Alan Turing, in his paper “Computing Machinery and Intelligence” published in the Mind journal in 1950, proposed an operational approach to the question of whether machines can think. He proposed replacing the question “Can machines think?” with an experiment he called “The imitation game”. The experiment compares the performance of a supposedly intelligent machine against the performance of a human on a given set of queries. Since then, AI researchers have grown up to serve many sectors including Special Needs (SN) or people with disabilities.
Deaf-and-dumb students face problems when attending mainstream colleges unless they receive proper help and support. One of the difficulties experienced by Special Needs (SN) learners is the lack of understanding of sign language interacting with the teachers directly, without the help of a sign language translator, which will augment the learning process more efficient. The analysis of the real-time student feedback in the class is becoming increasingly important in forecasting, learning outcomes as well as providing effective instructional strategies for learners to get best results.
Building an Artificial Intelligence (AI) model enables SN students to overcome the language barrier that prevents them from directly interacting with the teacher in the classroom assessment. This model is a quick, easy, and oral evaluation classroom tool that helps teachers check students’ understanding in “real-time”. This indirect assessment provides information that can be used to modify/improve the course content, adjust teaching methods in the day-to-day delivery of the course. This model composes of a Speech Recognizer, Sign Language Recognizer, and Report Generator. It generates a report for students’ understanding and class evaluation in advance before ending the course based on the speech recognition and image processing tools. This model will help the SN students to achieve their learning objectives by being able to get an accurate and real evaluation of their understating during the classes. Also, the proposed AI model helps the teacher to get some insights into his/her teaching methodologies during the class as the model will observe and record the feedback of the students. This model will have a significant positive impact on SN student success and on effective lecturing.
AI model generates a report for students’ understanding and class evaluation before completing the course. It customizes the courses, teaching methods, and activities to suit SN learners’ needs. Also, it predicts SN learners’ learning outcomes based on their responses. In addition, this model monitors and guides SN learners in an effective learning environment. AI model will reduce the failure rate of the students, identify students at risk, help teachers choose a strategy to support and motivate them, and overcome the language barrier between the Deaf-Dumb students and teachers.
About the Author
Samar Mouti has 16 years of teaching experience in Syria and the United Arab Emirates. She is a program leader of the Information Technology Department at Khawarizmi International College, Abu Dhabi, UAE. Her research interest includes Artificial Intelligence techniques, Natural Language Processing, Expert Systems, and Neural Networks.