碩士 / 中原大學 / 資訊工程研究所 / 91 / This paper is using the low-cost hardware to simply the complexity of building an underwater acoustic signal recognition system and shorter the training time of characteristic.
The system is based on TI TMS320C6711 DSK, using the AD535 chip to do A/D transformation. After that, the system uses the digital signal to make preprocessing and the Fast Fourier Transform to get sum of spectra or Welch Periodogram. The result is scaled and stands for a set of signal characteristic. These signal characteristics of ships are adjusted by the following method:K-Mean, average method, recursive concentration, the minimum distance method to get single characteristics center. As to several characteristic centers, the adaptive resonance theory and backprogation network have been traced, finally, the adaptive resonance theory shows a better result.
Identifer | oai:union.ndltd.org:TW/091CYCU5392045 |
Creators | Jie-Yeh Cheng, 鄭傑爗 |
Contributors | Chu-Kuei Tu, 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 | 65 |
Page generated in 0.0075 seconds