Fuzzy Markov Model Based on FCM for Electromagnetic Environment Parameters Prediction

摘要

It is an important basis for spectrum management to predict accurately the change trend of parameters in electromagnetic environment, which can help decision makers to develop the optimal action for reducing risk and improving the economic and social benefits. Markov prediction model as a heuristic method is widely used in nonlinear systems. For two shortages in traditional Markov model, this paper puts forward a new fuzzy Markov model based on FCM, in which, FCM algorithm is used to divide time series into a serial fuzzy states, the membership function is employed to calculate membership vector for each object about every fuzzy state. Then, using membership vector of predictive point as the weights, calculating predictive value by clustering center. Finally, the prediction model proposed in this paper is applied to predict indicate parameters in electromagnetic environment. The experimental results showed that the prediction model proposed in this paper is not only reasonable, effective, and also the prediction accuracy significantly improved.