%0 Conference Proceedings %T An Efficient Design of a Machine Learning-Based Elderly Fall Detector %+ Laboratoire Traitement du Signal et de l'Image (LTSI) %A Nguyen, L.P. %A Saleh, M. %A Le Bouquin Jeannès, R. %Z FNS, French Norwegian Foundation %Z MESR, Ministère de l'Education Nationale, de l'Enseignement Superieur et de la Recherche %Z EGU, European Geosciences Union %Z ERDF, European Regional Development Fund %< avec comité de lecture %B 4th International Conference on Internet of Things (IoT) Technologies for HealthCare, HealthyIoT 2017 %C Angers, France %Y Bastel J.-B.Ahmed M.U.Begum S. %I Springer Verlag %V 225 %P 34-41 %8 2017-10-24 %D 2017 %R 10.1007/978-3-319-76213-5_5 %K Elderly fall detection %K Inertial measurement unit %K K-nearest neighbors %K Micro electro mechanical system %K Multi-layer perceptron %K Support vector machine %Z Life Sciences [q-bio]/BioengineeringConference papers %X Elderly fall detection is an important health care application as falls represent the major reason of injuries. An efficient design of a machine learning-based wearable fall detection system is proposed in this paper. The proposed system depends only on a 3-axial accelerometer to capture the elderly motion. As the power consumption is proportional to the sampling frequency, the performance of the proposed fall detector is analyzed as a function of this frequency in order to determine the best trade-off between performance and power consumption. Thanks to efficient extracted features, the proposed system achieves a sensitivity of 99.73% and a specificity of 97.7% using a 40 Hz sampling frequency notably outperforming reference algorithms when tested on a large dataset. © 2018, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering. %G English %L hal-01740204 %U https://univ-rennes.hal.science/hal-01740204 %~ UNIV-RENNES1 %~ LTSI %~ STATS-UR1 %~ UR1-HAL %~ UR1-MATH-STIC %~ TEST-UR-CSS %~ UNIV-RENNES %~ UR1-MATH-NUM %~ UR1-BIO-SA