A Study on Sensor Data Mining Model and System Design
J. Environ. Nanotechnol., Volume 6, No 1 (March 2017) pp. 71-74
Abstract
The sensor data which is inputted from the sensor network is a stream of data having continuous and infinite properties and because of these properties, the previous data mining techniques cannot be used on sensor data. Application services in the sensor network are only event alert services that distinguish the events from sensors and alert to the supervisor. In this paper, we define the continuous sensor data mining model and design. The system can extract useful knowledge in continuous sensor data mining using gathered data from sensors in the sensor network. Sensor data is categorized into three data types, which are simple sensor data, sensor event data and continuous sensor data. The sensor data mining models describe and define about the outlier analysis, pattern analysis, and prediction analysis. After the definition, we design a system that can be based on the mining models in a sensor network environment.
