Automatic Modulation Classification for OFDM Signals Based On Modified K-Means Clustering Algorithm

Automatic Modulation Classification (AMC) has attracted many researchers’ attention in different civilian and military purposes. This paper presents a novel modulation classification algorithm based on modified K-means cluster analysis. Generally, we aim to distinguish OFDM signals from single-carrier modulations. In this regard, two statistics of the amplitude of received signal are calculated as key features. The extracted features of training data points are submitted to the clustering algorithm and centers for single-carrier and multicarrier modulations are assessed. Afterwards, each point of testing dataset is dedicated to its nearest center based on Euclidian distance and the classification is accomplished. The simulation results demonstrate that the algorithm is beneficial in a wide range from low to high SNRs.

Automatic Modulation Classification for OFDM Signals Based On Modified K-Means Clustering Algorithm Keywords:

Classification Algorithms , Automatic Modulation Classification (AMC) , Orthogonal Frequency-Division Multiplexing (OFDM) , multicarrier (MC) modulations , single-carrier (SC) modulations