2016 IEEE International Conference of Online Analysis and Computing Science (ICOACS 2016)

91 / 2015-12-31 21:22:55

Fletcher-Reeves Learning approach for High Order MQAM Signal Modulation Recognition

Fletcher-Reeves Conjugate Gradient, Modulation Recognition, Fuzzy C-mean Clustering, Cluster validity Index, Partition Entropy, Partition Coefficient

a new method of Modulation Recognition of communication signals is proposed based on Clustering Validity Indices. These indices provide a good basis for key feature extraction. To distinguish different modulation schemes, a Fuzzy C-mean (FCM) clustering is used to get the membership matrix of different clusters. Then, a clustering validity measure is applied to extract features. To enhance clustering results at low SNR, a neural network with a conjugate gradient learning algorithm is utilized. Fletcher-Reeves learning approach enhances the recognition rate and widely improves the speed and rate of convergence. Simulation results show the validity of proposed approach compared with other approaches using only clustering or using back propagation neural networks. Misclassification rate is less for low order MQAM signals. When SNR is 4 dB the recognition rate is about 91%. This algorithm is applicable in high order MQAM signals. In Non-cooperative Communications, the modulated signal parameters are unknown. Some Modulation Recognition algorithms rely on estimating these parameters first, then applying recognition algorithms. Proposed algorithm doesn’t need any prior information to achieve modulation recognition.