Papers Papers/2020



Authors: Mariana Abreu 1 ; Marília Barandas 1 ; Ricardo Leonardo 1 and Hugo Gamboa 2

Affiliations: 1 Associacao Fraunhofer Portugal Research, Rua Alfredo Allen 455/461, Porto and Portugal ; 2 Laboratorio de Instrumentacao, Engenharia Biomedica e Fisica da Radiacao (LIBPhys-UNL), Departamento de Fisica, Faculdade de Ciencias e Tecnologia, FCT, Universidade Nova de Lisboa, 2829-516 Caparica and Portugal

Keyword(s): Human Activity Recognition, Gesture Recognition, Smartphone Sensors, Feature Selection, Hidden Markov Models.

Related Ontology Subjects/Areas/Topics: Animation and Simulation ; Biomedical Engineering ; Biomedical Signal Processing ; Computer Vision, Visualization and Computer Graphics ; Detection and Identification ; Devices ; Health Information Systems ; Human-Computer Interaction ; Motion Control ; Physiological Computing Systems ; Wearable Sensors and Systems

Abstract: A wide array of activities is performed by humans, everyday. In healthcare, precocious detection of movement changes in daily activities and their monitoring, are important contributors to assess the patient general well-being. Several previous studies are successful in activity recognition, but few of them provide a meticulous discrimination. Hereby, we created a novel framework specialized in detailed human activities, where signals from four sensors were used: accelerometer, gyroscope, magnetometer and microphone. A new dataset was created, with 10 complex activities, suchlike opening a door, brushing the teeth and typing on the keyboard. The classifier was based on multiple hidden Markov models, one per activity. The developed solution was evaluated in the offline context, where it achieved an accuracy of 84±4.8%. It also showed a solid performance in other performed tests, where it was tested with different detailed activities, and in simulations of real time recognition. This s olution can be applied in elderly monitoring to access their well-being and also in the early detection of degenerative diseases. (More)


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

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:
Abreu, M.; Barandas, M.; Leonardo, R. and Gamboa, H. (2019). Detailed Human Activity Recognition based on Multiple HMM. In Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS, ISBN 978-989-758-353-7; ISSN 2184-4305, pages 171-178. DOI: 10.5220/0007386901710178

author={Mariana Abreu. and Marília Barandas. and Ricardo Leonardo. and Hugo Gamboa.},
title={Detailed Human Activity Recognition based on Multiple HMM},
booktitle={Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS,},


JO - Proceedings of the 12th International Joint Conference on Biomedical Engineering Systems and Technologies - BIOSIGNALS,
TI - Detailed Human Activity Recognition based on Multiple HMM
SN - 978-989-758-353-7
IS - 2184-4305
AU - Abreu, M.
AU - Barandas, M.
AU - Leonardo, R.
AU - Gamboa, H.
PY - 2019
SP - 171
EP - 178
DO - 10.5220/0007386901710178