Study on Recognition of Sub-health from Pulse Signal

Abstract

In this paper, pulse signal of radial artery were measured by using HK-2000C digital integrated pulse transducer and power spectrum was calculated. Then peak value, peak frequency, center of gravity (cg) and gravity frequency of power spectrum were extracted. And Linear Discriminant Analysis (LDA) was applied to pattern recognition of sub-health. The recognition accuracy is up to 80% by using cg and gravity frequency of power spectrum as features. And the recognition accuracy is up to 86.667% by using peak value and peak frequency of power spectrum as features. Using the method proposed in this paper the sub-health state can be identified, which suggests that the proposed method could lead to an easy and effective diagnostic tool.