Data Fusion in Wireless Sensor Networks : a statistical signal processing perspective /
This book describes the advanced tools required to design state-of-the-art inference algorithms for inference in wireless sensor networks. Written for the signal processing, communications, sensors and information fusion research communities, it covers the emerging area of data fusion in wireless se...
| Other Authors: | , |
|---|---|
| Format: | Book |
| Language: | English |
| Published: |
Stevenage :
Institution of Engineering & Technology,
2019
|
| Series: | IET control, robotics and sensors series ;
117 |
| Subjects: |
Table of Contents:
- Intro; Contents; About the editors; List of contributors; Introduction; Part I. Sensing model uncertainty; 1. Generalized score-tests for decision fusion with sensing model uncertainty
- Domenico Ciuonzo, Pierluigi Salvo Rossi, and Peter Willett; 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 design1.5 Conclusions and further reading; A.1 Appendix: Sketch of generalized score tests derivation; References; 2. Compressed distributed detection and estimation
- Thakshila Wimalajeewa and Pramod K. Varshney; 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 pdfs2.4 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
- Zuozhu Liu, Wenyu Zhang, Shaowei Lin, and Tony Q.S. Quek; 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 fusion3.3.1 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
- Seksan Laitrakun, Deepa Phanish, and Edward J. Coyle
- 4.1 Clustering in wireless sensor networks4.1.1 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
- Domenico Ciuonzo and Pierluigi Salvo Rossi