Vincent Rialle

Fall detection - Principles and Methods

Fall detection of the elderly is a major public health problem. Thus it has generated a wide range of applied research and prompted the development of telemonitoring systems to enable the early diagnosis of fall conditions. This article is a survey of systems, algorithms and sensors, for the automatic early detection of the fall of elderly persons. It points out the difficulty to compare the performances of the different systems due to the lack of a common framework. It then proposes a procedure for this evaluation.

Monitoring behavior in home using a smart fall sensor and position sensors

The authors developed a system for remotely monitoring human behavior during daily life at home, to improve the security and the quality of life. The activity was monitored through infrared position sensors and magnetic switches. For the falls detection the authors had to develop a smart sensor. The local communications were performed using RF wireless links to reduce the cabling and to allow mobility of the person. An application software performs data exploitation locally but it also performs remote data transmission through the network. This project aim at expanding the telecare solution to a larger population of elderly people who are presently forced to live in hospices.

New trends in health smart homes

The concept of Health Smart House aims at giving an autonomous life, in their own home, to people who would normally be placed in institutions: patients suffering from a chronic disease, handicapped people, and also fragile elderly. We propose an overview of the researches on the concept. It then presents the main trends in each the technological fields of concern-Information systems, home automations, ubiquitous sensors, robotic assistance-meanwhile it indicates the standards efforts leaded by some large consortiums, and the ethical point of view.

Modeling the progression of Alzheimer's disease for cognitive assistance in smart homes

Smart homes provide support to cognitively impaired people (such as those suffering from Alzheimer’s disease) so that they can remain at home in an autonomous and safe way. Models of this impaired population should benefit the cognitive assistance’s efficiency and responsiveness. This paper presents a way to model and simulate the progression of dementia of the Alzheimer’s type by evaluating performance in the execution of an activity of daily living (ADL). This model satisfies three objectives: first, it models an activity of daily living; second, it simulates the progression of the dementia and the errors potentially made by people suffering from it, and, finally, it simulates the support needed by the impaired person. To develop this model, we chose the ACT-R cognitive architecture, which uses symbolic and subsymbolic representations. The simulated results of 100 people suffering from Alzheimer’s disease closely resemble the results obtained by 106 people on an occupational assessment (the Kitchen Task Assessment).

Learning recurrent behaviors from heterogeneous multivariate time-series

OBJECTIVE For the last years, time-series mining has become a challenging issue for researchers. An important application lies in most monitoring purposes, which require analyzing large sets of time-series for learning usual patterns. Any deviation from this learned profile is then considered as an unexpected situation. Moreover, complex applications may involve the temporal study of several heterogeneous parameters. In that paper, we propose a method for mining heterogeneous multivariate time-series for learning meaningful patterns. METHODS The proposed approach allows for mixed time-series - containing both pattern and non-pattern data - such as for imprecise matches, outliers, stretching and global translating of patterns instances in time. RESULTS We present the results of our approach on synthetic data generated in the context of monitoring a person at home, as well as early results on few real sequences. The purpose is to build a behavioral profile of a person in their daily activities by analyzing the time variations of several quantitative or qualitative parameters recorded through a provision of sensors. CONCLUSIONS The results are very promising. They also highlight the difficulty of tuning the parameters of the method.

Efficacy of simple home-based technologies combined with a monitoring assistive center in decreasing falls in a frail elderly population (results of the Esoppe study).

BACKGROUND Increasing age often implies increasing frailty, and the oldest old are often described as a frail group with a high risk of developing functional impairments and multi-morbidities like falls at home, which often result in dependence in daily activities. This preliminary study evaluate the efficacy of light path coupled with tele-assistance service for preventing unintentional falls at home in a frail elderly population. METHODS Study design is a longitudinal prospective cohort study from 1st July 2009 to 30 June 2010. The program included 194 adults aged 65 and over living at home and registered on a list of frail elderly people. Participants were uniformly asked about their history of falls during the year prior to their most recent health examination. The recall period was one year. RESULTS We observed that 77 (40.5%) elderly fell at home, 29 (30.9%) in the exposed group and 48 (50.0%) in the unexposed group. The use of light path coupled with tele-assistance was significantly associated with the reduction in falls at home, odd ratio=0.33 95%CI [0.17-0.65] p value=0.0012. There was also a greater reduction in post-fall hospitalization rate among exposed group with odd ratio=0.30 95%CI [0.12-0.74] p value=0.0091. CONCLUSIONS This preliminary study showed that the use of light path coupled with tele-assistance service significantly reduced the incidence of unintentional falling at home among frail elderly population. This result should be confirmed by a randomized trial.

Preventing and Managing Indoor Falls with Home-Based Technologies in Mild and Moderate Alzheimer's Disease Patients: Pilot Study in a Community Dwelling

Background: Alzheimers disease (AD) is known to increase the risk of falls. We aim to determine the effectiveness of home-based technologies coupled with teleassistance service (HBTec-TS) in older people with AD. Methods: A study of falls and the HBTec-TS system (with a light path combined with a teleassistance service) was conducted in the community. The 96 subjects, drawn from a random population of frail elderly people registered as receiving an allocation for lost autonomy from the county, were aged 65 or more and had mild-to-moderate AD with 1 year of follow-up; 49 were in the intervention group and 47 in the control group. Results: A total of 16 (32.7%) elderly people fell in the group with HBTec-TS versus 30 (63.8%) in the group without HBTec-TS. The use of HBTec-TS was significantly associated with a reduction in the number of indoor falls among elderly people with mild-to-moderate AD (OR = 0.37, 95% CI = 0.15-0.88, p = 0.0245). Conclusion: The use of the HBTec-TS significantly reduced the incidence of primary indoor falling needing GP intervention or attendance at an emergency room among elderly people with AD and mild-to-moderate dementia.

Nouvelles directions en habitats intelligents pour la santé

Resume Le concept d’habitat intelligent pour la sante vise a redonner une vie autonome, dans leur domicile, a des personnes qui sinon devraient etre placees en institution specialisee : patients souffrant de certaines maladies chroniques, handicapes, mais aussi personnes âgees dependantes. Cet article propose un etat de l’art du concept des habitats intelligents pour la sante. Il presente ensuite les principales demarches menees dans tous les domaines technologiques qui sont concernes — systemes d’informations, equipements domotiques, capteurs ubiquitaires, assistance robotisee — en meme temps qu’il expose les essais de standardisation menes par quelques gros consortiums, et enfin quelques pistes de reflexions ethiques.

Heterogeneous knowledge representation using a finite automaton and first order logic: a case study in electromyography

In a certain number of situations, human cognitive functioning is difficult to represent with classical artificial intelligence structures. Such a difficulty arises in the polyneuropathy diagnosis which is based on the spatial distribution, along the nerve fibres, of lesions, together with the synthesis of several partial diagnoses. Faced with this problem while building up an expert system (NEUROP), we developed a heterogeneous knowledge representation associating a finite automaton with first order logic. A number of knowledge representation problems raised by the electrophysiological test features are examined in this study and the expert system architecture allowing such a knowledge modeling is laid out.

An hybrid refinement methodology for multivariate simulation in home health telecare

We deal with monitoring the health status of a patient at home so as to detect critical evolutions over a scale of several days or weeks. A multivariate simulation is used as a way to overcome the lack of experimental data required for studying this decision-making issue. The simulation process needs to be driven in a rigorous and robust way. Due to that, and to deal with heterogeneity and complexity, we make use of an hybrid and refinement methodology. It involves the fusion of several types of models and knowledge, as well as the implementation of a cascade structure for the simulation process.