Data Fusion in Wireless Sensor Networks: A statistical signal processing perspective
- Length: 352 pages
- Edition: 1
- Language: English
- Publisher: The Institution of Engineering and Technology
- Publication Date: 2019-05-06
- ISBN-10: 178561584X
- ISBN-13: 9781785615849
- Sales Rank: #0 (See Top 100 Books)
The role of data fusion has been expanding in recent years through the incorporation of pervasive applications, where the physical infrastructure is coupled with information and communication technologies, such as wireless sensor networks for the internet of things (IoT), e-health and Industry 4.0. In this edited reference, the authors provide advanced tools for the design, analysis and implementation of inference algorithms in wireless sensor networks.
The book is directed at the sensing, signal processing, and ICTs research communities. The contents will be of particular use to researchers (from academia and industry) and practitioners working in wireless sensor networks, IoT, E-health and Industry 4.0 applications who wish to understand the basics of inference problems. It will also be of interest to professionals, and graduate and PhD students who wish to understand the fundamental concepts of inference algorithms based on intelligent and energy-efficient protocols.
Cover Title Copyright Contents About the editors List of contributors Introduction Part I Sensing model uncertainty 1 Generalized score-tests for decision fusion with sensing model uncertainty 1.1 Uncertainty in decision fusion sensing model 1.2 Problem statement 1.2.1 Sensing model 1.2.2 Local processing and reporting 1.2.3 Resulting hypothesis testing 1.2.4 Background on clairvoyant LLR 1.3 Design of generalized score tests 1.3.1 Counting rule (CR) and GLRT 1.3.2 Generalized score tests 1.3.3 Computational complexity 1.4 Quantizer design 1.5 Conclusions and further reading A.1 Appendix: Sketch of generalized score tests derivation References 2 Compressed distributed detection and estimation 2.1 Introduction 2.2 Compressive sensing: background 2.3 Compressed detection 2.3.1 CS-based detection of known deterministic signals in the presence of iid noise 2.3.2 CS-based detection of unknown sparse signals in the presence of iid noise 2.3.3 CS-based detection of random Gaussian signals in the presence of iid noise 2.3.4 CS-based detection with multimodal data with arbitrary pdfs 2.4 Compressed parameter estimation 2.4.1 Parameter estimation with compressed data with iid Gaussian noise 2.4.2 Parameter estimation with compressed data with general Gaussian model 2.5 Summary References 3 Heterogeneous sensor data fusion by deep learning 3.1 Introduction 3.2 Challenges in heterogeneous sensor data fusion 3.2.1 Compressive representation learning 3.2.2 Missing data imputation 3.2.3 Inter- and intra-modal correlations 3.3 Deep learning techniques for heterogeneous sensor data fusion 3.3.1 Stacked autoencoder 3.3.2 Deep multimodal encoder 3.3.3 More neural network architectures 3.4 A case study 3.4.1 Dataset 3.4.2 Data preprocessing 3.4.3 Task 1: sensor data compression and reconstruction 3.4.4 Task 2: missing data imputation 3.5 Summary Acknowledgments References Part II Reporting channel uncertainty 4 Energy-efficient clustering and collision-aware distributed detection/estimation in random-access-based WSNs 4.1 Clustering in wireless sensor networks 4.1.1 Communication cost in multi-hop multilevel clusters 4.1.2 Optimal probabilities of electing clusterheads 4.2 Histogram-frame-based random access 4.2.1 System model 4.2.2 Protocol description 4.2.3 Mathematical model 4.3 Collision-aware fusion rule for distributed detection in a simple binary hypothesis testing problem 4.4 Collision-aware fusion rule for distributed detection in a composite hypothesis testing problem 4.5 Collision-aware fusion rule for distributed estimation 4.6 Conclusions and extensions References 5 Channel-aware decision fusion in MIMO wireless sensor networks 5.1 MIMO decision fusion 5.2 MIMO decision fusion with instantaneous CSI 5.2.1 Decode-and-fuse approaches 5.2.2 Decode-then-fuse approaches 5.2.3 Performance comparison 5.3 MIMO decision fusion with statistical CSI 5.3.1 LLR test 5.3.2 Energy test 5.3.3 Asymptotic performance of LLR and energy tests 5.3.4 Performance analysis 5.4 Conclusion References 6 Channel-aware detection and estimation in the massive MIMO regime 6.1 Introduction 6.2 System model 6.2.1 WSN model 6.2.2 Channel training and estimation 6.2.3 Favorable propagation 6.3 Inference in massive MIMO regime 6.3.1 Fusion techniques for HT 6.3.2 Fusion techniques for EST 6.4 Asymptotic performance analysis and optimization 6.4.1 Performance measures for HT 6.4.2 Performance measures and power-allocation for EST 6.5 Conclusions and further reading References Part III Distributed inference over graphs 7 Decentralized detection via running consensus 7.1 Introduction 7.1.1 The estimation problem 7.1.2 The detection problem 7.1.3 Asymptotic optimality criteria of running consensus in hypothesis testing problems 7.2 Hypothesis testing in sensor networks with running consensus 7.3 Asymptotic performance 7.3.1 Fixed sample size test 7.3.2 Sequential detection 7.4 Numerical examples 7.4.1 Fixed sample size test 7.4.2 Sequential test 7.5 Conclusions References 8 Distributed recursive testing of composite hypothesis in multi-agent networks 8.1 Introduction 8.1.1 Related work 8.1.2 Organization 8.1.3 Notation 8.1.4 Spectral graph theory 8.2 Problem formulation 8.2.1 System model and preliminaries 8.2.2 Preliminaries: generalized likelihood ratio tests 8.3 Distributed generalized likelihood ratio testing 8.3.1 Algorithm CIGLRT: consensus+innovations GLRT 8.3.2 Simplified model for CIGLRT 8.4 Main results: CIGLRT 8.5 Simulation experiments 8.6 Discussions and future directions References 9 Expectation–maximisation based distributed estimation in sensor networks 9.1 Introduction 9.2 The EM algorithm 9.3 Linear parameter estimation with anomalous data 9.4 Distributed routing-based approaches 9.4.1 Distributed forward–backward implementation 9.4.2 Distributed cyclic implementation 9.5 A distributed consensus-based approach 9.5.1 Distributed consensus basics 9.5.2 Distributed consensus-based EM algorithm 9.6 Distributed implementation based on consensus filters 9.6.1 Linear time-invariant consensus filter 9.6.2 Linear time-varying consensus filter 9.7 Numerical examples 9.8 Concluding remarks References Part IV Cross-layer issues 10 Distributed estimation in energy harvesting wireless sensor networks 10.1 Introduction 10.2 Related works and further readings 10.3 Distributed estimation in energy-harvesting wireless sensor networks 10.3.1 Maximum likelihood estimation for the case with no batteries at the sensors 10.3.2 Maximum likelihood estimation for the case with battery-enabled sensors 10.4 Deployment of energy harvesting sensors for distributed estimation 10.4.1 Optimization of sensor densities and energy thresholds 10.4.2 Solution for Bernoulli energy arrival case 10.4.3 Computer simulations and performance comparisons 10.5 Conclusion References 11 Secure estimation in wireless sensor networks in the presence of an eavesdropper 11.1 Introduction 11.2 Estimation with security constraints 11.2.1 Multiple antennas scenario 11.2.2 Multiple sensors scenario 11.2.3 Numerical results 11.3 Estimation with secrecy outage constraints 11.3.1 Multiple sensors scenario 11.3.2 Single sensor with multiple antennas scenario 11.3.3 Numerical results 11.4 Conclusion References 12 Robust fusion of unreliable data sources using error-correcting output codes 12.1 Introduction 12.1.1 Distributed inference networks 12.1.2 Byzantine generals problem 12.2 Error-correcting output codes for data fusion 12.3 Inference in parallel networks 12.3.1 Distributed classification 12.3.2 Target localization 12.4 Inference in tree networks 12.4.1 Distributed classification 12.4.2 Distributed estimation 12.5 Classification using crowdsourced data 12.6 Discussion Acknowledgments References 13 Conclusions and future perspectives Index
Donate to keep this site alive
1. Disable the AdBlock plugin. Otherwise, you may not get any links.
2. Solve the CAPTCHA.
3. Click download link.
4. Lead to download server to download.