The Research Of Communication Signals Modulation Recognition Based On Neighborhood Rough Set

As rapid development of wireless communication technology, the environment of communication became more and more complicated. Communication modulation signals using various modulation styles on wide frequency band. Obviously, when the communication signals have different modulation styles, then the modulation parameters of these communication signals are not identical. How to monitor and recognize these signals effectively, which becomes a very important research topic on many fields. The purpose of communication signals automatic modulation recognition is to judge signal modulation styles and estimate signal modulation parameters on the precondition of unknown modulation information.The main work in this paper can be summarized as follows:1. This paper introduces some relation and basic knowledge of high-order cumulants firstly, then the algorithm for feature parameters selection is introduced. According to the seven kinds communication modulation signals studied in this paper, select a group of feature parameters (γmax,σap,σdp,σaa, σaf,R,C42) based on the time-frequency characteristics of communication signals. Experimental results proved that this group of parameters could distinguish these communication modulation signals effectively.2. The theory of Neighborhood Rough Set and the algorithm for attribute reduction based on Neighborhood Rough Set is introduced in detail. The algorithm not only can deal with discrete data, but also to deal with continuous data directly, and intuitive, easy to understand. This is the first time applied Neighborhood Rough Set to the research of modulation signals recognition, and achieved good results.3. Using Back-Propagation Network as classification instruments. Some experimental results of 2ASK,BPSK,2FSK,4ASK,QPSK.4FSK and 16QAM, which are collected factually, proved that the method proposed in this paper has better recognition effect compared with other methods.