Wrist-Pulse Signal Diagnosis Using ICPulse

Traditional Chinese Pulse Diagnosis (TCPD) is one of the most important diagnostic techniques in Traditional Chinese Medicine (TCM) and computerized analysis of pulse signals is a crucial step for objectifying and standardizing TCPD. This paper presents an automated wrist-pulse signal diagnosis approach by using the independent component analysis (ICA) to extract pulse signal features. A wrist-pulse signal dataset is established, which includes both the samples from healthy people and patients with certain diseases. With the extracted features by ICA, a nearest neighborhood classifier is used to distinguish the unhealthy samples from healthy samples. The experimental results on the established dataset demonstrate the efficiency of the proposed ICA based pulse signal analysis method.