Ning Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Ning Wang has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Zongmin Wang
School of Water Conservancy and Transportation, Zhengzhou University, Zhengzhou 450001, China
4 shared publications - Bing Zhou
The College of Computer Science and Artificial Intelligence, Zhengzhou University, Zhengzhou, China
3 shared publications - Panpan Feng
School of Computer and Artificial Intelligence, Cooperative Innovation Center of Internet Healthcare of Henan Province, Zhengzhou University, Zhengzhou, China
3 shared publications - Bin Huang
Henan University
1 shared publication Bing Zhou
1 shared publication- Dange Liu
School of Computer and Artificial Intelligence, Collaborative Innovation Center for Internet Health of Henan Province, Zhengzhou University, Zhengzhou, China
1 shared publication
Latest Publications
- 31 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
ECG-Text multi-modal learning for zero-shot detection via time-frequency alignment and medical prompt learning
- 31 December 2025
- Published by Elsevier in Expert Systems with Applications
- Vol. 307
ECG-Text multi-modal learning for zero-shot detection via time-frequency alignment and medical prompt learning
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Bean: A Multibranch Network for 12 Leads Electrocardiogram Multilabel Classification Based on Ensemble Learning and Attention
Cardiovascular disease patients may suffer from multiple conditions, and in clinical diagnosis, doctors observe the waveform features of electrocardiogram signals in each lead and then assess disease abnormalities based on the positions of the leads. Therefore, it is essential to learn multilabel features and lead weights. Additionally, electrocardiogram is a time series physiological signal, and the semantic relationships between features must be considered. This paper proposes a branch network model based on ensemble learning and attention, which includes multibranch networks and a lead ensemble module. Each branch network embeds a global semantic attention module and a class specific classifier. First, the global semantic attention module in the branch network encodes the global semantic relationships of electrocardiogram feature data; the class specific classifier extracts semantic vectors for each class in the feature space, guided by the labels. Finally, the lead ensemble module adaptively updates the lead weights and integrates the outputs from all leads for classification. Extensive experiments were conducted on two benchmark datasets (PTB-XL and CPSC2018), and the results demonstrate the superiority of our proposed method. Case analysis further confirms that the features used by the proposed method for electrocardiogram classification align with clinical diagnostic rules.
- 19 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-13
Bean: A Multibranch Network for 12 Leads Electrocardiogram Multilabel Classification Based on Ensemble Learning and Attention
Cardiovascular disease patients may suffer from multiple conditions, and in clinical diagnosis, doctors observe the waveform features of electrocardiogram signals in each lead and then assess disease abnormalities based on the positions of the leads. Therefore, it is essential to learn multilabel features and lead weights. Additionally, electrocardiogram is a time series physiological signal, and the semantic relationships between features must be considered. This paper proposes a branch network model based on ensemble learning and attention, which includes multibranch networks and a lead ensemble module. Each branch network embeds a global semantic attention module and a class specific classifier. First, the global semantic attention module in the branch network encodes the global semantic relationships of electrocardiogram feature data; the class specific classifier extracts semantic vectors for each class in the feature space, guided by the labels. Finally, the lead ensemble module adaptively updates the lead weights and integrates the outputs from all leads for classification. Extensive experiments were conducted on two benchmark datasets (PTB-XL and CPSC2018), and the results demonstrate the superiority of our proposed method. Case analysis further confirms that the features used by the proposed method for electrocardiogram classification align with clinical diagnostic rules.
- 22 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 314
Semi-supervised multi-label cardiovascular diseases detection via contrastive learning and label inference
- 22 February 2025
- Published by Elsevier in Knowledge-Based Systems
- Vol. 314
Semi-supervised multi-label cardiovascular diseases detection via contrastive learning and label inference
- Open Access
- 29 January 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (3) , 3283-3304
DRL-based dependent task offloading with delay-energy tradeoff in medical image edge computing
Task offloading solves the problem that the computing resources of terminal devices in hospitals are limited by offloading massive radiomics-based medical image diagnosis model (RIDM) tasks to edge servers (ESs). However, sequential offloading decision-making is NP-hard. Representing the dependencies of tasks and developing collaborative computing between ESs have become challenges. In addition, model-free deep reinforcement learning (DRL) has poor sample efficiency and brittleness to hyperparameters. To address these challenges, we propose a distributed collaborative dependent task offloading strategy based on DRL (DCDO-DRL). The objective is to maximize the utility of RIDM tasks, which is a weighted sum of the delay and energy consumption generated by execution. The dependencies of the RIDM task are modeled as a directed acyclic graph (DAG). The sequence prediction of the S2S neural network is adopted to represent the offloading decision process within the DAG. Next, a distributed collaborative processing algorithm is designed on the edge layer to further improve run efficiency. Finally, the DCDO-DRL strategy follows the discrete soft actor-critic method to improve the robustness of the S2S neural network. The numerical results prove the convergence and statistical superiority of the DCDO-DRL strategy. Compared with other algorithms, the DCDO-DRL strategy improves the execution utility of the RIDM task by at least 23.07, 12.77, and 8.51% in the three scenarios.
- 29 January 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (3) , 3283-3304
Open AccessDRL-based dependent task offloading with delay-energy tradeoff in medical image edge computing
Task offloading solves the problem that the computing resources of terminal devices in hospitals are limited by offloading massive radiomics-based medical image diagnosis model (RIDM) tasks to edge servers (ESs). However, sequential offloading decision-making is NP-hard. Representing the dependencies of tasks and developing collaborative computing between ESs have become challenges. In addition, model-free deep reinforcement learning (DRL) has poor sample efficiency and brittleness to hyperparameters. To address these challenges, we propose a distributed collaborative dependent task offloading strategy based on DRL (DCDO-DRL). The objective is to maximize the utility of RIDM tasks, which is a weighted sum of the delay and energy consumption generated by execution. The dependencies of the RIDM task are modeled as a directed acyclic graph (DAG). The sequence prediction of the S2S neural network is adopted to represent the offloading decision process within the DAG. Next, a distributed collaborative processing algorithm is designed on the edge layer to further improve run efficiency. Finally, the DCDO-DRL strategy follows the discrete soft actor-critic method to improve the robustness of the S2S neural network. The numerical results prove the convergence and statistical superiority of the DCDO-DRL strategy. Compared with other algorithms, the DCDO-DRL strategy improves the execution utility of the RIDM task by at least 23.07, 12.77, and 8.51% in the three scenarios.
- 2 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Spa-Tem MI: A Spatial–Temporal Network for Detecting and Locating Myocardial Infarction
Worldwide, the automatic diagnosis (i.e., detection and localization) of myocardial infarction (MI) remains a challenging problem. Clinically, MI is mainly detected and located according to the changes and differences between each electrocardiogram (ECG) lead. Therefore, to capture the features of different MI locations with their corresponding leads, we proposes an end-to-end spatial-temporal MI network (Spa-Tem MI) for detecting and locating MI. To facilitate the extraction of spatial and temporal features, we proposed a width-concat method to convert 1-D multi-lead ECG signals into a 2-D ECG matrix. To learn the spatial and temporal features of MI, the Spa-Tem MI consists of a spatial feature extraction (SFE) module and a temporal feature extraction (TFE) module. The SFE module aims to obtain the spatial differences between leads via dense blocks. Through the self-attention mechanism, the TFE module can capture the global temporal changes of leads. The proposed method was validated with the real MI dataset HeMI, and the dataset was divided by the inter-patient paradigm. The precision, recall, F1 score, and Hamming loss of the results were 94.07%, 95.45%, 93.81%, and 0.03, respectively. In addition, the model was also verified with the public dataset PTB-XL. Compared with that of state-of-the-art methods, the proposed method achieved superior performance.
- 2 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-12
Spa-Tem MI: A Spatial–Temporal Network for Detecting and Locating Myocardial Infarction
Worldwide, the automatic diagnosis (i.e., detection and localization) of myocardial infarction (MI) remains a challenging problem. Clinically, MI is mainly detected and located according to the changes and differences between each electrocardiogram (ECG) lead. Therefore, to capture the features of different MI locations with their corresponding leads, we proposes an end-to-end spatial-temporal MI network (Spa-Tem MI) for detecting and locating MI. To facilitate the extraction of spatial and temporal features, we proposed a width-concat method to convert 1-D multi-lead ECG signals into a 2-D ECG matrix. To learn the spatial and temporal features of MI, the Spa-Tem MI consists of a spatial feature extraction (SFE) module and a temporal feature extraction (TFE) module. The SFE module aims to obtain the spatial differences between leads via dense blocks. Through the self-attention mechanism, the TFE module can capture the global temporal changes of leads. The proposed method was validated with the real MI dataset HeMI, and the dataset was divided by the inter-patient paradigm. The precision, recall, F1 score, and Hamming loss of the results were 94.07%, 95.45%, 93.81%, and 0.03, respectively. In addition, the model was also verified with the public dataset PTB-XL. Compared with that of state-of-the-art methods, the proposed method achieved superior performance.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (10) , 13845-13859
Adversarial Spatiotemporal Contrastive Learning for Electrocardiogram Signals
Extracting invariant representations in unlabeled electrocardiogram (ECG) signals is a challenge for deep neural networks (DNNs). Contrastive learning is a promising method for unsupervised learning. However, it should improve its robustness to noise and learn the spatiotemporal and semantic representations of categories, just like cardiologists. This article proposes a patient-level adversarial spatiotemporal contrastive learning (ASTCL) framework, which includes ECG augmentations, an adversarial module, and a spatiotemporal contrastive module. Based on the ECG noise attributes, two distinct but effective ECG augmentations, ECG noise enhancement, and ECG noise denoising, are introduced. These methods are beneficial for ASTCL to enhance the robustness of the DNN to noise. This article proposes a self-supervised task to increase the antiperturbation ability. This task is represented as a game between the discriminator and encoder in the adversarial module, which pulls the extracted representations into the shared distribution between the positive pairs to discard the perturbation representations and learn the invariant representations. The spatiotemporal contrastive module combines spatiotemporal prediction and patient discrimination to learn the spatiotemporal and semantic representations of categories. To learn category representations effectively, this article only uses patient-level positive pairs and alternately uses the predictor and the stop-gradient to avoid model collapse. To verify the effectiveness of the proposed method, various groups of experiments are conducted on four ECG benchmark datasets and one clinical dataset compared with the state-of-the-art methods. Experimental results showed that the proposed method outperforms the state-of-the-art methods.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks and Learning Systems
- Vol. 35 (10) , 13845-13859
Adversarial Spatiotemporal Contrastive Learning for Electrocardiogram Signals
Extracting invariant representations in unlabeled electrocardiogram (ECG) signals is a challenge for deep neural networks (DNNs). Contrastive learning is a promising method for unsupervised learning. However, it should improve its robustness to noise and learn the spatiotemporal and semantic representations of categories, just like cardiologists. This article proposes a patient-level adversarial spatiotemporal contrastive learning (ASTCL) framework, which includes ECG augmentations, an adversarial module, and a spatiotemporal contrastive module. Based on the ECG noise attributes, two distinct but effective ECG augmentations, ECG noise enhancement, and ECG noise denoising, are introduced. These methods are beneficial for ASTCL to enhance the robustness of the DNN to noise. This article proposes a self-supervised task to increase the antiperturbation ability. This task is represented as a game between the discriminator and encoder in the adversarial module, which pulls the extracted representations into the shared distribution between the positive pairs to discard the perturbation representations and learn the invariant representations. The spatiotemporal contrastive module combines spatiotemporal prediction and patient discrimination to learn the spatiotemporal and semantic representations of categories. To learn category representations effectively, this article only uses patient-level positive pairs and alternately uses the predictor and the stop-gradient to avoid model collapse. To verify the effectiveness of the proposed method, various groups of experiments are conducted on four ECG benchmark datasets and one clinical dataset compared with the state-of-the-art methods. Experimental results showed that the proposed method outperforms the state-of-the-art methods.