Recognizing Human Activities Based on Multi-Sensors Fusion
Rong Liu, Ming Liu · 2010
Usually the recognition of daily human activity need to collect multi-sensor data, this paper applies an information fusion algorithm based Naive Bayes so as to obtain higher-level contexts from a small number of sensor. The sensor data from accelerometer node are firstly classified by C4.5 Decision Tree algorithm, once the confusion matrix of each sensor node have be gotten, the sensor fusion can be performed at the classifier level by calculating the corresponding posterior probability. The Experimental results of daily human activity recognition indicate that the classifier fusion strategy based on Naive Bayes technique has achieved a higher correct classification by effectively fusion the classification result of hip and wrist classifiers.