碩士 / 中原大學 / 資訊工程研究所 / 86 / There are two emphases about this research. The one is underwater acoustic signal feature parameter extraction by using digital signal processing and then getting the template feature parameter by training the self-organization map neural network. The other is the fuzzy logic recognition system and establishes the fuzzy logic rules to membership functions modification. Finally, the two parts are integrated to prove that our research can be realized. During the feature parameter extraction stage, signal characteristic analysis and feature selection are discussed. Upon careful analysis the feature parameters of the signal and practical data obtain from calculation, the result shows the feature parameters obtaining from the Spectrum can distinguish ship signature effectively. In order to get each ship''s template feature parameter, a self-organization map neural network was used in the training phase for clustering the input data and generate the center of data set. During the recognition system modeling, an algorithm which using template feature parameter to conform the fuzzy logic rule and fuzzy logic inference is developed. After getting the result of recognition from the fuzzy recognition algorithm, a modify process is execute which modifying the membership function of the fuzzy logic rules. According to the deviation between the recognition result and actual result, the modification process repeat until recognition rate is increasing. In order to achieve real-time recognition, we have to simplify the algorithms for the purpose of saving calculation time. By using object-orient language, and developing modular system architecture. We shorten program develop time and improve system performance. Finally, a realizable real-time acoustic signal recognition system was established.
| Identifer | oai:union.ndltd.org:TW/086CYCU0392009 |
| Date | January 1998 |
| Creators | Chen Hsiang-I, 陳祥益 |
| Contributors | Tu Chu-Kuei, 杜筑奎 |
| Source Sets | National Digital Library of Theses and Dissertations in Taiwan |
| Language | zh-TW |
| Detected Language | English |
| Type | 學位論文 ; thesis |
| Format | 0 |
Page generated in 0.0166 seconds