Learning approach for classification of GENEActiv accelerometer data for unique activity identification

Recent popular emphasis on exercise for personal wellbeing has created a demand for techniques which monitor and classify human activities. Previous studies have shown promising results in applying various classification and feature extraction methods for identifying unique physical activities on various datasets. We apply learning techniques to GENEactiv accelerometer recordings to identify and monitor a wide range of daily activities. The dataset is composed of 92 participants, of ages 20-65, performing 25 unique activities, both ambulatory and non-ambulatory. The algorithm identified 130 different time and frequency domain features and selected the most efficient features with the sequential forward selection algorithm. With classification in two stages with both Gaussian mixture model (GMM) and hidden Markov model (HMM) we have combined the activities with similar features. We have also shown a comparative study between the two classifiers. We achieved an accuracy of 95.5% while classifying 10 unique activities with HMM and 89.7% while classifying 9. The most efficient result is obtained using HMM in 2-D feature space, where it is able to classify 15 unique activities at an accuracy of 90.12%.