| Summary: | 碩士 === 龍華科技大學 === 電機工程研究所 === 99 === In this study, we propose an ECG (electrocardiogram) telemonitoring system applied in a rest house envirment. ECG signals are acquired and fed into an SOC (system on chip). On the SOC, an adaptive resonant theory (ART) type network is equipped to classify the ECG signals. As an abnormal heartbeat is identified, the SOC transfers the heartbeat, through the wireless sensor network, to the PC for further analysis. The routing protocol of the wireless sensor network used was developed in the previous study. The functions of the routing protocol include the establishment and maintenance of the network topology, the increase and deletion of the sensor node, and the guarantee of the quality of service of the wireless sensor network.
The proposed ECG beat classification involves two phases. One is the off-line learning phase. With the proposed performance index, the product of the classification accuracy and the partition quality, an optimal value for the vigilance threshold and the corresponding cluster centers from the learning results can be determined. The other is the online examining phase, which classifies the input ECG beats. In this phase, the vigilance threshold value and the initial cluster centers are the optimal ones obtained in the learning phase. Under these conditions, the GreyART network enables real-time classification of ECG beats
|
|---|
