A system for ubiquitous fall monitoring at home via a wireless sensor network and a wearable mote Roberto Paoli a , Francisco J. Fernández-Luque b , Ginés Doménech c , Félix Martínez c , Juan Zapata c,⇑ , Ramón Ruiz c a Faculty of Engineering, University of Bologna, 40127 Bologna (BO), Italy b Ambiental Intelligence & Interaction S.L.L. (Ami2), Edificio CEEIM, módulo 11, Campus Universitario Espinardo, s/n 30100 Murcia, Spain c Departamento de Electrónica, Tecnología de Computadoras y Proyectos, Universidad Politécnica de Cartagena, Antiguo Cuartel de Antigones, Plaza del Hospital 1, 30202 Cartagena, Spain article info Keywords: Falls in the elderly Fall detection Accelerometer Activities of daily living Wireless sensor network abstract Accidental falls of our elderly, and physical injuries resulting, represent a major health and economic problem. Falls are the most common cause of serious injuries and are a major health threat in the stratum of older population. Early detection of a fall is a key factor when trying to provide adequate care to elderly person who has suffered an accident at home. Therefore, the detection of falls in the elderly remains a major challenge in the field of public health. Specific actions aimed at the fall detection can provide urgent care which allows, on the other hand, drastically reduce the cost of medical care, and improve pri- mary care service. In this paper, we present a support system for detecting falls of an elder person by the combination of a wearable wireless sensor node based on an accelerometer and a static wireless non- intrusive sensory infrastructure based on heterogeneous sensor nodes. This previous infrastructure called DIA (Dispositivo Inteligente de Alarma, in Spanish) is an AAL (Ambient Assisted Living) system that allows to infer a potential fall. This inference is reinforced for prompt attention by a specific sensorisation at portable node sensor in order to help distinguish between falls and daily activities of assisted person. The wearable node will not determine a falling situation, it will advice the reasoner layer about specific acceleration patterns that could, eventually, imply a falling. Is at the higher layer where the falling is determined from the whole context produced by mesh of fixed nodes. Experimental results have shown that the proposed system obtains high reliability and sensitivity in the detection of the fall. Ó 2011 Elsevier Ltd. All rights reserved. 1. Introduction 1.1. Background The main causes of serious injuries in the elderly people (above 65 years old) were the unintentional falls. Physical injuries result- ing cause that much of the social resources in the national health insurance system are aimed at alleviating the consequences of these accidents. Approximately 25–35% of the elderly persons suffered at least one fall per year experiencing related injuries. Nearly 30–40% of these falls resulted in a visit to the emergency room for treatment where they were hospitalized (Brewer, Ciolek, & Delaune, 2007; Changhua Healthcare Quality, 2010). In particu- lar, nearly 3% of the elderly falls were completely neglected for more than 20 min (Lindemann, Hock, Stuber, Keck, & Becker, 2005). These situations can endanger people fall, either serious accident or not. The estimated expenditure on medical care for the falls suffered by elderly residents and their related injuries will reach 32 billion euros in 2020 (Brewer et al., 2007). There is no doubt that falls and their consequences are one of the main items of expenditure for social security systems. 1.2. Motivation The goal of the DIA Project (Fernández-Luque, Zapata, Ruiz, & Iborra, 2009) is to provide an infrastructure of networked sensors that supports multiple applications simultaneously. The sensor network, like DIA, would spread throughout the environment, whether it is any room of home, routing and linking motes to the base station. In general, motes can be divided into two types: (1) fixed/infrastructure motes, for example attached alongside the walls and corridors, doors and furnishings and (2) mobile motes, whose geographical position can change over time. The goal of this project is to provide alerts to caregivers in the event of an accident, acute illness or strange (possibly dangerous) activities, and enable monitoring by authorized and authenticated caregivers. The sys- tem facilitates privacy by performing local computation, it 0957-4174/$ - see front matter Ó 2011 Elsevier Ltd. All rights reserved. doi:10.1016/j.eswa.2011.11.061 ⇑ Corresponding author. E-mail address: juan.zapata@upct.es (J. Zapata). Expert Systems with Applications 39 (2012) 5566–5575 Contents lists available at SciVerse ScienceDirect Expert Systems with Applications journal homepage: www.elsevier.com/locate/eswa