Vol.62 (Sensor 2014), pp.33-36

Potential worldwide deployment of WSNs for, e.g., environmental monitoring purposes could yield data in amounts of petabytes each year. Thus, in addition to the highly interesting technical challenges related to WSNs themselves, their widespread deployment would also require development of solutions for analyzing the potentially huge amounts of data they would generate. The contribution of this paper is two-fold. First, we propose an approach for constructing a decision tree based classification model for sensor data obtained from WSNs. Proposed model helps in analyzing uncovering patterns, associations, anomalies, and statistically significant structures and events in sensor data. Second, in order to speed up the performance of proposed decision tree based classification model, we propose ubiquitous parallel computing approach for construction decision tree on Graphic Processing Unit (GPU). Due to parallel features of GPU computing, we can accelerate the computing of decision tree algorithm.