e96
Oral abstracts / Annals of Physical and Rehabilitation Medicine 61S (2018) e1–e102
C2.19 PRM interventions research–Miscellaneous
D1.03 Rehabilitation systems and services research–Rehabilitation service organisation*
ISPR8-1835
Deep learning for the recognition of facial expression in the Colombian sign language
A.M. Rincon Vega ∗ , A. Vasquez , W. Amador , A. Rojas Universidad Manuela Beltran, Vicerrectoria de Investigaciones, Bogotá, Colombia ∗ Corresponding author. E-mail address:
[email protected] (A.M. Rincon Vega) Introduction/Background The communication of the deaf person has been considered as a set of manual movements, however many have ignored the importance of facial expression in the different communicative manifestations of this population; this is the reason because a group of Phonoaudiology, physiotherapy and engineering researchers integrate their knowledge to perform image processing and classification of facial expressions used in the Colombian Sign Language (LSC) analysis. The Objective was to establish the processing of images of facial expressions as a complementary means to manual movements for the interpretation of Colombian sign language. Material and method Qualitative study, descriptive, nonexperimental design, for which four phases were considered, in the first, data collection was carried out through recordings of deaf people as linguistic models producing facial expressions corresponding to the vocabulary of the clinical scenario. In phase two, the images are processed to identify the characteristic patterns of each sign. In the third phase, two Deep Learning techniques are used to classify the captured gestures. In the fourth phase, the accuracy of the images was validated techniques used. Results For the classification process, six facial expressions corresponding to the words pain, inflammation, fracture, irritable colon, dizziness, diabetes were analyzed. In this process, two Deep Learning techniques were validated, obtaining that the Single Shot Multibox Detector SSD technique has a precision of 94, 2% compared to the Convolutional Neural Network (CNN) technique, which has a degree of accuracy of 89.05%. Conclusion The development of technologies of this nature allows analyzing the facial expression in the communication of the deaf person as a distinctive feature for interaction with others. The algorithms of artificial vision based on Deep learning present a high level of efficiency in the classification of facial expression, this being an important factor to generate tools that facilitate the communication of deaf and hearing. Keywords Deep learning; Facial expression; Sign language Disclosure of interest The authors have not supplied their declaration of competing interest. https://doi.org/10.1016/j.rehab.2018.05.204
ISPR8-2440
Home rehabilitation in France. The model of stroke A. Schnitzler 1,∗ , L. Tlili 2 , J. Beaudreuil 2 , M. Jousse 2 , A. Yelnik 3 Hôpital Poincaré, physical medicine and rehabilitation, Garches, France 2 GH St.Louis-Lariboisière-F.-Widal, physical medicine and rehabilitation, Paris, France 3 PMR Service- GH St.Louis-Lariboisière-F.-Widal, physical medicine and rehabilitation, Paris, France ∗ Corresponding author. E-mail address:
[email protected] (A. Schnitzler)
1
Introduction/Background Ambulatory care is the most frequent type of rehabilitation for chronic diseases. French guidelines recommend after a stroke assessment and rehabilitation by a multidisciplinary team for all the patients with a persistent deficiency. According to the needs of each patient, different ways to provide home rehabilitation can be used in France. For simple needs targeting specific deficiency, rehabilitation can be provided by a professional alone in ambulatory care. Only Physiotherapy (PT) and speech therapy (ST) are refunded by the national health insurance. For complex needs a PRM multidisciplinary team, can be ordered either in day hospital (the patient living home and receiving rehabilitation during repeated stays) which is the main organization, or mobile rehabilitation team, the team coming each day at home like an early supported discharge team (not very developed in France). Material and method We report here the global activity base on the analysis of the national registry on the 80,000 annual new strokes (excluding transient attacks and deceased) Results After the acute care, 37% of stroke patients received a multidisciplinary rehabilitation during a mean of 3 months (33% in an inpatient center and 4% in an outpatient center). For the patient discharge at home 30% (directly discharge from an acute center) to 50% (discharge from a rehabilitation center) receive PT and 9 to 15% ST. At the chronic phase 35% of the patients receive PT at home. Ambulatory occupational therapy and ST are less developed and less available. Conclusion Effort is needed to improve multidisciplinary rehabilitation at home in France. Home hospital could be interesting to develop for dependent and fragile patients, mobile rehabilitation team for the rehabilitation of the instrumental activities of daily livings, and day hospital for rehabilitation requiring technical platform of a rehabilitation center. Keywords Home rehabilitation; Stroke; Care pathway Disclosure of interest The authors have not supplied their declaration of competing interest. https://doi.org/10.1016/j.rehab.2018.05.205 ISPR8-2369
Maison de rééducation et d’autonomie « MRA » a new model of practice in physical medicine & rehabilitation back on three years’ experience Y. Mohammad Maison de rééducation et d’autonomie, Val-D’oise, Beaumont-Sur-Oise, France E-mail address:
[email protected] Introduction/Background In France, Physical Medicine and Rehabilitation is practiced in the hospital. Private practice is often limited: Lack of PM&R physiciens, Absence of interdisciplinarity and very limited technical means.