TY - GEN
T1 - Continuous monitoring and distributed anomaly detection for ambient factors
AU - Shen, Yang Chi
AU - Chiang, Alvin
AU - Yeh, Yi Ren
AU - Lee, Yuh-Jye
N1 - Publisher Copyright:
© 2014 IEEE.
PY - 2014/3/12
Y1 - 2014/3/12
N2 - Considering the diverse application scenarios involving wireless sensor networks (WSNs), accurate continuous monitoring requires a solution to the essential task of estimating unmeasured locations in the monitored space. In this paper, we utilize Epsilon-Smooth Support Vector Regression (Epsilon-SSVR) to report monitoring information of environment, furthermore we combine spatial and temporal correlation to strengthen monitoring accuracy. However if our sensors are too sparsely deployed, the resulting coverage holes problem will adversely impact the monitoring result. Therefore, we utilize Uniform Design and different local interpolation methods to assist Epsilon-SSVR to mitigate the coverage holes problem. In our experiment, we compare our method with different methods applied to different sensors deployments. Epsilon-SSVR has better accuracy and computation speed than others. Besides continuous monitoring, we also propose a distributed anomaly detection mechanism to report anomaly information, in order to provide a reliable and real time anomaly monitoring system.
AB - Considering the diverse application scenarios involving wireless sensor networks (WSNs), accurate continuous monitoring requires a solution to the essential task of estimating unmeasured locations in the monitored space. In this paper, we utilize Epsilon-Smooth Support Vector Regression (Epsilon-SSVR) to report monitoring information of environment, furthermore we combine spatial and temporal correlation to strengthen monitoring accuracy. However if our sensors are too sparsely deployed, the resulting coverage holes problem will adversely impact the monitoring result. Therefore, we utilize Uniform Design and different local interpolation methods to assist Epsilon-SSVR to mitigate the coverage holes problem. In our experiment, we compare our method with different methods applied to different sensors deployments. Epsilon-SSVR has better accuracy and computation speed than others. Besides continuous monitoring, we also propose a distributed anomaly detection mechanism to report anomaly information, in order to provide a reliable and real time anomaly monitoring system.
KW - Anomaly detection
KW - Continuous monitoring
KW - SSVR
KW - Wireless sensor networks
UR - http://www.scopus.com/inward/record.url?scp=84946691720&partnerID=8YFLogxK
U2 - 10.1109/iThings.2014.14
DO - 10.1109/iThings.2014.14
M3 - Conference contribution
AN - SCOPUS:84946691720
T3 - Proceedings - 2014 IEEE International Conference on Internet of Things, iThings 2014, 2014 IEEE International Conference on Green Computing and Communications, GreenCom 2014 and 2014 IEEE International Conference on Cyber-Physical-Social Computing, CPS 2014
SP - 31
EP - 38
BT - Proceedings - 2014 IEEE International Conference on Internet of Things, iThings 2014, 2014 IEEE International Conference on Green Computing and Communications, GreenCom 2014 and 2014 IEEE International Conference on Cyber-Physical-Social Computing, CPS 2014
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2014 IEEE International Conference on Internet of Things, iThings 2014, Collocated with 2014 IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2014 and 2014 IEEE International Conference on Green Computing and Communications, GreenCom 2014
Y2 - 1 September 2014 through 3 September 2014
ER -