Learn to Sense: A Meta-Learning-Based Sensing and Fusion Framework for Wireless Sensor Networks

Wireless sensor networks (WSNs) act as the backbone of Internet of Things (IoT) technology. In WSN, field sensing and fusion are the most commonly seen problems, which involve collecting and processing of a huge volume of spatial samples in an unknown field to reconstruct the field or extract its features. One of the major concerns is how to reduce the communication overhead and data redundancy with prescribed fusion accuracy. In this paper, an integrated communication and computation framework based on meta-learning is proposed to enable adaptive field sensing and reconstruction. It consists of a stochastic-gradient-descent (SGD)-based base-learner used for the field model prediction aiming to minimize the average prediction error, and a reinforcement meta-learner aiming to optimize the sensing decision by simultaneously rewarding the error reduction with samples obtained so far and penalizing the corresponding communication cost. An adaptive sensing algorithm based on the above two-layer meta-learning framework is presented. It actively determines the next most informative sensing location, and thus considerably reduces the spatial samples and yields superior performance and robustness compared with conventional schemes. The convergence behavior of the proposed algorithm is also comprehensively analyzed and simulated. The results reveal that the proposed field sensing algorithm significantly improves the convergence rate.

[1]  Songhwai Oh,et al.  Vision-Based Coordinated Localization for Mobile Sensor Networks , 2016, IEEE Transactions on Automation Science and Engineering.

[2]  Gamini Dissanayake,et al.  Information-Driven Adaptive Sampling Strategy for Mobile Robotic Wireless Sensor Network , 2016, IEEE Transactions on Control Systems Technology.

[3]  Deanna Needell,et al.  Stochastic gradient descent, weighted sampling, and the randomized Kaczmarz algorithm , 2013, Mathematical Programming.

[4]  Martin D. Buhmann,et al.  Radial Basis Functions: Theory and Implementations: Preface , 2003 .

[5]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[6]  R. Nowak,et al.  Backcasting: adaptive sampling for sensor networks , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[7]  Liam Paninski,et al.  Asymptotic Theory of Information-Theoretic Experimental Design , 2005, Neural Computation.

[8]  G. Evans,et al.  Learning to Optimize , 2008 .

[9]  Frank L. Lewis,et al.  Adaptive Sampling using Non-linear EKF with Mobile Robotic Wireless Sensor Nodes , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[10]  H. Wynn,et al.  Maximum entropy sampling and optimal Bayesian experimental design , 2000 .

[11]  Dan O. Popa,et al.  A distributed multi-robot adaptive sampling scheme for the estimation of the spatial distribution in widespread fields , 2012, EURASIP J. Wirel. Commun. Netw..

[12]  Tong Zhang,et al.  Solving large scale linear prediction problems using stochastic gradient descent algorithms , 2004, ICML.

[13]  Robert D. Nowak,et al.  Faster Rates in Regression via Active Learning , 2005, NIPS.

[14]  F. Gini,et al.  Dynamic underwater glider network for environmental field estimation , 2016, IEEE Transactions on Aerospace and Electronic Systems.

[15]  Urbashi Mitra,et al.  Boundary Estimation in Sensor Networks: Theory and Methods , 2003, IPSN.

[16]  FARHAD GHASSEMI,et al.  Separable Approximation for Solving the Sensor Subset Selection Problem , 2011, IEEE Transactions on Aerospace and Electronic Systems.

[17]  Stephen P. Boyd,et al.  Sensor Selection via Convex Optimization , 2009, IEEE Transactions on Signal Processing.

[18]  Tong Zhang,et al.  Stochastic Optimization with Importance Sampling , 2014, ArXiv.

[19]  Ronald J. Williams,et al.  Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning , 2004, Machine Learning.

[20]  Pascal Bianchi,et al.  Adaptive Sampling for Incremental Optimization Using Stochastic Gradient Descent , 2015, ALT.

[21]  Robert Nowak,et al.  Active Learning and Sampling , 2008 .

[22]  Jitendra Malik,et al.  Learning to Optimize Neural Nets , 2017, ArXiv.

[23]  H. Robbins.  A Stochastic Approximation Method , 1951 .

[24]  Marcin Andrychowicz,et al.  Learning to learn by gradient descent by gradient descent , 2016, NIPS.

[25]  Frank L. Lewis,et al.  EKF-based Adaptive Sampling with Mobile Robotic Sensor Nodes , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.