AMMS

Dr. Ding-Geng Chen (aka Din Chen) is an elected fellow of the American Statistical Association (FASA), an elected Fellow of the Royal Society of South Africa (FRSSAf), and elected Member of the Academy of Science of South Africa. He is currently the executive director and professor in biostatistics at the College of Health Solutions, Arizona State University. He is also an extraordinary professor and the SARChI research chair in biostatistics at the University of Pretoria, an honorary professor at the University of KwaZulu-Natal, South Africa. Dr. Chen was the Wallace H. Kuralt distinguished professor in Biostatistics at the University of North Carolina at Chapel Hill, a professor in biostatistics at the University of Rochester Medical School, and the Karl E. Peace Endowed Eminent Scholar Chair in Biostatistics at Georgia Southern University. Dr. Chen has more than 300 referred professional publications and co-authored and co-edited 45 books on biostatistics, clinical trial methodology, meta-analysis, data science, causal inference, and public health research.

Speech Title: "Biostatistics and ML/AI in High-Dimensional Medical Imaging Analysis"

Abstract: Non-mydriatic retinal fundus imaging is widely used for screening diabetes, glaucoma, cataracts, cardiovascular diseases, and neurodegenerative disorders. However, these images often suffer from noise, low contrast, and structural distortions, which limit the performance of artificial intelligence and machine learning models that rely on accurate visual features. In this keynote, we present the development of biostatistical framework of robust PCA with ML/AI that addresses existing limitations in retinal image enhancement by integrating a Truncated Weighted Nuclear Norm (TWNN) with Adaptive Histogram Equalization (AHE). Multiple synthetic and publicly available retinal datasets, including EyeQ, DRIVE, STARE, and Kaggle, will be used to demonstrate that the proposed method substantially improves image fidelity and clearly reveals fine blood vessels. A user-friendly APP is created to enable rapid enhancement of degraded retinal images for clinical use. This framework establishes a robust methodological foundation for next-generation high-dimensional medical imaging analytics and accurate ML/AI based disease detection, bringing us closer to real-time, clinically actionable retinal image analysis.

Paulo Canas Rodrigues is a Professor of Statistics and Data Science at the Federal University of Bahia and the Director of the Statistical Learning Laboratory (SaLLy; www.SaLLy.ufba.br). Paulo completed his Ph.D. in Statistics at the Nova University of Lisbon, Portugal (2012), and his Habilitation in Mathematics, with a specialization in Statistics and Stochastic Processes, at the Lisbon University, Portugal (2019). His research in time series forecasting, statistical learning, artificial intelligence, statistics, and data science has resulted in more than 130 scientific papers, co-authored with over 200 collaborators from 95 universities in 31 countries. He has delivered more than 200 invited talks at conferences and scientific seminars. He was President of the International Society for Business and Industrial Statistics (ISBIS; 2013-2015), President of the Brazilian Region of the International Biometric Society (RBras; 2018-2020; 2020-2022), Council Member of the Brazilian Statistical Association (2020-2024), Co-Founder and Chairperson of the Latin American Regional Section of the International Association for Statistical Computing (2017-2019), and the Chair of the Special Interest Group on Data Science of the International Statistical Institute (2021-2023). Among other activities, he serves as the current President of the International Association for Statistical Computing, is a Member of the Representative Council of the International Biometric Society, and is a Council Member of the International Statistical Institute. Website: www.paulocanas.org; www.SaLLy.ufba.br.

Speech Title: "From Inference to Intelligence: The Evolving Role of Statistics in the Age of AI"

Abstract: Artificial Intelligence is changing the way we analyse and use data. But behind most AI methods are core ideas from statistics: uncertainty, estimation, and learning from data. In this lecture, I will show how modern AI systems, from machine learning to generative models, build upon and sometimes challenge traditional statistical thinking. We will revisit concepts such as inference, prediction, and interpretability, and see how they appear in today’s neural networks and large language models. I will also discuss why statistical reasoning is essential to make AI reliable, transparent, and fair. The goal is to open a conversation about how statistics and AI can grow together, and how statisticians can shape the future of data-driven science.

Carlos A. Coelho is a Full Professor of Statistics at the Mathematics Department of Faculdade de Ciências e Tecnologia of NOVA University of Lisbon. He holds a Ph.D. in Biostatistics by The University of Michigan, Ann Arbor, MI, U.S.A., and his main areas of research are Mathematical Statistics and Distribution Theory, namely the derivation of Likelihood Ratio Tests for elaborate structures of covariance matrices and for MANOVA-like models under the assumption of elaborate covariance structures, as well as the study and development of exact and near-exact distributions for these and other likelihood ratio test statistics used in Multivariate Analysis. Other areas of interest are Estimation, Univariate and Multivariate Linear, Generalized Linear and Mixed Models, etc. Carlos A. Coelho is an Elected Member of the International Statistical Institute and has served as Associate Editor in the Editorial Boards of REVSTAT and Journal of Interdisciplinary Mathematics and currently serves in the Editorial Boards of Journal of Applied Statistics, Journal of Statistical Theory and Practice, American Journal of Mathematical and Management Sciences and Discussiones Mathematicae-Probability and Statistics and is Associate Editor of the Springer Book series “Emerging Topics in Statistics and Biostatistics”. Carlos A. Coelho, a Fulbrighter, is also vice-president of Fulbrighters Portugal – the Portuguese Fulbright Alumni Association.

Assoc. Prof. S. Joseph Antony
University of Leeds, UK

Dr S. Joseph Antony is an Associate Professor at the School of Chemical and Process Engineering, University of Leeds, U.K. His research expertise is in the area multi-scale modelling and experimental mechanics of materials in both discrete and continuum form. He has a strong expertise in materials modelling including MD, DEM, FEM and analytical methods. His experimental approaches include a wide variety of advanced characterising and stress sensor techniques including photonics (PSA), AFM, SEM, PSAT and IR tomography, and DPIV. He focuses on linking the effects of material properties at exceedingly small scales (molecular/nano/micro) to bulk scale mechanical, electrical and chemo-mechanical properties in a wide variety of engineering applications. Joseph has published over 150 papers in several reputed international journals and conference proceedings. He actively participates in the activities of particle technology community in U.K and abroad. He has won many awards, including the prestigious M.I.T Young Research Fellowship for Exemplary Research in Computational Mechanics and the Certificate of Merit as an Example of Outstanding Achievements in U.K Particle Science and Technology in 2002, PTSG, IChemE, U.K. He has served as a guest editor for the Jl. Granular Matter and the lead editor of the book ‘Granular Materials: Fundamentals and Applications’, published by the Royal Society of Chemistry, London in 2004. His research sponsors include EPSRC, Royal Society, DTI, ICI, BNFL, P&G, Pfizer, Borax Hosakawa Micron, Bridon International Ltd, Merck Sharp & Dohme and DuPont (U.K). More details on his research activities can be found in: http://www.spanglefish.com/drsjosephantony/.

Prof. Saralees Nadarajah
University of Manchester, UK

Saralees Nadarajah is a Professor in the Department of Mathematics, University of Manchester, UK. His research interests include climate modeling, extreme value theory, distribution theory, information theory, sampling and experimental designs, and reliability. He is an author/co-author of four books, and has over 1000 refereed journal papers published or accepted. He has held positions in Florida, California, and Nebraska.

Prof. Gyu Myoung Lee
Liverpool John Moores University (LJMU)

Gyu Myoung Lee joined the Liverpool John Moores University (LJMU), UK in 2014, as a Senior Lecture in the department of Computer Science and was promoted to a Reader in 2017 and a Professor in 2020. He is also with KAIST Institute for IT convergence, Daejeon, Rep. of Korea, as an Adjunct Professor from 2012. Before joining the LJMU, he worked with the Institut Mines-Telecom, Telecom SudParis from 2008. Until 2012, he was invited to work with the Electronics and Telecommunications Research Institute (ETRI), Rep. of Korea. He worked as a research professor in KAIST, Rep. of Korea and as a guest researcher in National Institute of Standards and Technology (NIST), USA, in 2007. He worked as a visiting researcher in the University of Melbourne, Australia, in 2002. Furthermore, he also has work experience in industries in Rep. of Korea. His research interests include Internet of Things, Web of Things, computational trust, knowledge centric networking and services considering all vertical services, Smart Grid, energy saving networks, cloud-based big data analytics platform and multimedia networking and services. Dr. Lee has been actively participating in standardization meetings including ITU-T SG 13 (Future Networks and cloud) and SG20 (IoT and smart cities and communities), IETF and oneM2M, etc., and currently serves as a Rapporteur of Q16/13 (Knowledge centric trustworthy networking and services) and Q4/20 (e/Smart services, applications and supporting platforms) in ITU-T. He is also the chair of ITU-T Focus Group on Data Processing and Management (FG-DPM) to support IoT and smart cities & communities. He has contributed more than 300 proposals for standards and published more than 100 papers in academic journals and conferences. He received several Best Paper Awards in international and domestic conferences and served as a reviewer of IEEE journals/conference papers and an organizer/member of committee of international conferences. He is a Senior Member of IEEE.

Speech Title: "AI powered Trustworthy Decentralized Internet"

Abstract: Artificial Intelligence (AI) and Internet of Things (IoT) are very important technologies for the future, and recently there has been a lot of research activity to combine AI and IoT, called AIoT (Artificial Intelligence powered Internet of Things). In addition, data is becoming essential to support AI-based solutions with human interactions. Blockchain is revolutionizing the way transactions are recorded as a machine to create trust. In this context, this talk will introduce key concepts, features and characteristics of the Decentralized Internet (i.e., Web 3.0 and its vision as the Internet of Value), taking into account emerging ICTs integrating AIoT and Blockchain, and related EU projects such as GAIA-X. From the research on decentralized Internet research for Web 3.0, many researchers have recognized that there are security, privacy and trust concerns to realize a user-centric approach for decentralization. To cope with the negative effects of the decentralized Internet, it's necessary to build a trustworthy infrastructure with AI for the future digital economy toward the Internet of Value. Therefore, starting from the new economic paradigm for cyberspace, data ecosystem and its characteristics, this talk will present future directions for realizing decentralized Internet with AI-powered trust technology.

Dr. Gökhan Yıldırım is a faculty member at Bilkent University, Ankara, Türkiye. He earned his PhD in Applied Mathematics from the University of Southern California, USA. His research spans enumerative combinatorics, probability, statistical physics, and data science. Dr. Yıldırım has contributed to numerous collaborative research projects and published in prestigious peer-reviewed international journals, including Advances in Applied Mathematics, Nature Physics, Electronic Journal of Probability, and Electronic Journal of Combinatorics. His findings have been presented at leading international conferences and meetings worldwide. In addition to his research, Dr. Yıldırım is an experienced educator, regularly teaching courses in probability, statistics, discrete mathematics, and data science. He has also served on editorial and review boards of scientific journals and actively participated in program committees of international conferences.

Speech Title: "Sampling from Discrete Combinatorial Structures: Algorithms, Challenges, and Open Questions"

Abstract: Understanding the structure and properties of discrete combinatorial objects, such as pattern-avoiding permutations and inversion sequences, is a fundamental problem with applications across mathematics, statistical physics, and computer science. In this talk, I will explore sampling algorithms designed to efficiently generate these complex structures. Special emphasis will be placed on Markov Chain Monte Carlo (MCMC) methods, which have become indispensable tools for approximate sampling in high-dimensional combinatorial spaces. I will discuss the strengths and limitations of these algorithms, highlighting recent advancements and illustrating their practical performance. Additionally, several open questions will be presented, offering insight into ongoing challenges in the field and potential directions for future research. This talk aims to provide an accessible overview of the theoretical underpinnings, computational techniques, and open problems related to sampling from discrete combinatorial structures.

Dr Chris G. Antonopoulos
University of Essex, UK

Assist. Prof. Paola Lecca
Free University of Bozen-Bolzano, Italy

Paola Lecca is a theoretical physicist with a PhD in Computer Science and Telecommunication. Dr. Lecca is Assistant Professor at the Faculty of Engineering of the Free University of Bozen-Bolzano (Italy), where she carries out research activities in the fields of graph theory, modelling and analysis of dynamic networks, statistical inference, parallel computing, mainly in the application domains of bioinformatics, computational biology, biophysics and drug development. Dr. Lecca’s interests and scientific contributions relate to the mathematical foundations of data analysis, artificial intelligence and modelling techniques for complex systems that can be represented as networks of dynamic interactions. A member of various national and international scientific associations, Paola Lecca has also authored over a hundred articles in international scientific journals and conference proceedings in computational biology, biophysics and applied mathematics.

Speech Title: "The Bayesian basis of Decision-Making in Artificial Intelligence: Does It Help to Determine the Level of Confidence in Artificial Intelligence Results?"

Abstract: Artificial Intelligence systems can explicitly model uncertainty thanks to Bayesian statistics. Bayesian models produce a probability distribution over potential outcomes rather than a single deterministic output. By capturing the inherent uncertainty in data and model projections, this probabilistic approach facilitates risk assessment and well-informed decision-making. Furthermore, Bayesian decision theory provides a structured framework for making optimal decisions under uncertainty. However, the uncertainty in the prior probability function and background knowledge cannot be handled or represented generally by the Bayesian approach. This is a significant theoretical and practical drawback of Bayesianism. These limitations of the Bayesian approach will be presented and discussed in the talk and some perspectives will be given on the need to go beyond traditional Bayesianism.

Assoc. Prof. Ahmad Lutfi Amri Ramli
Universiti Sains Malaysia, Malaysia

Assoc. Prof. Dr. Ahmad Lutfi Amri Ramli is an esteemed academic at the School of Mathematical Sciences, Universiti Sains Malaysia (USM). He holds a PhD from Durham University, an MSc from Brunel University, and a BSc in Mathematics from USM. Dr. Lutfi’s research expertise lies in applied mathematics, with a focus on motion planning for robots integrating the knowledge from computer aided geometrical design, curve and surface modelling, and computational methods. His interest also extends to gamification in education, leveraging innovative approaches to enhance student engagement in mathematical learning As an academic leader and researcher, Dr. Lutfi has been actively involved in advancing research, fostering student development, and innovating teaching practices, contributing to the growth of mathematics and applied sciences.

Speech Title: "CAGD and Its Application in Transportation Research"

CAGD is used in transportation research for road design, vehicle trajectory planning, speed estimation, and optimizing autonomous navigation paths. It also enables the creation of smooth and efficient road alignments while ensuring safety and comfort. This talk will highlight a few key applications, such as safe speed estimation using parametric curves derived from GPS data and travel time prediction based on circular arc curvature to estimate speed from road geometry. These techniques provide valuable insights for traffic management and infrastructure development. By applying CAGD techniques, transportation research can leverage mathematical models to improve accuracy while reducing costs.