Prof. Kalyanmoy Deb

Koenig Endowed Chair Professor, Michigan State University, East Lansing, USA

Biography: Kalyanmoy Deb is Koenig Endowed Chair Professor at Department of Electrical and Computer Engineering in Michigan State University, USA. Prof. Deb's research interests are in evolutionary optimization and their application in optimization, modeling, and machine learning. He was awarded IEEE EC Pioneer Award, Infosys Prize, TWAS Prize in Engineering Sciences, CajAstur Mamdani Prize, Distinguished Alumni Award from IIT Kharagpur, Edgeworth-Pareto award, Bhatnagar Prize in Engineering Sciences, and Bessel Research award from Germany. He is fellow of IEEE, ASME, and three Indian science and engineering academies. He has published over 480 research papers with Google Scholar citation of 113,000 with h-index 107. He is in the editorial board on 18 major international journals. More information can be found from my COIN laboratory website

Title of Speech: Customized Metaheuristics for Intelligent System Design

Abstract: Population-based metaheuristics have been proposed and applied to various practical problems for the past three decades. In most occasions, they have been found to be advantageous over their point-based counterparts in solving complex and hard-to-solve problems. In this keynote talk, we highlight the importance of customizing a vanilla metaheuristic methodology for solving a practical problem class routinely, reliably, and in a computationally fast manner. A few case studies on intelligent system design will be presented highlighting the importance of customization in the design of metaheuristics.

Professor Juergen Branke

Warwick Business School, The University of Warwick Coventry, UK

Biography: Juergen Branke received his Ph.D. degree from University of Karlsruhe, Germany, in 2000. He is a Professor of Operational Research and Systems with the Warwick Business School, University of Warwick, U.K. He has been an active researcher in the area of evolutionary optimization since 1994 and has published more than 170 papers in international peer-reviewed journals and conferences. His research interests include multiobjective optimization, handling of uncertainty in optimization, dynamically changing optimization problems, simulation-based optimisation and the design of complex systems. He is area editor of the Journal of Heuristics and the Journal on Multi-Criteria Decision Analysis, as well as associate editor of IEEE Transactions in Evolutionary Computation and the Evolutionary Computation Journal.

Title of Speech: Design of Complex Systems via Simulation Optimization

Abstract: Simulation has become an invaluable tool to analyze complex systems, and is used across disciplines including engineering, manufacturing and social sciences. However, optimization based on simulation models is challenging, because the simulation model is usually a black box, because running a simulation to evaluate a solution is computationally expensive, and also because many simulation models are stochastic, turning the optimization problem into a stochastic problem. The seminar will explain two algorithms that are frequently used for simulation optimization: Metaheuristics and Bayesian optimization. It will then discuss ways of improving the ability of metaheuristics to cope with noise, and how Bayesian optimization can be used to take into account uncertainty about the input parameters of the simulation model. The seminar concludes with two application examples in the area of traffic light control and scheduling.

Professor M. Sohel Rahman

Bangladesh University of Engineering & Technology, Dhaka, Bangladesh

Biography: Dr. M. Sohel Rahman is a Professor of the CSE department of BUET. He had worked as a Visiting Research Fellow of King’s College London, UK during 2008-2011 and again as a Visiting Senior Research Fellow there during 2014-15. He is a Senior Member of both IEEE and ACM; member of American Mathematical Society (AMS) and London Mathematical Society (LMS). He is also a Peer-review Associate College Member of EPSRC, UK.
Dr. Rahman received different scholarships and fellowships including Commonwealth Scholarship, Commonwealth Fellowship, ACU Titular Fellowship, University College London-Big Data Institute visiting grant, London Mathematical Society Visiting Grant etc. He is also a recipient of the Bangladesh Academy of Sciences Gold Medal and UGC Award. He has led research and development projects funded by British Council, UGC-World Bank and BUET. He has so far published 80 peer-reviewed international journal papers. Among his notable results are the work on high dimensional Knapscak problems, sequence alignment problems, data structures and string combinatorics, sufficient conditions for Hamiltoninicity, Machine Learning based predictors in Bioinformatics, and metaheuristics solutions for hard problems.
He is an Academic Editor of PLOS One, Associate Editor of BMC Research Notes and had edited special issues as guest editors in Theoretical Computer Science, Journal of Graph Algorithms and Applications, Journal of Discrete Algorithms, Fundamenta Informaticae etc. He has also served as Program Committee members in a number of conference series’ of international repute. Dr. Rahman regularly writes reviews at Mathematical Review and Computing Review.

Title of Speech: Prediction based on biological sequences, where Machine Learning meets Life Sciences

Abstract: Due to the rapid development of fast sequencing technologies, we now have tremendous amount data on different biological sequences. For example, the number of sequence-known proteins has grown exponentially in recent years. On the contrary, the biochemical experiments to learn the attributes of proteins are expensive and time consuming. A large gap thus exists between the number of sequence-known proteins and that of attribute-known proteins. To catch up, researchers have started to rely on state of the art computational intelligence based methods (e.g., Machine Learning) to predict different attributes of proteins and other biological sequences. In this talk, we will discuss Machine Learning based methods for a number of prediction tasks in the domain of life sciences. We will discuss predictors that have been developed based on a machine learning based framework where the features are extracted from the primary sequence only. Overall, our research empirically asserts the natural belief that the functional and structural information of a biological sequence are intrinsically encoded within its primary sequence. This assertion culminates in generalizing a framework for sequence based feature extraction and selection that can be applied to any prediction problem in life sciences.