Segmentation of the human gait cycle using hidden Markov Models (HMM)

Abstract: This paper provides a supervised Hidden Markov Model (HMM) for the segmentation of the human gait cycle. The model arises, in turn, from the combination of two HMM models, each with three hidden states, making use of the DepmixS4 and RcppHMM libraries of the free software R. The valida...

Descripción completa

Detalles Bibliográficos
Autores principales:	Molina, Diego Edwards, Miralles, Mónica Teresita, Florentin, Raúl
Formato:	Parte de libro
Lenguaje:	Inglés
Publicado:	Springer Nature Switzerland 2024
Materias:	CICLO DE LA MARCHA MODELOS OCULTOS DE MARKOV
Acceso en línea:	https://repositorio.uca.edu.ar/handle/123456789/18415
Aporte de:	Repositorio Institucional de la Universidad Católica Argentina (UCA) de Universidad Católica Argentina

id	I33-R139-123456789-18415
record_format	dspace
spelling	I33-R139-123456789-184152024-07-19T05:01:24Z Segmentation of the human gait cycle using hidden Markov Models (HMM) Molina, Diego Edwards Miralles, Mónica Teresita Florentin, Raúl CICLO DE LA MARCHA MODELOS OCULTOS DE MARKOV Abstract: This paper provides a supervised Hidden Markov Model (HMM) for the segmentation of the human gait cycle. The model arises, in turn, from the combination of two HMM models, each with three hidden states, making use of the DepmixS4 and RcppHMM libraries of the free software R. The validation of the model was carried out with the cross-validation method in two different ways. The three accelerometer signals provided by the sensor located in the left ankle and in the right ankle, respectively, were processed in the 20 healthy young subjects (33.4 ± 7 years, height 172.6 ± 9.5 cm, muscle mass 73.2 ± 10.9 kg), the open base MAREA. The base has different tests in indoor and outdoor environment, allowing a variety of walking situations, even the combination of walking and running. In this way the model provides a new validation for the base. The results were expressed from the statistics derived from the confusion matrix: Accuracy, Sensitivity and Specificity. In the tests of walking for 3 min on the flat surface in close environment, the model reached: 99%, 84.1% and 93.2% respectively (sensor on left ankle).With the signals obtained from the right ankle, the valueswere 93%, 73% and 86.4%, respectively. In both cases, the acceleration signals were filtered with the Butterworth filter. The results are discussed with other authors who have used the same base with different algorithms. 2024-07-18T13:15:34Z 2024-07-18T13:15:34Z 2024 Parte de libro Molina, D. E., Miralles, M. T., Florentin, R. Segmentation of the human gait cycle using hidden Markov Models (HMM) [et al.]. En: Ballina, F.E., Armentano, R., Acevedo, R.C., Meschino, G.J. (eds) Advances in Bioengineering and Clinical Engineering. SABI 2023. IFMBE Proceedings, vol 114. Cham: Springer, 2024. doi: 10.1007/978-3-031-61973-1_8. Disponible en: https://repositorio.uca.edu.ar/handle/123456789/18415 978-3-031-61972-4 https://repositorio.uca.edu.ar/handle/123456789/18415 10.1007/978-3-031-61973-1_8 eng Atribución-NoComercial-CompartirIgual 4.0 Internacional http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Springer Nature Switzerland Ballina, F.E., Armentano, R., Acevedo, R.C., Meschino, G.J. (eds) Advances in Bioengineering and Clinical Engineering. SABI 2023. IFMBE Proceedings, vol 114. Cham: Springer, 2024
institution	Universidad Católica Argentina
institution_str	I-33
repository_str	R-139
collection	Repositorio Institucional de la Universidad Católica Argentina (UCA)
language	Inglés
topic	CICLO DE LA MARCHA MODELOS OCULTOS DE MARKOV
spellingShingle	CICLO DE LA MARCHA MODELOS OCULTOS DE MARKOV Molina, Diego Edwards Miralles, Mónica Teresita Florentin, Raúl Segmentation of the human gait cycle using hidden Markov Models (HMM)
topic_facet	CICLO DE LA MARCHA MODELOS OCULTOS DE MARKOV
description	Abstract: This paper provides a supervised Hidden Markov Model (HMM) for the segmentation of the human gait cycle. The model arises, in turn, from the combination of two HMM models, each with three hidden states, making use of the DepmixS4 and RcppHMM libraries of the free software R. The validation of the model was carried out with the cross-validation method in two different ways. The three accelerometer signals provided by the sensor located in the left ankle and in the right ankle, respectively, were processed in the 20 healthy young subjects (33.4 ± 7 years, height 172.6 ± 9.5 cm, muscle mass 73.2 ± 10.9 kg), the open base MAREA. The base has different tests in indoor and outdoor environment, allowing a variety of walking situations, even the combination of walking and running. In this way the model provides a new validation for the base. The results were expressed from the statistics derived from the confusion matrix: Accuracy, Sensitivity and Specificity. In the tests of walking for 3 min on the flat surface in close environment, the model reached: 99%, 84.1% and 93.2% respectively (sensor on left ankle).With the signals obtained from the right ankle, the valueswere 93%, 73% and 86.4%, respectively. In both cases, the acceleration signals were filtered with the Butterworth filter. The results are discussed with other authors who have used the same base with different algorithms.
format	Parte de libro
author	Molina, Diego Edwards Miralles, Mónica Teresita Florentin, Raúl
author_facet	Molina, Diego Edwards Miralles, Mónica Teresita Florentin, Raúl
author_sort	Molina, Diego Edwards
title	Segmentation of the human gait cycle using hidden Markov Models (HMM)
title_short	Segmentation of the human gait cycle using hidden Markov Models (HMM)
title_full	Segmentation of the human gait cycle using hidden Markov Models (HMM)
title_fullStr	Segmentation of the human gait cycle using hidden Markov Models (HMM)
title_full_unstemmed	Segmentation of the human gait cycle using hidden Markov Models (HMM)
title_sort	segmentation of the human gait cycle using hidden markov models (hmm)
publisher	Springer Nature Switzerland
publishDate	2024
url	https://repositorio.uca.edu.ar/handle/123456789/18415
work_keys_str_mv	AT molinadiegoedwards segmentationofthehumangaitcycleusinghiddenmarkovmodelshmm AT mirallesmonicateresita segmentationofthehumangaitcycleusinghiddenmarkovmodelshmm AT florentinraul segmentationofthehumangaitcycleusinghiddenmarkovmodelshmm
_version_	1807949589118976000

Segmentation of the human gait cycle using hidden Markov Models (HMM)

Ejemplares similares