Ke Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ke Zhang has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Zhelong Wang
Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China
4 shared publications - Fang Lin
Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of the Ministry of Education and the School of Control Science and Engineering, Dalian University of Technology, Dalian, China
3 shared publications - Hongyu Zhao
Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education, Dalian University of Technology, Dalian, China
3 shared publications - Hongkai Zhao
Dalian University of Technology
2 shared publications - Jiaxi Li
Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering, Dalian University of Technology, Dalian, China
2 shared publications - Sen Qiu
School of Control Science and Engineering, Dalian University of Technology, Dalian, China
2 shared publications
Latest Publications
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (6) , 2227-2236
A Hierarchical Multimodal Framework for Sedation Monitoring in ICU Patients
In the intensive care unit (ICU), monitoring sedation levels is crucial. Clinicians often rely on intermittent behavioral scales like the Richmond Agitation-Sedation Scale (RASS), which can be subjective and delay timely interventions. While electroencephalogram (EEG) offers a continuous and non-invasive alternative, but the complexity of consciousness renders a unimodal signal insufficient for comprehensive representation. To address these challenges, we propose a novel multimodal deep learning framework, Hierarchical Multimodal Fusion with Dynamic Correction (HMDC), that synergistically integrates EEG with peripheral physiological signals including blood pressure, heart rate, and oxygen saturation. The architecture features a dual-stream pathway to process both raw temporal EEG data and its spectral features from spectrograms. These neural representations are then intelligently fused and refined by a Dynamic Correction Module using a confidence-weighting mechanism. The model was developed and validated on a dataset comprising 2,880 labeled RASS assessments from 105 ICU patients, with scores ranging from −5 (comatose) to +1 (restless). The HMDC framework achieved a classification accuracy of 83.8%, significantly outperforming unimodal and simpler fusion baselines. By providing a temporally precise and physiologically grounded sedation assessment, this integrative approach establishes a robust correlation between multimodal signal patterns and clinical states, offering clinicians a unified tool for optimizing sedative titration and potentially minimizing delirium risks.
- 1 June 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Biomedical Engineering
- Vol. 73 (6) , 2227-2236
A Hierarchical Multimodal Framework for Sedation Monitoring in ICU Patients
In the intensive care unit (ICU), monitoring sedation levels is crucial. Clinicians often rely on intermittent behavioral scales like the Richmond Agitation-Sedation Scale (RASS), which can be subjective and delay timely interventions. While electroencephalogram (EEG) offers a continuous and non-invasive alternative, but the complexity of consciousness renders a unimodal signal insufficient for comprehensive representation. To address these challenges, we propose a novel multimodal deep learning framework, Hierarchical Multimodal Fusion with Dynamic Correction (HMDC), that synergistically integrates EEG with peripheral physiological signals including blood pressure, heart rate, and oxygen saturation. The architecture features a dual-stream pathway to process both raw temporal EEG data and its spectral features from spectrograms. These neural representations are then intelligently fused and refined by a Dynamic Correction Module using a confidence-weighting mechanism. The model was developed and validated on a dataset comprising 2,880 labeled RASS assessments from 105 ICU patients, with scores ranging from −5 (comatose) to +1 (restless). The HMDC framework achieved a classification accuracy of 83.8%, significantly outperforming unimodal and simpler fusion baselines. By providing a temporally precise and physiologically grounded sedation assessment, this integrative approach establishes a robust correlation between multimodal signal patterns and clinical states, offering clinicians a unified tool for optimizing sedative titration and potentially minimizing delirium risks.
- 14 May 2026
- Published by Elsevier in Acta Astronautica
- Vol. 247, 390-397
Two-stage geometric-dynamic approach for real-time space catalogued debris flux estimation
- 14 May 2026
- Published by Elsevier in Acta Astronautica
- Vol. 247, 390-397
Two-stage geometric-dynamic approach for real-time space catalogued debris flux estimation
- 21 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (23) , 40069-40082
Multitask Learning-Based Approach for Integrated Load Identification, Electrical Fault Detection, and Signal Purification
In recent years, the application of deep learning techniques for load identification in nonintrusive load monitoring (NILM) has gained significant momentum. However, the presence of load faults and noise interference caused by external environment during practical load identification poses a challenge. Electrical fault detection and signal denoising are crucial aspects in the research of load identification. To address these issues, a multi-task learning network (MTLNET) was proposed to address three tasks in parallel including load identification, fault detection, and signal denoising. To extract effective information from load signals, a novel feature representation called robust variational mode extraction-instantaneous amplitude (RVME-IA) was introduced. Furthermore, a multi-level feature fusion attention (MLFFA) module is employed to capture both local and global features for different tasks. For the classification subnets, a local enhance attention module (LEAM) is designed to locally amplify crucial information in the feature. To ensure optimal performance across the different tasks, a customized gate control (CGC) module is integrated into the proposed model. The proposed approach was evaluated on a self-collected high-frequency load fault dataset, as well as public NILM datasets. The experimental results indicate that the proposed model outperforms state-of-the-art methods in all three tasks.
- 21 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (23) , 40069-40082
Multitask Learning-Based Approach for Integrated Load Identification, Electrical Fault Detection, and Signal Purification
In recent years, the application of deep learning techniques for load identification in nonintrusive load monitoring (NILM) has gained significant momentum. However, the presence of load faults and noise interference caused by external environment during practical load identification poses a challenge. Electrical fault detection and signal denoising are crucial aspects in the research of load identification. To address these issues, a multi-task learning network (MTLNET) was proposed to address three tasks in parallel including load identification, fault detection, and signal denoising. To extract effective information from load signals, a novel feature representation called robust variational mode extraction-instantaneous amplitude (RVME-IA) was introduced. Furthermore, a multi-level feature fusion attention (MLFFA) module is employed to capture both local and global features for different tasks. For the classification subnets, a local enhance attention module (LEAM) is designed to locally amplify crucial information in the feature. To ensure optimal performance across the different tasks, a customized gate control (CGC) module is integrated into the proposed model. The proposed approach was evaluated on a self-collected high-frequency load fault dataset, as well as public NILM datasets. The experimental results indicate that the proposed model outperforms state-of-the-art methods in all three tasks.
- 1 June 2024
- Published by Elsevier in Information Fusion
- Vol. 111
A comprehensive evaluation method for frailty based on semi-supervised learning and transfer-learning
- 1 June 2024
- Published by Elsevier in Information Fusion
- Vol. 111
A comprehensive evaluation method for frailty based on semi-supervised learning and transfer-learning
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (5) , 3102-3113
Method for Incomplete and Imbalanced Data Based on Multivariate Imputation by Chained Equations and Ensemble Learning
The classification analysis of incomplete and imbalanced data is still a challenging task since these issues could negatively impact the training of classifiers, which were also found in our study on the physical fitness assessments of patients. And in fields such as healthcare, there are higher requirements for the accuracy of the generated imputation values. To train a high-performance classifier and pursue high accuracy, we attempted to resolve any potential negative impact by using a novel algorithmic approach based on the combination of multivariate imputation by chained equations and the ensemble learning method (MICEEN), which can solve the two problems simultaneously. We used multivariate imputation by chained equations to generate more accurate imputation values for the training set passed to ensemble learning to build a predictor. On the other hand, missing values were introduced into minority classes and used them to generate new samples belonging to the minority classes in order to balance the distribution of classes. On real-world datasets, we perform extensive experiments to assess our method and compare it to other state-of-the-art approaches. The advantages of the proposed method are demonstrated by experimental results for the benchmark datasets and self-collected datasets of physical fitness assessment of tumor patients with varying missing rates.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 28 (5) , 3102-3113
Method for Incomplete and Imbalanced Data Based on Multivariate Imputation by Chained Equations and Ensemble Learning
The classification analysis of incomplete and imbalanced data is still a challenging task since these issues could negatively impact the training of classifiers, which were also found in our study on the physical fitness assessments of patients. And in fields such as healthcare, there are higher requirements for the accuracy of the generated imputation values. To train a high-performance classifier and pursue high accuracy, we attempted to resolve any potential negative impact by using a novel algorithmic approach based on the combination of multivariate imputation by chained equations and the ensemble learning method (MICEEN), which can solve the two problems simultaneously. We used multivariate imputation by chained equations to generate more accurate imputation values for the training set passed to ensemble learning to build a predictor. On the other hand, missing values were introduced into minority classes and used them to generate new samples belonging to the minority classes in order to balance the distribution of classes. On real-world datasets, we perform extensive experiments to assess our method and compare it to other state-of-the-art approaches. The advantages of the proposed method are demonstrated by experimental results for the benchmark datasets and self-collected datasets of physical fitness assessment of tumor patients with varying missing rates.