A Comparative Study on Fitness Activity Recognition

Human Activity Recognition (RAH) has become a field of high interest and relevance in the Context Awareness area. When knowing what the user is doing a system can provide good information to increase the quality of the delivered data. Commercial smartwatches and smartphones contain several sensors that can sense an userś movement and help identifying which activity an user is performing in a certain moment. In this paper we compare the smartwatch and the smartphone on human activity recognition, observing accuracy and comfort while users are practicing fitness activities. While analyzing the results of the comparative experiment executed between a Smartphone and a Smartwatch, the second one showed to be a good choice on a qualitative and a quantitative way which can form the basis of new a fitness application, including applications that automatically track the activities done.

[1]  Bill N. Schilit,et al.  Context-aware computing applications , 1994, Workshop on Mobile Computing Systems and Applications.

[2]  Slim Abdennadher,et al.  Human Activity Recognition - Using Sensor Data of Smartphones and Smartwatches , 2016, ICAART.

[3]  Mi Zhang,et al.  Human Daily Activity Recognition With Sparse Representation Using Wearable Sensors , 2013, IEEE Journal of Biomedical and Health Informatics.

[4]  Gary M. Weiss,et al.  Applications of mobile activity recognition , 2012, UbiComp.

[5]  Luis González Abril,et al.  Mobile activity recognition and fall detection system for elderly people using Ameva algorithm , 2017, Pervasive Mob. Comput..

[6]  Gregory D. Abowd,et al.  Towards a Better Understanding of Context and Context-Awareness , 1999, HUC.

[7]  Paul J. M. Havinga,et al.  Towards detection of bad habits by fusing smartphone and smartwatch sensors , 2015, 2015 IEEE International Conference on Pervasive Computing and Communication Workshops (PerCom Workshops).

[8]  Paul J. M. Havinga,et al.  Complex Human Activity Recognition Using Smartphone and Wrist-Worn Motion Sensors , 2016, Sensors.

[9]  James H. Aylor,et al.  Computer for the 21st Century , 1999, Computer.

[10]  Manolis Tsiknakis,et al.  The MobiFall dataset: An initial evaluation of fall detection algorithms using smartphones , 2013, 13th IEEE International Conference on BioInformatics and BioEngineering.