Yue Teng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yue Teng has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
- Junxin Chen
Dalian University of Technology, Dalian, China
2 shared publications - Li-Bo Zhang
Department of Radiology, General Hospital of Northern Theater Command, Shenyang, China
2 shared publications - Bo Fang
University of Sydney, Australia, Australia
1 shared publication - Giancarlo Fortino
University of Calabria
1 shared publication - Haoyue Li
College of Medicine and Biological Information Engineering, Northeastern University, Shenyang, China
1 shared publication - Marcin Woźniak
Faculty of Applied Mathematics, Silesian University of Technology, Gliwice, Poland
1 shared publication
Latest Publications
- 1 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (6) , 8754-8762
EMCNet: Ensemble Multiscale Convolutional Neural Network for Single-Lead ECG Classification in Wearable Devices
The rapid advancements in wearable devices have enabled continuous and real-time monitoring and analysis of physiological parameters. Owing to the benefits of detecting cardiovascular diseases, arrhythmia recognition from the wearable ECG (Electrocardiogram) signals has drawn much attention. In this paper, we present a novel method of using an ensemble of multiscale convolutional neural networks, the so-called EMCNet, for classifying the single-lead ECG waves acquired by wearable devices. The EMCNet includes two primary modules. Two component classifiers are first developed, which input the filtered ECG recordings and time-frequency spectrograms, and output the prediction probabilities of corresponding categories. These prediction probabilities are then sent to an improved weight matrix based on soft voting to produce the final classification result. Numerous experiments have been conducted, with results clearly demonstrating the efficacy and benefits of the EMCNet.
- 1 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (6) , 8754-8762
EMCNet: Ensemble Multiscale Convolutional Neural Network for Single-Lead ECG Classification in Wearable Devices
The rapid advancements in wearable devices have enabled continuous and real-time monitoring and analysis of physiological parameters. Owing to the benefits of detecting cardiovascular diseases, arrhythmia recognition from the wearable ECG (Electrocardiogram) signals has drawn much attention. In this paper, we present a novel method of using an ensemble of multiscale convolutional neural networks, the so-called EMCNet, for classifying the single-lead ECG waves acquired by wearable devices. The EMCNet includes two primary modules. Two component classifiers are first developed, which input the filtered ECG recordings and time-frequency spectrograms, and output the prediction probabilities of corresponding categories. These prediction probabilities are then sent to an improved weight matrix based on soft voting to produce the final classification result. Numerous experiments have been conducted, with results clearly demonstrating the efficacy and benefits of the EMCNet.
- Top Cited Papers
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 21 (4) , 936-947
A Robust Deep Learning Framework Based on Spectrograms for Heart Sound Classification
Heart sound analysis plays an important role in early detecting heart disease. However, manual detection requires doctors with extensive clinical experience, which increases uncertainty for the task, especially in medically underdeveloped areas. This paper proposes a robust neural network structure with an improved attention module for automatic classification of heart sound wave. In the preprocessing stage, noise removal with Butterworth bandpass filter is first adopted, and then heart sound recordings are converted into time-frequency spectrum by short-time Fourier transform (STFT). The model is driven by STFT spectrum. It automatically extracts features through four down sample blocks with different filters. Subsequently, an improved attention module based on Squeeze-and-Excitation module and coordinate attention module is developed for feature fusion. Finally, the neural network will give a category for heart sound waves based on the learned features. The global average pooling layer is adopted for reducing the model's weight and avoiding overfitting, while focal loss is further introduced as the loss function to minimize the data imbalance problem. Validation experiments have been conducted on two publicly available datasets, and the results well demonstrate the effectiveness and advantages of our method.
- 22 February 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 21 (4) , 936-947
Top Cited PapersA Robust Deep Learning Framework Based on Spectrograms for Heart Sound Classification
Heart sound analysis plays an important role in early detecting heart disease. However, manual detection requires doctors with extensive clinical experience, which increases uncertainty for the task, especially in medically underdeveloped areas. This paper proposes a robust neural network structure with an improved attention module for automatic classification of heart sound wave. In the preprocessing stage, noise removal with Butterworth bandpass filter is first adopted, and then heart sound recordings are converted into time-frequency spectrum by short-time Fourier transform (STFT). The model is driven by STFT spectrum. It automatically extracts features through four down sample blocks with different filters. Subsequently, an improved attention module based on Squeeze-and-Excitation module and coordinate attention module is developed for feature fusion. Finally, the neural network will give a category for heart sound waves based on the learned features. The global average pooling layer is adopted for reducing the model's weight and avoiding overfitting, while focal loss is further introduced as the loss function to minimize the data imbalance problem. Validation experiments have been conducted on two publicly available datasets, and the results well demonstrate the effectiveness and advantages of our method.