Deep Learning for Classifying Physical Activities from Accelerometer Data

Abstract

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two physical movement datasets collected from several volunteers who carried tri-axial accelerometer sensors. The first dataset is from the UCI machine learning repository, which contains 14 different activities-of-daily-life (ADL) and is collected from 16 volunteers who carried a single wrist-worn tri-axial accelerometer. The second dataset includes ten other ADLs and is gathered from 8 volunteers who placed the sensors on their hips. Our experiment results show that the RNN model provides the accuracy performance compared to the state-of-the-art methods in classifying the fundamental movement patterns with an overall accuracy of 84.89% and an overall F1-score of 82.56%. Our results indicate that the proposed method will provide the medical doctors and trainers a promising way to precisely track and understand a patient’s physical activities for better treatment.

Deep Learning performance in predicting dairy cows’ behaviour from a tri-axial accelerometer data

“…In the latter eld, even pose estimation and locomotion pattern recognition achieved excellent results [19]. However, so far behaviour classi cation in dairy cows through the application of tri-axial accelerometers has been mainly performed through classical ML models, whereas DL application to accelerometery data was investigated in humans [16,20].…”

“…The DL models were initially created in the 1990s for the application in computer vision, but since then they have been applied to miscellaneous domains such as self-driving cars, nance and even livestock farming [16,17,18]. Although DL models in animal production have been recently applied to computer vision with the aim of identifying for example individuals [17] or behaviours [19], at our knowledge their application to tri-axial accelerometery data for behaviour classi cation is scarce and mainly applied to humans [16,20]. The aim of this study was to assess the performance of a CNN in classifying the behaviour of healthy dairy cows on the basis of data acquired through a tri-axial accelerometer and compare the results with the performance attained from the same raw data through the use of classical ML models [21].…”