Data recovery in wireless sensor networks based on attribute correlation and extremely randomized trees
- PDF / 5,319,048 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 2 Downloads / 176 Views
ORIGINAL RESEARCH
Data recovery in wireless sensor networks based on attribute correlation and extremely randomized trees Hongju Cheng1,2,3 · Leihuo Wu1 · Ruixing Li3 · Fangwan Huang1 · Chunyu Tu1 · Zhiyong Yu1,2 Received: 26 May 2019 / Accepted: 1 August 2019 © Springer-Verlag GmbH Germany, part of Springer Nature 2019
Abstract In wireless sensor networks, collected data usually have a certain degree of loss and are unable to meet actual application needs due to node failures or energy limitation, etc. The current data recovery methods in wireless sensor networks focus on the usage of spatial–temporal correlation between perceptual data but seldom exploit the correlation between different attributes. This paper proposes a data recovery algorithm based on the Attribute Correlation and Extremely randomized Trees (ACET). Firstly, the Spearman’s correlation coefficient is adopted to construct the correlation model between different attributes. In case that a given attribute is lost, the correlation model is used to select other attributes that have a strong correlation with this attribute, and then take advantage of them to train the extremely randomized trees. Finally, the lost data can be recovered by the trained model. Experimental results show that the correlation between attributes can improve the effectiveness of data recovery compared with other methods. Keywords Wireless sensor network · Data recovery · Extremely randomized trees · Attribute correlation
1 Introduction Wireless Sensor Networks (WSN) (Akyildiz et al. 2002) are a group of distributed sensor nodes with storage, acquisition, and communication capabilities. They are typically deployed in specific monitoring areas, such as underwater, forest, volcano, etc. (Mo et al. 2009; Song et al. 2010; Shabir et al. 2017), to collect temperature, humidity, light intensity, and other data from the covered areas. It has been widely used in the military, environmental monitoring, medical and health fields. However, due to sensor node failure and limited energy, sensor nodes are vulnerable to the deployment environment like mountains, buildings and the harsh natural environment. The collected data usually has a certain degree of loss. In actual applications, such as worker recruitment (Wang et al. 2019), task allocation (Wang et al. * Zhiyong Yu [email protected] 1
College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116, China
2
Key Laboratory of Spatial Data Mining and Information Sharing, Ministry of Education, Fuzhou 350116, China
3
Department of Computer, Minjiang Teachers College, Fuzhou 350108, China
2018; Huang et al. 2019), vehicle navigation (Chen et al. 2019), door event detection (Gong et al. 2018) and city data analysis (Guo et al. 2019), it is not possible to directly use the relevant tools for analysis if the data is incomplete. And the reliability of the result will be reduced if the lost data is deleted directly. How to recover the lost data in the acquisition process becomes a research hotspot of wireless
Data Loading...
