Tarek Elfouly

Ahmed Badawy, Tamer Khattab, Daniele Trinchero et al.

We propose an intuitive, simple and hardware friendly, yet surprisingly novel and efficient, received signal's angle of arrival (AoA) estimation scheme. Our intuitive, two-phases cross-correlation based scheme relies on a switched beam antenna array, which is used to collect an omni-directional signal using few elements of the antenna array in the first phase. In the second phase, the scheme switches the main beam of the antenna array to scan the angular region of interest. The collected signal from each beam (direction or angle) is cross correlated with the omni-directional signal. The cross-correlation coefficient will be the highest at the correct AoA and relatively negligible elsewhere. The proposed scheme simplicity stems from its low computational complexity (only cross-correlation and comparison operations are required) and its independence of the transmitted signal structure (does not require information about the transmitted signal). The proposed scheme requires a receiver with switched beam antenna array, which can be attached to a single radio frequency chain through phase shifters, hence, its hardware friendliness. The high efficiency of our system can be observed by comparing its performance with the literature's best performing MUSIC algorithm. The comparison demonstrates that our scheme outperforms the MUSIC algorithm, specially at low SNR levels. Moreover, the number of sources that can be detected using our scheme is bound by the number of switched beams, rather than the number of antenna elements in the case of the MUSIC algorithm.

Ahmed Ben Said, Amr Mohamed, Tarek Elfouly et al.

In this paper, we present a joint compression and classification approach of EEG and EMG signals using a deep learning approach. Specifically, we build our system based on the deep autoencoder architecture which is designed not only to extract discriminant features in the multimodal data representation but also to reconstruct the data from the latent representation using encoder-decoder layers. Since autoencoder can be seen as a compression approach, we extend it to handle multimodal data at the encoder layer, reconstructed and retrieved at the decoder layer. We show through experimental results, that exploiting both multimodal data intercorellation and intracorellation 1) Significantly reduces signal distortion particularly for high compression levels 2) Achieves better accuracy in classifying EEG and EMG signals recorded and labeled according to the sentiments of the volunteer.