Identifying Types of Physical Activity With a Single Accelerometer: Evaluating Laboratory-trained Algorithms in Daily Life

Abstract

Abstract-Accurate identification of physical activity types has been achieved in laboratory conditions using single-site accelerometers and classification algorithms. This methodology is then applied to free-living subjects to determine activity behaviour. This study aimed at analysing the reproducibility of the accuracy of laboratory-trained classification algorithms in free-living subjects during daily life. A support vector machine (SVM), a feed-forward neural network (NN) and a decision tree (DT) were trained with data collected by a waist-mounted accelerometer during a laboratory trial. The reproducibility of the classification performance was tested on data collected in daily life using a multiple-site accelerometer (IDEEA) augmented with an activity diary for 20 healthy subjects (age: 30 ± 9; BMI: 23.0 ± 2.6 kg/m 2 ). Leave-one-subject-out cross-validation of the training data showed accuracies of 95.1 ± 4.3%, 91.4 ± 6.7% and 92.2 ± 6.6% for the SVM, NN and DT, respectively. All algorithms showed a significantly decreased accuracy in daily life as compared to the reference truth represented by the IDEEA and diary classifications (75.6 ± 10.4%, 74.8 ± 9.7%, and 72.2 ± 10.3%; p<0.05). In conclusion, cross-validation of training data overestimates the accuracy of the classification algorithms in daily life.Index Terms-Assessment of daily physical activity, classification algorithms, IDEEA, physical activity, triaxial accelerometer

Physical activity classification utilizing SenseWear activity monitor in manual wheelchair users with spinal cord injury

“…[1][2][3][4][5] The benefits of detecting physical activities (PAs) using wearable devices include the ability to track regular PA, provide accurate energy expenditure (EE) estimation and assist in behavioral modifications that may lead to a healthier active lifestyle in community settings. [6][7][8][9][10] However, there are only a limited number of studies that have detected and classified PAs performed by individuals who rely on wheelchairs for mobility using wearable devices.…”

Physical Activity Recognition From Smartphone Accelerometer Data for User Context Awareness Sensing

“…Accelerometers are very popular sensors in the field of biomedicine and can be used for tremor analysis, assessment of physical activity, qualification of metabolic energy expenditure [9], measurement of gait parameters [10], fall detection [11], postural detection and transition [12], [13], and the measurement of activities performed in daily living [14], [15]. Most of these applications make use of computational techniques that require the implementation of machine learning algorithms, these algorithms serve to solve nonlinear multivariate problems.…”

Inexpensive and Power-Efficient Wireless Health Monitoring System for the Aging Population

“…MEMS accelerometers have also been used to study activities of daily livings (ADLs) [21,22,23,24]. In this field, Wockets [13] is a notable open source project which aims to build hardware and software that permits automatic, 24/7 physical activity and context detection on mobile phones.…”

“…ADL classifications using analog accelerometers typically use classifiers such as LDA (linear discriminant analysis), naive Bayes, SVM (support vector machine), ANN (artificial neural network), decision tree classifier, etc, which have been compared by [22,31,32]. The proposed ADL classification employs decision tree learning as decision trees can be efficiently implemented as a number of if-else or switch statements.…”