| 講演抄録/キーワード |
| 講演名 |
2012-08-28 15:40
SVM based Classification for Underwater Transient Signals in Ocean Background Noise ○Juho Kim・Tae-Hoon Bok・Jinho Bae・Dong-Guk Paeng・Chong Hyun Lee(Jeju National Univ.)・Seongil Kim(Agency for Defense Development) US2012-57 |
| 抄録 |
(和) |
In this paper, new method for classification of underwater transient mechanical signals was proposed. The classifier uses SVM algorithm and 16 orders LPC coefficients as feature vectors. The proposed classifier is composed of two steps. The mechanical signals are separated from biological signals at the first SVM classifier and then classification of mechanical signal is preformed at the second SVM. For experiment, three kinds of underwater biological signals and two kinds of mechanical signals were used. The recognition rate was higher than 90% at high Signal to Noise Ratio (SNR) when clean signal used. When underwater ambient noise was added, the recognition rate dropped but was better than the Bayesian classifier. |
| (英) |
In this paper, new method for classification of underwater transient mechanical signals was proposed. The classifier uses SVM algorithm and 16 orders LPC coefficients as feature vectors. The proposed classifier is composed of two steps. The mechanical signals are separated from biological signals at the first SVM classifier and then classification of mechanical signal is preformed at the second SVM. For experiment, three kinds of underwater biological signals and two kinds of mechanical signals were used. The recognition rate was higher than 90% at high Signal to Noise Ratio (SNR) when clean signal used. When underwater ambient noise was added, the recognition rate dropped but was better than the Bayesian classifier. |
| キーワード |
(和) |
underwater transient signal / SVM classification / underwater noise / / / / / |
| (英) |
underwater transient signal / SVM classification / underwater noise / / / / / |
| 文献情報 |
信学技報, vol. 112, no. 186, US2012-57, pp. 115-120, 2012年8月. |
| 資料番号 |
US2012-57 |
| 発行日 |
2012-08-20 (US) |
| ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
| PDFダウンロード |
US2012-57 |