Vol.:(0123456789) 1 3 Journal of Ambient Intelligence and Humanized Computing https://doi.org/10.1007/s12652-018-0724-4 ORIGINAL RESEARCH Ambient assistance service for fall and heart problem detection Amina Makhlouf 1  · Isma Boudouane 1  · Nadia Saadia 1  · Amar Ramdane Cherif 2 Received: 30 April 2017 / Accepted: 15 February 2018 © Springer-Verlag GmbH Germany, part of Springer Nature 2018 Abstract Continuous monitoring of vital signs and activity measures has the potential to provide remote health monitoring and rapid detection of critical events such as heart attacks and falls. This paper proposes a multimodal system for monitoring the elderly at their homes. The system proposed contains three ambient assistance services (Fall detection, Heart disorder detection and Location) and an emergency service. A three-axis accelerometer, pulse oximeter and eight photoelectric sensors are applied for fall detection, cardiac problems detection and location respectively. The emergency service provides data fusion of this sensors and sends detailed information about the statue of the followed person to the doctor. This multimodal system is mod- eled by Colored Timed and Stochastic Petri nets (CTSPN) simulated in CPNTools. Experimental tests for each service have been performed on 10 subjects. The results show that falls can be detected from walking or standing with 87% of accuracy, 82% of sensitivity and 92% of specifcity, from a total data set of 50 emulates falls and 50 normal activities daily living. The results obtained during the tests validate the detection of tachycardia with 100% of success. The location was done with 94% of sensitivity. The proposed system minimizes the false positive and false negative. Keyword Ambient assistance service · Multimodal systems · Fall detection · Heart disorder detection · Location 1 Introduction The elderly population increases considerably with changes in the quality of life and the various support services. In 2000, there were already 420 million people with more than 65 years old (about 7% of the world population), and the statistics estimated that this number will reach 1500 million (about 16% of the world population) in the 2050 (Steg et al. 2006; Destatis 2011). The fall and injuries that result are a major health problem for the elderly. National Safety Coun- cil (NSC) estimates that the highest mortality rate among persons over 65 years is due to falls. Heart rate is an important factor for cardiovascular dis- ease. It is also related to an increase in mortality due to heart failure to the elderly (Fox et al. 2007; Maddox et al. 2008). Heart rate monitoring and falls detection can give a good indication of the health status of the elderly. This infor- mation can help to provide the necessary medical service. The rising cost of healthcare requires an adapted method for reducing hospital readmissions. Home monitoring in real- time or near-real is the solution to follow the elderly in their home and send information to the doctor. The monitoring systems of elderly people in their envi- ronment provide several services (Foko et al. 2013): • extend the time people can live in their preferred environ- ment by increasing their autonomy; • support maintaining health and functional capability of the elderly individuals; • promote a better and healthier life style for individuals at risk; • support Caregiver, families and care organizations; • increase the efciency and productivity of used resources in the ageing societies. This paper proposes a multimodal monitoring system of elderly in their environment which provides three ambient assistance services for fall detection, cardiac problem detec- tion and the location of elderly. This system included also * Amina Makhlouf amina.makhlouf14@gmail.com 1 LRPE Laboratory, University of Sciences and Technology Houari Boumediene, BP 32 EL ALIA, 16111 Bab Ezzouar Algiers, Algeria 2 LISV Laboratory, University of Versailles Saint-Quentin-en-yvelines, 10-12 avenue de l’Europe, 78140 Velizy, France