Neural-net-based receiver structures for single- and multiamplitude bandlimited signals in CCI and ACI channels

• Published in: IEEE transactions on vehicular technology Vol. 46; no. 3; pp. 791 - 798
• Main Authors: Bouras, D.P., Mathiopoulos, P.T., Makrakis, D.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.08.1997; Institute of Electrical and Electronics Engineers
• Subjects: Applied sciences; Artificial intelligence; AWGN; Bit error rate; Computer science; control theory; systems; Connectionism. Neural networks; Decision feedback equalizers; Detection, estimation, filtering, equalization, prediction; Digital communication; Exact sciences and technology; Information, signal and communications theory; Interchannel interference; Neural networks; Performance analysis; Radiofrequency interference; Signal analysis; Signal and communications theory; Signal, noise; Telecommunications and information theory; Very large scale integration; Learning; Additive noise; Performance evaluation; Bit error rate; Receiver; Neural network; Band limited signal; Algorithm; Signal detection
• ISSN: 0018-9545; 1939-9359
• DOI: 10.1109/25.618204

This paper presents analysis and performance-evaluation results for several neural-network-based nondecision-feedback receiver structures, which improve the performance of bandlimited single- and multiamplitude signals transmitted over additive interference channels, such as cochannel interference (CCI) and adjacent channel interference (ACI). In particular, we propose, analyze, and evaluate a training algorithm for Nyquist-filtered single- and multiamplitude signals, based upon a novel nonuniform signal-sampling technique. We also introduce a novel nonlinear activation function for multiamplitude signals and evaluate its performance via computer simulation and in conjunction with various bandlimited signaling formats, detection techniques, and neural-network structures. Bit-error rate (BER) performance-evaluation results of the proposed neural-network receivers for coherent and noncoherent detection of Nyquist- and Butterworth-filtered single- and multiamplitude signals have shown performance improvements in the presence of CCI and ACI.