Research On Novel Pulse Acquisition Device And Pulse Signal Analysis Method

TCM is an important part of Chinese traditional culture, Chinese civilization is the art treasures. Chinese medicine is broad and profound, has a long history, for thousands of years, Chinese medicine has made an important contribution to the health of the Chinese nation, and it is still an indispensable important subject in medical practice. With the development of society, the crystallization of Electropulsograph as Chinese medicine combined with modern technology, to solve the traditional objective and scientific, however, at this stage to stay sphygmography promotion and application in the laboratory stage, and with the aging of society, people have urgent needs of wearable medical preparation.In order to deal with the above situation, this paper designed a wearable pulse pulse diagnosis detection and analysis system based on. To solve the problem of the size of hardware device through the worm and the screw drive structure, the piezoresistive sensor is fit to extract the TCM pulse signal, and the design of the automatic search for the best algorithm to simulate the pulse pressure, floating or sinking, in traditional Chinese medicine pulse technique, in addition, combined with the characteristics of the output signal of the sensor is designed the corresponding signal conditioning circuit; software PC control by Arduino controller, communicate with PC via Bluetooth, mobile phone terminal PC acquisition, waveform drawing, information extraction and machine feature in time domain control interface.On the analysis of the pulse, the nonlinear analysis of the pulse, slippery pulse, wiry pulse signals of three kinds of recursive method in quantitative analysis, from the construction of the reconstructed phase space can be found with obvious periodic pulse signal. From the exact recursive graph to extract 10 parameters of the pulse signals, then using the gray level co-occurrence matrix to extract the texture feature parameters of 4 kinds of saturated recursive graph. The parameters of flat pulse, slippery pulse, wiry pulse extraction was 22 compared and analyzed the difference between the pulse. Finally, by using deep belief network (DBN) methods to classify three kinds of pulse signal, impact on the classification accuracy by adjusting different hidden layers and nodes.