Search

This paper presents a new platform to monitor stroke patients activities during their everyday life at home. This platform is intended to be a part of a smart objects ecosystem for home monitoring using common objects embedding sensors. The monitoring is performed with a self-contained smart cup that can be used to drink at different times of the day. The smart cup embeds various sensors in order to detect its movements and the liquid level. Activity analysis is performed on the collected data in order to provide information to the therapists on the patient's sedentariness and independence on the daily life tasks (sitting, walking, drinking and going up and down the stairs). This paper presents the design concept of the smart cup along with the implementation and mainly focuses on the activity analysis process. We used a linear classifier: the Support Vector Machine (SVM) classifier. Indeed, the classification of stroke patient's activities is a binary classification. Moreover, as we decided to use DCT features, SVM is the classifier that gives better classification performances. The results show a recognition precision above 92% on all activities with the smart cup. A comparative study has been carried out in order to assess the performances of the linear SVM classifier and a non-linear Multi-Layered Perceptron (MLP) classifier. The result of this study shows that the linear SVM classifier offers better performances on classifying everyday life activities with a smart cup.

This paper presents a platform prototype to monitor alcohol consumption for festival's attendees. The platform also aims to raise awareness about alcohol consumption in order to help people control or even reduce their alcohol consumption. The platform consists of a self-contained smart cup which the attendee uses during the day. This platform allows to easily follow the user's alcohol intake based on a model in order to display alerts if necessary. The smart cup embeds sensors to detect the liquid level and its movements. In addition, activity recognition is performed from the collected data in order to recognize when the user drinks and enhance the alcohol intake assessment. The smart cup also embeds LEDs visual displays that provides information about the alcohol intake estimation. This paper presents the design concept of the smart cup along with the technical implementation. Then, the data processing and analysis is presented for the alcohol intake estimation method using activity recognition with a Support Vector Machine classifier. An experiment have also been carried out and shows a good level of recognition above 90% for the “drinking” activity. Next, the feedback identification for the alcohol intake estimation is detailed in the last section. Finally, perspectives for the detection of abnormal behavior based on the alcohol intake assessment and the movements of the cup are introduced.

Les nouvelles technologies sont de plus en plus utilisees pour repondre aux besoins specifiques des individus avec trouble du spectre de l’autisme (TSA). Les interfaces homme-machine explorant le sens du toucher apparaissent comme un canal d’interaction potentiellement interessant pour les personnes avec TSA. Notre but est d’etablir une revue systematique de l’existant concernant les interfaces tactiles et haptiques dediees au TSA. Nous mettons l’accent sur les approches de developpement et les etudes utilisateurs effectuees. Les resultats montrent qu’il existe une grande variete de technologies et d’interfaces destinees aux individus avec TSA. Les interfaces tactiles ou haptiques viennent en complement d’autres modalites d’interaction homme-machine dans le developpement de robots, de manettes de jeu, d’objets tangibles interactifs, de tablettes ou encore d’environnements virtuels. Toutefois, les etudes utilisateurs, lorsqu’elles existent, n’atteignent pas a l’heure actuelle un niveau de qualite methodologique suffisant pour permettre d’etayer leur validite pour l’aide aux personnes avec TSA. Les modalites tactiles et haptiques meriteraient d’etre davantage investiguees dans les recherches sur les interfaces homme-machine pour l’autisme.

Conference of 2017 Zooming Innovation in Consumer Electronics International Conference, ZINC 2017 ; Conference Date: 31 May 2017 Through 1 June 2017; Conference Code:129086; International audience; We present a study on the influence of the applied force on tactile perception thresholds, during exploration of tactile textures generated with electrovibration. Combined with screen-integrated force detection this could lead to more realistic texture feedback on touch screens while exploring a virtual surface. From a first user study, three force levels corresponding to the light (0.2 N-1.5 N), medium (1.5 N-3.0 N), and high force (3.0 N-7.0 N) categories were deduced. In a second study, the users were asked to apply these force levels while following a line on the screen. We determined the perception thresholds of 10 participants for specific electrovibration stimuli (100 Hz, 160 Hz, 240 Hz, 360 Hz, and 540 Hz sine signals) using a staircase method. No force effect on the perception threshold has been measured for 100 Hz and 160 Hz, while it decreased with increasing applied force at 240 Hz, 360 Hz, and 540 Hz.

This paper presents a new ecosystem of smart objects designed to monitor motor functions of stroke patients during rehabilitation sessions at the hospital. The ecosystem has been designed starting from an observational study as well as the Action Research Arm Test. It includes a jack and a cube for hand grasping monitoring and a smart watch for the arm dynamic monitoring. The objects embed various sensors able to monitor the pressure of the fingers, the position of the fingers, their orientation, their movements and the tremors of the patient during the manipulation tasks. The developed objects can connect, via Bluetooth or Wi-Fi technology, to an Android mobile application in order to send collected data during the execution of the manipulation task. Performances achieved during the sessions will be displayed on the tablet. Using the collected data, the therapists could assess the upper arm motor abilities of the patient by accessing qualitative information that is usually evaluated by visual estimations or not reported and adapt the rehabilitation program if necessary. The objects, as well as the visualization interfaces, have been evaluated with health care professionals in terms of design and functionalities. The results from this evaluation show that the objects׳ design is adapted to bring useful information on the patient׳s motor activities, while the visualization interfaces are useful, but require new functionalities. Finally, a preliminary study has been carried out with stroke patients in order to assess the usability and acceptability of such an ecosystem during rehabilitation sessions. This study indicated that the patients are willing to use the ecosystem during the sessions thanks to its easy usage.

Conference of 16th Euromicro Conference on Digital System Design, DSD 2013 ; Conference Date: 4 September 2013 Through 6 September 2013; Conference Code:101116; International audience; The main idea behind this project is to provide a unified platform which will cover a complete process for embedded systems learning. A modular approach is considered for skills practice through supporting individualization in learning. This platform shall facilitate a novel development of universal approach in creative learning environment and knowledge management that encourage use of ICT. New learning model is challenging the education of engineers in embedded systems design through real-time experiments that stimulate curiosity with ultimate goal to support students to understand and construct their personal conceptual knowledge based on experiments. In addition to the technological approach, the use of cognitive theories on how people learn will help students to achieve a stronger and smarter adaptation of the subject. Applied methodology will be evaluated from the scientific point of view in parallel with the implementation in order to feedback results to the R&D.

Part 5: Gesture and Tactile User Interfaces; International audience; We present the design and evaluation of a tactile editor, TactiPEd for the rapid and easy prototyping of vibrotactile patterns. It is based on the graphical metaphor of the shape of the device, which is used for the tuning of the main tactile characteristics, including amplitude, frequency and duration of tactile sequences. The editor includes file systems functionalities using the XML format along with playing and recording functionalities. The editor was thoroughly evaluated: a usability evaluation was conducted with 9 participants, the designed metaphor-based patterns were analyzed for insights on cross-device design and finally the editor was tested with several devices. TactiPEd was successfully and easily used with little training and enabled users to design patterns in little time. The resulting patterns shared common characteristics across the devices for a given metaphor.

Conference of 2013 IEEE World Haptics Conference, WHC 2013 ; Conference Date: 14 April 2013 Through 17 April 2013; Conference Code:98366; International audience; We present the design, implementation and evaluation of a novel wrist-based vibrotactile multi-actuator bracelet, based on a coplanar circular configuration of actuators, for the provision of intuitive and informative haptic feedback for navigation tasks. A two-phase evaluation was conducted in order to assess the perception of the vibrotactile feedback provided by the bracelet and in particular, the ability of users to discriminate a range of vibrotactile patterns. First, a pilot study designed to test perception of different kinds of pattern was conducted with the aim of both refining the pattern design and aiding the choice of a discriminable set of patterns. Second, an identification experiment with the previously chosen set of patterns was conducted with the aim of conveying navigational directions and points of interest to the user. Results highlighted the difficulties in identifying the number of activated actuators as well as their position on the wrist, which subsequently had an impact on the pattern recognition. It was found that one-way horizontal and vertical movements were difficult to perceive correctly, however, less specific movements such as circular or alternating lateral movements and rhythm proved to be suitable parameters for the perception of patterns as long as the patterns were not too similar in design.

Conference of 2013 IEEE World Haptics Conference, WHC 2013 ; Conference Date: 14 April 2013 Through 17 April 2013; Conference Code:98366; International audience; We describe a mechanism for the delivery of haptic feedback to users of a simple game via the use of probabilistic inference. This not only enables the creation of dynamically changing game conditions but also a more adaptable, accessible and enjoyable haptic gaming environment for potential use by visually impaired users. The ViPong proof of concept application uses a mouse instrumented with a custom built lateral vibrator to enable a person to compete eyes-free in a game of pong using only haptic feedback linked to the position of the ball. A preliminary user study shows that it is possible to build eyes-free games using such a mechanism for haptic feedback generation. It also shows that there is some effect on the game play from varying levels of uncertainty injected into the algorithm, with participants performing less well under condition where the uncertainty added to the position of the game ball is high.

This chapter explains a vision based platform developed within a European project on decision support and self-management for stroke survivors. The objective is to provide a low cost home rehabilitation system. Our main concern is to maintain the patients' physical activity while carrying a continuous monitoring of his physical and emotional state. This is essential for recovering some autonomy in daily life activities and preventing a second damaging stroke. Post-stroke patients are initially subject to physical therapy under the supervision of a health professional to follow up on their daily physical activity and monitor their emotional state. However, due to social and economical constraints, home based rehabilitation is eventually suggested. Our vision platform paves the way towards having low cost home rehabilitation.