Classification Accuracies of Physical Activities Using Smartphone Motion Sensors

Abstract

BackgroundOver the past few years, the world has witnessed an unprecedented growth in smartphone use. With sensors such as accelerometers and gyroscopes on board, smartphones have the potential to enhance our understanding of health behavior, in particular physical activity or the lack thereof. However, reliable and valid activity measurement using only a smartphone in situ has not been realized.ObjectiveTo examine the validity of the iPod Touch (Apple, Inc.) and particularly to understand the value of using gyroscopes for classifying types of physical activity, with the goal of creating a measurement and feedback system that easily integrates into individuals’ daily living.MethodsWe collected accelerometer and gyroscope data for 16 participants on 13 activities with an iPod Touch, a device that has essentially the same sensors and computing platform as an iPhone. The 13 activities were sitting, walking, jogging, and going upstairs and downstairs at different paces. We extracted time and frequency features, including mean and variance of acceleration and gyroscope on each axis, vector magnitude of acceleration, and fast Fourier transform magnitude for each axis of acceleration. Different classifiers were compared using the Waikato Environment for Knowledge Analysis (WEKA) toolkit, including C4.5 (J48) decision tree, multilayer perception, naive Bayes, logistic, k-nearest neighbor (kNN), and meta-algorithms such as boosting and bagging. The 10-fold cross-validation protocol was used.ResultsOverall, the kNN classifier achieved the best accuracies: 52.3%–79.4% for up and down stair walking, 91.7% for jogging, 90.1%–94.1% for walking on a level ground, and 100% for sitting. A 2-second sliding window size with a 1-second overlap worked the best. Adding gyroscope measurements proved to be more beneficial than relying solely on accelerometer readings for all activities (with improvement ranging from 3.1% to 13.4%).ConclusionsCommon categories of physical activity and sedentary behavior (walking, jogging, and sitting) can be recognized with high accuracies using both the accelerometer and gyroscope onboard the iPod touch or iPhone. This suggests the potential of developing just-in-time classification and feedback tools on smartphones.

Energy-Efficient Technologies in Device-to-Device Based Proximity Service

“…[Altun and Barshan, 2010;Lee and Mase, 2002]). Recently, in [Wu et al, 2012], a hybrid accelerometer and gyroscope approach was used for the classification of 9 activities using an iPhone 4. They showed insights of the benefits of adding gyroscope signals into the recognition system achieving improvements ranging from 3.1% to 13.4% in classification accuracy.…”

Smartphone-Based Human Activity Recognition

“…Accelerometers have been included in smartphones since [Lane et al, 2010, while gyroscopes were introduced more recently (2010) in mid-and high-end devices and they have demonstrated to improve the recognition performance in HAR systems when used in combination with accelerometers such as in [Anguita et al, 2013d;Wu et al, 2012]. As these sensors are both based on MEMS technologies, they are small, affordable and therefore suitable for commercial use and integration in portable devices.…”

“…Some smartphonebased approaches have been already proposed in the literature [Berchtold et al, 2010;Brezmes et al, 2009;Kwapisz et al, 2011;Wu et al, 2012]. In [Kwapisz et al, 2011], for example, it was presented one of the first approaches to exploit an Android smartphone and its embedded triaxial accelerometer for HAR.…”

“…MEMS gyroscopes made its entrance in the smartphones market a couple of years after accelerometers and they have not been fully explored [Wu et al, 2012]. We also study two feature selection mechanisms for allowing a faster recognition: the utilization of exclusively time domain features from the inertial data and the adaptation of the L1-L2-SVM which controls over the number of non-informative features as part of its model construction process.…”

The Benefits of Personalized Smartphone-Based Activity Recognition Models

“…The majority of other smartphone-based systems only evaluate hybrid models [3,7,15,27], and a number of other studies [6,10] do not provide enough information in their methodology to determine the model type. We view this as problematic because of the dramatic difference in performance and applications between different model types.…”