The Study on Hidden Markov Models Incorporated with Fuzzy Cluster for Feature Extraction Applied to Bird Sound Recognition System
| Autor: | Hsiang-En Huang, 黃祥恩 |
|---|---|
| Rok vydání: | 2005 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 93 Fuzzy cluster analysis (FCA) is an general data analysis method of feature extraction. The target of FCA is to sort cases (people, things, events, etc.) into several clusters (groups) and further to find out the cluster center. A cluster center of cluster is describing the data characteristic. In general, it is a useful method for static data, but it is not good enough to deal with the relationship of clusters which with dynamic data. This research proposed a new FCA method to deal with feature extraction, and further, involved probability concept from the Hidden Markov Models. The proposed method would describe the relationship of clusters when data are sequentially order. Thus, our FCA method provided not only cluster date but also involved time sequence information for feature extraction. This research took each cluster as a state, and utilize the FCA to calculate the fuzzy partition matrix. And then calculate the state-transition probability and initial state probability distribution by fuzzy partition matrix. Finally, we can record the cluster’s relationship between the two continually data with time sequence information for feature extraction Our proposed method has been applied to the bird song recognition system to extract bird song’s feature and build the database. The advantages of adopting our method for bird recognition system are: reducing the database storage capacity, well recognition speed, and better recognition rate. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|