A new approach for feature extraction using neural response has been developed in this paper through combining the hierarchical architectures with the sparse coding technique. As far as proposed layered model, at each layer of hierarchy, it concerned two components that were used are sparse coding and pooling operation. While the sparse coding was used to solve increasingly complex sparse feature representations, the pooling operation by comparing sparse outputs was used to measure the match between a stored prototype and the input sub-image. It is recommended that value of the best matching should be kept and discarding the others. The proposed model is implemented and tested taking into account two ranges of recognition tasks i.e. image recognition and speech recognition (on isolated word vocabulary). Experimental results with various parameters demonstrate that proposed scheme leads to extract more efficient features than other methods.

No abstract

Cooperative communication has been proposed recently in wireless communication systems because of its producing high network reliability and considerable error rate decrease with an extension in the coverage area in wireless networks without need for an increase in the infrastructure. The most challenging problem in implementing cooperation protocols in cooperative wireless networks is the relay selection. This paper proposes a relay selection technique based on Decode-and-Forward (DF) relaying protocol, using the available channel state information (CSI) at the source and the relays. We first establish a closed form symbol error rate (SER) by using the concept of moment generating function (MGF) for both M phase shift keying (MPSK) and M quadrature amplitude modulation (MQAM) signals. By finding the cumulative density function (CDF)and the probability density function (PDF); this facilitated the derivation of a new SER and can propose an optimal power method with relay selection (RS) technique where only the best relay is selected that maximizes the signal-to-noise ratio (SNR) to achieve the transmission process and develop the performance of the system. Finally, simulation results provided good confirmation of the theoretical analysis.

No abstract

No abstract