Yiwei Lin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yiwei Lin has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Jinshan Xu
Zhejiang University of Technology
8 shared publications - Zhenqin Chen
College of Computer Science, Zhejiang University of Technology, Hangzhou, China
7 shared publications - Fengdan Hu
Zhejiang Shuren University, Hangzhou 310015, China
2 shared publications Cong Cheng
1 shared publication- FengBo Wang1 shared publication
- Fengdan Hu
College of Computer Science, Zhejiang University of Technology, Hangzhou, China
1 shared publication
Latest Publications
- 7 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Robust and interpretable ECG denoising via stage-aware conditional diffusion with co-evolving guidance
- 7 October 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 334
Robust and interpretable ECG denoising via stage-aware conditional diffusion with co-evolving guidance
- 14 July 2026
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 180, 103485
GLF-Net: A quasi-periodic prior-guided waveform segmentation network for ECG delineation
- 14 July 2026
- Published by Elsevier in Artificial Intelligence in Medicine
- Vol. 180, 103485
GLF-Net: A quasi-periodic prior-guided waveform segmentation network for ECG delineation
- 7 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 322
FM-FECG: An observation-informed flow matching framework for non-invasive fetal ECG extraction
- 7 April 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 322
FM-FECG: An observation-informed flow matching framework for non-invasive fetal ECG extraction
- 10 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (1) , 534-546
DIFF-FECG: A Conditional Diffusion-Based Method for Fetal ECG Extraction From Abdominal ECG
Fetal electrocardiography (FECG) is a crucial tool for assessing fetal cardiac health and pregnancy status. Direct invasive FECG provides reliable fetal heart rate signals, but poses risks and is limited to use during labor. Conversely, non-invasive monitoring of the fetal heart is possible via abdominal electrocardiography (AECG), which detects fetal heart waveforms using electrodes positioned on the mother’s abdomen. However, this method is often subject to interference from maternal cardiac activity and other external sources. To address this issue, we propose a novel diffusion method, DIFF-FECG, aimed at improving the extraction of FECG signals from AECG recordings. This method leverages a condition-driven diffusion process to learn specific conditional probability distributions, enabling the effective separation of high-quality FECG signals from noisy AECG data. By adaptively managing the inherent non-Gaussian noise characteristics of MECG within the AECG, DIFF-FECG achieves more effective FECG reconstruction. Furthermore, the quality of the generated FECG signals is also enhanced by adding reconstruction loss and multiple reconstructions. Experimental results on two public databases demonstrate that the proposed DIFF-FECG method yields satisfactory results, with an average Pearson correlation coefficient of 0.922 for the estimated FECG. These findings underscore the potential of diffusion probabilistic models in advancing FECG signal extraction techniques, thereby contributing to improved fetal health monitoring.
- 10 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 7 (1) , 534-546
DIFF-FECG: A Conditional Diffusion-Based Method for Fetal ECG Extraction From Abdominal ECG
Fetal electrocardiography (FECG) is a crucial tool for assessing fetal cardiac health and pregnancy status. Direct invasive FECG provides reliable fetal heart rate signals, but poses risks and is limited to use during labor. Conversely, non-invasive monitoring of the fetal heart is possible via abdominal electrocardiography (AECG), which detects fetal heart waveforms using electrodes positioned on the mother’s abdomen. However, this method is often subject to interference from maternal cardiac activity and other external sources. To address this issue, we propose a novel diffusion method, DIFF-FECG, aimed at improving the extraction of FECG signals from AECG recordings. This method leverages a condition-driven diffusion process to learn specific conditional probability distributions, enabling the effective separation of high-quality FECG signals from noisy AECG data. By adaptively managing the inherent non-Gaussian noise characteristics of MECG within the AECG, DIFF-FECG achieves more effective FECG reconstruction. Furthermore, the quality of the generated FECG signals is also enhanced by adding reconstruction loss and multiple reconstructions. Experimental results on two public databases demonstrate that the proposed DIFF-FECG method yields satisfactory results, with an average Pearson correlation coefficient of 0.922 for the estimated FECG. These findings underscore the potential of diffusion probabilistic models in advancing FECG signal extraction techniques, thereby contributing to improved fetal health monitoring.
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Multimodal Polysomnography-Based Automatic Sleep Stage Classification via Multiview Fusion Network
Sleep staging is a standard diagnostic method for evaluating sleep quality, which would enable early diagnosis of sleep disorders as well as mental diseases. Polysomnography (PSG), a set of physiological signals recorded externally, is a standard media for sleep staging. Developing automatic algorithms to analyze the PSG signals with the purpose of better sleep staging is demanding, as manual assessment is tedious and time-consuming. However, it is challenged by the noisy nature of the PSG signals, i.e., features contributing to sleep staging are embedded in different types and scales of signals in both time and frequency domains. In this article, we propose a hybrid deep learning architecture that uses multimodal PSG signals, specifically electroencephalogram (EEG) and electrooculogram (EOG), and their frequency representations as inputs, to accomplish sleep stage classification tasks. To this end, we design the multiscale local feature extractor (MSLFE) with a multibranch convolutional neural network (CNN) of different convolutional kernel sizes and the global relationship modeling (GRM) module to extract features in both time and frequency domains effectively. A cross-linked fusion (CLF) module is further introduced to enable an effective fusion of multimodal and multiattribute features while avoiding bidirectional representation redundancy for high-quality feature maps. We carried out a set of experiments on the SleepEDF-ST and SleepEDF-SC to validate the effectiveness of the proposed method, where classification performance in terms of precision, recall, and F1-score higher than 84% are obtained on most of the sleep stages. Comparisons with the state-of-the-art methods confirm the effectiveness of the proposed method in improving sleep quality evaluation and diagnosis. Source code is available at: https://github.com/ZJUT-CBS/MMNet .
- 18 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Multimodal Polysomnography-Based Automatic Sleep Stage Classification via Multiview Fusion Network
Sleep staging is a standard diagnostic method for evaluating sleep quality, which would enable early diagnosis of sleep disorders as well as mental diseases. Polysomnography (PSG), a set of physiological signals recorded externally, is a standard media for sleep staging. Developing automatic algorithms to analyze the PSG signals with the purpose of better sleep staging is demanding, as manual assessment is tedious and time-consuming. However, it is challenged by the noisy nature of the PSG signals, i.e., features contributing to sleep staging are embedded in different types and scales of signals in both time and frequency domains. In this article, we propose a hybrid deep learning architecture that uses multimodal PSG signals, specifically electroencephalogram (EEG) and electrooculogram (EOG), and their frequency representations as inputs, to accomplish sleep stage classification tasks. To this end, we design the multiscale local feature extractor (MSLFE) with a multibranch convolutional neural network (CNN) of different convolutional kernel sizes and the global relationship modeling (GRM) module to extract features in both time and frequency domains effectively. A cross-linked fusion (CLF) module is further introduced to enable an effective fusion of multimodal and multiattribute features while avoiding bidirectional representation redundancy for high-quality feature maps. We carried out a set of experiments on the SleepEDF-ST and SleepEDF-SC to validate the effectiveness of the proposed method, where classification performance in terms of precision, recall, and F1-score higher than 84% are obtained on most of the sleep stages. Comparisons with the state-of-the-art methods confirm the effectiveness of the proposed method in improving sleep quality evaluation and diagnosis. Source code is available at: https://github.com/ZJUT-CBS/MMNet .
- 1 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Sample Point Classification of Abdominal ECG Through CNN-Transformer Model Enables Efficient Fetal Heart Rate Detection
Monitoring fetal heart rate (FHR) is essential for the early detection of fetal distress and ensuring safe delivery. Direct invasive fetal electrocardiography (FECG) provides reliable FHR signals but is limited to use during labor. Noninvasive fetal heart monitoring can be achieved through abdominal electrocardiography (AECG), where fetal heartbeat waveforms are captured from electrodes placed on maternal abdomen. However, accurately locating fetal R-peaks and obtaining FHRs remain challenging due to interference from uterine contractions and maternal heartbeats. To address this challenge, we proposed an end-to-end fetal R-peak detection method based on sample point classification. Inspired by semantic segmentation in image analysis, we utilized an encoder-decoder model to classify each point in the 1-D AECG signal. The model captures the global contextual information of fetal heartbeat waveforms by combining convolutional neural networks (CNNs) and transformer, resulting in a high-precision classification of each sample point in the AECG signal. Moreover, to mitigate the impact of misclassified points on fetal R-peak detection, we proposed a postprocessing method based on the periodicity of heartbeats. The effectiveness of the proposed method is validated on two AECG databases, achieving satisfactory results with an average F1-score of 98.91%. These findings demonstrate the potential application of long-term fetal monitoring using portable devices. The code is publicly available at https://github.com/ZJUT-CBS/FR-Net .
- 1 December 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-12
Sample Point Classification of Abdominal ECG Through CNN-Transformer Model Enables Efficient Fetal Heart Rate Detection
Monitoring fetal heart rate (FHR) is essential for the early detection of fetal distress and ensuring safe delivery. Direct invasive fetal electrocardiography (FECG) provides reliable FHR signals but is limited to use during labor. Noninvasive fetal heart monitoring can be achieved through abdominal electrocardiography (AECG), where fetal heartbeat waveforms are captured from electrodes placed on maternal abdomen. However, accurately locating fetal R-peaks and obtaining FHRs remain challenging due to interference from uterine contractions and maternal heartbeats. To address this challenge, we proposed an end-to-end fetal R-peak detection method based on sample point classification. Inspired by semantic segmentation in image analysis, we utilized an encoder-decoder model to classify each point in the 1-D AECG signal. The model captures the global contextual information of fetal heartbeat waveforms by combining convolutional neural networks (CNNs) and transformer, resulting in a high-precision classification of each sample point in the AECG signal. Moreover, to mitigate the impact of misclassified points on fetal R-peak detection, we proposed a postprocessing method based on the periodicity of heartbeats. The effectiveness of the proposed method is validated on two AECG databases, achieving satisfactory results with an average F1-score of 98.91%. These findings demonstrate the potential application of long-term fetal monitoring using portable devices. The code is publicly available at https://github.com/ZJUT-CBS/FR-Net .