IEEE Transactions on Computers
On Distributed Fault-Tolerant Detection in Wireless Sensor Networks
IEEE Transactions on Computers
Distributed fault detection of wireless sensor networks
DIWANS '06 Proceedings of the 2006 workshop on Dependability issues in wireless ad hoc networks and sensor networks
Fault detection of wireless sensor networks
Computer Communications
Sensor network data fault types
ACM Transactions on Sensor Networks (TOSN)
Knowledge analysis & application to multimedia content recognition problems
Knowledge analysis & application to multimedia content recognition problems
The MEMS IMU Error Modeling Analysis Using Support Vector Machines
KAM '09 Proceedings of the 2009 Second International Symposium on Knowledge Acquisition and Modeling - Volume 01
Motion fault detection and isolation in Body Sensor Networks
PERCOM '11 Proceedings of the 2011 IEEE International Conference on Pervasive Computing and Communications
Gaussian Mixture Modeling by Exploiting the Mahalanobis Distance
IEEE Transactions on Signal Processing - Part I
Data reconciliation in a smart home sensor network
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
Significant amount of research and development is being directed on monitoring activities of daily living of senior citizens who live alone as well as those who have certain motion disorders such as Alzheimer's and Parkinson's. A combination of sophisticated inertial sensing, wireless communication and signal processing technologies has made such a pervasive and remote monitoring possible. Due to the nature of the sensing and communication mechanisms, these monitoring sensors are susceptible to errors and failures. In this paper, we address the issue of identifying and isolating faulty sensors in a Body Sensor Network that is used for remote monitoring of daily living activities. We identify three different types of faults in a Body Sensor Network and propose fault isolation strategies using history-based and non-history based approaches. The contributions of this paper are: (i) faulty sensor node identification in a small number of deployed body sensors (accelerometers); and (ii) identification of a faulty sensor node using a statically or dynamically bound group of sensor nodes that is sharing similar sensor signal patterns.