By 2050, about one third of the French population will be over 65. Our laboratory's current research focuses on the monitoring of elderly people at home, to detect a loss of autonomy as early as possible. Our aim is to quantify criteria such as the international activities of daily living (ADL) or the French Autonomie Gerontologie Groupes Iso-Ressources (AGGIR) scales, by automatically classifying the different ADL performed by the subject during the day. A Health Smart Home is used for this. Our Health Smart Home includes, in a real flat, infrared presence sensors (location), door contacts (to control the use of some facilities), temperature and hygrometry sensor in the bathroom, and microphones (sound classification and speech recognition). A wearable kinematic sensor also informs postural transitions (using pattern recognition) and walk periods (frequency analysis). This data collected from the various sensors are then used to classify each temporal frame into one of the ADL that was previously acquired (seven activities: hygiene, toilet use, eating, resting, sleeping, communication, and dressing/undressing). This is done using support vector machines. We performed a 1-h experimentation with 13 young and healthy subjects to determine the models of the different activities, and then we tested the classification algorithm (cross validation) with real data.

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.

Over the years, smartphones have become tools for scientific and clinical research. They can, for instance, be used to assess range of motion and joint angle measurement. In this paper, our aim was to determine if smartphones are reliable and accurate enough for clinical motion research. This work proposes an evaluation of different smartphone sensors performance and different manufacturer algorithm performances with the comparison to the gold standard, an industrial robotic arm with an actual standard use inertial motion unit in clinical measurement, an Xsens product. Both dynamic and static protocols were used to perform these comparisons. Root Mean Square (RMS) mean values results for static protocol are under 0.3° for the different smartphones. RMS mean values results for dynamic protocol are more prone to bias induced by Euler angle representation. Statistical results prove that there are no filter effect on results for both protocols and no hardware effect. Smartphones performance can be compared to the Xsens gold standard for clinical research.

Assessment of joint functional and proprioceptive abilities is essential for balance, posture, and motor control rehabilitation. Joint functional ability refers to the capacity of movement of the joint. It may be evaluated thereby measuring the joint range of motion (ROM). Proprioception can be defined as the perception of the position and of the movement of various body parts in space. Its role is essential in sensorimotor control for movement acuity, joint stability, coordination, and balance. Its clinical evaluation is commonly based on the assessment of the joint position sense (JPS). Both ROM and JPS measurements require estimating angles through goniometer, scoliometer, laser-pointer, and bubble or digital inclinometer. With the arrival of Smartphones, these costly clinical tools tend to be replaced. Beyond evaluation, maintaining and/or improving joint functional and proprioceptive abilities by training with physical therapy is important for long-term management. This review aims to report Smartphone applications used for measuring and improving functional and proprioceptive abilities. It identifies that Smartphone applications are reliable for clinical measurements and are mainly used to assess ROM and JPS. However, there is lack of studies on Smartphone applications which can be used in an autonomous way to provide physical therapy exercises at home.

Considering the important role of the cervical joint position sense on control of human posture and locomotion, accurate and reliable evaluation of neck proprioceptive abilities appears of great importance. Although the cervicocephalic relocation test (CRT) to the neutral head position (NHP) usually is used for both research and clinical purposes, its test-retest reliability has not been clearly established yet. The purpose of the present experiment was to 1) evaluate the test-retest reliability of the CRT to NHP and 2) to determine the number of trial recordings required to ensure reliable measurements. To this aim, 40 young healthy adults performed the CRT to NHP on two separate occasions. Ten trials were performed for each rotation side. Absolute and variable errors, processed along their horizontal, vertical, and global components, were used to assess the cervical joint repositioning accuracy and consistency, respectively. Mean difference between test and retest with 95% confidence interval, intraclass correlation coefficient, and Bland and Altman graphs with limits of agreement were used as statistical methods for assessing test-retest reliability. Results show that the CRT to NHP when executed in its original form (i.e., 10 trials) has a fair to excellent reliability (ICC ranged from 0.52 to 0.81 and from 0.49 to 0.77, for absolute and variable errors, respectively); the test-retest reliability of this test increases as the number of trials used to establish subject's repositioning errors increases; and using the mean of eight trials is sufficient to ensure fair to excellent reliability of the measurements (ICC ranged from 0.39 to 0.78 and from 0.44 to 0.78, for absolute and variable errors, respectively).

Improvements in medicine increase life expectancy in the world and create a new bottleneck at the entrance of specialized and equipped institutions. To allow elderly people to stay at home, researchers work on ways to monitor them in their own environment, with non-invasive sensors. To meet this goal, smart homes, equipped with lots of sensors, deliver information on the activities of the person and can help detect distress situations. In this paper, we present a global speech and sound recognition system that can be set-up in a flat. We placed eight microphones in the Health Smart Home of Grenoble (a real living flat of 47m²) and we automatically analyze and sort out the different sounds recorded in the flat and the speech uttered (to detect normal or distress french sentences). We introduce the methods for the sound and speech recognition, the post-processing of the data and finally the experimental results obtained in real conditions in the flat.