摘要
A neural-based network is applied to data communication receiver to investigate the feasibility of the network over intersymbol interference(ISI) and additive white Gaussian noise channel environments. With a 3-layered perceptron with either backward error propagation and extended Kalman filter training algorithms, it can be shown that it closely approximates the theoretical optimum receiver as the number of network trainings increases. The simulations are made on the network operations and error rate performance over several important parameters. Once the problem on the network training is solved the proposed data receiver is an alternative to the optimum Viterbi channel decoder.
| 原文 | 英語 |
|---|---|
| 主出版物標題 | 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 |
| 發行者 | Institute of Electrical and Electronics Engineers Inc. |
| 頁面 | 2933-2936 |
| 頁數 | 4 |
| ISBN(電子) | 0780305930 |
| DOIs | |
| 出版狀態 | 已出版 - 1992 |
| 對外發佈 | 是 |
| 事件 | 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 - San Diego, 美國 持續時間: 10 05 1992 → 13 05 1992 |
出版系列
| 名字 | Proceedings - IEEE International Symposium on Circuits and Systems |
|---|---|
| 卷 | 6 |
| ISSN(列印) | 0271-4310 |
Conference
| Conference | 1992 IEEE International Symposium on Circuits and Systems, ISCAS 1992 |
|---|---|
| 國家/地區 | 美國 |
| 城市 | San Diego |
| 期間 | 10/05/92 → 13/05/92 |
文獻附註
Publisher Copyright:© 1992 IEEE.
指紋
深入研究「A neural-based digital communication receiver for inter-symbol interference and white Gaussian noise channels」主題。共同形成了獨特的指紋。引用此
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver