Breath Odor Pathological Feature Extraction And Analysis Based On Wavelet Transform

The Traditional Chinese Medicine(TCM), which is formed and developed by the ancient people in the long-term medical practice, has a long history. TCM auscultation, as a collection of disease information and diagosis method in TCM diagnosis, is supported by TCM theory. It is convenient, no-damage and non-invasive diagnosis. However, due to historical conditions, the diagnosis based on TCM theory is also a lack of objective and quantifiable criteria. Then the TCM is considered to be an empirical science, which hindered the development Seriously. Therefore, on the basis of maintaining the advantages in the TCM diagnosis, how to combine the TCM with modern computer technology, and achieving the objective of TCM diagnosis standardization, are a great and arduous task.Breath diagnosis, i.e. diagnosis based on the breath of people, is developing quickly and steadily. Electronic nose technology is also called artificial olfactory system.Its basic principle is the use of gas sensor sensing the corresponding gas component and then capture the response signal,then analysis by pattern recognition technology.The work of this thesis can be divided into three parts: design and implementation of the e-nose system, research on the algorithm of odor data feature extraction, and the classification of the odor data. The design of the e-nose system includes hardware and software. Hardware design includes the optimization of sensor array, the adjustment, collecting, and communication of sensor signals, and building of the sampling system. Software design is coding of the sampling system.The research on odor data feature extraction is the core part of this thesis. Odor data is the electric signals from the output of the sensor array. The traditional feature extraction is to extract the static geometrical features, such as peak value of the curve, position of the peak value, slopes, and the area under the curve, etc. These method is many disadvantages. Because the response of the sensor is not just depend on the types of odors, but also affected by the temperature, humidity and concentration of the odor. The static geometrical features cannot always represent the types of odors. This thesis introduces the wavelet transform technique to extract features. These features can represent the class-related information of odors roundly, which make good inputs for classification.