• Title/Summary/Keyword: Hearing-impaired people

Search Result 72, Processing Time 0.018 seconds

Barrier Free Accessibility to Trains for All

  • Rentzsch, Manfred;Seliger, Denis;Meissner, Thomas;Wessner, Claudia
    • International Journal of Railway
    • /
    • v.1 no.4
    • /
    • pp.143-148
    • /
    • 2008
  • This paper is the output of a collaborative European project concerning the barrier free accessibility for disabled persons to regional and long distance trains in Europe. Disabled people represent around 13% of the population in Europe. This is approximately 63 million people. The range of disabilities includes people with reduced mobility including wheel chair users, viewing and hearing impaired people and other forms of impairment. Improving accessibility aims at contributing to the provision of public transport services to all citizens in an equitable way. The purpose of the project was to analyse and to evaluate the existing solutions at selected European railways for all required modules at the entrance (doors, information and safety solutions), to derive a design concept, to develop a mock-up in meeting the needs of rail travellers with the above mentioned impairments and to test it with user groups. The project also aims at deriving components for the determination of standards. The EUPAX Design Mock-up test was performed to verify the advantages of the layout of the train segment including the different modules such as access area (including the access door, gaps between platform and train as well as boarding aid devices), entrance vestibule, information systems inside and outside the train, emergency facilities, toilet with all conveniences and the additional test arrangements regarding push buttons, steps and emergency equipment. For this purpose a questionnaire was developed for the assessment of the EUPAX segment and the additional test arrangements. With the help of this questionnaire it was possible to execute a quantitative and qualitative evaluation. During three test phases 67 experts and handicapped persons from 6 countries have evaluated the Industrial Design mock-up based on this questionnaire. The test group covered persons from North (Denmark) to the South (Italy) and from the West (Spain) to the Middle of Europe (Germany). This is especially important for the generalization (harmonisation) of the results for all European countries. According to COST 335 the information for people with reduced mobility should be clear, concise, accurate and timely. So that all information can be received from persons, they must be transferred on at least two of the three possible ways (acoustical, visual, tactile), a so called "2-sense-principle". Based on the results ergonomic specifications/ solutions for the ergonomic design of the access area, the acoustic, visual and tactile information and the emergency devices including the emergency communication system were developed, related to the benefiting passenger groups.

  • PDF

Analysis of Understanding Using Deep Learning Facial Expression Recognition for Real Time Online Lectures (딥러닝 표정 인식을 활용한 실시간 온라인 강의 이해도 분석)

  • Lee, Jaayeon;Jeong, Sohyun;Shin, You Won;Lee, Eunhye;Ha, Yubin;Choi, Jang-Hwan
    • Journal of Korea Multimedia Society
    • /
    • v.23 no.12
    • /
    • pp.1464-1475
    • /
    • 2020
  • Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.