Physical Activity Classification for Elderly People in Free-Living Conditions

Abstract

Physical activity is strongly linked with mental and physical health in the elderly population and accurate monitoring of activities of daily living (ADLs) can help improve quality of life and well-being. This study presents and validates an inertial sensors-based physical activity classification system developed with older adults as the target population. The dataset was collected in free living conditions without placing constraints on the way and order of performing ADLs. Four sensor locations (chest, lower back, wrist, and thigh) were explored to obtain the optimal number and combination of sensors by finding the best tradeoff between the system's performance and wearability. Several feature selection techniques were implemented on the feature set obtained from acceleration and angular velocity signals to classify four major ADLs (sitting, standing, walking, and lying). Support vector machine was used for the classification of the ADLs. The findings show the potential of different solutions (single-sensor or multi-sensor) to correctly classify the ADLs of older people in free living conditions. Considering a minimal set-up of a single sensor, the sensor worn at the L5 achieved the best performance. A two-sensor solution (L5 + thigh) achieved a better performance with respect to a single-sensor solution. On the other hand, considering more than two sensors did not provide further improvements. Finally, we evaluated the computational cost of different solutions and it was shown that a feature selection step can reduce the computational cost of the system and increase the system performance in most cases. This can be helpful for real-time applications.

Performance Analysis of Boosting Classifiers in Recognizing Activities of Daily Living

“…Although the change (increase or decrease) in the performance was not quite significant as compared with the performances achieved through the whole feature set, the number of features was significantly reduced from 561 to 150 using the CFS approach (over 70% reduction in several features). The number of features has implications on the computational complexity of the system [35,37]. A large number of features increases the computational complexity of the system and makes the systems infeasible to operate in real-time scenarios.…”

The Use of Inertial Measurement Units for the Study of Free Living Environment Activity Assessment: A Literature Review

“…Indeed, there are two types of environments: those that are familiar to the subject and those that are unfamiliar. Concerning articles using familiar environments, some studies in FLEs are limited to the habitats of the participants [ 6 , 17 , 27 , 37 , 38 , 41 , 69 , 72 , 73 , 79 , 80 , 83 , 84 , 91 ]. While others include all the environments frequented daily by the participant like library, gym, university, etc.…”

“…In addition, some studies have highlighted the difficulties of transposing high-performance algorithms intended for controlled environments to free-living conditions, in particular because of the greater complexity of movements and their associations [ 33 ]. Nevertheless, these challenges have been, and are still being, met today through studies allowing interesting and reliable quantitative feedback using inertial sensors of the movements carried out in free-living settings [ 37 , 38 , 39 , 40 ]. The increasing use of machine learning and efficient algorithms also contributed to this effort, by allowing the processing of complex data and allowing to transpose protocols from laboratory to natural conditions.…”

Improving Heart Rate Estimation on Consumer Grade Wrist-Worn Device Using Post-Calibration Approach

“…There are numerous PAL estimation methods depending on the locations of the devices in the physical activity research field [35]. The methods used in this study were based on the implementation of the four methods proposed by Freedson et al [39], Troiano et al [40], and Crouter et al [41], which are four of the most adopted PAL estimation methods included as a comparative experiment of physical activity [38]. The methods from Freedson et al [39] and Troiano et al [40] were designed for hip placement.…”