A Comparative Study on Fitness Activity Recognition

• Igor Lopes de Faria UFBA
• Vaninha Vieira UFBA

Resumo

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.

Palavras-chave: Ubiquitous Computing, Smartphone, Smartwatch, Human Activity Recognition