Energy expenditure estimation through daily activity recognition using a smart-phone

Abstract

This paper presents a 3-step system that estimates the real-time energy expenditure of an individual in a nonintrusive way. First, using the user's smart-phone's sensors, we build a Decision Tree model to recognize his physical activity (running, standing, ...). Then, we use the detected physical activity, the time and the user's speed to infer his daily activity (watching TV, going to the bathroom, ...) through the use of a reinforcement learning environment, the Partially Observable Markov Decision Process framework. Once the daily activities are recognized, we translate this information into energy expenditure using the compendium of physical activities. By successfully detecting 8 physical activities at 90%, we reached an overall accuracy of 80% in recognizing 17 different daily activities. This result leads us to estimate the energy expenditure of the user with a mean error of 26% of the expected estimation.

A CNN Model for Physical Activity Recognition and Energy Expenditure Estimation from an Eyeglass-Mounted Wearable Sensor

“…Traditionally, PAR and EE estimation models were developed based on classical signal processing techniques [21,23,26], statistical and classical machine learning [20]. Nevertheless, the superior performance of deep learning, such as convolutional neural networks (CNNs), long short-term memory (LSTM), and attention mechanisms, makes them attractive for PAR and EE estimation applications [33,34].…”

“…PAR is an actively researched topic due to its various real-world applications in areas such as humancomputer interaction [12,13], security and surveillance systems [14,15], and healthcare systems [16][17][18][19]. In some studies [20,21], researchers have integrated PAR and EE estimation through wearable technology.…”