The objective of the study is to assess the hearing performance of cochlear implant users in three device microphone configurations: omni-directional, directional, and beamformer (BEAMformer two-adaptive noise reduction system), in localization and speech perception tasks in dynamically changing listening environments. Seven cochlear implant users aided with Cochlear CM-24 devices with Freedom speech processor participated in the study. For the localization test in quiet and in background noise, subjects demonstrated significant differences between different microphone settings. Confusion matrices showed that in about 70% cases cochlear implant subjects correctly localized sounds within a horizontal angle of 30-40◦ (±1◦ loudspeaker apart from signal source). However localization in noise was less accurate as shown by a large number of considerable errors in localization in the confusion matrices. Average results indicated no significant difference between three microphone configurations. For speech presented from the front 3 dB SNR improvements in speech intelligibility in three subjects can be observed for beamforming system compared to directional and omni-directional microphone settings. The benefits of using different microphone settings in cochlear implant devices in dynamically changing listening conditions depend on the particular sound environment

Microphone array with minimum variance (MVDR) beamformer is a commonly used method for ambient noise suppression. Unfortunately, the performance of the MVDR beamformer is poor in a real reverberant room due to multipath wave propagation. To overcome this problem, we propose three improvements. Firstly, we propose end-fire microphone array that has been shown to have a better directivity index than the corresponding broadside microphone array. Secondly, we propose the use of unidirectional microphones instead of omnidirectional ones. Thirdly, we propose an adaptation of its adaptive algorithm during the pause of speech, which improves its robustness against the room reverberation and deviation from the optimal receiving direction. The performance of the proposed microphone array was theoretically analyzed using a diffuse noise model. Simulation analysis was performed for combined diffuse and coherent noise using the image model of the reverberant room. Real room tests were conducted using a four-microphone array placed in a small office room. The theoretical analysis and the real room tests showed that the proposed solution considerably improves speech quality.

Beamforming training (BT) is considered as an essential process to accomplish the communications in the millimeter wave (mmWave) band, i.e., 30 ~ 300 GHz. This process aims to find out the best transmit/receive antenna beams to compensate the impairments of the mmWave channel and successfully establish the mmWave link. Typically, the mmWave BT process is highly-time consuming affecting the overall throughput and energy consumption of the mmWave link establishment. In this paper, a machine learning (ML) approach, specifically reinforcement learning (RL), is utilized for enabling the mmWave BT process by modeling it as a multi-armed bandit (MAB) problem with the aim of maximizing the long-term throughput of the constructed mmWave link. Based on this formulation, MAB algorithms such as upper confidence bound (UCB), Thompson sampling (TS), epsilon-greedy (e-greedy), are utilized to address the problem and accomplish the mmWave BT process. Numerical simulations confirm the superior performance of the proposed MAB approach over the existing mmWave BT techniques.

With the advent of massive MIMO and mmWave, Antenna selection is the new frontier in hybrid beamforming employed in 5G base stations. Tele-operators are reworking on the components while upgrading to 5G where the antenna is a last-mile device. The burden on the physical layer not only demands smart and adaptive antennas but also an intelligent antenna selection mechanism to reduce power consumption and improve system capacity while degrading the hardware cost and complexity. This work focuses on reducing the power consumption and finding the optimal number of RF chains for a given millimeter wave massive MIMO system. At first, we investigate the power scaling method for both perfect Channel State Information (CSI) and imperfect CSI where the power is reduced by ��/���� and ��/√���� respectively. We further propose to reduce the power consumption by emphasizing on the subdued resolution of Analog-to-Digital Converters (ADCs) with quantization awareness. The proposed algorithm selects the optimal number of antenna elements based on the resolution of ADCs without compromising on the quality of reception. The performance of the proposed algorithm shows significant improvement when compared with conventional and random antenna selection methods.

An intelligent security model for the big data environment is presented in this paper. The proposed security framework is data sensitive in nature and the level of security offered is defined on the basis of the data secrecy standard. The application area preferred in this work is the healthcare sector where the amount of data generated through the digitization and aggregation of medical equipment’s readings and reports is huge. The handling and processing of this great amount of data has posed a serious challenge to the researchers. The analytical outcomes of the study of this data are further used for the advancement of the medical prognostics and diagnostics. Security and privacy of this data is also a very important aspect in healthcare sector and has been incorporated in the healthcare act of many countries. However, the security level implemented conventionally is of same level to the complete data which not a smart strategy considering the varying level of sensitivity of data. It is inefficient for the data of high sensitivity and redundant for the data of low sensitivity. An intelligent data sensitive security framework is therefore proposed in this paper which provides the security level best suited for the data of given sensitivity. Fuzzy logic decision making technique is used in this work to determine the security level for a respective sensitivity level. Various patient attributes are used to take the intelligent decision about the security level through fuzzy inference system. The effectiveness and the efficacy of the proposed work is verified through the experimental study.