Collaborative query processing among heterogeneous sensor networks
Proceedings of the 1st ACM international workshop on Heterogeneous sensor and actor networks
MWM: a map-based world model for wireless sensor networks
Autonomics '08 Proceedings of the 2nd International Conference on Autonomic Computing and Communication Systems
Spatio-temporal event detection using dynamic conditional random fields
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
DEAMON: energy-efficient sensor monitoring
SECON'09 Proceedings of the 6th Annual IEEE communications society conference on Sensor, Mesh and Ad Hoc Communications and Networks
Map-based modeling and design of wireless sensor networks with OMNeT++
SPECTS'09 Proceedings of the 12th international conference on Symposium on Performance Evaluation of Computer & Telecommunication Systems
Continuous monitoring of global events in sensor networks
International Journal of Sensor Networks
A system for distributed event detection in wireless sensor networks
Proceedings of the 9th ACM/IEEE International Conference on Information Processing in Sensor Networks
Modeling and detecting events for sensor networks
Information Fusion
Pattern-based event detection in sensor networks
Distributed and Parallel Databases
Hi-index | 0.00 |
Event detection is a crucial task for wireless sensor network applications, especially environment monitoring. Existing approaches for event detection are mainly based on some predefined threshold values, and thus are often inaccurate and incapable of capturing complex events. For example, in coal mine monitoring scenarios, gas leakage or water osmosis can hardly be described by the overrun of specified attribute thresholds, but some complex pattern in the full-scale view of the environmental data. To address this issue, we propose a non-threshold based approach for the real 3D sensor monitoring environment. We employ energy- efficient methods to collect a time series of data maps from the sensor network and detect complex events through matching the gathered data to spatio-temporal data patterns. Finally, we conduct trace driven simulations to prove the efficacy and efficiency of this approach on detecting events of complex phenomena from real-life records.