Speakers

Keynotes & Plenaries

Submission Method

Please submit your full paper/abstract to us via the Microsoft Submission System: http://confsys.iconf.org/conference/bdmo2022.

Fast Registration Channel

Fast registration channel is opened up for listeners. Interested participants should register in advance by filling out the Registration Form at least one month before the conference.

Need Help

Please feel free to write an email to us if you have any query concerning to the conference.

Keynote Speaker

Professor Hiroyuki Yamauchi, IEEE Senior Member
University of Quebec at Chicoutimi, Canada

Biography: Professor Hamid Mcheick is a full professor in Computer Science department at the University of Québec at Chicoutimi, Canada. He has more than 25 years of experience in both academic and industrial area. He has done his PhD in Software Engineering and Distributed System in the University of Montreal, Canada. He is working on design and adaptation of smart software applications; designing healthcare framework for medical domain; and designing smart Internet of Things and edge framework. He has supervised many post-doctorate, PhD, master and bachelor students. He has nine book chapters, more than 60 research papers in international journals and more than 150 research papers in international/national conference and workshop proceedings in his credit. Dr. Mcheick has given many keynote speeches and tutorials in his research area. Dr. Mcheick has gotten many grants from governments, industrials and academics. He is a chief in editor, chair, co-chair, reviewer, member in many organizations (such as IEEE, ACM, Springer, Elsevier, Inderscience) around the world.

Design Adaptation Architectural Model for Healthcare System

Abstract: Today, health system is reshaping the research in the medical domain due to its potential to concurrently overcome the challenges encountered in the traditional healthcare systems. Prediction of exacerbation of Chronic Obstructive Pulmonary Disease (COPD) is considered one of the most difficult problems in the medical field. Many issues face researchers in the medical domain, such as modelling context (risk factors) of a patient, uncertainty, accuracy of these factors and their relationship, and preventing exacerbation. These issues have been handled in may research projects. However, traditional treatment plan and non-fully automatic applications are still used and have many issues, such as accuracy and performance. The goal of this research is to build reliable mechanisms to improve life quality of COPD patients and to protect them against risk factors. In this talk, I will present COPD healthcare architectural model including context modelling, context representation and rule-based recommendations.


Professor Dmitry Goldgof, IEEE Fellow
University of South Florida, USA

Biography: Dmitry B. Goldgof is an educator and scientist working in the area of Medical Image Analysis, Image and Video Processing, Computer Vision, Deep Learning and AI. Dr. Goldgof is currently Distinguished University Professor and Vice Chair in the Department of Computer Science and Engineering at the University of South Florida in Tampa. Dr. Goldgof has graduated 33 Ph.D. and 48 MS students, holds 14 patents, published over 120 journal and 260 conference papers, 20 books chapters and edited 5 books (over 17,000 citations, h-index 63, i10-index 220). Professor Goldgof is a Fellow of IEEE, a Fellow of IAPR, a Fellow of AAAS, Fellow of AAIA and a Fellow of AIMBE.

 

Mitigating Shortcut Learning of Deep Neural Networks in Medical Image Analysis
 

Abstract: Deep learning has emerged as the leading machine learning tool in the domain of image analysis. Deep learning tools have been recently applied to healthcare problems, including computer-aided detection/diagnosis, disease prediction, image segmentation, etc. However, translation of deep learning technology from research to actual clinical use is highly challenging. Deep learning models need to be not only highly accurate but scalable and robust. Shortcut learning is when a deep learning model finds and follows a "shortcut" strategy to achieve astonishing results under familiar circumstances but fails under slightly different settings. Solutions to avoid shortcut learning are crucial to prove the clinical utility and maturity of the developed models. Thus, leading to more fair, reliable, robust and transparent deep learning based clinical decision support systems.

 

Professor Theodora Varvarigou
National Technical University of Athens, Greece

Biography: Theodora Varvarigou is a professor at the School of Electrical and Computer Engineering of the National Technical University of Athens (NTUA). She received the B. Tech degree in Electrical Engineering from NTUA in 1988, the MS degrees in Electrical Engineering (1989) and in Computer Science (1991) from Stanford University, California. She received her Ph.D. degree from Stanford University as well in 1991. She has worked as a researcher at AT&T Bell Labs, USA and as an Assistant Professor at the Technical University of Crete, Chania, Greece. Prof. Varvarigou has great experience in cutting edge technologies, such as Cloud computing, multimedia content processing, semantic web, social networking technologies etc. She has published more than 200 papers in leading international journals, conferences and books. She has participated and co-ordinated numerous EC projects. From 2008-2012, she held the chair of the postgraduate program “Engineering Economic Systems” of NTUA.