Feature Selection and Activity Recognition System Using a Single Triaxial Accelerometer
Activity recognition is required in various applica- tions such as medical monitoring and rehabilitation. Previously developed activity recognition systems utilizing triaxial accelerom- eters have provided mixed results, with subject-to-subject variabil- ity. This paper presents an accurate activity recognition system utilizing a body worn wireless accelerometer, to be used in the real- life application of patient monitoring. The algorithm utilizes data from a single, waist-mounted triaxial accelerometer to classify gait events into six daily living activities and transitional events. The accelerometer can be worn at any location around the circumfer- ence of the waist, thereby reducing user training. Feature selection is performed using Relief-F and sequential forward floating search (SFFS) from a range of previously published features, as well as new features introduced in this paper. Relevant and robust features that are insensitive to the positioning of accelerometer around the waist are selected. SFFS selected almost half the number of fea- tures in comparison to Relief-F and provided higher accuracy than Relief-F. Activity classification is performed using Na ̈ ıve Bayes and k -nearest neighbor ( k -NN) and the results are compared. Activity recognition results on seven subjects with leave-one-person-out er- ror estimates show an overall accuracy of about 98% for both the classifiers. Accuracy for each of the individual activity is also more than 95%.