Xin-Hua Chen
Algorithm Engineer 

2021 / 02  -  2022/ 08

​X. -H. Chen, Y. -L. Shen and T. -S. Chi,"Single Lead ECG Cross-Session Identification Based on Conditional Domain Adversarial Network"

​        Biometric human identification systems have been mainly implemented based on fingerprint, face, iris, and voice recognition. However, counterfeits generated from deep-learning technologies make such systems more and more vulnerable. On the other hand, the electrocardiogram (ECG) signal, which can only be measured from a living body, provides a secure alternative for identity authentication. For an ECG identification system, the most difficult challenge is to face heart rate variability caused by different physiological states and long-term cardiac states. In other words, the system must have cross-session generalization ability to identify ECG signals recorded in different periods of time. In this article, we propose a robust ECG identification model using a single heartbeat recorded from lead-I by treating the cross-session identification task as a cross-domain task. The proposed model is referred to as the conditional domain adversarial neural network for cross-session ECG signals (CDAN-CS), which combines the temporal convolutional neural network (TCN) and the cross-domain model of conditional domain adversarial network with entropy (CDAN-E).

        Averaged over experimental results on three databases, the proposed model achieves 100% accuracy and F1 -score for ECG signals within the same session and 99.76% accuracy and 90.5% F1 -score for cross-session ECG signals. The averaged F1 -score of 90.5% is 8.44% higher than the averaged F1 -score achieved by the baseline TCN model. The robust results from CDAN-CS validate the idea of tackling the cross-session ECG identification task using domain adaptation models.

​

See more in IEEE Sensors Journal Volume 24, Issue 11​...

​​

​

 

​​

2020 / 08  -  2020 / 12

"Cardiovascular Disease Classification Using Single-Lead ECG"

        Myocardial infarction (MI) causes irreversible damage to heart muscles and even leads up to death. We often use blood tests or electrocardiogram (ECG) signals to diagnose acute MI in the emergency department. However, these examinations take time after the attack, which may decrease the survival rate.

        Rapid and accurate diagnosis of MI is critical to avoid deaths; therefore, our computer-aided diagnosis help automate the detection of heart disease on ECG.

​

​

2019 / 02  -  2020 / 01

"Brain Imaging Recognition on Alzheimer's Disease and Mild Cognitive Impairment "

        As technologies advance, artificial intelligence has stretched out into various fields. Even the diagnosis isn't dependent solely on a single doctor's decision. Instead, it requires deep learning to reinforce and assist the accuracy of the diagnosis, which can even surpass human work.

        In this research topic, after preprocessing functional Magnetic Resonance Imaging (fMRI) using Matlab, we revised Heung-Il Suk's deep learning method to provide diagnostic assistance for patients with Alzheimer's disease(AD) or Mild Cognitive Impairment(MCI). 
        Considering the state-of-the-art methods neglected individual biological characteristics so that the evaluation tends to overestimate the accuracy, we tried to split data into the subject level to obtain a more accurate result in a real-world scenario.

​