The Objective Research For The Pulse Signal Of People Body Based On Wavelet And Fuzzy Diagnosis

The pulse-diagnosis is a part of the motherland medical for sciences. It is indispensable objective basis of dialectical management. But the qualities and subjectivity of pulse-diagnosis affected its accuracy and feasibility which become the limitation factor for the Chinese medicine pulse-diagnosis'application,development and communication. Thus, impersonal research of the pulse-diagnosis has important meaning for inheriting and expanding of our country Chinese medicine.The structure of this treatise is organized as below:1,introduces the correlation theory of fuzzy set, identification method of membership function and the usual method to realize fuzzy diagnosis has been studied.2,based on the characteristics of pulse signal, wavelet transform is originally used to process and analysis it and the threshold method to de-noising pulse signal has been studied. wavelet analysis has a good qualities both in time domain and frequency domain and is an ideal tool in analyzing unsteady signal, so it is used to detect the singularity of pulse signal ,and signal is characterized by a new feature which is the energy of its wavelet transform in different scales. The energy value of different scales is used to discern pulse signal by fuzzy cluster analysis and fuzzy diagnosis as input vector.3,used eigenvector composed of energy value of different scales of wavelet transform as the feature of pulse signal. Fuzzy diagnosis need standard pulse model bank beforehand, while fuzzy cluster analysis is classified by feature without participation of any model. Pulse of been extracted in different scales of energy feature is classified by fuzzy cluster analysis and come into being standard pulse model bank, which is used to help unsorted pulse find the closest pulse in standard pulse model bank by fuzzy diagnosis. Though the training sample is limited in the text, the emulational result indicates: for some particular characteristic (such as the energy in different scales by wavelet transformation) of the pulse signal, we make use of the fuzzy diagnosis to identify pulse is viable and effective . Finally, uses Visual Basic6.0 development environment in Windows operation system and Database of SQL Server2000, the software design of EMR expert system on TCM pulse-diagnosis has been introduced.As the algorithms implemented in this treatise are in accordance with process of pulse waves and Chinese pulse manifestations. Hence, it could be used for reference in objective process of Traditional Chinese Medical Science and other pattern recognition systems.