概率图模型理论及其在通信中的应用 : 英文

本教材总体上分为基础理论和典型应用两个部分。在第一部分中，本教材以概率论、图论为基础，介绍了概率论和图论的相关概念和实例。随后引入贝叶斯网络、马尔科夫随机场、因子图等有向或无向概率图模型，给出基本的消息传递规则，得到了最基本的和积算法和最大和算法。进一步地，本教材依次介绍了概率图模型上的置信传播、近似消息传递、变分推断、混合消息传递等一系列推断算法。在此基础上，本教材重点分析了高斯置信传播的收敛特性。在第二部分中，首先介绍数字通信系统的基本结构，并针对数字通信系统中的信道均衡、信道估计、多用户检测、网络同步与定位等实际问题，详细介绍了采用概率图模型实现通信网络智能化的大量实例，实现了理论与应用的结合。

武楠，北京理工大学集成电路与电子学院教授，研究方向为空天通信网络理论与关键技术，全国高校黄大年式教师团队成员，曾获国家级教学成果一等奖（序6）、二等奖（序5）、北京市教学成果特等奖、一等奖、北京市高等学校青年教学名师奖、北京市教书育人榜样、北京高校优秀本科育人团队。发表学术论文100余篇，以第一/通讯作者发表SCI论文50余篇，Google Scholar引用1500余次，SCI引用900余次。发表《卫星通信接收机同步技术》等专著2部，《数字通信接收机同步、信道估计和信号处理》等译著4部。

Part I Theories of Probabilistic Graphical Models Chapter 1 Introduction 1.1 Probability Theory 1.1.1 Probability Distributions 1.1.2 Joint Distribution and Marginal Distribution 1.1.3 Basic Rules in Probability 1.1.4 Independence and Conditional Independence 1.1.5 Expectation and Covariance 1.2 Graph Theory 1.2.1 Graphs and Subgraphs 1.2.2 Paths and Connection 1.2.3 Cycles and Loops 1.3 Summary 1.4 Relevant Literatures Chapter 2 Graphical Models 2.1 Bayesian Networks 2.1.1 Independence Properties 2.1.2 Bayesian Networks 2.1.3 From Distributions to Graphs 2.2 Markov Random Fields 2.2.1 Markov Random Fields Definition 2.2.2 Factorization Properties 2.2.3 From Distributions to Graphs 2.2.4 Relation to Directed Graphs 2.3 Inference in Graphical Models 2.3.1 Factor Graphs 2.3.2 Messages and Their Representations 2.3.3 Sum-Product Algorithm and the Max-Sum Algorithm 2.3.4 Loopy Belief Propagation 2.4 Summary 2.5 Relevant Literatures Chapter 3 Approximate Inference Based on Message Passing 3.1 Gaussian Belief Propagation 3.2 Approximate Message Passing 3.2.1 Principle of Approximate Message Passing 3.2.2 Generalized Approximate Message Passing 3.2.3 Bilinear Generalized Approximate Message Passing 3.2.4 Vector Approximate Message Passing 3.2.5 Bilinear Vector Approximate Message Passing 3.3 Variational Inference 3.3.1 Principle of Variational Inference 3.3.2 Variational Message Passing 3.3.3 Expectation Propagation 3.4 Hybrid Message Passing Frameworks 3.5 Summary 3.6 Relevant Literatures Chapter 4 Convergence Analysis of Gaussian Belief Propagation 4.1 Gaussian Belief Propagation in Pairwise Graphical Model 4.2 Existence Conditions of Fixed Points for Gaussian BP 4.2.1 Convergence Analysis of Outgoing Messages' Precisions 4.2.2 Convergence Analysis of Outgoing Messages' Means 4.2.3 Relations to Convergence Conditions of Incoming Messages' Parameters 4.3 Gaussian Belief Propagation in Higher-Order Graphical Model 4.4 Summary 4.5 Relevant Literatures Part II Applications of Probabilistic Graphical Models in Digital Communication Chapter 5 Digital Communication 5.1 Single Carrier Communication 5.1.1 Phase Shift Keying 5.1.2 Quadrature Amplitude Modulation 5.2 Multicarrier Communication 5.2.1 Orthogonal Frequency Division Multiplexing 5.2.2 M -Modulation and Demodulation in OFDM Communication 5.3 Non -orthogonal Transmission 5.3.1 Faster than Nyquist Signaling: FTN 5.3.2 Spectrally Efficient Frequency Division Multiplexing: SEFDM 5.4 Summary 5.5 Relevant Literatures Chapter 6 Equalization 6.1 Time Domain Equalization 6.2 Frequency Domain Equalization 6.3 Equalization for Non -orthogonal Transmission 6.4 Summary 6.5 Relevant Literatures Chapter 7 Channel Estimation 7.1 Receivers for Frequency Selective Channels 7.1.1 Approximate Message Passing -Based Channel Estimator 7.1.2 Variational Message Passing -Based Channel Estimator 7.2 Receivers for Doubly Selective Channels 7.3 Receivers for Non -linear Channels 7.4 Summary 7.5 Relevant Literatures Chapter 8 Multi -user Detection 8.1 Direct -Sequence Code Division Multiple Access 8.1.1 Multi -user Detection for Asynchronous Transmission 8.1.2 Multi -user Detection for Synchronous Transmission 8.2 Orthogonal Frequency Division Multiple Access 8.3 Non -orthogonal Multiple Access 8.3.1 Joint Data and Active User Detection 8.3.2 Joint Channel Estimation, User Activity Tracking and Data Detection 8.4