Yinghao Liu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yinghao Liu has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Chao Lian
School of Information Science and Engineering, Northeastern University, Shenyang 110819, China
10 shared publications - Yuliang Zhao
Northeastern University
8 shared publications - Changzeng Fu
Northeastern University, Qinhuangdao, China
4 shared publications Jian Li
3 shared publications- Jian Li
Beijing Normal University
3 shared publications - Zhikun Zhan
School of Computer Science and Engineering, Northeastern University, Shenyang, China
3 shared publications
Latest Publications
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 55855-55868
Smart Wristband for Analysis of Subtle Movement Differences in Ball Games
- 1 December 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 13 (23) , 55855-55868
Smart Wristband for Analysis of Subtle Movement Differences in Ball Games
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (18) , 27580-27591
Texture-Guided Multiscale Feature Representation and Learning for Rotating Machinery Fault Diagnosis
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (18) , 27580-27591
Texture-Guided Multiscale Feature Representation and Learning for Rotating Machinery Fault Diagnosis
- 12 February 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 193
MCADFNet: Multi-scale cross-modal attention dynamic decision fusion network for Parkinson’s quantitative grading
- 12 February 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 193
MCADFNet: Multi-scale cross-modal attention dynamic decision fusion network for Parkinson’s quantitative grading
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 44326-44337
SMI-DSNet: Spatio-Temporal Matrix Imaging and Dual-Stream Networks for Enhanced Heart Sound Signal Classification
Heart sound signal analysis is a crucial tool for diagnosing cardiovascular diseases (CVDs), where accurate classification is essential for clinical decision-making. However, current heart sound recognition methods lack sufficient interpretability and cannot fully utilize the information of time-series data from sensors. To overcome these challenges, we propose the spatio-temporal matrix images and dual-stream network (SMI-DSNet), a novel framework that integrates spatio-temporal matrix representations with a dual-stream deep learning architecture. The innovative SMI technique transforms 1-D heart sound signals into 2-D matrix images, capturing key features that are clinically relevant for diagnosis and thereby enhancing the interpretability of heart sound data analysis. The dual-stream network integrates ResNet-18 for spatial feature extraction with BiGRU to capture long-range temporal dependencies in heart sound signals, thereby comprehensively harnessing the information encoded within the time series. In addition, a crossattention module is introduced to refine feature fusion by emphasizing pathological features based on physiological insights. Evaluated on public datasets, SMI-DSNet attains an exceptional classification accuracy of 99.5%, outperforming contemporary methods, including CNN-BiLSTM and Vision Transformer. These results highlight the high precision of the model, demonstrating its potential for clinical application.
- 27 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (24) , 44326-44337
SMI-DSNet: Spatio-Temporal Matrix Imaging and Dual-Stream Networks for Enhanced Heart Sound Signal Classification
Heart sound signal analysis is a crucial tool for diagnosing cardiovascular diseases (CVDs), where accurate classification is essential for clinical decision-making. However, current heart sound recognition methods lack sufficient interpretability and cannot fully utilize the information of time-series data from sensors. To overcome these challenges, we propose the spatio-temporal matrix images and dual-stream network (SMI-DSNet), a novel framework that integrates spatio-temporal matrix representations with a dual-stream deep learning architecture. The innovative SMI technique transforms 1-D heart sound signals into 2-D matrix images, capturing key features that are clinically relevant for diagnosis and thereby enhancing the interpretability of heart sound data analysis. The dual-stream network integrates ResNet-18 for spatial feature extraction with BiGRU to capture long-range temporal dependencies in heart sound signals, thereby comprehensively harnessing the information encoded within the time series. In addition, a crossattention module is introduced to refine feature fusion by emphasizing pathological features based on physiological insights. Evaluated on public datasets, SMI-DSNet attains an exceptional classification accuracy of 99.5%, outperforming contemporary methods, including CNN-BiLSTM and Vision Transformer. These results highlight the high precision of the model, demonstrating its potential for clinical application.
- 21 June 2025
- Published by Elsevier in Information Fusion
- Vol. 124
A survey for wearable sensors empowering smart healthcare in the era of large language models
- 21 June 2025
- Published by Elsevier in Information Fusion
- Vol. 124
A survey for wearable sensors empowering smart healthcare in the era of large language models
- 11 April 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 045020
Simulated and experimental fine damage models for steel railway tracks
The integrity of railway track structures is gravely threatened by rail damage, posing significant risks to the safe operation of railway transportation systems. However, existing detection techniques, including computer vision, ultrasound, acoustic emission, and thermal imaging, exhibit inherent limitations in identifying minor defects and concealed damage at the rail’s underside. To address this challenge, a rail damage detection method based on modal analysis is proposed, integrating finite element (FE) simulations with experimental measurements to enable the effective identification of various damage types and severities. Initially, a three-dimensional rail model is constructed using SolidWorks, and its dynamic characteristics are thoroughly analyzed through Ansys FE simulations. Subsequently, a compact micro-electromechanical system sensor array is designed and deployed to capture rail vibration signals, with actual modal properties extracted via PolyMAX software and compared against the simulation model to validate its reliability. Based on this validated model, the influence of different damage conditions on the rail’s natural frequencies is further examined. Findings reveal a pronounced correlation between damage severity and the reduction in natural frequency, with greater damage leading to a more significant decline. Effectively detecting early-stage, imperceptible rail damage, this method provides a robust technological foundation for rail structural health monitoring and holds substantial engineering applicability.
- 11 April 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (4) , 045020
Simulated and experimental fine damage models for steel railway tracks
The integrity of railway track structures is gravely threatened by rail damage, posing significant risks to the safe operation of railway transportation systems. However, existing detection techniques, including computer vision, ultrasound, acoustic emission, and thermal imaging, exhibit inherent limitations in identifying minor defects and concealed damage at the rail’s underside. To address this challenge, a rail damage detection method based on modal analysis is proposed, integrating finite element (FE) simulations with experimental measurements to enable the effective identification of various damage types and severities. Initially, a three-dimensional rail model is constructed using SolidWorks, and its dynamic characteristics are thoroughly analyzed through Ansys FE simulations. Subsequently, a compact micro-electromechanical system sensor array is designed and deployed to capture rail vibration signals, with actual modal properties extracted via PolyMAX software and compared against the simulation model to validate its reliability. Based on this validated model, the influence of different damage conditions on the rail’s natural frequencies is further examined. Findings reveal a pronounced correlation between damage severity and the reduction in natural frequency, with greater damage leading to a more significant decline. Effectively detecting early-stage, imperceptible rail damage, this method provides a robust technological foundation for rail structural health monitoring and holds substantial engineering applicability.
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (3) , 2048-2061
Multimodal Depression Assessment Framework Integrating Personality and Gait for Older Adults With Medical Conditions
Elderly individuals often suffer from underlying medical conditions, resulting in a significant decline in quality of life and a heightened susceptibility to depression. Presently, AI screening tools based on behavioral indicators offer an objective and effective approach to diagnosing depression. However, current AI depression screening tools are primarily tailored to adolescents and adults, exhibiting shortcomings in their applicability and accuracy for elderly individuals with underlying medical conditions. To address the above issues, firstly, this paper constructs a depression dataset for elderly people with underlying diseases by using semi-structured interviews. Secondly, based on cognitive science insights, it is recognized that personality factors significantly influence behavioral expressions and also determine the attitudes of elderly individuals toward current life circumstances/health issues. Therefore, besides annotating depression severity, the Big Five-10 personality scale was utilized to annotate participant personalities. Finally, a late fusion-based multi-task learning framework was proposed, and the effects of introducing gait information and personality annotation on the performance of depression assessment were investigated. The experimental findings affirm the importance of integrating gait information and personality assessment in improving depression detection effectiveness. This study provides valuable foundational resources, as well as beneficial references and insights, for the research on depression in the elderly.
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Affective Computing
- Vol. 16 (3) , 2048-2061
Multimodal Depression Assessment Framework Integrating Personality and Gait for Older Adults With Medical Conditions
Elderly individuals often suffer from underlying medical conditions, resulting in a significant decline in quality of life and a heightened susceptibility to depression. Presently, AI screening tools based on behavioral indicators offer an objective and effective approach to diagnosing depression. However, current AI depression screening tools are primarily tailored to adolescents and adults, exhibiting shortcomings in their applicability and accuracy for elderly individuals with underlying medical conditions. To address the above issues, firstly, this paper constructs a depression dataset for elderly people with underlying diseases by using semi-structured interviews. Secondly, based on cognitive science insights, it is recognized that personality factors significantly influence behavioral expressions and also determine the attitudes of elderly individuals toward current life circumstances/health issues. Therefore, besides annotating depression severity, the Big Five-10 personality scale was utilized to annotate participant personalities. Finally, a late fusion-based multi-task learning framework was proposed, and the effects of introducing gait information and personality annotation on the performance of depression assessment were investigated. The experimental findings affirm the importance of integrating gait information and personality assessment in improving depression detection effectiveness. This study provides valuable foundational resources, as well as beneficial references and insights, for the research on depression in the elderly.
- 30 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Incorporating image representation and texture feature for sensor-based gymnastics activity recognition
- 30 January 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 311
Incorporating image representation and texture feature for sensor-based gymnastics activity recognition