DCode

Keynote Speakers

  • Home
  • Keynote Speakers

AI based e-Testing as a common yardstick for measuring human abilities

The university of electro-communications, Professor Maomi Ueno

Biography

Maomi Ueno received the Ph.D. degree in computer science from the Tokyo Institute of Technology in 1994. He has been a professor of the Graduate School of Information Systems at the University of Electro-Communications since 2013. He received Best Paper awards from IEEE International Conference on Tools with Artificial Intelligence (ICTAI2008), e-Learn2004, e- Learn2005, and e-Learn2007 ED-MEDIA2008,. His interests are e-learning, e-testing, e-portfolio, machine learning, data mining, Bayesian statistics, and Bayesian networks.

Abstract

It is difficult to evaluate a person’s ability or performances because there is no common yardstick for measuring individual human abilities. For example, in general, paper based tests have different characteristics (difficulties, accuracies, and so on) because they depend on items of each test. Recently, e-testing technologies from AI approach, for which each test form has equivalent measurement accuracy but with a different set of items, have become popular. Even if different examinees with the same ability take different tests, their test scores should be guaranteed to be equivalent. We introduce state-of the-art e-testing technologies from AI approach. Furthermore, performance assessments, in which human raters assess examinee performance on practical tasks, have been often used for measuring higher-order abilities. Performance assessment has been applied to various formats, including personnel rating, essay-writing, speaking tests for language exams, programming, and so on. However, one limitation of performance assessments is that their accuracy for ability measurement strongly depends on rater and task characteristics such as rater severity and task difficulty. To resolve this problem, various e-testing technologies for performance assessments, which considers rater and task characteristics, have been developed. We also introduce several state-of-the-art e-testing technologies for performance assessments including its applications to automated essay scoring (AES) systems. Finally, we introduce a couple of large scale e-testing practices for national examinations in Japan.

Intelligent Clinical Training during the COVID-19 Pandemic

Thammasat University, Professor Dr. Siriwan Suebnukarn

Biography

Professor Siriwan Suebnukarn serves as Vice Rector for Research and Innovation at Thammasat University, Thailand. Professor Suebnukarn’s combined background in Dentistry and Computer Science gives her a rather unique set of skills to tackle some important outstanding problems in Medical Informatics and Education. Her research work has included Artificial Intelligence in Education, Intelligent User Interfaces, and User Modeling. She developed an Intelligent Virtual Reality Clinical Training Simulator for which she won the prestigious International Federation of Inventor Association’s (IFIA) Lady Prize for the Best Women’s Invention and the National Outstanding Researcher Award in Education.

Abstract

Clinical training is one of the most challenging areas for education especially during the COVID-19 pandemic. There are limited access to apprenticeship training in the complex scenarios with corresponding difficulty training in a time-effective manner. Professor Suebnukarn’s work on intelligent clinical training systems provides one effective solution to this problem by introducing intelligent clinical training systems that can supplement tutoring sessions by expert clinical instructors. The Bayesian representation techniques and algorithms for generating tutoring feedback in medical problem-based learning group problem solving made important contributions to the field of Intelligent Tutoring Systems. In particular, it was one of the first systems for tutoring groups of students and the first intelligent tutoring systems for medical problem-based learning. The virtual reality simulator she developed is one of the most sophisticated dental simulators. It stands out as the first dental simulator to integrate sophisticated analysis of the surgical procedure. Particularly noteworthy is also the creative way to understand important issues such as differences in expert and novice performance, the effectiveness of virtual pre-operative practice, and the teaching effectiveness of the simulator. The systems have been implemented in undergrad pre-clinical training and postgrad pre-surgical training with strong scientific evidence of their effectiveness.

Towards robust Machine Learning models for grape ripeness assessment

The University of Trás-os-Montes e Alto Douro (UTAD)
Prof. Pedro Melo-Pinto

Biography

Pedro Melo-Pinto graduated from University of Porto in 1984 and received a Ph.D. from the University of Trás-os-Montes e Alto Douro (UTAD) in 1998. He is a member of Centro ALGORITMI (Universidade do Minho), and he is Full Professor at UTAD where he served as Pro-rector. He has published over 100 papers in international journals, book chapters and conferences, he has served several times as guest editor for different journals, and he has been involved in more than 20 national and international R&D projects. He currently serves as member of The Portuguese Strategic Infrastructures (for the Digital Areas) Monitoring Committee and of the editorial board of Remote Sensing and Journal of Advanced Computational Intelligence and Intelligent Informatics. He is also a member of the reviewer board for many journals including Information Sciences, Expert Systems with Applications, Fuzzy Sets and Systems, Sensors and Food Chemistry. He was Chair of EuroFuse 2011 and NATO 2001 Advanced Research Workshop. He is a member of the International Society of Applied Intelligence and of APPIA (Portuguese Association for AI).
His current scientific interests include Computer Vision and Machine Learning, in particular its applications to the Agro-forestry area.

Abstract

World population will grow to nine billion by 2050 and the need for agricultural production must double. Clearly, this cannot be achieved by simply doubling the inputs (land, water, seeds, labor, etc.) because of constrained resources and environmental concerns. The efficiency of the agricultural and farming system must increase in a sustainable and consistent manner. The growing importance of precision agriculture (with better-utilization of inputs and/or enhancement of productivity) demands novel methods to make the most out of the data generated. Machine learning algorithms (ML) combined with hyperspectral imaging (HSI) is a promising alternative to predict important quality parameters in fruits, namely grapes, and assist on harvesting critical decisions. However, the large amount of data generated by HSI, together with the large variability associated with the problem (varieties involved, climate, terroir, etc.), raise unusual challenges for data-driven modelling. Several ML approaches have been proposed to handle such data characteristics, but selecting a suitable methodology that best address the problem under study and make sure it generalizes well, is a cumbersome task. Our work is focused in two fundamental and novel aspects to address the natural variability arising from different grape varieties, vintages and growth conditions: the essential wavelength bands selection (with the purpose of reducing the dimensionality of data without losing predictive power) and the generalization ability of the ML model under such demanding conditions. Moreover, to increase the acceptance and understanding of the decisions and predictions made, more transparent AI methodologies are needed.

Select Your Color

RTL/LTR Option