BiographyDr. Sofia Colombi holds a master’s degrees in Nuclear Engineering from Politecnico di Milano (Milano, Italy) and a PhD in experimental Physics from University of Trento (Trento, Italy). She has been working since 2017 on research programs merging fundamental and applied physics in the fields of medical applications and space radiation protection. Dr. Colombi’s expertise is in experimental techniques for radiation detection, data analysis, dosimetry, software implementation, hardware investigation and optimization, as well as Monte Carlo simulations. Her work has included experimental activities performed at international laboratories, such as GSI (Darmstadt, Germany), Trento Protontherapy Center (Trento, Italy), Heidelberg Ion Beam Therapy Center (Heidelberg, Germany), amounting to over 80 beam hours. Dr. Colombi’s research has focused on investigating various aspects of the radiation-matter interaction, aiming to enhance treatment planning in particle therapy and to devise more effective passive countermeasures against space radiation. 

After a working experience at the cancer therapy center Ebg MedAustron (Wiener Neustadt, Austria) under the lead of Dr. Giulio Magrin, she was admitted in the Doctoral Program in Physics at the University of Trento and Trento Institute for Fundamental Physics and Application (TIFPA). There, she was part of the biophysics group first leaded by Prof. Marco Durante and then by Prof. Chiara La Tessa. During her doctoral journey, Dr. Colombi was part of the FOOT (FragmentatiOn Of Target) international collaboration and experiment, for the characterization of beam fragments production in cancer therapy and space radiation protection. Genuinely interested in STEM and constantly looking for stimulating challenges, Dr. Colombi was selected among the 15 international students who took part in the first ever ESA-FAIR Space Radiation School in 2019.

After completing her doctoral studies in February 2021, Dr. Colombi pursued a postdoctoral position with the Italian National Institute for Nuclear Physics (INFN) at the Physics Department of University of Bologna, where she was also tutoring and lecturing physics and engineering students, as well as supervising undergraduate students in their thesis projects. Dr. Colombi joined EmTDLab in November 2022 as radiation effects and simulation engineer, where she oversees the research and development of the radiation shielding function used to select materials offering optimal space radiation shielding performances, conducting Monte Carlo simulations to verify results and refining the accuracy of the model developed.

Title: EmTDLab innovative systematic search for the next-gen radiation shielding materials

Abstract: In the context of the 'New Space' era, space radiation emerges as the predominant constraint for spacecraft operations. This is primarily due to the considerable human health and electronics risks associated with exposure to the space radiation environment. The radiation environment in the Solar System is a complex mixture of particles of solar and galactic origin with a broad range of energies. The three most relevant sources are Galactic Cosmic Rays (GCRs), Solar Particle Events (SPEs) and secondary radiation generated from the interaction of the incoming external radiation with any material (e.g., the spacecraft hull). Current radiation shielding solutions are inefficient from an economic and technical point of view. However, as the research community deepen his knowledge in physics and chemistry, it paves the way for integrating computational intelligence within material science. Moreover, the emergence of advanced computational architectures, coupled with systems and methodologies tailored to harness this power, strengthens the case for computational materials science, also known as materials informatics.

EmTDLab is the sole company researching and designing a computational system for the systematic discovery of novel ionizing radiation shielding materials. The core challenge in materials science lies in identifying materials with optimal properties. Historically, we've been restricted to experimental discovery, bound by the constraints and costs of a trial-and-error method. When it comes to shielding materials against particle radiation, only a limited number of materials have been explored and crafted for electronics component and humans’  protection and shielding in manned spacecraft. Until recently, the development andoptimization of both single and multilayer material configurations have been largely empirical, incrementally optimised over decades. However, the advent of the computational materials science revolution is reshaping our approach. Systematic searches and optimization strategies set the stage for devising materials based on their desired properties. Specifically, EmTDLab employs systematic computational searches through evolutionary algorithms. Beginning with atomic elements, these are iteratively paired with other elements to create material compounds. The material design will lead to a given material composition (single layer shield) or a set of compositions (multi-layer) that takes the primary incoming radiation beam of a specific exposure as an input, and that provides the radiation shielding efficiency of the specific configuration under study. The identified optimal simulated candidate materials can subsequently be synthesized and large-scale manufactured. Applying such a systematic material search techniques to discover new radiation shielding materials has never been undertaken.


BiographyDerrickI-Hsien Ting is an Associate Professor in the Department of Information Management at, the National University of Kaohsiung, TAIWAN. He has a PhD degree in Computer Science, from the University of York, UK, His research interests focus on Data Mining and E-commerce, particularly on Web Mining, Social Network Analysis, Web Intelligence, E-commerce, and Semantic Web. He was a program chair of ASONAM 2011 in Kaohsiung and program chair of the KMO conference from 2013– 2024. Besides, he joined as chair of more than 30 International conferences and as a program committee member for more than 100 International conferences. Furthermore, he is now the managing editor of the international journal of Information Privacy, Security and Integrity and on the editor board for more than 10 International journals.

TitleSocial Bots Detection: Social network analysis approach

AbstractWith the growth of social networking websites, social media has become a major platform for marketing, such as social business, political manipulation, influence and brand management, etc. However, social media marketing is very different from traditional marketing. Social media marketing needs to face many users and repeat the same process frequently. It is therefore a very human power-consuming task. This situation is the reason why Robotic Process Automation and Social-bots is now very popular on many social networking websites. However, there are many negative effects when applying social-bots for social marketing. For example, it may affect political and election results, spread misinformation and fake news speedily, lower the trust of social networking websites and cause cyberbullying, etc. Therefore, in addition to those social networking websites, more and more researchers are devoting to proposing efficient ways to detect social-bots. In this talk, I will introduce Social-bots and the approach to detect social-bots.


Biography: Dr. Azuraliza Abu Bakar is a professor and faculty member of the Center for Artificial Intelligence, Faculty of Information Science and Technology, University Kebangsaan Malaysia (The National University of Malaysia). She graduated with Mathematics (BSc) and Computer Science (MSc) from the University Kebangsaan Malaysia (UKM). Professor Azuraliza received her doctoral degree in Artificial Intelligence from the University Putra Malaysia in 2002. She has been a lecturer in UKM since 2003 in the Center for Artificial Intelligence and continues her work as a Professor with a speciality in Data Analytics. Throughout her service as a lecturer, Professor Azuraliza has held various positions, including Head of the System Science and Management Department, Chairperson of the Center for Artificial Intelligence Technology, and Deputy Dean for Research and Innovation. She is the head of UKM's Data Mining and Computational Intelligence Research Group, Principal Researcher of the Data Mining and Optimization Lab, and Co Researcher in Sentiment Analysis Lab. Her main research areas are Data Analytics and Artificial Intelligence, specifically in Rough Set Theory, Feature Selection Algorithms, Nature Inspired Computing and Sentiment Analysis. She is the head of 13 research projects (including 3 in progress) and a member of 42 research projects. She led LAB40: Living Analytics for Enhancing The B40's Well-being Program. LAB40 is a program that combines data analytics
research in the areas of people's well-being, including poverty, socioeconomics, health security, education, and gender, for intelligent decision-making that enhances the well-being of the people, especially the B40s.She has supervised 24 completed and 8 in progress PhDs and over 50 MSc and BSc students. She has been the external examiner for 40 PhD candidates in Malaysia. She is the author of four research books and has published 109 journals, seven book chapters and more than 90 research proceedings. Her primary publication fingerprints are data mining, feature extraction, data stream mining, social network analytics, link prediction, community detection, and social economic analytics.

At the National Level, she was appointed as (1) member of the National Action Council for Cost of Living (NACCOL) in 2018-2021, (2) Technical Committee Member of the Big Data Project for the Ministry of Education in June 2019, (3) Panel and Domain Expert for Career Advancement Program (Ministry of Higher Education) (4) Fund Evaluation Panel for Ministry of Higher Education, Malaysia Science Academy, and Ministry of Science and Technology (MOSTI)). (7) Committee member of Big Data Project for National TVET Council (2021) (8) Consultant for National Higher Education Fund Corporation (PTPTN) in sentiment analysis for public opinion (2019), and (9) Consultation member for Long-Covid effects among workers in Malaysia. In academics, she teaches Advanced Artificial Intelligence, Data Mining and Knowledge Discovery, Fundamental Data Science, and Machine Learning. She has served on the panel of assessors for several local universities on developing the Data Science Program and Artificial Intelligence Program. She has served roughly twenty conferences and workshop program committees and was Program Chair for MCAIT in 2012, 2014, 2016, and 2018. She is a member of the IEEE Computational Intelligence Society.

Title: Social Economics Analytics: Leveraging Socio-economic Data for the Nation Wellbeing

Abstract: The Sustainable Development Goals (SDGs), also known as the Global Goals, were adopted by the United Nations in 2015 as a universal call to action to end poverty, protect the planet, and ensure that by 2030 all people enjoy peace and prosperity. The aim of research to achieve the SDG covers the creativity, know-how, technology and financial resources from all of society, which is necessary to achieve the SDGs in every context. The availability of the vast amount of socio-economics data that covers various aspects and profiles is a valuable treasure that contributes to knowledge and decision-making. Socio-economic analytics is an effort to combine research and development of big data analytics in fields involving the well-being of the people and the country to improve society with high impact. The data-intensive technology such as AI and machine learning allows people to get solutions according to personal needs, profiles and activities. It utilizes various related data sources such as economic, social, health, education, and transportation data by exploring essential knowledge that will help those responsible for making decisions, enacting policies and planning initiatives that can improve living standards and incomes and reduce the cost of living for the people. The ultimate goal of achieving the 'No Poverty'' SDG is to improve the living standards for the nation's income groups towards zero poverty. The government initiatives in handling socio-economics problems could be identifying the targeted group based on certain specific indicators, developing appropriate Multidimensional Poverty Index (MPI) indicators, and setting up initiatives for financial literacy among household income classes.

The socio-economics analytics use cases employing well-known and advance Machine Learning algorithms for predictive model development are presented. The model uses datasets related to household income, expenditure, and poverty obtained from several sources at the national level. (1) Households Financial Burden Risk Prediction Model (determiningn the factors that contribute to the risk of the financial burden of a household, patterns of households with financial burden from different income groups, and states.). (2) Gendering Analytics (determining gender-based factors contributing to households' financial risk or non-risk and finding patterns of households with financial risk). (3)Multidimensional Poverty Indicators (MPI) based on machine learning (identifying the appropriate indicators and dimensions that will provide data-driven MPI measurement employing feature fusion and ensemble learning). (4) Clustered-based Multidimensional Poverty Indicators (MPI) to identify the appropriate indicators and dimensions for data-driven MPI measurement. (5) Households Spending Behaviour Model for Income Class (finding factors that affect the spending patterns among the household to develop a household overspending model using machine learning. (6) Model of Risk to Retain and Potential to Exit from the low-income group of households. The use cases are based on the three preliminaries: source of data, data preparation and labeling baselines, and machine learning algorithms used for predictive model development. The standard processes in predictive model development employed are data preprocessing and preparation, model development, model evaluation and deployment. Finally, we present the challenges and way forward for socio-economics analytics towards the ensemble algorithms for decision analytics.


BiographyAndres Iglesias is a professor of Computer Science and Artificial Intelligence at the University of Cantabria, Santander, Spain, where he leads the "Computer Graphics & Artificial Intelligence" research group, and was Head of Department (2008-2012), and Postgraduate Studies Coordinator (2005-2012). Since 2013, he has also been invited/guest professor at Toho University, Funabashi, Japan. He is also the current chair of the Technical Committee 5 - Information Technology Applications, Workgroup 5.10- Computer Graphics and Virtual Worlds at IFIP, the UN-recognized UNESCO-established international organization comprised by more than 50 national societies and academies in the field of computer science. He was also Chair of the Steering Board of ICMS, the society responsible for the regular ICMS event, part of the ICM (International Congress of Mathematicians, the world's largest event in Mathematics).

His research is highly inter/multidisciplinary, having published journal papers in 33 different categories of Web of Science Journal Citation Reports, including most categories of Computer Science, Mathematics, Physics and Engineering. His publication profile includes more than 300 international scientific papers, 17 books (15 in English, 2 in Spanish; published by Elsevier, Springer, IEEE, and Thomson Publishers). He also holds 4 patents/IPR and 36 research projects (mostly public-funded), totalling 5.86 million Euros. He has also edited 13 special issues of journals, 11 of them JCR-indexed. He is recognized in the Stanford-Elsevier Ranking among the 2% most-cited researchers in the field of "Artificial Intelligence and Image Processing" for both the 2021 and 2022 editions.

Prof. Iglesias has been chairman/organizer of 65 international conferences and workshops, including several top (CORE-A and CORE-B) conferences, such as ICCS, Cyberworlds or ICMS, Steering/Advisory committee member of 35 international conferences, program committee member of 270 international conferences, reviewer of more than 200 papers in JCR journals and more that 750 papers of international conferences. He is also associate editor and editorial board member of several international scientific journals. He has been a project expert evaluator for the European Union (FP7, Horizon 2020) and for several national research agencies, including NSF (USA) and other public research agencies in Spain (ANEP, ANECA), Germany (DFG), Canada (ORF), Cyprus (RPF), Iceland (IRF), The Netherlands (NWO), Japan, etc. He has also held research stays at different international institutions in several countries, such as United Kingdom, Japan, USA, Turkey, Venezuela, Argentina, etc.

During the last years, he has pioneered the worldwide research on the application of artificial intelligence (AI) techniques to curve and surface reconstruction. His research has been applied to challenging problems in industrial design and manufacturing, medical sciences (non-invasive medical imaging, melanoma detection from macroscopic/dermoscopic images), swarm robotics, fractal images, dynamical systems, and other fields.

TitleSwarm Intelligence for Shape Reconstruction in the Context of the European Project PDE-GIR: Recent Advances and Future Trends

AbstractShape reconstruction plays a crucial role in various domains, including computer graphics and animation, computer vision, and image processing. It involves the capture or recovery of the shape and appearance of real-world objects from diverse inputs, which can be geometric (such as a cloud of scanned data points), visual (a single image or a collection from multiple viewpoints), or a combination of both. However, this process is widely recognized as challenging and computationally expensive.

Addressing this challenge is a key objective of the MSCA European project PDE-GIR. This project aims to explore innovative methods, particularly leveraging partial differential equations (PDE), either independently or in conjunction with other techniques, to tackle complex instances. A promising avenue being explored involves the integration of PDE with artificial intelligence (AI) methods, which have gained significant attention in recent years due to remarkable developments in the field of AI, including deep learning, generative AI, real-time object detection, biometric recognition, and more, which are reshaping the current landscape of today’s digital world in ways that were unimaginable just a few years ago.

One of the most remarkable AI approaches is swarm intelligence, a groundbreaking computing technology with applications spanning academic and industrial fields. Swarm intelligence systems consist of simple agents that interact locally with each other or their environment, exhibiting basic behavioral patterns and operating autonomously in a decentralized and self-organized manner. Despite the simplicity of individual agents, their local interactions give rise to a collective intelligence, enabling the swarm to perform sophisticated tasks and develop complex behavioral patterns unattainable to the individual agents.

This presentation will explore some of the most recent advances achieved in the PDE-GIR project, concluded at the end of October 2023, focusing on the application of swarm intelligence methods to shape reconstruction. The discussion will encompass diverse academic, professional, and industrial domains, including computer-assisted design and manufacturing, computer animation, computer vision, medical imaging, and swarm robotics. Additionally, the presentation will touch upon future trends and potential avenues for further research in this exciting field.