Laura Montanini

Multimodal Interaction in a Elderly-Friendly Smart Home: A Case Study

This paper discusses different and multimodal user-system interfaces proposed in the framework of a smart home designed to support the independent living of elderly and frail users. It is shown how different technologies and solutions may be complemented and integrated to provide effective interaction both for routine activities of daily living and anomalous situations.

Data Management in Ambient Assisted Living Platforms Approaching IoT: A Case Study

The adoption of the Internet of Things paradigm in Ambient Assisted Living platforms requires the investigation and analysis of issues related to data collection and processing. In fact, the peculiarities of Ambient Assisted Living services and applications pose specific requirements on the way data originated from sensors should be processed (locally or remotely), delivered (as raw data, or in aggregated fashion), and, of course, how they should be shared or protected. This paper analyses the issues related to data management starting from a review of the state of the art, in order to draw general trends or widespread approaches, that are then discussed and evaluated with respect to a practical implementation presented as a case study.

Comparison of RGB-D Mapping Solutions for Application to Food Intake Monitoring

Food intake behaviours are strictly correlated to health, especially for elderly people. Dietary habits monitoring is one of the most challenging activity for researchers in AAL scenario. RGB-D sensors, such as Kinect, provide multiple useful data to perform behavioural analysis in an unobtrusive way. Unfortunately, when using the Kinect sensor, depth and RGB data are not available with the same point of view, and a mapping algorithm is required in order to associate a 3D point to the same pixel in both the RGB and depth frames. In this paper, some techniques for RGB-D mapping of Kinect sensor data are compared, and a proposed implementation is described. Some experimental results in specific conditions are finally provided.

A simple object for elderly vitality monitoring: The smart insole

In the framework of Ambient Assisted Living solutions, it is very important to monitor the degree of vitality of elderly users in their daily activities, for example to evaluate if the user is spending too much time in a static condition, or not. In fact this could denote an anomalous trend, possibly related to cognitive or physical conditions worsening. For such a kind of monitoring to be effective, the sensor technology shall be the less intrusive as possible, and not require any specific action by the user. To this aim, the paper presents a smart insole equipped with force sensors, that is able to classify different dynamic states (sitting, walking, standing,...) and transmit related data to a supervising system. Preliminary experimental results show the feasibility of the approach, and the effectiveness of the insole in correctly detecting and classifying the users activities.

MQTT in AAL systems for home monitoring of people with dementia

The paradigmatic shift brought by the Internet of Things has already revolutionized many key sectors, like environmental monitoring, grid and energy management, manufacturing, and it can be seen as a promising solution to address challenging societal issues, like the ability to provide significant enhancement to quality of life for the elderly and, in general, people in need. As a consequence, Internet of Things emerges also as the possible next evolution for the Ambient Assisted Living domain. One major issue to address in this context is the identification of a suitable middleware able to leverage the potentialities offered by the Internet of Things and, at the same time, ensure the necessary support to services and functions related to healthcare and personal assistance. This paper provides an overview of middleware solutions designed for Internet of Things in health and wellness domains, and presents a case study related to assistive technology for the home monitoring of people with dementia. It is illustrated how a specific middleware designed for telemetry applications, the MQTT, can be effectively applied in assistive scenarios too, with different architectural options and communication technologies.

Interoperability in IoT infrastructures for enhanced living environments

The concept of Internet of Things is being applied in several areas and involves a dramatically increasing number of market sectors. There is a large variety of commercial products, and the competition between different vendors often causes incompatibility among the available solutions. Due to the lack of a reference standard, in the highly fragmented arena of Ambient Assisted Living systems and Smart Home environments, the support to interoperability is recognized as a key requirement for the deployment of successful products. This paper provides a state-of-the-art review of IoT adoption in the field of Ambient Assisted Living systems and Smart Home environments, by describing the most widespread solutions and their main key points, with a specific focus on the features designed to support interoperability. This is currently a matter of interest at a European level, as demonstrated, for example, by the inclusion of interoperability among the requirements that project proposals have to fulfill to be eligible for funding through the AAL Joint Platform calls published in the last years.

Unobtrusive Monitoring of Physical Activity in AAL - A Simple Wearable Device Designed for Older Adults

Many solutions and projects proposed within the Ambient Assisted Living research area, aim at monitoring the degree of vitality of elderly users in their daily activities, and in their home environment, to possibly avoid or strongly limit the need for clinical evaluations. In fact, the information on the subject’s vitality, manifested through his/her activity profile, may be used to evaluate possible anomalous trends, related to cognitive or physical decay. For such a kind of analysis to be realistically affordable, the monitoring device shall be unobtrusive, and transparent to the user. With the aim of striving for the simplest and most reliable design compatible with the aforementioned requirements, this paper presents a wearable device equipped with a sensing insole hosting force sensors, and the related electronics for signal processing and data transmission. The device locally classifies different dynamic states (sitting, walking, standing) and transmits the corresponding information to a supervising system. Preliminary experimental results confirm the effectiveness of the approach, in correctly detecting and classifying the user’s activities.

Low complexity head tracking on portable android devices for real time message composition

For the people who are totally or partially unable to move or control their limbs and cannot rely on verbal communication, it is very important to obtain an interface capable of interpreting their limited voluntary movements, in order to allow communications with friends, relatives and care providers, or to send commands to a system. This paper presents a real time software application for disabled subjects, suffering from both motor and speech impairments, that provides message composition and speech synthesis functionalities based on face detection and head tracking. The proposed application runs on portable devices equipped with Android Operating System, and relies upon the O.S.’s native computer vision primitives, without resorting to any external software library. This way, the available camera sensors are exploited, and the device computational requirements accomplished. Experimental results show the effectiveness of the application in recognizing the user’s movements, and the reliability of the message composition and speech synthesis functionalities.

Chapter 4 – The Human Factor in the Design of Successful Ambient Assisted Living Technologies

The increasing incidence of ageing population in modern societies challenges the ability of families, states and communities to sustain new emerging needs. Assistive devices can help older people to maintain their ability in performing activities of daily living and, therefore, their independence. However, despite the huge public and private investments and efforts in research and development, the so-called silver market has not been able to grow at the expected pace: many barriers stand in the way leading from prototypes to products, especially when the target is an inhomogeneous group, as elderly people, and an explicit understanding of users, their needs, expectations and limitations, is not accounted for during the design process. This Chapter discusses the basic role of the human centric approach in the design of assistive technologies, and, by analyzing the outcomes of previous experiences, provides a set of guidelines that can help transforming a disruptive prototype into a successful product.

Real time message composition through head movements on portable Android devices

The paper presents a computer vision application, to enable message composition by head tracking. The application runs in real time on portable Android devices, exploits the available camera sensors, and accomplishes the device computational requirements. Satisfactory results in correct movements detection, and reliable composition of messages, are obtained by experiments.