Optimal Decision Fusion Based Automatic Modulation Classification by Using Wireless Sensor Networks in Multipath Fading Channel

Abstract

Automatic modulation classification (AMC) is deployed, as the intermediate step between signal detection and demodulation, to identify modulation schemes automatically.Modulation classification is a challenging task, especially in a noncooperative environment, owing to the lack of prior information on the transmitted signal at the receiver; the problem will be more challenging in the multipath fading channel. The proposed AMC method based on optimal decision fusion by using wireless sensor networks provides a more accurate classification result than any one of the individual signal alone. Wireless sensor networks offer increased reliability and optimal decision fusion provides huge gains in overall classification performance as compared to that of the single sensor. Thus, optimal decision fusion based AMC by using wireless sensor networks greatly enhances classification performance of weak signals in non-cooperative communication environment. Classification performances of optimal decision fusion based AMC by using wireless sensor networks in the multipath fading channel are investigated and evaluated in terms of correct classification probability. Through Monte Carlo simulations, we demonstrate that the proposed AMC algorithm can greatly outperform that of single sensor in multipath fading channel.

Decision fusion methods for automatic modulation classification with multiple sensors in multipath fading channels

“…Under the assumption that the variances for a different modulation formats are approximately the same, as previously used in defining classification thresholds values, [3]- [7], [10]- [12], the suboptimal JDF (SJDF) method can be defined with a corresponding decision rule given as,…”

“…By using maximum-likelihood criterion, optimal combining hard decision fusion (OCHDF) method is introduced in [10]. The fusion centre select as a final decision, M D , modulation format that is the most likely cause of the obtained set of decisions D, under SNR conditions defined with a set of SNR value estimates, SNR C .…”

“…The fusion centre select as a final decision, M D , modulation format that is the most likely cause of the obtained set of decisions D, under SNR conditions defined with a set of SNR value estimates, SNR C . OCHDF method, [10], is defined as,…”

“…The channel coefficients h(k), k=0,1,…,L-1 are randomly generated with parameter ı h =0.05, and w.l.o.g. h(0) is set to 1, in a same manner as in [3], [5]- [7], [10]- [11]. The AWGN channel is modeled as non-dispersive channel with L=1.…”

“…Likelihood-ratio based DF method that uses multiple sensors for discrimination between the two modulation types is given in [9]. An generalization of this DF method, that allows the classification of more than two modulation formats is given in [10], applied for QAM signals classification in the presence of multipath fading. Significant advantages compared to the single sensor scenario were displayed for the AMC algorithm described in [4].…”