A New Approach for High Order MQAM Signal Modulation Recognition

摘要

In this paper, a new modulation recognition algorithm is proposed. Communication Signals are recognized and classified based on Clustering techniques. Proposed algorithm uses Clustering Validity Measures as a key features extracted from MQAM signals. Fuzzy C-mean Clustering (FCM) is applied on received MQAM signal to produce a membership matrix of different clusters. Clustering Validity Measures are applied on the membership function. Different MQAM signals have different values of Validity Measures. This feature recognizes most MQAM signals with high confidentiality. At low SNR cases, a neural network with a conjugate gradient Learning approach is utilized to enhance algorithm performance. Fletcher-Reeves learning approach can improve the speed and rate of convergence. Simulation results prove the validity of proposed algorithm. No prior information is needed using proposed algorithm. Misclassification rate is less for low order MQAM signals.