KEYNOTE SPEAKER
Xiaoli Li, Institute for Infocomm Research A*STAR, Singapore, Nanyang Technological University, Singapore
Speech Title:
Time-Series Sensor Data Analytics: From Cutting-Edge Research to Real-World Impact
Abstract:
The proliferation of sensors in industries such as manufacturing, aerospace, semiconductors, transportation, education and healthcare has created a critical demand for innovative AI solutions to analyze time-series sensor data. These solutions enable applications ranging from enhancing equipment availability and efficiency to enabling data-driven maintenance and intelligent system control. In this talk, we will explore recent advances in deep learning-based AI research tailored to address key challenges in equipment diagnostics and remaining useful life prediction. Key focus areas include achieving high prediction accuracy, compressing models for edge computing deployment, considering data privacy and overcoming domain adaptation barriers. By showcasing real-world use cases, we will demonstrate how these AI-driven approaches bridge the gap between academic research and industrial applications, driving more efficient and intelligent systems across diverse sectors.
Bio of the Keynote Speaker Xiaoli is the Department Head and Senior Principal Scientist at the Institute for Infocomm Research (I²R), A*STAR, Singapore, and an adjunct full professor at the School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore. His research spans artificial intelligence, data mining, machine learning, and bioinformatics, with over 370 peer-reviewed publications and more than ten best paper awards.
Xiaoli serves as the Editor-in-Chief of the Annual Review of Artificial Intelligence and as an Associate Editor for top-tier journals, including IEEE Transactions on Artificial Intelligence and Knowledge and Information Systems. He is also a regular chair and area chair for leading AI conferences such as AAAI, IJCAI, ICLR, NeurIPS, KDD, and ICDM. In addition to his academic achievements, Xiaoli has extensive industry experience, leading over ten R&D projects in collaboration with global industry leaders across aerospace, telecommunications, insurance, and professional services. He is an IEEE Fellow, a Fellow of the Asia-Pacific Artificial Intelligence Association (AAIA), a Clarivate Highly Cited Researcher, and ranked among the world’s top 2% scientists in AI by Stanford University and top computer scientists by Research.com.
Bio of the Keynote Speaker Xiaoli is the Department Head and Senior Principal Scientist at the Institute for Infocomm Research (I²R), A*STAR, Singapore, and an adjunct full professor at the School of Computer Science and Engineering, Nanyang Technological University (NTU), Singapore. His research spans artificial intelligence, data mining, machine learning, and bioinformatics, with over 370 peer-reviewed publications and more than ten best paper awards.
Xiaoli serves as the Editor-in-Chief of the Annual Review of Artificial Intelligence and as an Associate Editor for top-tier journals, including IEEE Transactions on Artificial Intelligence and Knowledge and Information Systems. He is also a regular chair and area chair for leading AI conferences such as AAAI, IJCAI, ICLR, NeurIPS, KDD, and ICDM. In addition to his academic achievements, Xiaoli has extensive industry experience, leading over ten R&D projects in collaboration with global industry leaders across aerospace, telecommunications, insurance, and professional services. He is an IEEE Fellow, a Fellow of the Asia-Pacific Artificial Intelligence Association (AAIA), a Clarivate Highly Cited Researcher, and ranked among the world’s top 2% scientists in AI by Stanford University and top computer scientists by Research.com.
Pietro Simone Oliveto, Southern University of Science and Technology (SUSTech), Shenzhen, China.
Speech Title:
Computational Complexity Analysis of Sexual Evolution for the Design of Better General Purpose Algorithms for AI
Abstract:
Large classes of the general-purpose optimisation algorithms at the heart of modern artificial intelligence and machine learning technologies are inspired by models of Darwinian evolution. In this talk we show how the foundational computational complexity analysis of such algorithms leads to an understanding of their behaviour and performance. Such understanding in turn allows informed decisions on how to set their many parameters and how to improve the algorithms to allow for the obtainment of better solutions in shorter time. We provide two concrete examples of how such analyses can lead to counter intuitive insights into how to design sexual evolution inspired algorithms (using populations and recombination) and how to set their parameters such that they can considerably outperform their single trajectory and mutation only (asexual) counterparts at hillclimbing unimodal functions, and at escaping from local optima. We conclude the talk by presenting experimental results that confirm the superiority of the designed algorithms that was proven for benchmark functions with significant structures, for classical combinatorial optimisation problems with practical applications.
Bio of the Keynote Speaker Pietro Oliveto is a Professor of Computer Science at the Southern University of Science and Technology (SUSTech) Shenzhen, China. He received the Laurea degree and PhD degree in computer science respectively from the University of Catania, Italy in 2005 and from the University of Birmingham, UK in 2009. He has been EPSRC PhD+ Fellow (2009-2010) and EPSRC Postdoctoral Fellow (2010-2013) at the University of Birmingham, UK and Vice-Chancellor's Fellow (2013-2016) and EPSRC Early Career Fellow (2015-2020) at the University of Sheffield, UK. Before moving to SUSTech he was Chair in Algorithms at the Department of Computer Science, University of Sheffield, UK.
His main research interest is the performance analysis, in particular the time complexity, of bio-inspired computation techniques including evolutionary algorithms, genetic programming, artificial immune systems, hyper-heuristics and algorithm configurators. He is currently building a Theory of Artificial Intelligence Lab at SUSTech.
He has guest-edited journal special issues of Computer Science and Technology, Evolutionary Computation, Theoretical Computer Science, IEEE Transactions on Evolutionary Computation and Algorithmica. He has co-Chaired the IEEE symposium on Foundations of Computational Intelligence (FOCI) from 2015 to 2021 and has been co-program Chair of the ACM Conference on Foundations of Genetic Algorithms (FOGA 2021) and Theory Track co-chair at GECCO 2022 and GECCO 2023. He is part of the Steering Committee of the annual workshop on Theory of Randomized Search Heuristics (ThRaSH), was Leader of the Benchmarking Working Group of the EU-COST Action ImAppNIO, is member of the EPSRC Peer Review College and recently completed his term as Associate Editor of IEEE Transactions on Evolutionary Computation.
Bio of the Keynote Speaker Pietro Oliveto is a Professor of Computer Science at the Southern University of Science and Technology (SUSTech) Shenzhen, China. He received the Laurea degree and PhD degree in computer science respectively from the University of Catania, Italy in 2005 and from the University of Birmingham, UK in 2009. He has been EPSRC PhD+ Fellow (2009-2010) and EPSRC Postdoctoral Fellow (2010-2013) at the University of Birmingham, UK and Vice-Chancellor's Fellow (2013-2016) and EPSRC Early Career Fellow (2015-2020) at the University of Sheffield, UK. Before moving to SUSTech he was Chair in Algorithms at the Department of Computer Science, University of Sheffield, UK.
His main research interest is the performance analysis, in particular the time complexity, of bio-inspired computation techniques including evolutionary algorithms, genetic programming, artificial immune systems, hyper-heuristics and algorithm configurators. He is currently building a Theory of Artificial Intelligence Lab at SUSTech.
He has guest-edited journal special issues of Computer Science and Technology, Evolutionary Computation, Theoretical Computer Science, IEEE Transactions on Evolutionary Computation and Algorithmica. He has co-Chaired the IEEE symposium on Foundations of Computational Intelligence (FOCI) from 2015 to 2021 and has been co-program Chair of the ACM Conference on Foundations of Genetic Algorithms (FOGA 2021) and Theory Track co-chair at GECCO 2022 and GECCO 2023. He is part of the Steering Committee of the annual workshop on Theory of Randomized Search Heuristics (ThRaSH), was Leader of the Benchmarking Working Group of the EU-COST Action ImAppNIO, is member of the EPSRC Peer Review College and recently completed his term as Associate Editor of IEEE Transactions on Evolutionary Computation.