Human activity recognition from smart watch sensor data using a hybrid of principal component analysis and random forest algorithm

Serkan Balli,Musa Peker,Ensar Arif Sağbaş

doi:10.1177/0020294018813692

Serkan Balli, Musa Peker + Show 1 more

Open Access

https://doi.org/10.1177/0020294018813692

Copy DOI

Abstract

Background: Detecting of human movements is an important task in various areas such as healthcare, fitness and eldercare. It is now possible to achieve this aim using mobile applications. These applications provide users, doctors and related persons a better understanding about daily physical activities. It can also lead to various useful habits by following the activities of the users in their daily life. In addition, dangerous actions such as the fall of elderly people or young children are identified and necessary precautions are taken as soon as possible. Classification of human motions with motion sensor data is among the current topics of study. Smart watches have these sensors built-in. Thus, it is possible to follow the activities of a user carrying only a smart watch. Methods: The purpose of this work is to detect human movements using smart watch sensor data and machine learning methods. The data are obtained from the accelerometer, gyroscope, step counter and heart rate sensors of the smart watch. The obtained data have been divided into 2 s windows and a data set containing 500 patterns for each class has been created for each class. Results and Discussion: After the features were determined, the data set to which the principal component analysis has been applied was classified by random forest, support vector machine, C4.5 and k-nearest neighbor methods, and their performances were compared. The most successful result was obtained from the random forest method.

Highlights

The use of wearable technology is rapidly increasing, and its effects are observed positively in the user’s healthcare follow-up
The principal component analysis (PCA) method was used as a feature dimensionality reduction in order to increase the classification accuracy of a random forest (RF) classifier and to decrease the variance of the attributes in datasets
Three principal components have been obtained by applying the PCA preprocessing algorithm to the 14 features extracted from the obtained sensor data

Summary

Introduction

The use of wearable technology is rapidly increasing, and its effects are observed positively in the user’s healthcare follow-up. Wearable sensors are small devices that people can carry around while performing their daily activities. It is possible to achieve this aim using mobile applications These applications provide users, doctors and related persons a better understanding about daily physical activities. Classification of human motions with motion sensor data is among the current topics of study. It is possible to follow the activities of a user carrying only a smart watch. Methods: The purpose of this work is to detect human movements using smart watch sensor data and machine learning methods. The data are obtained from the accelerometer, gyroscope, step counter and heart rate sensors of the smart watch. The most successful result was obtained from the random forest method

Objectives

Methods

Results

Conclusion