Multi-sensor signal fusion-based modulation classification by using wireless sensor networks

Automatic modulation classification (AMC) is applied as the intermediate step between signal detection and demodulation to identify modulation schemes. AMC is a challenging task, especially in a non-cooperative environment, owing to the lack of prior information on the transmitted signal at the receiver. The proposed modulation classification scheme based on multi-sensor signal fusion makes the premise that the combined signal from multiple sensors provides a more accurate description than any one of the individual signals alone. Multi-sensor signal fusion offers increased reliability and huge processing gains in overall performance as compared with the single sensor, thus making AMC of weak signals in non-cooperative communication environment more reliable and successful. Signal-to-noise ratio improvement through multi-sensor signal fusion is studied by using second-order and fourth-order moments method. The classification performance based on multi-sensor signal fusion is investigated in the additive white Gaussian noise channel as well as the flat fading channel and is evaluated in terms of correct classification probability by taking the effects of timing synchronization, phase jitter, phase offset, and frequency offset into consideration, respectively. Through Monte Carlo simulations, we demonstrate that the proposed multi-sensor signal fusion-based AMC algorithm can greatly outperform other existing AMC methods.