A Novel Hybrid Cuckoo Search- Extreme Learning Machine Approach for Modulation Classification

• Published in: IEEE access Vol. 7; pp. 90525 - 90537
• Main Authors: Shah, Syed Ihtesham Hussain, Alam, Sheraz, Ghauri, Sajjad A., Hussain, Asad, Ahmed Ansari, Faraz
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; automatic modulation recognition; Birds; Classification; Classification algorithms; Cognitive radio; cuckoo search algorithm; Extreme learning machine; Fading channels; Feature extraction; Frequency shift keying; Gabor Features; Gabor filters; Machine learning; Modulation; Phase shift keying; Quadrature amplitude modulation; Search algorithms; Signal to noise ratio
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2926615

This paper presents a novel hybrid extreme learning machine (ELM) with cuckoo search algorithm (CSA) for the classification purposes of the digitally modulated signals, such as phase shift keying (PSK), frequency shift keying (FSK), and quadrature amplitude modulation (QAM). Nine modulation schemes having different orders have been considered for this paper. First, the Gabor filter is used to extract the key features from the received signal which are then optimized by the CSA. Finally, the ELM is used to classify the modulation schemes using these optimized features. Our proposed CSA-ELM approach is not only fast convergent and robust but also manifests improved percentage classification accuracy at low SNRs and lower sample size for both AWGN and Rayleigh fading channels.