Mobile and wearable devices have enabled numerous applications, including activity tracking, wellness monitoring, and human–computer interaction, that measure and improve our daily lives. Many of these applications are made possible by leveraging the rich collection of low-power sensors found in many mobile and wearable devices to perform human activity recognition (HAR). Recently, deep learning has greatly pushed the boundaries of HAR on mobile and wearable devices. This paper systematically categorizes and summarizes existing work that introduces deep learning methods for wearables-based HAR and provides a comprehensive analysis of the current advancements, developing trends, and major challenges. We also present cutting-edge frontiers and future directions for deep learning-based HAR.

In this paper, a brief review of the multilevel inverter (MLI) topologies is presented. The two-level Voltage Source Inverter (VSI) requires a suitable filter to produce sinusoidal output waveforms. The high-frequency switching and the PWM method are used to create output waveforms with the least amount of ripples. Due to the switching losses, the traditional two-level inverter has some restrictions when running at high frequencies. For addressing this problem, multilevel inverters (MLI) with lower switching frequencies and reduced total harmonic distortion (THD) are employed, eliminating the requirement for filters and bulky transformers. Furthermore, improved performance at the high switching frequency, higher power quality (near to pure sinusoidal), and fewer switching losses are just a few of the benefits of MLI inverters. However, each switch has to have its own gate driver for implementing MLI, which adds to the system's complexity. Therefore, reducing the number of switches of MLI is necessary. This paper presents a review of some of the different current topologies using a lower number of switches. Doi: 10.28991/ESJ-2022-06-01-014 Full Text: PDF

No abstract

The use of beamforming technology in standalone (SA) millimeter wave communications results in directional transmission and reception modes at the mobile station (MS) and base station (BS). This results in initial beam access challenges, since the MS and BS are now compelled to perform spatial search to determine the best beam directions that return highest signal levels. The high number of signal measurements here prolongs access times and latencies, as well as increasing power and energy consumption. Hence this paper proposes a first study on leveraging deep learning schemes to simplify the beam access procedure in standalone mmWave networks. The proposed scheme combines bidirectional recurrent neural network (BRNN) and long short-term memory (LSTM) to achieve fast initial access times. Namely, the scheme predicts the best beam index for use in the next time step once a MS accesses the network, e.g., transition from sleep to active (or idle) modes. The scheme eliminates the need for beam scanning, thereby achieving ultra-low access times and energy efficiencies as compared to existing methods.

No abstract