Guijin Wang, PhD
Associate Professor, Tsinghua University
Office: Rohm Building, Room 6-207
PhD, Electronic Engineering, Tsinghua University (2003)
BS, Electronic Engineering, Tsinghua University (1998)
Artificial intelligence technology has made significant progress in analysis of image, speech, and text. With the continuous accumulation of biomedical data and urgent need for intelligent analysis, we believe that it will make breakthroughs in cardiovascular disease which threatens human health, based on analyzing electrocardiographs (ECGs) that play important roles in disease diagnosis.
Our lab explores patterns from large amount of ECGs through deep learning techniques, in order to acquire cardiologist-level performance for better clinical services. Currently our deep learning models have achieved better results in ECG segmentation, premature heart beats recognition and atrial fibrillation detection, etc. Through our cooperation with several hospitals, we have built an ECG database which will enhance the power of deep learning. In the future, we will seek opportunities to apply AI-based ECG diagnosis techniques in wearable devices.
Zhang, C., Wang, G., Zhao, J., Gao, P., Lin, J., & Yang, H. Patient-specific ECG classification based on recurrent neural networks and clustering technique. In Biomedical Engineering (BioMed), 2017 13th IASTED International Conference on (pp. 63-67). IEEE..
Gao, P., Zhao, J., Wang, G., & Guo, H. Real time ECG characteristic point detection with randomly selected signal pair difference (RSSPD) feature and random forest classifier. In Engineering in Medicine and Biology Society (EMBC), 2016 IEEE 38th Annual International Conference of the (pp. 732-735). IEEE.
Fu, D., Xia, Z., Gao, P., Wang H., Lin, J., & Sun, L. ECG Delineation with Randomly Selected Wavelet Feature and Random Forest Classifier. IEICE TRANS(Vol.E101-D,No.8).
Xia, Z., Wang, G., Fu, D., Wang, H., Chen, M., Xie, P., & Yang, H. Real-Time ECG Delineation with Randomly Selected Wavelet Transform Feature and Random Walk Estimation. EMBC. In press.
Xie, P., Wang, G., Zhang, C., Chen, M., Yang, H., Lv, T., Sang, Z., & Zhang, P. Bidirectional Recurrent Neural Network and Convolutional Neural Network (BiRCNN) for ECG Beat Classification. EMBC. In press.
Chen, M., Wang, G., Xie, P., Sang, Z., Lv, T., Zhang, P., & Yang, H. (2018). Region Aggregation Network: Improving Convolutional Neural Network for ECG Characteristic Detection. EMBC. In press.