Browsing by Author "Zhou, Dian"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    IEEE Access Special Section Editorial: Advanced Information Sensing and Learning Technologies for Data-Centric Smart Health Applications
    (IEEE, 2021-02) Zhang, Qingxue; Piuri, Vincenzo; Clancy, Edward A.; Zhou, Dian; Penzel, Thomas; Hu, Wenchuang Walter; Electrical and Computer Engineering, School of Engineering and Technology
    Smart health is bringing vast and promising possibilities on the road to comprehensive health management. Smart health applications are strongly data-centric and, thus, empowered by two key factors: information sensing and information learning. In a smart health system, it is crucial to effectively sense individuals’ health information and intelligently learn from its high-level health insights. These two factors are also closely coupled. For example, to enhance the signal quality, a sensing array requires advanced information learning techniques to fuse the information, and to enrich medical insights in mobile health monitoring, we need to combine “multimodal signal processing and machine learning techniques” and “nonintrusive multimodality sensing methods.” In new smart health application exploration, challenges arise in both information sensing and learning, especially their areas of interaction.
  • Thumbnail Image
    Item
    Machine Learning Electrocardiogram for Mobile Cardiac Pattern Extraction
    (MDPI, 2023-06-19) Zhang, Qingxue; Zhou, Dian; Electrical and Computer Engineering, School of Engineering and Technology
    Background: Internet-of-things technologies are reshaping healthcare applications. We take a special interest in long-term, out-of-clinic, electrocardiogram (ECG)-based heart health management and propose a machine learning framework to extract crucial patterns from noisy mobile ECG signals. Methods: A three-stage hybrid machine learning framework is proposed for estimating heart-disease-related ECG QRS duration. First, raw heartbeats are recognized from the mobile ECG using a support vector machine (SVM). Then, the QRS boundaries are located using a novel pattern recognition approach, multiview dynamic time warping (MV-DTW). To enhance robustness with motion artifacts in the signal, the MV-DTW path distance is also used to quantize heartbeat-specific distortion conditions. Finally, a regression model is trained to transform the mobile ECG QRS duration into the commonly used standard chest ECG QRS durations. Results: With the proposed framework, the performance of ECG QRS duration estimation is very encouraging, and the correlation coefficient, mean error/standard deviation, mean absolute error, and root mean absolute error are 91.2%, 0.4 ± 2.6, 1.7, and 2.6 ms, respectively, compared with the traditional chest ECG-based measurements. Conclusions: Promising experimental results are demonstrated to indicate the effectiveness of the framework. This study will greatly advance machine-learning-enabled ECG data mining towards smart medical decision support.