Brain is the controlling center of our body. With the advent of time, newer and newer brain diseases are being discovered. Thus, because of the variability of brain diseases, existing diagnosis or detection systems are becoming challenging and are still an open problem for research. Detection of brain diseases at an early stage can make a huge difference in attempting to cure them. In recent years, the use of artificial intelligence (AI) is surging through all spheres of science, and no doubt, it is revolutionizing the field of neurology. Application of AI in medical science has made brain disease prediction and detection more accurate and precise. In this study, we present a review on recent machine learning and deep learning approaches in detecting four brain diseases such as Alzheimer's disease (AD), brain tumor, epilepsy, and Parkinson's disease. 147 recent articles on four brain diseases are reviewed considering diverse machine learning and deep learning approaches, modalities, datasets etc. Twenty-two datasets are discussed which are used most frequently in the reviewed articles as a primary source of brain disease data. Moreover, a brief overview of different feature extraction techniques that are used in diagnosing brain diseases is provided. Finally, key findings from the reviewed articles are summarized and a number of major issues related to machine learning/deep learning-based brain disease diagnostic approaches are discussed. Through this study, we aim at finding the most accurate technique for detecting different brain diseases which can be employed for future betterment.
We propose and investigate a dual-hop cooperative relaying scheme using non-orthogonal multiple access (NOMA) (termed NOMA-RS), where two sources communicate with their corresponding destinations in parallel over the same frequency band via a common relay. In this scheme, after receiving symbols transmitted in parallel by both sources with different allocated powers, the relay forwards a super-position coded composite signal using NOMA to the destinations. One of the main benefits of NOMA-RS is that multiple (two) sources can share the same relay, unlike the previous works. Through the simulations and mathematical analysis, we demonstrate the effectiveness of the proposed protocol in terms of ergodic sum capacity by considering perfect and imperfect successive interference cancellation.
15 September 2016 in Wireless Communications and Mobile Computing
In this paper, a full-duplex (FD) non-orthogonal multiple access (NOMA) scheme for a cooperative relay sharing network (termed as FD-NOMA-RS) is presented, in which two source-destination pairs share a dedicated FD relay FD-R. Following the principle of uplink NOMA, both sources transmit their symbols to FD-R, forming a NOMA pair, by depending on their channel conditions with respect to FD-R. The FD-R then decodes these symbols and simultaneously transmits a superimposed composite signal to the destinations with a processing delay $\tau$ according to the principle of downlink NOMA. The ergodic sum capacity, outage probability and outage sum capacity of FD-NOMA-RS are investigated comprehensively along with analytical derivations, considering both perfect and imperfect interference cancellation. A simulation is conducted to corroborate the correctness of the analysis presented here. Moreover, the effectiveness of FD-NOMA-RS is demonstrated through analysis and simulation and then compared with that of its counterpart, the half-duplex system.
4 December 2017 in IEEE Wireless Communications Letters
A coordinated direct and relay transmission is proposed using uplink non-orthogonal multiple access (NOMA) (termed as UP-NOMA). A two-user uplink NOMA scenario is considered, where a cell-center user directly communicates with a base station (BS), whereas a cell-edge user needs the assistance of a half-duplex decode-and-forward relay to communicate with the BS. The ergodic sum capacity of UP-NOMA is analyzed under both perfect and imperfect successive interference cancellation. The superiority of UP-NOMA over conventional multiple access is demonstrated through simulation and analysis.
This letter proposes a strategy to efficiently utilize the spectrum of unpaired users in non-orthogonal multiple access (NOMA) systems. This is done by pairing multiple similar gain users to a single distant user in a nonoverlapping frequency band pairing fashion. We consider a case where the number of far users in a cell is larger than the number of near users. Thus, some far users cannot be paired and should get data using conventional multiple access (OMA). In such case, we propose a strategy where a near user can be paired with multiple (two) far users to optimally utilize the spectrum of unpaired users in the NOMA system. Performance of the proposed pairing scheme is evaluated in terms of ergodic sum capacity over independent Rayleigh flat fading channel. Analytical and simulation results show that significant increase in the capacity gain of the system is achieved by using the proposed strategy compared to OMA and conventional NOMA.