A novel monitoring system for fall detection in older people

Carla Taramasco, Tomas Rodenas, Felipe Martinez, Paola Fuentes, Roberto Munoz, Rodrigo Olivares, Victor Hugo C. De Albuquerque, Jacques Demongeot

Resultado de la investigación: Article

5 Citas (Scopus)

Resumen

Each year, more than 30% of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: Long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93% of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user's privacy, which constitutes an additional advantage of this alternative.

Idioma originalEnglish
Número de artículo8423052
Páginas (desde-hasta)43563-43574
Número de páginas12
PublicaciónIEEE Access
Volumen6
DOI
EstadoPublished - 27 jul 2018

Huella dactilar

Monitoring
Recurrent neural networks
Sensors
Learning algorithms
Long short-term memory
Hot Temperature

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Citar esto

Taramasco, C., Rodenas, T., Martinez, F., Fuentes, P., Munoz, R., Olivares, R., ... Demongeot, J. (2018). A novel monitoring system for fall detection in older people. IEEE Access, 6, 43563-43574. [8423052]. https://doi.org/10.1109/ACCESS.2018.2861331
Taramasco, Carla ; Rodenas, Tomas ; Martinez, Felipe ; Fuentes, Paola ; Munoz, Roberto ; Olivares, Rodrigo ; De Albuquerque, Victor Hugo C. ; Demongeot, Jacques. / A novel monitoring system for fall detection in older people. En: IEEE Access. 2018 ; Vol. 6. pp. 43563-43574.
@article{0774d55f171a47a09651adfb7f8b1584,
title = "A novel monitoring system for fall detection in older people",
abstract = "Each year, more than 30{\%} of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: Long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93{\%} of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user's privacy, which constitutes an additional advantage of this alternative.",
keywords = "artificial neural networks, Fall detection, older people",
author = "Carla Taramasco and Tomas Rodenas and Felipe Martinez and Paola Fuentes and Roberto Munoz and Rodrigo Olivares and {De Albuquerque}, {Victor Hugo C.} and Jacques Demongeot",
year = "2018",
month = "7",
day = "27",
doi = "10.1109/ACCESS.2018.2861331",
language = "English",
volume = "6",
pages = "43563--43574",
journal = "IEEE Access",
issn = "2169-3536",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Taramasco, C, Rodenas, T, Martinez, F, Fuentes, P, Munoz, R, Olivares, R, De Albuquerque, VHC & Demongeot, J 2018, 'A novel monitoring system for fall detection in older people', IEEE Access, vol. 6, 8423052, pp. 43563-43574. https://doi.org/10.1109/ACCESS.2018.2861331

A novel monitoring system for fall detection in older people. / Taramasco, Carla; Rodenas, Tomas; Martinez, Felipe; Fuentes, Paola; Munoz, Roberto; Olivares, Rodrigo; De Albuquerque, Victor Hugo C.; Demongeot, Jacques.

En: IEEE Access, Vol. 6, 8423052, 27.07.2018, p. 43563-43574.

Resultado de la investigación: Article

TY - JOUR

T1 - A novel monitoring system for fall detection in older people

AU - Taramasco, Carla

AU - Rodenas, Tomas

AU - Martinez, Felipe

AU - Fuentes, Paola

AU - Munoz, Roberto

AU - Olivares, Rodrigo

AU - De Albuquerque, Victor Hugo C.

AU - Demongeot, Jacques

PY - 2018/7/27

Y1 - 2018/7/27

N2 - Each year, more than 30% of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: Long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93% of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user's privacy, which constitutes an additional advantage of this alternative.

AB - Each year, more than 30% of people over 65 years-old suffer some fall. Unfortunately, this can generate physical and psychological damage, especially if they live alone and they are unable to get help. In this field, several studies have been performed aiming to alert potential falls of the older people by using different types of sensors and algorithms. In this paper, we present a novel non-invasive monitoring system for fall detection in older people who live alone. Our proposal is using very-low-resolution thermal sensors for classifying a fall and then alerting to the care staff. Also, we analyze the performance of three recurrent neural networks for fall detections: Long short-term memory (LSTM), gated recurrent unit, and Bi-LSTM. As many learning algorithms, we have performed a training phase using different test subjects. After several tests, we can observe that the Bi-LSTM approach overcome the others techniques reaching a 93% of accuracy in fall detection. We believe that the bidirectional way of the Bi-LSTM algorithm gives excellent results because the use of their data is influenced by prior and new information, which compares to LSTM and GRU. Information obtained using this system did not compromise the user's privacy, which constitutes an additional advantage of this alternative.

KW - artificial neural networks

KW - Fall detection

KW - older people

UR - http://www.scopus.com/inward/record.url?scp=85050771312&partnerID=8YFLogxK

U2 - 10.1109/ACCESS.2018.2861331

DO - 10.1109/ACCESS.2018.2861331

M3 - Article

VL - 6

SP - 43563

EP - 43574

JO - IEEE Access

JF - IEEE Access

SN - 2169-3536

M1 - 8423052

ER -

Taramasco C, Rodenas T, Martinez F, Fuentes P, Munoz R, Olivares R y otros. A novel monitoring system for fall detection in older people. IEEE Access. 2018 jul 27;6:43563-43574. 8423052. https://doi.org/10.1109/ACCESS.2018.2861331