Junjie Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Junjie Zhang has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Borui Jiang
School of Communication and Information Engineering, Chongqing University of Posts and Telecommunications, China
1 shared publication - Fengyi Wang
Department of Rehabilitation Medicine, West China Hospital of Sichuan University, Chengdu, China
1 shared publication - Fengyi Wang
Department of Rehabilitation Medicine, West China Hospital of Sichuan University, Chengdu, China.
1 shared publication - Hai-Tao Wang
Department of Rehabilitation Medicine, MianYang Central Hospital, China
1 shared publication - Hongwei Shi
Sichuan University, College of Computer Science
1 shared publication Huachen Xiang
School of Computer Science and Technology Sichuan University Sichuan China West China
1 shared publication
Latest Publications
- 3 November 2024
- Published by Springer Nature
- p. 279-298
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-label Medical Image Classification
- 3 November 2024
- Published by Springer Nature
- p. 279-298
Pseudo-Prompt Generating in Pre-trained Vision-Language Models for Multi-label Medical Image Classification
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
PFIMPA: A Multimodal Approach to Predict Physical Function Impairment in Older Adults Using Physical Activity From Wrist-Worn Accelerometer
Diagnosing physical function impairment (PFI) in older adults is challenging due to delayed diagnosis and cumbersome clinical assessments. We propose PFIMPA, a novel artificial intelligence method that enables seamless remote PFI assessment using physical activity (PA) data provided by wrist-worn accelerometers for the first time. To capture the complex cumulative and dynamic characteristics of PA, we designed a comprehensive feature representation method that integrates demographic information, clinical PA features, time-frequency domain features, and PA sequence conversion image features (PASCIs) based on Gramian Angular Field, Markov Transfer Field, and Recursive Plot transformations. We developed a lightweight convolutional neural network enhanced by Convolutional Block Attention Module to extract spatio-temporal features from PASCIs, further encapsulating the correlation, accumulation, and transition properties of PA. PFI detection is achieved through a three-stage feature-level fusion method combined with machine learning and hyperparameter optimization. The PASCIs module achieves an AUC of 83.72% in PFI prediction, while the multimodal approach combining clinical, time-frequency, and PASCIs features improves the AUC to 87.16%, surpassing state-of-the-art time series classification models. PFIMPA represents a significant advancement in PFI assessment for older adults, enabling seamless remote monitoring and timely intervention.
- 30 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-13
PFIMPA: A Multimodal Approach to Predict Physical Function Impairment in Older Adults Using Physical Activity From Wrist-Worn Accelerometer
Diagnosing physical function impairment (PFI) in older adults is challenging due to delayed diagnosis and cumbersome clinical assessments. We propose PFIMPA, a novel artificial intelligence method that enables seamless remote PFI assessment using physical activity (PA) data provided by wrist-worn accelerometers for the first time. To capture the complex cumulative and dynamic characteristics of PA, we designed a comprehensive feature representation method that integrates demographic information, clinical PA features, time-frequency domain features, and PA sequence conversion image features (PASCIs) based on Gramian Angular Field, Markov Transfer Field, and Recursive Plot transformations. We developed a lightweight convolutional neural network enhanced by Convolutional Block Attention Module to extract spatio-temporal features from PASCIs, further encapsulating the correlation, accumulation, and transition properties of PA. PFI detection is achieved through a three-stage feature-level fusion method combined with machine learning and hyperparameter optimization. The PASCIs module achieves an AUC of 83.72% in PFI prediction, while the multimodal approach combining clinical, time-frequency, and PASCIs features improves the AUC to 87.16%, surpassing state-of-the-art time series classification models. PFIMPA represents a significant advancement in PFI assessment for older adults, enabling seamless remote monitoring and timely intervention.
- Open Access
Multimodal Physical Fitness Monitoring (PFM) Framework Based on TimeMAE-PFM in Wearable Scenarios
Physical function monitoring (PFM) plays a crucial role in healthcare especially for the elderly. Traditional assessment methods such as the Short Physical Performance Battery (SPPB) have failed to capture the full dynamic characteristics of physical function. Wearable sensors such as smart wristbands offer a promising solution to this issue. However, challenges exist, such as the computational complexity of machine learning methods and inadequate information capture. This paper proposes a multi-modal PFM framework based on an improved TimeMAE, which compresses time-series data into a low-dimensional latent space and integrates a self-enhanced attention module. This framework achieves effective monitoring of physical health, providing a solution for real-time and personalized assessment. The method is validated using the NHATS dataset, and the results demonstrate an accuracy of 70.6% and an AUC of 82.20%, surpassing other state-of-the-art time-series classification models.
Open AccessMultimodal Physical Fitness Monitoring (PFM) Framework Based on TimeMAE-PFM in Wearable Scenarios
Physical function monitoring (PFM) plays a crucial role in healthcare especially for the elderly. Traditional assessment methods such as the Short Physical Performance Battery (SPPB) have failed to capture the full dynamic characteristics of physical function. Wearable sensors such as smart wristbands offer a promising solution to this issue. However, challenges exist, such as the computational complexity of machine learning methods and inadequate information capture. This paper proposes a multi-modal PFM framework based on an improved TimeMAE, which compresses time-series data into a low-dimensional latent space and integrates a self-enhanced attention module. This framework achieves effective monitoring of physical health, providing a solution for real-time and personalized assessment. The method is validated using the NHATS dataset, and the results demonstrate an accuracy of 70.6% and an AUC of 82.20%, surpassing other state-of-the-art time-series classification models.
- Open Access
- 26 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 74-80
Ergonomic Load Differentiates Pediatric and Adult Physiotherapy
Musculoskeletal disorders caused by ergonomic loads are a common concern for physiotherapists, and there is a lack of quantitative studies on this topic in clinical physiotherapy. This study aims to objectively explore the differences in ergonomic loads between pediatric and adult therapy sessions among physiotherapists. The study includes 82 physiotherapy sessions, 41 each for adult physical therapy (APT) and pediatric physical therapy (CPT). Inertial sensing technology was used to track the therapists' posture during the sessions, and the ergonomic load was assessed quantitatively using an automated procedure that references the Rapid Entire Body Assessment (REBA). The Fatigue Scale-14 (FS-14) was used to assess fatigue. The results of the study indicate that pediatric physiotherapists feel more physically exhausted than adult physiotherapists after performing the treatment. Overall, pediatric physiotherapy poses greater ergonomic risks than adult physiotherapy (p=0.004), especially in the legs (p<0.001). However, in the upper extremity and wrist segments, the risks of physiotherapy for adults are greater than those of physiotherapy for children (p<0.001). The study concludes that the ergonomic load induced by pediatric physiotherapy is generally higher than adult physiotherapy, and therefore, pediatric physiotherapy should receive more attention to maintain the health and well-being of physiotherapists.
- 26 May 2023
- Published by Association for Computing Machinery (ACM)
- p. 74-80
Open AccessErgonomic Load Differentiates Pediatric and Adult Physiotherapy
Musculoskeletal disorders caused by ergonomic loads are a common concern for physiotherapists, and there is a lack of quantitative studies on this topic in clinical physiotherapy. This study aims to objectively explore the differences in ergonomic loads between pediatric and adult therapy sessions among physiotherapists. The study includes 82 physiotherapy sessions, 41 each for adult physical therapy (APT) and pediatric physical therapy (CPT). Inertial sensing technology was used to track the therapists' posture during the sessions, and the ergonomic load was assessed quantitatively using an automated procedure that references the Rapid Entire Body Assessment (REBA). The Fatigue Scale-14 (FS-14) was used to assess fatigue. The results of the study indicate that pediatric physiotherapists feel more physically exhausted than adult physiotherapists after performing the treatment. Overall, pediatric physiotherapy poses greater ergonomic risks than adult physiotherapy (p=0.004), especially in the legs (p<0.001). However, in the upper extremity and wrist segments, the risks of physiotherapy for adults are greater than those of physiotherapy for children (p<0.001). The study concludes that the ergonomic load induced by pediatric physiotherapy is generally higher than adult physiotherapy, and therefore, pediatric physiotherapy should receive more attention to maintain the health and well-being of physiotherapists.