Dissertation > Excellent graduate degree dissertation topics show

Pulse signal feature extraction and recognition research

Author: WenXiaoMing
Tutor: CaiKunBao
School: Chongqing University
Course: Signal and Information Processing
Keywords: Pulse Signal Pattern Recognition Support Vector Machine Feature Extraction Wavelet Transform
CLC: TP391.41
Type: Master's thesis
Year: 2009
Downloads: 179
Quote: 5
Read: Download Dissertation

Abstract


With the development of medicine, pulse diagnosis as a noninvasive means and methods by foreign persons of appreciation and attention, but Chinese medicine since ancient times has been the pulse of information that is obtained by a finger pulse, although the pulse diagnosis is a simple, non-invasive and painless features, and easy to be accepted by patients, but in the long-term medical practice also exposed some flaws. With the sensor technology and computer processing technology, to achieve the objective of pulse diagnosis, research pulse detection methods, hoping to use modern science and technology methods and instruments to promote the modernization of pulse diagnosis, has become common concern scholars problems, which is the purpose of this study. This thesis focuses on feature extraction and selection of the basic concepts and theories were elaborated initially explored separability criterion will focus on analyzing wavelet transform coefficients of the specific meaning of scale, but by extracting characteristic parameters for different The experimental results were compared. Wavelet analysis is a frequency domain and the time domain have good analytical method for local, i.e. at low frequencies with higher frequency resolution and lower time resolution in the high frequency portion has a high time resolution rate and lower frequency resolution, it is known as a mathematical analysis of the signal microscope, especially for non-stationary signal processing. In this paper, multi-resolution analysis of wavelet analysis algorithm - Euclidean distance analysis of 20 cases of heroin addicts and 20 normal healthy pulse signal. By extracting the scaling coefficient, and calculate the scale factor to the central square of the distance class, out of heroin addicts in the healthy human pulse signals a significant difference between the initially proposed for dividing the drug and the criterion of normal healthy people, according to the The criterion of 20 normal healthy people have all been detected, and the drug was mistakenly seized B13 as normal healthy people. The paper also support vector machine basic concepts and theories were elaborated, highlighting specific methods estimate the optimal classification face discussion and analysis, pattern recognition to improve a solid theoretical basis. Pulse signal on the basis of feature extraction, using support vector network pulse signal samples in 40 cases (20 cases of heroin addicts and 20 normal healthy people pulse signal) for pattern recognition and optimal classification surface, reaching better results.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. ISAR Imaging Simulation of Space Targets and Target Recognition Based on ISAR Images,TN957.52
  3. Research on Autamatic Music Structrue Analysis,TN912.3
  4. Research on Feature Extraction and Classification of Pulse Waveform for Cholecystitis and Nephrotic Syndrome Diagnosis,TP391.41
  5. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  6. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  7. Research on Feature Extraction and Classification of Tongue Shape and Tooth-Marked Tongue in TCM Tongue Diagnosis,TP391.41
  8. Feature Extraction, Selection and Combination in Lipreading,TP391.41
  9. Multi-currency Notes Technology Research and Implementation,TP391.41
  10. The Research on Paper Currency Classification Method Based on Harr-Like Feature and Minimal Ball Including Samples,TP391.41
  11. Research on Visual Detection and Tracking of Mobile Robots,TP242.62
  12. Intrusion detection based on the ultrasonic echo envelope in the military security patrols,E919
  13. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  14. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  15. The Study of Palmprint Image Identification Based on Wavelet Analysis,TP391.41
  16. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  17. Research on Key Technologies of Auto-stereoscopic 3D Augmented Reality,TP391.41
  18. The Research on Electrode 3D Model Classification and Retrieval Based on SVM and Shape Features,TP391.41
  19. Road traffic marking detection and identification and mapping method,TP391.41
  20. CUDA-based video fire detection system,TP391.41
  21. Mammary gland lumps Texture feature extraction and auxiliary diagnostic methods research,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Pattern Recognition and devices > Image recognition device
© 2012 www.DissertationTopic.Net  Mobile