state-of-the-art methods in detection accuracy, while maintaining strong adaptability and robustness across challenging biomedical imaging scenarios. These results underscore the potential of FACellDet as an accurate and generalizable solution for automated cell detection in heterogeneous microscopic cell images, thereby facilitating reliable cell analysis to accelerate biomedical research and clinical workflows. Note to Practitioners—This work addresses the need for accurate and efficient cell detection and counting in biomedical images, where manual methods are time-consuming and error-prone, and existing automated approaches often struggle with dense or diverse cells. FACellDet offers a practical deep learning solution adaptable to various cell types and imaging conditions, improving both detection accuracy and robustness through innovative feature alignment and enhanced supervisory signals. This system can streamline laboratory workflows and support high-throughput research and clinical diagnostics. While FACellDet demonstrates strong performance across challenging datasets, its current deployment requires adequate computational resources. Future development could focus on creating lightweight versions and integrating the framework with automated imaging systems, further broadening its accessibility and impact in routine biomedical practice.
- 6 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23 (15455955) , 4375-4387
Feature-Aligned Cell Detection for Heterogeneous Microscopic Images With Focal Attenuated Distance Transform
Accurate and robust cell detection in microscopic images is a fundamental yet challenging task due to diverse imaging conditions, dense cell distributions, and morphological variability. In this study, we propose FACellDet, a novel dual-branch hierarchical encoder-decoder framework that integrates adaptive feature alignment and a new supervisory signal to enhance cell detection. Specifically, a Coordinate-Attention-based Feature Alignment (CAFA) module is introduced to address spatial misalignment during multi-scale feature fusion, substantially improving cell detection precision. Furthermore, we design a Focal Attenuated Distance (FAD) map as an intermediate representation, providing highly discriminative and spatially informative cues, particularly in crowded regions. FACellDet features a dual-branch architecture, with the main branch predicting FAD maps for cell detection, while the auxiliary branch generates density maps to estimate cell counts for suppressing false detections. Extensive experiments on diverse cell types and imaging modalities from multiple public and in-house datasets demonstrate that our approach outperforms state-of-the-art methods in detection accuracy, while maintaining strong adaptability and robustness across challenging biomedical imaging scenarios. These results underscore the potential of FACellDet as an accurate and generalizable solution for automated cell detection in heterogeneous microscopic cell images, thereby facilitating reliable cell analysis to accelerate biomedical research and clinical workflows. Note to Practitioners—This work addresses the need for accurate and efficient cell detection and counting in biomedical images, where manual methods are time-consuming and error-prone, and existing automated approaches often struggle with dense or diverse cells. FACellDet offers a practical deep learning solution adaptable to various cell types and imaging conditions, improving both detection accuracy and robustness through innovative feature alignment and enhanced supervisory signals. This system can streamline laboratory workflows and support high-throughput research and clinical diagnostics. While FACellDet demonstrates strong performance across challenging datasets, its current deployment requires adequate computational resources. Future development could focus on creating lightweight versions and integrating the framework with automated imaging systems, further broadening its accessibility and impact in routine biomedical practice.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (5) , 8370-8384
Machine Learning-Based Early Detection of Sarcopenia-Prone Risk Using Five-Time Sit-to-Stand Test Analysis
Sarcopenia, characterized by progressive loss of muscle mass and function, significantly impacts the quality of life in aging populations. Early detection and personalized intervention are crucial yet challenging due to the limited accessibility and scalability of traditional diagnostic methods. Building upon our previous work on gait-based assessment, this study presents a novel framework for early sarcopenia-prone risk detection using the five-time sit-to-stand (5TSTS) test, embodying Healthcare Industry 5.0’s vision of mass personalization with human-centered technology. Utilizing the Internet of Things (IoT)-enabled wearable inertial measurement units (IMUs) and advanced analytics, our system segments 5TSTS into four biomechanically significant submotions [standing up (StU), standing transition (StT), sitting down (SiD), and sitting transition (SiT)]. This granular segmentation allows mass personalization in diagnostic evaluations by capturing individual-specific biomechanical profiles via wavelet-based feature extraction and machine learning (ML) techniques. Our framework employs big data analytics tools, including the extreme gradient boosting (XGBoost)-based feature selection and support vector machine synthetic minority oversampling technique (SVMSMOTE), to handle class imbalance and optimize individualized predictive accuracy. Tested on data from 52 elderly participants (aged 65–84 years), the system achieves outstanding personalized classification accuracy—up to 97.97% for multiclass risk stratification and 99.28% for binary (healthy versus sarcopenia-prone) classification—highlighting its potential for precise, patient-specific clinical decision-making. Furthermore, the wireless capability of our IoT-enabled wearable IMUs, coupled with minimal setup requirements, facilitates seamless data integration into cloud-based healthcare systems. This integration supports real-time remote monitoring and personalized health management. By leveraging advanced sensing, analytics, and connectivity technologies, our approach significantly advances personalized, accessible, and scalable sarcopenia-prone risk assessment, thereby contributing directly to the vision of Healthcare Industry 5.0.
- 5 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (5) , 8370-8384
Machine Learning-Based Early Detection of Sarcopenia-Prone Risk Using Five-Time Sit-to-Stand Test Analysis
Sarcopenia, characterized by progressive loss of muscle mass and function, significantly impacts the quality of life in aging populations. Early detection and personalized intervention are crucial yet challenging due to the limited accessibility and scalability of traditional diagnostic methods. Building upon our previous work on gait-based assessment, this study presents a novel framework for early sarcopenia-prone risk detection using the five-time sit-to-stand (5TSTS) test, embodying Healthcare Industry 5.0’s vision of mass personalization with human-centered technology. Utilizing the Internet of Things (IoT)-enabled wearable inertial measurement units (IMUs) and advanced analytics, our system segments 5TSTS into four biomechanically significant submotions [standing up (StU), standing transition (StT), sitting down (SiD), and sitting transition (SiT)]. This granular segmentation allows mass personalization in diagnostic evaluations by capturing individual-specific biomechanical profiles via wavelet-based feature extraction and machine learning (ML) techniques. Our framework employs big data analytics tools, including the extreme gradient boosting (XGBoost)-based feature selection and support vector machine synthetic minority oversampling technique (SVMSMOTE), to handle class imbalance and optimize individualized predictive accuracy. Tested on data from 52 elderly participants (aged 65–84 years), the system achieves outstanding personalized classification accuracy—up to 97.97% for multiclass risk stratification and 99.28% for binary (healthy versus sarcopenia-prone) classification—highlighting its potential for precise, patient-specific clinical decision-making. Furthermore, the wireless capability of our IoT-enabled wearable IMUs, coupled with minimal setup requirements, facilitates seamless data integration into cloud-based healthcare systems. This integration supports real-time remote monitoring and personalized health management. By leveraging advanced sensing, analytics, and connectivity technologies, our approach significantly advances personalized, accessible, and scalable sarcopenia-prone risk assessment, thereby contributing directly to the vision of Healthcare Industry 5.0.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (5) , 4409-4422
A Novel Framework of Hierarchical EMG-FMG Fusion to Enhance Long-Term and Multi-Position Robustness for Real-Time Motion Intent Recognition
Prosthetics, exoskeletons, and rehabilitation devices that seamlessly respond to the user's motion intent are essential for improving the quality of life for individuals with physical disabilities. However, existing motion intent recognition systems based on Electromyography (EMG) often experience significant performance degradation over time and limb positions. To address this, this paper proposed a Hierarchical EMG-FMG Fusion (HEFF) framework that incorporates Force Myography (FMG) as a complementary modality to enhance robustness in long-term and multi-position motion intent recognition. The HEFF framework introduced three new strategies: (1) Complementary Pyramid Fusion, a neural network architecture that effectively integrates the complementary characteristics of EMG and FMG; (2) Position Compensation and Pairing, to increase the generalizability of the model by producing augmented training data mimicking the temporal and positional variability; and (3) Feedback-based Baseline Correction, to dynamically counteract FMG baseline drift. The robustness of the system was evaluated through 10 distinct motions performed in 3 different limb positions, retested after an interval of approximately 7 days. Notably, the training data were only collected in a single limb position on the first day. The real-time experiments with 15 subjects showed that the HEFF framework maintained 91.89% classification accuracy in the primary limb position and 85.39% across multiple unseen positions. According to offline analysis, HEFF improved classification accuracy by up to 34.99% across various limb positions compared to the conventional fusion method. These results highlight HEFF's robustness across various conditions, being well-suited for assistive technology applications.
- 20 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (5) , 4409-4422
A Novel Framework of Hierarchical EMG-FMG Fusion to Enhance Long-Term and Multi-Position Robustness for Real-Time Motion Intent Recognition
Prosthetics, exoskeletons, and rehabilitation devices that seamlessly respond to the user's motion intent are essential for improving the quality of life for individuals with physical disabilities. However, existing motion intent recognition systems based on Electromyography (EMG) often experience significant performance degradation over time and limb positions. To address this, this paper proposed a Hierarchical EMG-FMG Fusion (HEFF) framework that incorporates Force Myography (FMG) as a complementary modality to enhance robustness in long-term and multi-position motion intent recognition. The HEFF framework introduced three new strategies: (1) Complementary Pyramid Fusion, a neural network architecture that effectively integrates the complementary characteristics of EMG and FMG; (2) Position Compensation and Pairing, to increase the generalizability of the model by producing augmented training data mimicking the temporal and positional variability; and (3) Feedback-based Baseline Correction, to dynamically counteract FMG baseline drift. The robustness of the system was evaluated through 10 distinct motions performed in 3 different limb positions, retested after an interval of approximately 7 days. Notably, the training data were only collected in a single limb position on the first day. The real-time experiments with 15 subjects showed that the HEFF framework maintained 91.89% classification accuracy in the primary limb position and 85.39% across multiple unseen positions. According to offline analysis, HEFF improved classification accuracy by up to 34.99% across various limb positions compared to the conventional fusion method. These results highlight HEFF's robustness across various conditions, being well-suited for assistive technology applications.