Massive multiple-input multiple-output (MIMO) wireless communications refers to the idea equipping cellular base stations (BSs) with a very large number of antennas, and has been shown to potentially allow for orders of magnitude improvement in spectral and energy efficiency using relatively simple (linear) processing. In this paper, we present a comprehensive overview of state-of-the-art research on the topic, which has recently attracted considerable attention. We begin with an information theoretic analysis to illustrate the conjectured advantages of massive MIMO, and then we address implementation issues related to channel estimation, detection and precoding schemes. We particularly focus on the potential impact of pilot contamination caused by the use of non-orthogonal pilot sequences by users in adjacent cells. We also analyze the energy efficiency achieved by massive MIMO systems, and demonstrate how the degrees of freedom provided by massive MIMO systems enable efficient single-carrier transmission. Finally, the challenges and opportunities associated with implementing massive MIMO in future wireless communications systems are discussed.

/pdf/an-overview-of-massive-mimo-benefits-and-challenges-5e3yrz2gcj.pdf

An Overview of Massive MIMO: Benefits and Challenges

There is considerable pressure to define the key requirements of 5G, develop 5G standards, and perform technology trials as quickly as possible. Normally, these activities are best done in series but there is a desire to complete these tasks in parallel so that commercial deployments of 5G can begin by 2020. 5G will not be an incremental improvement over its predecessors; it aims to be a revolutionary leap forward in terms of data rates, latency, massive connectivity, network reliability, and energy efficiency. These capabilities are targeted at realizing high-speed connectivity, the Internet of Things, augmented virtual reality, the tactile internet, and so on. The requirements of 5G are expected to be met by new spectrum in the microwave bands (3.3-4.2 GHz), and utilizing large bandwidths available in mm-wave bands, increasing spatial degrees of freedom via large antenna arrays and 3-D MIMO, network densification, and new waveforms that provide scalability and flexibility to meet the varying demands of 5G services. Unlike the one size fits all 4G core networks, the 5G core network must be flexible and adaptable and is expected to simultaneously provide optimized support for the diverse 5G use case categories. In this paper, we provide an overview of 5G research, standardization trials, and deployment challenges. Due to the enormous scope of 5G systems, it is necessary to provide some direction in a tutorial article, and in this overview, the focus is largely user centric, rather than device centric. In addition to surveying the state of play in the area, we identify leading technologies, evaluating their strengths and weaknesses, and outline the key challenges ahead, with research test beds delivering promising performance but pre-commercial trials lagging behind the desired 5G targets.

5G : A tutorial overview of standards, trials, challenges, deployment, and practice

tions. Bootstrap has found many applications in engineering field, including artificial neural networks, biomedical engineering, environmental engineering, image processing, and radar and sonar signal processing. Basic concepts of the bootstrap are summarized in each section as a step-by-step algorithm for ease of implementation. Most of the applications are taken from the signal processing literature. The principles of the bootstrap are introduced in Chapter 2. Both the nonparametric and parametric bootstrap procedures are explained. Babu and Singh (1984) have demonstrated that in general, these two procedures behave similarly for pivotal (Studentized) statistics. The fact that the bootstrap is not the solution for all of the problems has been known to statistics community for a long time; however, this fact is rarely touched on in the manuscripts meant for practitioners. It was first observed by Babu (1984) that the bootstrap does not work in the infinite variance case. Bootstrap Techniques for Signal Processing explains the limitations of bootstrap method with an example. I especially liked the presentation style. The basic results are stated without proofs; however, the application of each result is presented as a simple step-by-step process, easy for nonstatisticians to follow. The bootstrap procedures, such as moving block bootstrap for dependent data, along with applications to autoregressive models and for estimation of power spectral density, are also presented in Chapter 2. Signal detection in the presence of noise is generally formulated as a testing of hypothesis problem. Chapter 3 introduces principles of bootstrap hypothesis testing. The topics are introduced with interesting real life examples. Flow charts, typical in engineering literature, are used to aid explanations of the bootstrap hypothesis testing procedures. The bootstrap leads to second-order correction due to pivoting; this improvement in the results due to pivoting is also explained. In the second part of Chapter 3, signal processing is treated as a regression problem. The performance of the bootstrap for matched filters as well as constant false-alarm rate matched filters is also illustrated. Chapters 2 and 3 focus on estimation problems. Chapter 4 introduces bootstrap methods used in model selection. Due to the inherent structure of the subject matter, this chapter may be difficult for nonstatisticians to follow. Chapter 5 is the most impressive chapter in the book, especially from the standpoint of statisticians. It provides real data bootstrap applications to illustrate the theory covered in the earlier chapters. These include applications to optimal sensor placement for knock detection and land-mine detection. The authors also provide a MATLAB toolbox comprising frequently used routines. Overall, this is a very useful handbook for engineers, especially those working in signal processing.

Probability and Random Processes

In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to encode large-scale data and to maneuver billions of model parameters. However, it is a challenge to deploy these cumbersome deep models on devices with limited resources, e.g., mobile phones and embedded devices, not only because of the high computational complexity but also the large storage requirements. To this end, a variety of model compression and acceleration techniques have been developed. As a representative type of model compression and acceleration, knowledge distillation effectively learns a small student model from a large teacher model. It has received rapid increasing attention from the community. This paper provides a comprehensive survey of knowledge distillation from the perspectives of knowledge categories, training schemes, teacher-student architecture, distillation algorithms, performance comparison and applications. Furthermore, challenges in knowledge distillation are briefly reviewed and comments on future research are discussed and forwarded.

Knowledge Distillation: A Survey

Approximate computing has recently emerged as a promising approach to energy-efficient design of digital systems. Approximate computing relies on the ability of many systems and applications to tolerate some loss of quality or optimality in the computed result. By relaxing the need for fully precise or completely deterministic operations, approximate computing techniques allow substantially improved energy efficiency. This paper reviews recent progress in the area, including design of approximate arithmetic blocks, pertinent error and quality measures, and algorithm-level techniques for approximate computing.

/pdf/approximate-computing-an-emerging-paradigm-for-energy-z7hetfdl3q.pdf

Approximate computing: An emerging paradigm for energy-efficient design

Techniques for recovering a desired transmission in the presence of interfering transmissions are described. 
Method and apparatus are disclosed for performing data detection on a received signal to obtain a detected signal for a first set of code channels; 
reconstructing a signal for the first set of code channels based on the detected signal; 
canceling the reconstructed signal for the first set of code channels from the received signal; and 
performing data detection, reconstruction, and cancellation for at least one additional set of code channels.

Successive multi-user detection for wireless communication

Efficient implementation of deep neural networks on CPU-based systems is very critical because applications proliferate to embedded and Internet of Things (IoT) systems. Many CPUs for personal computers and embedded systems equip Single Instruction Multiple Data (SIMD) instructions, which can be utilized to implement an efficient GEneral Matrix Multiply (GEMM) library that is very necessary for efficient deep neural network implementation. While many deep neural networks show quite good performance even at 1-bit or 2-bit precision, the current CPU instruction and library do not efficiently support arithmetic operations below 8-bit. We propose TernGEMM, a special GEMM library using SIMD instructions for Deep Neural Network (DNN) inference with ternary weights and activations under 8-bit. TernGEMM improves the speed by replacing slow multiply-add with logical operations and also accumulating a number of multiplications without bit expansion operations. We compared the speedup of TernGEMM with tiling optimization and GEMMLowp, an 8-bit precision GEMM library. For Intel CPU, the speedup of ×2.052, ×2.973, and ×2.986 is achieved on ResNet-50, MobileNet-V2, EfficientNet-B0, respectively. For ARM CPU, TernGEMM’s speedup is ×2.143, ×1.765, and ×1.856, respectively.

TernGEMM: GEneral Matrix Multiply Library with Ternary Weights for Fast DNN Inference

We investigate the weighted-sum distortion minimization problem in transmitting two correlated Gaussian sources over Gaussian channels using two energy harvesting nodes. To this end, we develop offline and online power control policies to optimize the transmit power of the two nodes. In the offline case, we cast the problem as a convex optimization and investigate the structure of the optimal solution. We also develop a generalized water-filling based power allocation algorithm to obtain the optimal solution efficiently. For the online case, we quantify the distortion of the system using a cost function and show that the expected cost equals the expected weighted-sum distortion. Based on Banach's fixed point theorem, we further propose a geometrically converging algorithm to find the minimum cost via simple iterations. Simulation results show that our online power control outperforms the greedy power control where each node uses all the available energy in each slot and performs close to that of the proposed offline power control. Moreover, the performance of our offline power control almost coincides with the performance limit of the system.

Optimal Power Control for Transmitting Correlated Sources with Energy Harvesting Constraints

With the emergence of 5G era, network slicing has received much attention due to its ability to support various services. Network slicing is an approach to partition a single physical network into multiple slices supporting separate services and has been extended to the handover scenario (where the UE moves from one cell to another) recently. In this paper, we propose a deep reinforcement learning (DRL)-based handover-aware network slicing technique for the cell selection and network slicing. Key ingredient of the proposed technique is to use action elimination to reduce the size of slice allocation decision space. In our work, we first determine the target cell providing the maximum user-requested services to the handover UE, and then assign network slices to the handover UE by exploiting action elimination-assisted DRL. From the numerical results, we demonstrate that the proposed technique outperforms the conventional network slicing techniques in terms of throughput.

Action Elimination-assisted Deep Reinforcement Learning for B5G Cell Selection and Network Slicing

Recently, greedy algorithm has received much attention as a cost-effective means to reconstruct the sparse signals from compressed measurements. Much of previous work has focused on the investigation of a single candidate to identify the support (index set of nonzero elements) of the sparse signals. Well-known drawback of the greedy approach is that the chosen candidate is often not the optimal solution due to the myopic decision in each iteration. In this paper, we propose a greedy sparse recovery algorithm investigating multiple promising candidates via the tree search. Two key ingredients of the proposed algorithm, referred to as the matching pursuit with a tree pruning (TMP), to achieve efficiency in the tree search are the {\it pre-selection} to put a restriction on columns of the sensing matrix to be investigated and the {\it tree pruning} to eliminate unpromising paths from the search tree. In our performance guarantee analysis and empirical simulations, we show that TMP is effective in recovering sparse signals in both noiseless and noisy scenarios.

Byonghyo Shim

Papers

Successive multi-user detection for wireless communication

TernGEMM: GEneral Matrix Multiply Library with Ternary Weights for Fast DNN Inference

Optimal Power Control for Transmitting Correlated Sources with Energy Harvesting Constraints

Action Elimination-assisted Deep Reinforcement Learning for B5G Cell Selection and Network Slicing

Greedy Sparse Signal Recovery with Tree Pruning.