Dissertation > Excellent graduate degree dissertation topics show

Research on the Automatic Classification of Cough

Author: LiWen
Tutor: FangChangShi；TianLianFang
School: South China University of Technology
Course: Control Theory and Control Engineering
Keywords: Cough classification Feature Extraction Mel Frequency Cepstral Coefficients (MFCC) Dynamic Time Warping (DTW)
CLC: TN912.34
Type: Master's thesis
Year: 2010
Downloads: 50
Quote: 2
Read: Download Dissertation

Abstract


Coughing is a widely exists in one of the clinical symptoms, it is a protective mechanism by the airway sudden breath. Depending on the cause of the cough sound characteristics very different type of cough sound analysis of the patient is of great value to diagnose the cause of the patient in clinical medicine. In order to get rid of the artificial classification of complex, cumbersome and differences drawbacks, the coughing sound of automatic classification technology, in-depth research. A variety of different classification type cough, the article uses the common classification of the wet and dry, the appropriate classification method can highlight the differences in wet and dry cough, making it easy to provide a more accurate classification results through analysis. On the other hand, has a larger value of medical diagnosis wet and dry distinction. And Research in the field of speech recognition and cough identification Summary exposition, and a coughing classification system based on MFCC and DTW template matching technique based on the the cough mechanism of characteristics. After analysis of the characteristics of the cough and voice channel model based the LPCC not suitable for cough classification, so MFCC feature parameters based on auditory characteristics. In order to improve the parameters of the dynamic performance of MFCC secondary feature processing, additional standard MFCC order differential. Taking into account the template training and cough classification of environmental noise inconsistency could lead to a decline in system performance, this paper proposes a MFCC feature parameters to improve the robustness of the system with an improved noise suppression. In template matching units using DTW matching algorithm to adapt to cough isolated and duration differences sound clips, and relaxation of the starting and ending point technology into the the DTW algorithms to reduce the sensitivity of the endpoint detection results. At the same time, the article also improved K-means algorithm to sample automated template library training to minimize manual intervention and to ensure the stability of the template library. By a number of experiments, the results show that this technology and improve cough algorithm for automatic classification achieved good classification. Finally, the development of a software system based on the above algorithm, to facilitate the use and testing of the hospital, coughing automatic classification system into experimental testing phase to provide help.

Related Dissertations

  1. Application of Q-Learning in the Content-Based Image Retrieval Technology,TP391.41
  2. Research and System Implementation of Image Retrieval Method Based on Fuzzy Clustering,TP391.41
  3. Academic Network Repetitions disambiguation algorithm,TP301.6
  4. Real-time video display system key technology research,TP391.41
  5. CT images of the lung nodule feature extraction method,TP391.41
  6. Term Weight-Based Chinese Text Classification Algorithm,TP391.1
  7. Automatic Classification of Pavement Based on Laser Data,TN247
  8. Research on Biological Visual Features Extraction in Images Combining Sparse Coding,TP391.41
  9. Research of Image Processing for Seam Track Based on Laser Optical Sensor with Structured Light,TP391.41
  10. Neural Signal Analysis and Decoding of Primary Motor Cortex in Rats,TN911.6
  11. Research of Preprocess Technique for 3D Space Handwriting Based on 3D Accelerometer,TP212
  12. The Research of Product Feature Extraction in B2C Website,TP311.13
  13. The Research on Fault Diagnosis Method Based on Continuous Hidden Markov Model with Feature Weighted,TH165.3
  14. Research on Feature Extraction of Cough Sound and Its Application in Identification,TN912.34
  15. Research of Sleep Stage Based on ECG Signal during Day Time Nap Sleep,TN911.7
  16. Extraction of Pleural Indentation and Lung Cavity of Lung Nodules in CT Images,TP391.41
  17. Research and Implement of Content-based Image Retrieval System,TP391.41
  18. The Research on Algorithm of Automatic Fingerprint Classification,TP391.41
  19. Web-based Face Image Retrieval System,TP391.41
  20. Research of Feature Extraction Based on Space Handwriting Recognition,TP391.41
  21. Co-components Development and Application Based on Product Design Model,TP311.52

CLC: > Industrial Technology > Radio electronics, telecommunications technology > Communicate > Electro-acoustic technology and speech signal processing > Speech Signal Processing > Speech Recognition and equipment
© 2012 www.DissertationTopic.Net  Mobile