Rapid population growth and the increase in older people in need of care produce significant changes in healthcare and quality of life in many nations. Home care, compared to hospitalization, can be a valid and less expensive alternative. To help people with disabilities, we need to identify daily physical activities without supporting others. There are several automatic techniques for recognizing human activities. Nowadays, development in I CT and Artificial Intelligence enable intelligent systems to monitor the conditions and activities of elderly people. Moreover, nanotechnology such as MEMS offers advantages of small size, low power consumption, and analyzing human motion. These technologies can recognize when it is necessary to act in dangerous situations. The proposed solution in this manuscript represents an integrated prototype that provides an efficient technological tool to caregivers serving promptly and assuring efficient performance throughout the entire health care system process. In the present work, we use an IoT platform in which, through inertial sensors, we collect kinematic data transferred to a convolutional neural network to classify human activities. For accurate identification of the localization of the subjects, we integrated the system with an ultrasonic network. Then to verify the correct inter-pretation, we used Virtual Reality. © 2022 University of Split, FESB.

Home care system for the elderly and pathological conditions

Bibbo, Luigi
;
Carotenuto, Riccardo;Merenda, Massimo;Messina, Giacomo
2022-01-01

Abstract

Rapid population growth and the increase in older people in need of care produce significant changes in healthcare and quality of life in many nations. Home care, compared to hospitalization, can be a valid and less expensive alternative. To help people with disabilities, we need to identify daily physical activities without supporting others. There are several automatic techniques for recognizing human activities. Nowadays, development in I CT and Artificial Intelligence enable intelligent systems to monitor the conditions and activities of elderly people. Moreover, nanotechnology such as MEMS offers advantages of small size, low power consumption, and analyzing human motion. These technologies can recognize when it is necessary to act in dangerous situations. The proposed solution in this manuscript represents an integrated prototype that provides an efficient technological tool to caregivers serving promptly and assuring efficient performance throughout the entire health care system process. In the present work, we use an IoT platform in which, through inertial sensors, we collect kinematic data transferred to a convolutional neural network to classify human activities. For accurate identification of the localization of the subjects, we integrated the system with an ultrasonic network. Then to verify the correct inter-pretation, we used Virtual Reality. © 2022 University of Split, FESB.
2022
convolutional neural networks; environmental sensors; human activity; indoor positioning; inertial sensors; virtual reality
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12318/131986
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
social impact