- author = "Alejandro Baldominos and Carmen {del Barrio} and Yago Saez",
- title = "Exploring the Application of Hybrid Evolutionary Computation Techniques to Physical Activity Recognition",
- booktitle = "GECCO '16 Companion: Proceedings of the Companion Publication of the 2016 Annual Conference on Genetic and Evolutionary Computation",
- year = "2016",
- editor = "Tobias Friedrich and Frank Neumann and Andrew M. Sutton and Martin Middendorf and Xiaodong Li and Emma Hart and Mengjie Zhang and Youhei Akimoto and Peter A. N. Bosman and Terry Soule and Risto Miikkulainen and Daniele Loiacono and Julian Togelius and Manuel Lopez-Ibanez and Holger Hoos and Julia Handl and Faustino Gomez and Carlos M. Fonseca and Heike Trautmann and Alberto Moraglio and William F. Punch and Krzysztof Krawiec and Zdenek Vasicek and Thomas Jansen and Jim Smith and Simone Ludwig and JJ Merelo and Boris Naujoks and Enrique Alba and Gabriela Ochoa and Simon Poulding and Dirk Sudholt and Timo Koetzing",
- isbn13 = "978-1-4503-4323-7",
- pages = "1377--1384",
- address = "Denver, Colorado, USA",
- month = "20-24 " # jul,
- keywords = "genetic algorithms, genetic programming",
- organisation = "SIGEVO",
-
DOI = "
doi:10.1145/2908961.2931732",
- publisher = "ACM",
- publisher_address = "New York, NY, USA",
-
abstract = "his paper focuses on the problem of physical activity
recognition, i.e., the development of a system which is
able to learn patterns from data in order to be able to
detect which physical activity (e.g. running, walking,
ascending stairs, etc.) a certain user is
performing.
While this field is broadly explored in the literature, there are few works that face the problem with evolutionary computation techniques. In this case, we propose a hybrid system which combines particle swarm optimization for clustering features and genetic programming combined with evolutionary strategies for evolving a population of classifiers, shaped in the form of decision trees. This system would run the segmentation, feature extraction and classification stages of the activity recognition chain.
For this paper, we have used the PAMAP2 dataset with a basic preprocessing. This dataset is publicly available at UCI ML repository. Then, we have evaluated the proposed system using three different modes: a user-independent, a user-specific and a combined one. The results in terms of classification accuracy were poor for the first and the last mode, but it performed significantly well for the user-specific case. This paper aims to describe work in progress, to share early results an discuss them. There are many things that could be improved in this proposed system, but overall results were interesting especially because no manual data transformation took place.",
- notes = "Distributed at GECCO-2016.",
