Smart homes play a strategic role for improving life quality of people, enabling to monitor people at home with numerous intelligent devices. Sensors can be installed to provide a continuous assistance without limiting the resident’s daily routine, giving her/him greater comfort, well-being and safety. This paper is based on the development of domestic technological solutions to improve the life quality of citizens and monitor the users and the domestic environment, based on features extracted from the collected data. The proposed smart sensing architecture is based on an integrated sensor network to monitor the user and the environment to derive information about the user’s behavior and her/his health status. The proposed platform includes biomedical, wearable, and unobtrusive sensors for monitoring user’s physiological parameters and home automation sensors to obtain information about her/his environment. The sensor network stores the heterogeneous data both locally and remotely in Cloud, where machine learning algorithms and data mining strategies are used for user behavior identification, classification of user health conditions, classification of the smart home profile, and data analytics to implement services for the community. The proposed solution has been experimentally tested in a pilot study based on the development of both sensors and services for elderly users at home.

Introduction
Life expectancy has increased significantly in the last years thanks to the rapid growth in medical science. The number of people aged 65 and older is increasing [1]. Consequently, the percentage of elderly people that prefer to stay in their homes and communities is growing: this phenomenon is called “Aging in Place” [2]. In this context, smart home technologies could significantly support people to have a better life quality, to live independently and to stay in contact with family and caregivers [3]. Thanks to their software and hardware components, smart homes allow collectin data and, thus, to monitor the health status, the behavior and the life quality of elderly users, avoiding risky situations and putting the users in contact with their family, caregivers and medical staff [4]. Thus, modern sensor-embedded houses, or smart houses, can not only assist elderly people but also help to resolve the social isolation they could face [5,6]. In this scenario, smart home technologies hold a great promise for the future of healthcare and well-being of older adults, people with disabilities, and the general population overall [7].
Smart homes have been extensively researched in the last years. The “Smart Rooms” implemented by the MIT Media Lab [8] could be defined as the first approach to this topic. Thereafter, several papers have been published on this topic with a wide range of prospective applications. A review of the state of the art of smart homes is presented in [9,10,11], while an international selection of leading smart home projects, as well as the associated technologies of wearable/implantable monitoring systems and assistive robotics are presented in [5]. A review of sensor technology used in smart homes with a focus on direct environment sensing and infrastructure mediated sensing is provided in [12]. A review of the potential of smart homes to support independent living is provided in [13], identifying some of the health needs of elderly people who could live at home if provided with adequate support, the range and type of technologies that could be employed to this objective, and suitable metrics to be used to measure the effectiveness of these technologies. Many research projects have been delivered on smart homes with the objective to provide an ecosystem of medical and home automation sensors, computers or smartphone, wireless networks [14] and software services for healthcare monitoring and control [5]. Many of them can be grouped into distinct categories, such as projects for facilitating the connection between the elderly and their informal caregiver, projects for monitoring health parameters and generate alerts messages in relation to a specific programmable situation, or projects that realize the smart home monitoring with the focus to learn and to predict the habits of its inhabitants in order to manage elderly safety and improve life quality. The use of a new architecture and technologies for intelligent environments, which includes smart user interface, dynamic configuration of the smart sensors, wireless control, tracking of the elderly people and flexible user services interaction, was proposed by Brumitt et al. in the EasyLiving project [15] at Microsoft Research. A multi-disciplinary research project, namely the CASAS Smart Home project, has been presented by the Washington State University. The objective of the project was to improve the safety, the life quality, the comfort and the state of the smart home residents using intelligent software agents and sensors and environment controllers [16,17]. In [18], Cook et al. proposed an intelligent and versatile home environment, namely MavHome project, which acquires data, and learns and predicts the residents habits to maximize their comfort and wellness, while reducing operating cost. The DOREMI project [19] is oriented to reduce the cognitive decline, malnutrition, and sedentariness of elderly people, and to increase the social interaction with the use of cognitive virtual games and virtual companion. The use of software platform and smart object permits to stimulate and to unobtrusively monitor the elderly daily life activities. In addition, different AAL platforms and solutions exist and have been studied in different European projects, see for instance [20,21,22,23,24]. Although the described smart home projects apply very interesting concepts in real scenarios, they often do not integrate all technological aspects such as biomedical sensors, wireless sensor network, home automation devices, behavioral analysis, Cloud infrastructure, custom Cloud services and flexibility, interoperability and extensibility of the acquisition software platform.
This paper is focused on the development of domestic technological solutions to improve the life quality of citizens and monitor the users and the environment where they spend most of their time, i.e., their house, based on features extracted from the collected data. The innovative system described in this paper is based on an integrated sensor network to monitor the user and the environment to derive information about the user’s behavior, her/his health status, her/his social condition, etc. The proposed platform includes biomedical, wearable, and unobtrusive sensors for monitoring user’s physiological parameters and home automation sensors to obtain information about her/his environment, e.g., energy consumptions, light status, user movement, etc. The sensor network stores the heterogeneous data both locally and remotely in Cloud, where machine learning algorithms and data mining strategies are used for user-health behavior identification, classification of user health conditions, classification of the smart home profile, and data analytics to implement services for the community. One of the aspects of our proposed architecture with respect to the existing ones is the user interaction with the architecture, namely the way the user can interact with the system by using, as a user interface, an Android app that can be run on most commercial smartphones/tablets to perform biomedical measurements from any of the devices. More specifically, the app layout depends on the specific logged-in user in a dynamic fashion. Each user is presented with the subset of devices, among those present in the house, which she/he has the permission to use. The app serves to initiate the measurement process from any of such devices. The proposed solution has been experimentally tested in a pilot study carried out in a small city of Veneto Region, Italy, within the context of the Health@Home project [25]. The pilot involved the development of both sensors and services for elderly users at home. Thus, the ICT technologies, characteristics of a smart home, are used to collect data and information, with the aim to provide ad-hoc services (e.g., care and social services) for elderly users and to improve their quality of life. It is worth pointing out that the idea of bringing integrated monitoring services to citizens’ homes, is not confined to the vertical e-Health domain. In fact, the concept of “Smart Home” is well integrated in horizontal domains such as “Smart Buildings” and “Smart Cities” [7,26,27]. The Health@Home project platform aims at the overall development of an e-market place where services are offered, which make use of citizen’s data collected in their home environments. The ultimate goal of the project is to generate service models that are economically sustainable by coupling social/sanitary support (e.g., catering, social assistance, etc.) with house-related interventions (e.g., maintenance of appliances) exploiting a unique ICT platform. This is the reason for the sensor network architecture proposed in this paper, here specifically exploited for advanced domestic monitoring as a part of the whole system.
The paper is organized as follows. The hardware and software of the proposed smart sensing architecture are described in Section 2. The pilot case is detailed in Section 3, while an extensive analysis of the results of the pilot study is presented in Section 4. Some remarks and future works conclude this paper in Section 5.

Read all the article >