RNNs on Monitoring Physical Activity Energy Expenditure in Older People

TL;DR

This study develops an advanced RNN model tailored for estimating physical activity energy expenditure in older adults, integrating static and activity data to improve accuracy over existing methods.

Contribution

It introduces a novel RNN architecture with enhanced data integration and aggregation techniques specifically designed for elderly populations.

Findings

Achieved approximately 10% accuracy improvement over the state of the art.

Reduced training input requirements by a factor of 10.

Demonstrated potential for linking PAEE to health and well-being metrics.

Abstract

Through the quantification of physical activity energy expenditure (PAEE), health care monitoring has the potential to stimulate vital and healthy ageing, inducing behavioural changes in older people and linking these to personal health gains. To be able to measure PAEE in a monitoring environment, methods from wearable accelerometers have been developed, however, mainly targeted towards younger people. Since elderly subjects differ in energy requirements and range of physical activities, the current models may not be suitable for estimating PAEE among the elderly. Because past activities influence present PAEE, we propose a modeling approach known for its ability to model sequential data, the Recurrent Neural Network (RNN). To train the RNN for an elderly population, we used the GOTOV dataset with 34 healthy participants of 60 years and older (mean 65 years old), performing 16 different activities. We used accelerometers placed on wrist and ankle, and measurements of energy counts by means of indirect calorimetry. After optimization, we propose an architecture consisting of an RNN with 3 GRU layers and a feedforward network combining both accelerometer and participant-level data. In this paper, we describe our efforts to go beyond the standard facilities of a GRU-based RNN, with the aim of achieving accuracy surpassing the state of the art. These efforts include switching aggregation function from mean to dispersion measures (SD, IQR, ...), combining temporal and static data (person-specific details such as age, weight, BMI) and adding symbolic activity data as predicted by a previously trained ML model. The resulting architecture manages to increase its performance by approximatelly 10% while decreasing training input by a factor of 10. It can thus be employed to investigate associations of PAEE with vitality parameters related to metabolic and cognitive health and mental well-being.