loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Evangelia Pippa 1 ; Iosif Mporas 2 and Vasileios Megalooikonomou 1

Affiliations: 1 University of Patras, Greece ; 2 University of Patras and University of Hertfordshire, Greece

Keyword(s): Human Motion Detection, Machine Learning, Feature Extraction.

Related Ontology Subjects/Areas/Topics: Artificial Intelligence ; Business Analytics ; Cardiovascular Technologies ; Computing and Telecommunications in Cardiology ; Data Engineering ; Decision Support Systems ; Decision Support Systems, Remote Data Analysis ; Health Engineering and Technology Applications ; Knowledge-Based Systems ; Symbolic Systems

Abstract: In order to plan and deliver health care in a world with increasing number of older people, human motion monitoring is a must in their surveillance, since the related information is crucial for understanding their physical status. In this article, we focus on the physiological function and motor performance thus we present a light human motion identification scheme together with preliminary evaluation results, which will be further exploited within the FrailSafe Project. For this purpose, a large number of time and frequency domain features extracted from the sensor signals (accelerometer and gyroscope) and concatenated to a single feature vector are evaluated in a subject dependent cross-validation setting using SVMs. The mean classification accuracy reaches 96%. In a further step, feature ranking and selection is preformed prior to subject independent classification using the ReliefF ranking algorithm. The classification model using feature subsets of different size is evaluated in order to reveal the best dimensionality of the feature vector. The achieved accuracy is 97% which is a slight improvement compared to previous approaches evaluated on the same dataset. However, such an improvement can be considered significant given the fact that it is achieved with lighter processing using a smaller number of features. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 44.210.120.182

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Pippa, E.; Mporas, I. and Megalooikonomou, V. (2016). Feature Selection Evaluation for Light Human Motion Identification in Frailty Monitoring System. In Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AGEINGWELL 2016) - ICT4AWE; ISBN 978-989-758-180-9; ISSN 2184-4984, SciTePress, pages 88-95. DOI: 10.5220/0005912200880095

@conference{ict4awe16,
author={Evangelia Pippa. and Iosif Mporas. and Vasileios Megalooikonomou.},
title={Feature Selection Evaluation for Light Human Motion Identification in Frailty Monitoring System},
booktitle={Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AGEINGWELL 2016) - ICT4AWE},
year={2016},
pages={88-95},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005912200880095},
isbn={978-989-758-180-9},
issn={2184-4984},
}

TY - CONF

JO - Proceedings of the International Conference on Information and Communication Technologies for Ageing Well and e-Health (ICT4AGEINGWELL 2016) - ICT4AWE
TI - Feature Selection Evaluation for Light Human Motion Identification in Frailty Monitoring System
SN - 978-989-758-180-9
IS - 2184-4984
AU - Pippa, E.
AU - Mporas, I.
AU - Megalooikonomou, V.
PY - 2016
SP - 88
EP - 95
DO - 10.5220/0005912200880095
PB - SciTePress