scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Performance Analysis on Machine Learning-Based Channel Estimation

25 May 2021-IEEE Transactions on Communications (Institute of Electrical and Electronics Engineers (IEEE))-Vol. 69, Iss: 8, pp 5183-5193
TL;DR: In this article, the authors investigated the mean square error (MSE) performance of machine learning-based channel estimation in orthogonal frequency division multiplexing (OFDM) systems and derived a clear analytical relation between the size of the training data and performance.
Abstract: Recently, machine learning-based channel estimation has attracted much attention. The performance of machine learning-based estimation has been validated by simulation experiments. However, little attention has been paid to the theoretical performance analysis. In this paper, we investigate the mean square error (MSE) performance of machine learning-based estimation. Hypothesis testing is employed to analyze its MSE upper bound. Furthermore, we build a statistical model for hypothesis testing, which holds when the linear learning module with a low input dimension is used in machine learning-based channel estimation, and derive a clear analytical relation between the size of the training data and performance. Then, we simulate the machine learning-based channel estimation in orthogonal frequency division multiplexing (OFDM) systems to verify our analysis results. Finally, the design considerations for the situation where only limited training data is available are discussed. In this situation, our analysis results can be applied to assess the performance and support the design of machine learning-based channel estimation.
Citations
More filters
Posted Content
TL;DR: In this paper, the authors proposed a new channel estimation method with the assistance of deep learning in order to support the least square estimation, which is a low-cost method but having relatively high channel estimation errors.
Abstract: Deep learning has demonstrated the important roles in improving the system performance and reducing computational complexity for $5$G-and-beyond networks. In this paper, we propose a new channel estimation method with the assistance of deep learning in order to support the least squares estimation, which is a low-cost method but having relatively high channel estimation errors. This goal is achieved by utilizing a MIMO (multiple-input multiple-output) system with a multi-path channel profile used for simulations in the 5G networks under the severity of Doppler effects. Numerical results demonstrate the superiority of the proposed deep learning-assisted channel estimation method over the other channel estimation methods in previous works in terms of mean square errors.

3 citations

Journal ArticleDOI
TL;DR: In this article , the authors comprehensively survey AI-based channel estimation for multicarrier systems and discuss current challenges and point out future research directions based on recent findings, including reinforcement learning, classical learning, neural networks, and reinforcement learning.
Abstract: Abstract Multicarrier modulation allows for deploying wideband systems resilient to multipath fading channels, impulsive noise, and intersymbol interference compared to single-carrier systems. Despite this, multicarrier signals suffer from different types of distortion, including channel noise sources and long- and short-term fading. Consequently, the receiver must estimate the channel features and compensate it for data recovery based on channel estimation techniques, such as non-blind, blind, and semi-blind approaches. These techniques are model-based and designed with accurate mathematical channel models encompassing their features. Nevertheless, complex environments challenge accurate mathematical channel estimation modeling, which might neither be accurate nor correspond to reality. This impairment decreases the system performance due to the channel estimation accuracy loss. Fortunately, (AI) algorithms can learn the relationship among different system variables using a model-driven or model-free approach. Thereby, AI algorithms are used for channel estimation by exploiting its complexity without unrealistic assumptions, following a better performance than conventional techniques under the same channel. Hence, this paper comprehensively surveys AI-based channel estimation for multicarrier systems. First, we provide essential background on conventional channel estimation techniques in the context of multicarrier systems. Second, the AI-aided channel estimation strategies are investigated using the following approaches: classical learning, neural networks, and reinforcement learning. Lastly, we discuss current challenges and point out future research directions based on recent findings.

3 citations

Journal ArticleDOI
TL;DR: In this paper , a comprehensive overview of channel estimation techniques for 5G communication networks is presented, with a comprehensive review of the coordinated multipoint (CoMP) strategies in 5G radio networks, and its reliance on channel state information (CSI).
Abstract: New enabling technologies that include millimeter wave (mmWave) communication, massive multiple-input-multiple-output (MIMO), and ultradense networks are set to transform the wireless communication systems. These emerging technologies contribute toward the evolution of fifth generation (5G) systems that promise greater connectivity, throughput, mobility, and reliability for communication networks. This article presents a comprehensive overview of techniques for channel estimation, particularly, frequency division duplex (FDD)-based estimation techniques for a communication network. An exhaustive literature survey of FDD-based estimation schemes is presented, with a comprehensive review of the coordinated multipoint (CoMP) strategies in 5G radio networks, and its reliance on acquisition of channel state information (CSI). Since accurate CSI promotes the adoption of channel precoding, and reliable signal detection in FDD-based 5G systems, therefore, channel estimation for CSI in conjunction with CoMP transmission is preferable. We also present future research directions for FDD-based channel estimation and CoMP in 5G.

1 citations

Journal ArticleDOI
TL;DR: In this paper , a channel estimation method based on deep learning was proposed for mmWave massive MIMO systems, which can directly estimate channel state information (CSI) from received data without performing pilot signals estimate in advance, which simplifies the estimation process.
References
More filters
Book
18 Nov 2016
TL;DR: Deep learning as mentioned in this paper is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts, and it is used in many applications such as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames.
Abstract: Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all the knowledge that the computer needs. The hierarchy of concepts allows the computer to learn complicated concepts by building them out of simpler ones; a graph of these hierarchies would be many layers deep. This book introduces a broad range of topics in deep learning. The text offers mathematical and conceptual background, covering relevant concepts in linear algebra, probability theory and information theory, numerical computation, and machine learning. It describes deep learning techniques used by practitioners in industry, including deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology; and it surveys such applications as natural language processing, speech recognition, computer vision, online recommendation systems, bioinformatics, and videogames. Finally, the book offers research perspectives, covering such theoretical topics as linear factor models, autoencoders, representation learning, structured probabilistic models, Monte Carlo methods, the partition function, approximate inference, and deep generative models. Deep Learning can be used by undergraduate or graduate students planning careers in either industry or research, and by software engineers who want to begin using deep learning in their products or platforms. A website offers supplementary material for both readers and instructors.

38,208 citations

Book
28 Jul 2013
TL;DR: In this paper, the authors describe the important ideas in these areas in a common conceptual framework, and the emphasis is on concepts rather than mathematics, with a liberal use of color graphics.
Abstract: During the past decade there has been an explosion in computation and information technology. With it have come vast amounts of data in a variety of fields such as medicine, biology, finance, and marketing. The challenge of understanding these data has led to the development of new tools in the field of statistics, and spawned new areas such as data mining, machine learning, and bioinformatics. Many of these tools have common underpinnings but are often expressed with different terminology. This book describes the important ideas in these areas in a common conceptual framework. While the approach is statistical, the emphasis is on concepts rather than mathematics. Many examples are given, with a liberal use of color graphics. It is a valuable resource for statisticians and anyone interested in data mining in science or industry. The book's coverage is broad, from supervised learning (prediction) to unsupervised learning. The many topics include neural networks, support vector machines, classification trees and boosting---the first comprehensive treatment of this topic in any book. This major new edition features many topics not covered in the original, including graphical models, random forests, ensemble methods, least angle regression and path algorithms for the lasso, non-negative matrix factorization, and spectral clustering. There is also a chapter on methods for ``wide'' data (p bigger than n), including multiple testing and false discovery rates. Trevor Hastie, Robert Tibshirani, and Jerome Friedman are professors of statistics at Stanford University. They are prominent researchers in this area: Hastie and Tibshirani developed generalized additive models and wrote a popular book of that title. Hastie co-developed much of the statistical modeling software and environment in R/S-PLUS and invented principal curves and surfaces. Tibshirani proposed the lasso and is co-author of the very successful An Introduction to the Bootstrap. Friedman is the co-inventor of many data-mining tools including CART, MARS, projection pursuit and gradient boosting.

19,261 citations

Book
16 Mar 2001

7,058 citations

Book
01 Jan 1959
TL;DR: The general decision problem, the Probability Background, Uniformly Most Powerful Tests, Unbiasedness, Theory and First Applications, and UNbiasedness: Applications to Normal Distributions, Invariance, Linear Hypotheses as discussed by the authors.
Abstract: The General Decision Problem.- The Probability Background.- Uniformly Most Powerful Tests.- Unbiasedness: Theory and First Applications.- Unbiasedness: Applications to Normal Distributions.- Invariance.- Linear Hypotheses.- The Minimax Principle.- Multiple Testing and Simultaneous Inference.- Conditional Inference.- Basic Large Sample Theory.- Quadratic Mean Differentiable Families.- Large Sample Optimality.- Testing Goodness of Fit.- General Large Sample Methods.

6,480 citations

01 Jan 1998

5,511 citations