Recognition of Sedentary Behavior by Machine Learning Analysis of Wearable Sensors during Activities of Daily Living for Telemedical Assessment of Cardiovascular Risk.

Eliasz Kańtoch

doi:10.3390/s18103219

Abstract

With the recent advancement in wearable computing, sensor technologies, and data processing approaches, it is possible to develop smart clothing that integrates sensors into garments. The main objective of this study was to develop the method of automatic recognition of sedentary behavior related to cardiovascular risk based on quantitative measurement of physical activity. The solution is based on the designed prototype of the smart shirt equipped with a processor, wearable sensors, power supply and telemedical interface. The data derived from wearable sensors were used to create feature vector that consisted of the estimation of the user-specific relative intensity and the variance of filtered accelerometer data. The method was validated using an experimental protocol which was designed to be safe for the elderly and was based on clinically validated short physical performance battery (SPPB) test tasks. To obtain the recognition model six classifiers were examined and compared including Linear Discriminant Analysis, Support Vector Machines, K-Nearest Neighbors, Naive Bayes, Binary Decision Trees and Artificial Neural Networks. The classification models were able to identify the sedentary behavior with an accuracy of 95.00% ± 2.11%. Experimental results suggested that high accuracy can be obtained by estimating sedentary behavior pattern using the smart shirt and machine learning approach. The main advantage of the developed method to continuously monitor patient activities in a free-living environment and could potentially be used for early detection of increased cardiovascular risk.

Highlights

Demographic changes and increasing societal demands require more effective methods of providing health services based on novel technologies information and telecommunications (ICT), artificial intelligence and telemedicine
We investigated the following classification models: Binary decision trees, Discriminant Analysis model, Naive Bayes (Gaussian), k-nearest neighbors classification (k = 5, distance = Euclidean), Support vector machines for binary classification and artificial neural networks with the following topology: one neuron has been placed on the output layer, 12 neurons on the hidden layer and two neurons in the input layer
We investigated six different classification models to measure the performance intensity, acceleration, and pulse wave sensor data as well as output from classification model

Summary

Introduction

Demographic changes and increasing societal demands require more effective methods of providing health services based on novel technologies information and telecommunications (ICT), artificial intelligence and telemedicine. According to the Eurostat during the period from 2016 to 2080 older persons will likely account for an increasing share of the general population. Those aged 65 years or over will represent 29.1% of the population of EU Member States by 2080, compared to. According to the Center for Disease Control and Prevention, the leading major causes of morbidity, disability, and mortality in 2015 were cardiovascular diseases (CVD) [2]. Treatment of these diseases is challenging for the healthcare systems in all developed countries due to the ageing population, limited access to the healthcare service

Objectives

Methods

Results

Conclusion