Sharif Digital Repository

To enable a relevance feedback paradigm to evolve itself by users' feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic... 

In this paper, we try to develop and implement the HRV signal processing into a Field Programmable Gate Array (FPGA) for extracting this signals feature  

In this short paper, we study the deafness problem raised in the directional multi Gigabit transmission of IEEE 802.11ad standard which causes the devices to experience unequal chance of accessing the medium. We define three groups of Quasi-Omni (QO) antennas and propose two simple approaches to mitigate the deafness problem. Our simulation results show that the fairness increases up to 99% compared with current definition of IEEE 802.11ad which is less than 40%. © 2017 IEEE  

A novel burst correction coding for correction of bulk errors in block-based image coding is developed. The algorithm makes artificial correlation between image pixels that distorts the image. By choosing appropriate parameters, one can control this distortion to lie in acceptable ranges. Our method can exactly correct an erroneously decoded block when using lossless codecs. In the presence of lossy codecs, the algorithm encounters a processing error which makes a noisy image after correction. The Wiener filter is used to reduce this noise. Experimental results show that our method can correct corrupted large blocks in images; the ability that other previously reported approaches have not...