The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SIGNAL PROCESSING
Transactions ID Number: 53-639
Full Name: Wang Luyu
Position: Student
Age: ON
Sex: Female
Address: No.66,Xinmofan Road,Nanjing,JiangSu
Country: CHINA
Tel: 15850589418
Tel prefix: 86
Fax: NULL
E-mail address: xiaoshishoufei@yahoo.com.cn
Other E-mails: baichoufei1699@163.com
Title of the Paper: new compressed wide spectrum sensing scheme based on bp network
Authors as they appear in the Paper: Wang Luyu;Zhu Qi
Email addresses of all the authors: xiaoshishoufei@yahoo.com.cn,baichoufei1699@163.com,zhuqi@njupt.edu.cn
Number of paper pages: 11
Abstract: Spectrum sensing of cognitive radio (CR) requires ability of sensing quickly and accurately with up to GHz bandwidth, which asks for a high-performance AD converter. It challenged people who work in spectrum sensing at traditional Nyquist sampling rate. The framework of Compressed Sensing (CS) breaks the sampling limitation, making it possible to reconstruct and estimate signals via fewer measurements than that requires traditionally. However, reconstruction in CS is NP-hard, which has a high computational complexity, unable to meet real-time request. This paper proposes a new compressed wide spectrum sensing scheme based on BP neural network. In this scheme, the BP neural network technology is added into the normal CS-based detection scheme for wideband signals, replacing for the reconstruction process. In this way, the computational complexity transfers from reconstruction and estimation into network training process, which can be done before spectrum sensing.!
As with blocky sparsity character, signals can be detected without destructive reconstruction, leading to input signals without completely retained. So 1-bit quantification is carried out by which the network load can be mitigated. Simulation results show that with 1-bit quantization, the system can respond in a short period of time. Compared with normal CS-based detection scheme, our new one presents a much shorter consumption as well as a better robustness performance to noise.
Keywords: Spectrum sensing; Compressed sensing; BP neural network; Robustness to noise;Time consuming
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: 973 Program (2007CB310607), National Natural Science Foundation of China (61071092) and National Science & Technology Key Project (2011ZX03001-006-02, 2011ZX03005-004-03))
IP ADDRESS: 222.93.102.59
