Study on the Recognition of Electrogastric Signals Combining Multiple Decomposition Features

2016 Revista de la Facultad de Ingeniería  
After de-noising, electrogastric signals can be analyzed and the category of the signals can be obtained. It can be observed from Fig.1 that the amount of the raw data of the generated waveform is too large. For the convenience of calculation, appropriate processing is necessary. In this paper, a method of kernel principal component analysis is used due to the characteristics of the waveform data.
doi:10.21311/002.31.6.17 fatcat:ceio3evbwvc77n4g6xjfkctbfm