Search

This article studies a reinforcement learning (RL) approach for beam tracking problems in millimeter-wave massive multiple-input multiple-output (MIMO) systems. Entire beam sweeping in traditional beam training problems is intractable due to prohibitive search overheads. To solve this issue, a partially observable Markov decision process (POMDP) formulation can be applied where decisions are made with partial beam sweeping. However, the POMDP cannot be straightforwardly addressed by existing RL approaches which are intended for fully observable environments. In this paper, we propose a deep recurrent Q-learning (DRQN) method which provides an efficient beam decision policy only with partial observations. Numerical results validate the superiority of the proposed method over conventional schemes.

In this work, we study codebook designs for full-dimension multiple-input multiple-output (FD-MIMO) systems with a multi-panel array (MPA). We propose novel codebooks which allow precise beam structures for MPA FD-MIMO systems by investigating the physical properties and alignments of the panels. We specifically exploit the characteristic that a group of antennas in a vertical direction exhibit more correlation than those in a horizontal direction. This enables an economical use of feedback bits while constructing finer beams compared to conventional codebooks. The codebook is further improved by dynamically allocating the feedback bits on multiple parts such as beam amplitude and co-phasing coefficients using reinforcement learning. The numerical results confirm the effectiveness of the proposed approach in terms of both performance and computational complexity.

We develop a solution-processable, Ag-sandwiched carbon-nanotube-coated, durable (SAND) architecture that enables power-efficient and highly consistent cyclic heating up to 400 °C at 6 V with neither structural degradation nor substrate breakage. The Ag/CNT/Ag-stacked SAND structure, comprising an airbrushed carbon nanotube (CNT) network layer sandwiched by the Ag layers reduced with ionic Ag ink coatings, can be created by a facile and scalable all-solution-processable fabrication protocol without resorting to vacuum-assisted nanofabrication. Through a systematic comparison with Ag-only and CNT/Ag- or Ag/CNT-bilayered structures, we show that the SAND architecture can improve the joule-heating efficiency and uniformity, and more importantly, the anti-breaking durability to overcome the thermal expansion discrepancy against the underlying substrate. This is analytically interpreted through a thermal stress-induced substrate breaking mechanism, where the increasing difference in the thermal expansion between the substrate and coated layers upon heating can be effectively suppressed within the SAND architecture. Readily applicable to more scalable, diverse substrates ranging from brittle glass to large-area polymer films, the SAND architecture can be utilized in the flexible and reliable anti-failure heating devices required in such applications as machine and vehicle components, sensor systems, and safety and warm-up gears.

Limited computing resources of internet-of-things (IoT) nodes incur prohibitive latency in processing input data. This triggers new research opportunities toward task offloading systems where edge servers handle intensive computations of IoT devices. Deploying the computing servers at existing base stations may not be sufficient to support IoT nodes operating in a harsh environment. This requests mobile edge servers to be mounted on unmanned aerial vehicles (UAVs) that provide on-demand mobile edge computing (MEC) services. Time-varying offloading demands and mobility of UAVs need a joint design of the optimization variables for all time instances. Therefore, an online decision mechanism is essential for UAV-aided MEC networks. This article presents an overview of recent deep reinforcement learning (DRL) approaches where decisions about UAVs and IoT nodes are taken in an online manner. Specifically, joint optimization over task offloading, resource allocation, and UAV mobility is addressed from the DRL perspective. For the decentralized implementation, a multi-agent DRL method is proposed where multiple intelligent UAVs cooperatively determine their computations and communication policies without central coordination. Numerical results demonstrate that the proposed decentralized learning strategy is superior to existing DRL solutions. The proposed framework sheds light on the viability of the decentralized DRL techniques in designing self-organizing IoT networks.

We study a deep learning (DL) based limited feedback methods for multi-antenna systems. Deep neural networks (DNNs) are introduced to replace an end-to-end limited feedback procedure including pilot-aided channel training process, channel codebook design, and beamforming vector selection. The DNNs are trained to yield binary feedback information as well as an efficient beamforming vector which maximizes the effective channel gain. Compared to conventional limited feedback schemes, the proposed DL method shows an 1 dB symbol error rate (SER) gain with reduced computational complexity.

We propose a preprocessing system that transforms the real world into 3D mesh virtual world to provide augmented reality (AR) services. The proposed system uses a monocular RGB camera to obtain sequential images to generate real space. First, we create 3D real-world space composed of point clouds using sequential color images. And then, we segment the objects in each color image and assign an identification number for each object. Also, we execute ‘3D point labeling’, which assigns identification numbers from 2D segmented object to 3D point cloud through a simple projection manner with several parameters. This process could collect 3D point cloud with same the label by as an object. Finally, only the 3D point clouds that have the same identification number by as an object are used to generate 3D mesh. This paper confirmed that 3D mesh could be created using the only general monocular camera without the help of special 3D sensors.