Electrocardiogram (ECG) analysis is one of the most important approaches to cardiac arrhythmia detection. In this paper, we propose an ECG analysis approach with adaptive feature selection and support vector machines (SVMs). Many wavelet transform-based coefficients are used as candidates, but only a few coefficients are selected for classification problem of each class pair. In addition, the several variation classes are partitioned into two or more subclasses to improve the training efficiency of SVMs. The experimental results show that the proposed ECG analysis approach can obtain high recognition rate and reliable results.

No abstract

An ideal homecare system needs to process multiple diagnostic signals using a portable battoy-driven device, and provide a real-time audiohideo intei$ace for telemedicine application. In this paper, we present a low cost real-time homecare system based on a commercial digital camera platjorm. In addition to the wpical media recording functions of a digital camera, such as MPEG recording, the proposed system can further compress phonocardiogram (PCG) signal concurrently'.Index Termshomecare system, phonocardiogram, electrocardiogram, PCG, and ECG.Education and Institute of Applied Electronic Technology, National Taiwan Normal University, Taipei, Taiwan. His current research interests include system-on-a-chip (SoC) with embedded sothvare design, digital camera system, homecare system, pattern recognition, and color imaging science.

No abstract