| 講演抄録/キーワード |
| 講演名 |
2006-04-12 11:30
Novel Method for Blind Recognition of Communication Signal Based on Time-frequency Analysis and Neural Network ○Weihong Fu(Xidian Univ.)・Xiaoniu Yang(National Key Lab of Jiangnan Electronic Comm. Research. Inst.)・Xingwen Zeng(Xidian Univ.) SANE2006-56 |
| 抄録 |
(和) |
In this paper, we present a novel method for blind recognition of communication signal to solve the problem of the signal classification and recognition in communication reconnaissance. In this method, we use time-frequency analysis technology to extract the feature of the signals, and the neural network (backwards propagation network) to classify and recognize the signals. The simulation results show that in case of no noise」ャblind recognition method proposed in this paper can correctly recognize more than 85% signals averagely and recognition ratio of PSK signals can reach up to 98%. If the ratio of signal to noise is high, the average recognition ratio of the signals can also reach about 85%. Moreover, we need not know any prior information of the signals to recognize any signals within broad frequency band and we need not perform carrier frequency synchronization and estimate the parameter of the signal. Therefore, this method has practical application in communication reconnaissance and breaks a new path for blind reconnaissance of the communication signal. |
| (英) |
In this paper, we present a novel method for blind recognition of communication signal to solve the problem of the signal classification and recognition in communication reconnaissance. In this method, we use time-frequency analysis technology to extract the feature of the signals, and the neural network (backwards propagation network) to classify and recognize the signals. The simulation results show that in case of no noise」ャblind recognition method proposed in this paper can correctly recognize more than 85% signals averagely and recognition ratio of PSK signals can reach up to 98%. If the ratio of signal to noise is high, the average recognition ratio of the signals can also reach about 85%. Moreover, we need not know any prior information of the signals to recognize any signals within broad frequency band and we need not perform carrier frequency synchronization and estimate the parameter of the signal. Therefore, this method has practical application in communication reconnaissance and breaks a new path for blind reconnaissance of the communication signal. |
| キーワード |
(和) |
communication reconnaissance / neural network / time-frequency analysis / Signal blind recognition / / / / |
| (英) |
communication reconnaissance / neural network / time-frequency analysis / Signal blind recognition / / / / |
| 文献情報 |
信学技報, vol. 106, no. 1, SANE2006-56, pp. 303-307, 2006年4月. |
| 資料番号 |
SANE2006-56 |
| 発行日 |
2006-04-03 (SANE) |
| 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 |
SANE2006-56 |