Multi-Sensor Signal based Situation Recognition with Bayesian Networks

In this paper, we propose an intelligent situation recognition model by collecting andanalyzing multiple sensor signals. Multiple sensor signals are collected for fixed time window. Atraining set of collected sensor data for each situation is provided to K2-learning algorithm to generateBayesian networks representing causal relationship between sensors for the situation. Statisticalcharacteristics of sensor values and topological characteristics of generated graphs are learned for eachsituation. A neural network is designed to classify the current situation based on the extracted featuresfrom collected multiple sensor values. The proposed method is implemented and tested with UCImachine learning repository data. KCI Citation Count: 2