A Learning-Based Approach to Confident Event Detection in Heterogeneous Sensor Networks

Wireless sensor network applications, such as those for natural disaster warning, vehicular traffic monitoring, and surveillance, have stringent accuracy requirements for detecting or classifying events and demand long system lifetimes. Through quantitative study, we show that existing event detection approaches are challenged to explore the sensing capability of a deployed system and choose the right sensors to meet user-specified accuracy. Event detection systems are also challenged to provide a generic system that efficiently adapts to environmental dynamics and works easily with a range of applications, machine learning approaches, and sensor modalities. Consequently, we propose Watchdog, a modality-agnostic event detection framework that clusters the right sensors to meet user-specified detection accuracy during runtime while significantly reducing energy consumption. Watchdog can use different machine learning techniques to learn the sensing capability of a heterogeneous sensor deployment and meet accuracy requirements. To address environmental dynamics and ensure energy savings, Watchdog wakes up and puts to sleep sensors as needed to meet user-specified accuracy. Through evaluation with real vehicle detection trace data and a building traffic monitoring testbed of IRIS motes, we demonstrate the superior performance of Watchdog over existing solutions in terms of meeting user-specified detection accuracy, energy savings, and environmental adaptability.

[1]  Matt Welsh,et al.  Simulating the power consumption of large-scale sensor network applications , 2004, SenSys '04.

[2]  Feng Zhao,et al.  Information-driven dynamic sensor collaboration , 2002, IEEE Signal Process. Mag..

[3]  Andreas Krause,et al.  A fresh perspective: Learning to sparsify for detection in massive noisy sensor networks , 2013, 2013 ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN).

[4]  Chenyang Lu,et al.  A Holistic Approach to Decentralized Structural Damage Localization Using Wireless Sensor Networks , 2008, 2008 Real-Time Systems Symposium.

[5]  Amy L. Murphy,et al.  Solving the Wake-Up Scattering Problem Optimally , 2009, EWSN.

[6]  Xin Jin,et al.  Diagnostic powertracing for sensor node failure analysis , 2010, IPSN '10.

[7]  Dusit Niyato,et al.  Sleep and Wakeup Strategies in Solar-Powered Wireless Sensor/Mesh Networks: Performance Analysis and Optimization , 2007, IEEE Transactions on Mobile Computing.

[8]  Andreas Krause,et al.  Robust sensor placements at informative and communication-efficient locations , 2011, TOSN.

[9]  Cecilia Mascolo,et al.  Evolution and sustainability of a wildlife monitoring sensor network , 2010, SenSys '10.

[10]  Christopher M. Bishop,et al.  Pattern Recognition and Machine Learning (Information Science and Statistics) , 2006 .

[11]  Mingyan Liu,et al.  Network coverage using low duty-cycled sensors: random & coordinated sleep algorithms , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[12]  Tarek F. Abdelzaher,et al.  SATIRE: a software architecture for smart AtTIRE , 2006, MobiSys '06.

[13]  Nisheeth Shrivastava,et al.  Target tracking with binary proximity sensors: fundamental limits, minimal descriptions, and algorithms , 2006, SenSys '06.

[14]  Guoliang Xing,et al.  Watchdog: Confident Event Detection in Heterogeneous Sensor Networks , 2010, 2010 16th IEEE Real-Time and Embedded Technology and Applications Symposium.

[15]  Ryan Newton,et al.  The pothole patrol: using a mobile sensor network for road surface monitoring , 2008, MobiSys '08.

[16]  Pradeep K. Khosla,et al.  Sensing capacity for discrete sensor network applications , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..

[17]  Uri Lerner,et al.  Hybrid Bayesian networks for reasoning about complex systems , 2002 .

[18]  Deborah Estrin,et al.  Capturing high-frequency phenomena using a bandwidth-limited sensor network , 2006, SenSys '06.

[19]  Joseph A. Paradiso,et al.  A framework for the automated generation of power-efficient classifiers for embedded sensor nodes , 2007, SenSys '07.

[20]  Bruce H. Krogh,et al.  Lightweight detection and classification for wireless sensor networks in realistic environments , 2005, SenSys '05.

[21]  Guoliang Xing,et al.  PBN: towards practical activity recognition using smartphone-based body sensor networks , 2011, SenSys.

[22]  Ákos Lédeczi,et al.  Shooter localization and weapon classification with soldier-wearable networked sensors , 2007, MobiSys '07.

[23]  Ashish Goel,et al.  Set k-cover algorithms for energy efficient monitoring in wireless sensor networks , 2003, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[24]  Guoliang Xing,et al.  Integrated coverage and connectivity configuration for energy conservation in sensor networks , 2005, TOSN.

[25]  Venkatesh Saligrama,et al.  Adaptive statistical sampling methods for decentralized estimation and detection of localized phenomena , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..

[26]  Pramod K. Varshney,et al.  Distributed Detection and Data Fusion , 1996 .

[27]  Xiaohua Jia,et al.  Data fusion improves the coverage of wireless sensor networks , 2009, MobiCom '09.

[28]  Lei Chen,et al.  A Weighted Moving Average-based Approach for Cleaning Sensor Data , 2007, 27th International Conference on Distributed Computing Systems (ICDCS '07).

[29]  C. R. Ramakrishnan,et al.  A methodology for in-network evaluation of integrated logical-statistical models , 2008, SenSys '08.

[30]  Shaojie Tang,et al.  Canopy closure estimates with GreenOrbs: sustainable sensing in the forest , 2009, SenSys '09.

[31]  Radford M. Neal Pattern Recognition and Machine Learning , 2007, Technometrics.

[32]  Eyal Amir,et al.  Real‐time Bayesian anomaly detection in streaming environmental data , 2007 .

[33]  Youngki Lee,et al.  SeeMon: scalable and energy-efficient context monitoring framework for sensor-rich mobile environments , 2008, MobiSys '08.

[34]  Gyula Simon,et al.  Sensor network-based countersniper system , 2004, SenSys '04.

[35]  V. Cerný Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm , 1985 .

[36]  Luca Benini,et al.  Activity Recognition from On-Body Sensors: Accuracy-Power Trade-Off by Dynamic Sensor Selection , 2008, EWSN.

[37]  Tian He,et al.  Differentiated surveillance for sensor networks , 2003, SenSys '03.

[38]  Yixin Chen,et al.  Fast Sensor Placement Algorithms for Fusion-Based Target Detection , 2008, 2008 Real-Time Systems Symposium.

[39]  ČernýV. Thermodynamical approach to the traveling salesman problem , 1985 .

[40]  G. Pottie,et al.  Entropy-based sensor selection heuristic for target localization , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[41]  Joseph A. Paradiso,et al.  CargoNet: a low-cost micropower sensor node exploiting quasi-passive wakeup for adaptive asychronous monitoring of exceptional events , 2007, SenSys '07.

[42]  Matt Welsh,et al.  Resource aware programming in the Pixie OS , 2008, SenSys '08.

[43]  Alhussein A. Abouzeid,et al.  Stochastic Event Capture Using Mobile Sensors Subject to a Quality Metric , 2006, IEEE Transactions on Robotics.

[44]  Wei Hong,et al.  Model-Driven Data Acquisition in Sensor Networks , 2004, VLDB.

[45]  Anish Arora,et al.  Barrier coverage with wireless sensors , 2005, MobiCom '05.

[46]  Tian He,et al.  Exploring In-Situ Sensing Irregularity in Wireless Sensor Networks , 2007, IEEE Transactions on Parallel and Distributed Systems.

[47]  David E. Culler,et al.  Design of a wireless sensor network platform for detecting rare, random, and ephemeral events , 2005, IPSN 2005. Fourth International Symposium on Information Processing in Sensor Networks, 2005..

[48]  Eyal Amir,et al.  Real-time Bayesian Anomaly Detection for Environmental Sensor Data , 2007 .

[49]  Yu Hen Hu,et al.  Vehicle classification in distributed sensor networks , 2004, J. Parallel Distributed Comput..

[50]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[51]  Ruzena Bajcsy,et al.  The Sensor Selection Problem for Bounded Uncertainty Sensing Models , 2005, IEEE Transactions on Automation Science and Engineering.

[52]  Feng Zhao,et al.  Information-Driven Dynamic Sensor Collaboration for Tracking Applications , 2002 .

[53]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[54]  Wei Wang,et al.  Coverage for target localization in wireless sensor networks , 2006, 2006 5th International Conference on Information Processing in Sensor Networks.

[55]  Daji Qiao,et al.  A Novel On-Demand Framework for Collaborative Object Detection in Sensor Networks , 2008, IEEE INFOCOM 2008 - The 27th Conference on Computer Communications.

[56]  Themis Palpanas,et al.  Distributed Real-Time Detection and Tracking of Homogeneous Regions in Sensor Networks , 2006, 2006 27th IEEE International Real-Time Systems Symposium (RTSS'06).

[57]  S. Sitharama Iyengar,et al.  Grid Coverage for Surveillance and Target Location in Distributed Sensor Networks , 2002, IEEE Trans. Computers.

[58]  Gang Zhou,et al.  VigilNet: An integrated sensor network system for energy-efficient surveillance , 2006, TOSN.