Reconstruction and classification of wireless signals based on compressive sensing approach

The procedure for the classification and reconstruction of randomly under-sampled signals transmitted through the communication channel, is proposed in this paper. The focus of this work is on the wireless communication signals that operate in the same frequency band and may interfere with each other. In the first stage, the separation of signal components is done by applying the concept of eigenvalue decomposition. Next, the compressive sensing approach is used to reduce the number of transmitted samples and to provide accurate signal reconstruction upon transmission. In the last step, the classification is done by observing the time-frequency characteristics of reconstructed separated components. The theory is proved by the experimental results.