Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks
The spatial–temporal correlation is an important feature of sensor data in wireless sensor networks (WSNs). Most of the existing works based on the spatial–temporal correlation can be divided into two parts: redundancy reduction and anomaly detection. These two parts are pursued separately in existi...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2016-09-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/16/10/1601 |
| _version_ | 1828150447252176896 |
|---|---|
| author | Gang Li Bin He Hongwei Huang Limin Tang |
| author_facet | Gang Li Bin He Hongwei Huang Limin Tang |
| author_sort | Gang Li |
| collection | DOAJ |
| description | The spatial–temporal correlation is an important feature of sensor data in wireless sensor networks (WSNs). Most of the existing works based on the spatial–temporal correlation can be divided into two parts: redundancy reduction and anomaly detection. These two parts are pursued separately in existing works. In this work, the combination of temporal data-driven sleep scheduling (TDSS) and spatial data-driven anomaly detection is proposed, where TDSS can reduce data redundancy. The TDSS model is inspired by transmission control protocol (TCP) congestion control. Based on long and linear cluster structure in the tunnel monitoring system, cooperative TDSS and spatial data-driven anomaly detection are then proposed. To realize synchronous acquisition in the same ring for analyzing the situation of every ring, TDSS is implemented in a cooperative way in the cluster. To keep the precision of sensor data, spatial data-driven anomaly detection based on the spatial correlation and Kriging method is realized to generate an anomaly indicator. The experiment results show that cooperative TDSS can realize non-uniform sensing effectively to reduce the energy consumption. In addition, spatial data-driven anomaly detection is quite significant for maintaining and improving the precision of sensor data. |
| first_indexed | 2024-04-11T21:44:38Z |
| format | Article |
| id | doaj.art-1ed61cad218842dd9bcb9a69c9195943 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T21:44:38Z |
| publishDate | 2016-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-1ed61cad218842dd9bcb9a69c91959432022-12-22T04:01:27ZengMDPI AGSensors1424-82202016-09-011610160110.3390/s16101601s16101601Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor NetworksGang Li0Bin He1Hongwei Huang2Limin Tang3School of Electronics and Information Engineering, Tongji University, Shanghai 201804, ChinaSchool of Electronics and Information Engineering, Tongji University, Shanghai 201804, ChinaDepartment of Geotechnical Engineering, Tongji University, Shanghai 200092, ChinaSchool of Electronics and Information Engineering, Tongji University, Shanghai 201804, ChinaThe spatial–temporal correlation is an important feature of sensor data in wireless sensor networks (WSNs). Most of the existing works based on the spatial–temporal correlation can be divided into two parts: redundancy reduction and anomaly detection. These two parts are pursued separately in existing works. In this work, the combination of temporal data-driven sleep scheduling (TDSS) and spatial data-driven anomaly detection is proposed, where TDSS can reduce data redundancy. The TDSS model is inspired by transmission control protocol (TCP) congestion control. Based on long and linear cluster structure in the tunnel monitoring system, cooperative TDSS and spatial data-driven anomaly detection are then proposed. To realize synchronous acquisition in the same ring for analyzing the situation of every ring, TDSS is implemented in a cooperative way in the cluster. To keep the precision of sensor data, spatial data-driven anomaly detection based on the spatial correlation and Kriging method is realized to generate an anomaly indicator. The experiment results show that cooperative TDSS can realize non-uniform sensing effectively to reduce the energy consumption. In addition, spatial data-driven anomaly detection is quite significant for maintaining and improving the precision of sensor data.http://www.mdpi.com/1424-8220/16/10/1601spatial–temporal correlationdata-driven sleep schedulingdata-driven anomaly detectionWSN |
| spellingShingle | Gang Li Bin He Hongwei Huang Limin Tang Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks Sensors spatial–temporal correlation data-driven sleep scheduling data-driven anomaly detection WSN |
| title | Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks |
| title_full | Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks |
| title_fullStr | Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks |
| title_full_unstemmed | Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks |
| title_short | Temporal Data-Driven Sleep Scheduling and Spatial Data-Driven Anomaly Detection for Clustered Wireless Sensor Networks |
| title_sort | temporal data driven sleep scheduling and spatial data driven anomaly detection for clustered wireless sensor networks |
| topic | spatial–temporal correlation data-driven sleep scheduling data-driven anomaly detection WSN |
| url | http://www.mdpi.com/1424-8220/16/10/1601 |
| work_keys_str_mv | AT gangli temporaldatadrivensleepschedulingandspatialdatadrivenanomalydetectionforclusteredwirelesssensornetworks AT binhe temporaldatadrivensleepschedulingandspatialdatadrivenanomalydetectionforclusteredwirelesssensornetworks AT hongweihuang temporaldatadrivensleepschedulingandspatialdatadrivenanomalydetectionforclusteredwirelesssensornetworks AT limintang temporaldatadrivensleepschedulingandspatialdatadrivenanomalydetectionforclusteredwirelesssensornetworks |