This paper describes an accelerometer based gait analysis system for the assessment of fall risk. The assessment is based on 22 different features calculated from the signal. The different features are combined using machine learning algorithms in order to decide whether the subject has an increased fall risk. Results from Naive Bayes, Neural Networks, Locally Weighted Learning, Support Vector Machines and C4.5 are reported and compared. It is argued that the neural networks provide low accuracy results because of the high dimensionality of the feature space compared to the available data. It is shown that FD-NEAT (a method from neuro evolution which simultaneously learns the network topology, the network weights and the relevant features) outperforms the other methods in the given classification task. The system is evaluated on a database consisting of 40 elderly with known fall risk and 40 healthy elderly controls.
Jansen, B, TAN, MYL, Bautmans, I, Van Keymolen, B, Mets, T & Deklerck, R 2011, Accelerometer based gait analysis - multi variate assessment of fall risk with FD-NEAT. in Proceedings of Biosignals 2011. INSTICC Press, Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet, Stockholm, Sweden, 21/09/09. <http://www.etro.vub.ac.be/PUB_Files/IRIS/bjansen/BiosignalsJansen2011.pdf>
Jansen, B., TAN, M. Y. L., Bautmans, I., Van Keymolen, B., Mets, T., & Deklerck, R. (2011). Accelerometer based gait analysis - multi variate assessment of fall risk with FD-NEAT. In Proceedings of Biosignals 2011 INSTICC Press. http://www.etro.vub.ac.be/PUB_Files/IRIS/bjansen/BiosignalsJansen2011.pdf
@inproceedings{2d98121c77834807a49275de17c50ee3,
title = "Accelerometer based gait analysis - multi variate assessment of fall risk with FD-NEAT.",
abstract = "This paper describes an accelerometer based gait analysis system for the assessment of fall risk. The assessment is based on 22 different features calculated from the signal. The different features are combined using machine learning algorithms in order to decide whether the subject has an increased fall risk. Results from Naive Bayes, Neural Networks, Locally Weighted Learning, Support Vector Machines and C4.5 are reported and compared. It is argued that the neural networks provide low accuracy results because of the high dimensionality of the feature space compared to the available data. It is shown that FD-NEAT (a method from neuro evolution which simultaneously learns the network topology, the network weights and the relevant features) outperforms the other methods in the given classification task. The system is evaluated on a database consisting of 40 elderly with known fall risk and 40 healthy elderly controls.",
keywords = "accelerometer, gait analysis",
author = "Bart Jansen and TAN, {Maxine Yen Ling} and Ivan Bautmans and {Van Keymolen}, Bart and Tony Mets and Rudi Deklerck",
year = "2011",
month = jan,
day = "26",
language = "English",
isbn = "978-989-8425-35-5",
booktitle = "Proceedings of Biosignals 2011",
publisher = "INSTICC Press",
note = "Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet ; Conference date: 21-09-2009 Through 25-09-2009",
}