MyoGym : introducing an open gym data set for activity recognition collected using myo armband
Koskimäki, Heli; Siirtola, Pekka; Röning, Juha (2017-09-01)
Heli Koskimäki, Pekka Siirtola, and Juha Röning. 2017. MyoGym: introducing an open gym data set for activity recognition collected using myo armband. In Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers (UbiComp ’17). Association for Computing Machinery, New York, NY, USA, 537–546. DOI:Heli Koskimäki, Pekka Siirtola, and Juha Röning. 2017. MyoGym: introducing an open gym data set for activity recognition collected using myo armband. In Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers (UbiComp ’17). Association for Computing Machinery, New York, NY, USA, 537–546. DOI:https://doi.org/10.1145/3123024.3124400
© 2017 Copyright is held by the owner/author(s). Publication rights licensed to ACM. This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 2017 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2017 ACM International Symposium on Wearable Computers (UbiComp '17). Maui, Hawaii, September 11 - 15, 2017, https://doi.org/10.1145/3123024.3124400.
https://rightsstatements.org/vocab/InC/1.0/
https://urn.fi/URN:NBN:fi-fe202003208605
Tiivistelmä
Abstract
The activity recognition research has remained popular although the first steps were taken almost two decades ago. While the first ideas were more like a-proof-of-concept studies the area has become a fruitful soil to novel methods of machine learning, to adaptive modeling, signal fusion and several different types of application areas. Nevertheless, one of the slowing aspects in methodology development is the burden in collecting and labeling enough versatile data sets. In this article, a MyoGym data set is introduced to be used in activity recognition classifier development, in development of models for unseen activities, in signal fusion, and many other areas not yet known. The data set includes 6D motion signals and 8 channel electromyogram data from 10 persons and from 30 different gym exercises, each of them consisting a set of ten repetitions. The benchmark results provided, in this article, are in purpose made straightforward that their repetitiveness should be easy for any newcomer in the area.
Kokoelmat
- Avoin saatavuus [32009]