INVITED SPEAKERS

 

Senior Lecturer Philippe Durand, Conservatoire National des Arts et Métiers, France

Speech Title: Attempt to predict violent meteoric phenomena by topological and Neural approach.

Abstract: In this presentation, we propose different methods to predict the evolution of an exceptional storm disturbance, evolving in the form of Arcus between 6am and 8am and having caused a lot of damage on the west coast of Corsica on August 18, 2022. We compare the results from different approaches. First, we test an approach from topological data analysis (TDA) to characterize the exceptional situation. This method is based on the analysis of persistence diagrams. In a second approach, we combine different hybrid architectures of classical LSTM-CNN neural network with or without the addition of a quantum layer (QNN) which exploits quantum circuits as well as more original architectural approaches, on a series of Eumetstat satellite data from METEO France and C.A.P.E. data. The prediction in the case of the quantum neural network gives interesting results and more quickly....

Biography: Philippe Durand is Senior Lecturer and Assistant Professor in the Mathematics and Statistics Department of the National Conservatory of Arts and Crafts in the Mathematical and Numerical Modeling Department (M2N), he works on the interaction between mathematical engineering and the theoretical tools of mathematics including usage has been increasing since the introduction of modern mathematics in the early sixties. He is interested in the mathematization of gauge theories in physics and string theory, he also works on tensor analysis applied to networks as well as the application of topological and statistical methods to image processing. In image processing, he used remote sensing images and especially radar images, he invested different methods of pattern recognition, and in particular the tools of mathematical morphology for the extraction of texture information. Currently I am focusing on the use of topological data analysis and different approaches to applying classical or quantum neural networks to image processing. He published his results in various journals of mathematical engineering, and various proceedings of image processing conferences.

 

Dr. Yanglong Lu, The Hong Kong University of Science and Technology, Hong Kong, China

Speech Title: Imaging techniques in metal additive manufacturing process monitoring and control

Abstract: Metal additive manufacturing (MAM) has transformed the production of complex, high-performance components across industries such as aerospace, automotive, and healthcare. However, achieving consistent quality poses a significant challenge due to the process's inherent complexity and susceptibility to defects. Recent advancements in machine learning (ML), particularly when combined with image-based monitoring and control, hold great promise for addressing these issues by enabling real-time defect detection, process optimization, and adaptive control. By leveraging techniques such as deep learning and computer vision, ML can extract valuable insights from the vast amounts of image data generated during MAM processes. This capability allows for the precise identification of defects like porosity, cracking, and thermal distortions, while also facilitating the prediction of anomalies and the optimization of critical process parameters such as laser power, scanning speed, and feed rate. These innovations pave the way for closed-loop control systems that can dynamically adjust process conditions, thereby reducing defects, enhancing part quality, and improving overall process stability. However, significant challenges remain, including the need for high-quality labeled datasets, computationally efficient algorithms, and robust generalization across diverse materials and geometries. To overcome these obstacles, it is essential to integrate domain expertise, physics-based models, and advanced ML techniques, along with the development of standardized datasets and evaluation protocols. This presentation will explore how ML is integrating imaging techniques to advance MAM manufacturing systems.

Biography: Prof. Lu currently serves as an Assistant Professor in the Department of Mechanical and Aerospace Engineering at the Hong Kong University of Science and Technology. He obtained his Bachelor's and Doctoral degrees in Mechanical Engineering from the Georgia Institute of Technology in 2016 and 2020, respectively. Following that, he worked as a Postdoctoral Researcher at the University of Michigan, Ann Arbor, for one year. His research focuses on additive manufacturing process monitoring, multiphysics field simulation, machine fault diagnosis, and structural optimization. He has published about 40 research papers in renowned international journals and conferences and has filed three US patents. He has served as a Session Chair at well-known international academic conferences such as ASME and IISE. He has received several awards, including the Best Doctoral Dissertation Award from ASME, finalist in the 2023 US National Science Foundation Manufacturing Blue Sky Competition, the Postdoctoral Association Conference Award from the University of Michigan, and the Poster Competition Award from ASME Manufacturing and Lifecycle Design Conference, among others. Currently, he is leading projects funded by University Grants Committee (Hong Kong), Innovation and Technology Commission (Hong Kong), and the Hong Kong University of Science and Technology-Industry Collaboration Center, among others.

 

Dr. Sergii Khlamov, Kharkiv National University of Radio Electornics, Ukraine

Speech Title: Astronomical Image Segmentation in Computer Vision for Automated Object Detection and Classification

Abstract: Automated analysis of astronomical images has become increasingly important due to the growing volume of data generated by modern sky surveys and observatories. This paper presents an image segmentation approach designed to improve the automated detection and classification of objects in astronomical frames. The approach combines classical image processing and modern computer vision techniques to isolate and characterize objects of interest, even in the presence of noise, telescope aberrations, low contrast, or overlapping sources commonly found in wide-field images captured by charge-coupled device (CCD) cameras. The segmentation pipeline employs adaptive thresholding, background subtraction, and morphological filtering to enhance the visibility of both point-like and extended sources. Following segmentation, detected objects are classified based on photometric intensity profiles, shape descriptors, and spatial distribution features. This classification process enables the differentiation between various imaging artifacts and celestial objects, including stars, galaxies, small Solar System objects (SSOs), such as asteroids, comets, and even artificial satellites. The paper describes the modern features for astronomical image processing implemented in the Lemur software within the scope of the Collection Light Technology (CoLiTec) project (https://colitec.space). The Lemur software is designed to perform a sequence of the following main steps: pre-processing (astronomical information collection -> worst data rejection -> useful data extraction -> data mining -> classification -> background alignment -> brightness equalization), image processing (segmentation -> typical form analysis -> recognition patterns applying -> detection of the object’s image -> astrometry -> photometry -> objects identification -> tracks detection), knowledge discovery (SSOs or artificial satellites to be discovered, tracks parameters for the investigation, light curves of the variable stars, scientific reports in the international formats). The Lemur software has facilitated over 1,700 discoveries of asteroids, including 5 NEOs, 21 Trojan asteroids of Jupiter, and 1 Centaur. In total, it has been used in about 800,000 observations, during which five comets were discovered.

Biography: Dr. Sergii Khlamov holds a Ph.D, MSc and BSc degrees with honors at the Kharkiv National University of Radio Electronics, Ukraine, where continues working. The Ph.D dissertation title was "Computational data processing methods for detecting objects with near-zero apparent motion" of the specialty 01.05.02 "Mathematical modeling and computational methods". Dr. Khlamov's research focuses on several areas, including computational methods, mathematical modeling (statistical and in situ), image recognition, image filtering, image processing, machine/computer vision, observational astronomy, computer science, big data and data science, data mining, knowledge discovery in databases, machine learning, internet of things, artificial intelligence, etc. Since 2014 Dr. Sergii Khlamov is a senior researcher of the Collection Light Technology (CoLiTec) project and the developer of the Lemur software for detecting the moving space objects (asteroids/satellites) in a series of astronomical frames. Also, Dr. Khlamov has more than 12 years of experience in Test Automation and Quality Assurance in the different top IT companies. Dr. Sergii Khlamov has up to 200 national and international publications, including 11 monographs, 23 patents. Currently he is a scientific supervisor of the Ukrainian project of fundamental scientific research “Development of computational methods for detecting objects with near-zero and locally constant motion by optical electronic devices” #0124U000259 in 2024-2026 years.

 

Abhishek Shukla, Syracuse University, NY, USA

Biography: Abhishek Shukla is a well-established Principal Software Engineer with over 16 years of stints in the technology world. He did his Master's from Syracuse University, New York, USA. In fact, over these years, Abhishek has contributed immensely to the field of AI, ML, and Software Engineering by authoring 19 scholarly articles. Apart from research, Abhishek has contributed to more than 100 conferences as a technical program committee member, reviewer, keynote speaker, and advisory board member. His dedication and expertise have been recognized by the Indian Achievers' Forum, which honored him with the Outstanding Professional Achievement & Contribution towards Nation Building 2024 award IAF INDIA. The career path for Abhishek includes stints in India, South Korea, and the USA; his versatility fits all kinds of professional environments. He has demonstrated outstanding contributions toward AI and ML for e-commerce applications-features that put him in a league of leadership within global technologies. Currently, Abhishek continues to drive innovation and excellence in technology, integrating wide experiences and an academic foundation into furthering the fields of AI, ML, and Software Engineering.

Speech Title: Advanced Image Processing Techniques in Medical Imaging-Development of Diagnostic Precision

Abstract: Integration of advanced image processing techniques in medical imaging has considerably enhanced diagnostic accuracy and quality of patient care. This presentation would discuss state-of-the-art methodologies including but not limited to fast deconvolution of images, fusion of multiple views, and cell nuclei segmentation that enhance the contrast and resolution of optical microscope images. These will allow clinicians to have better visualizations of anatomical structures for informed clinical decisions. Further discussion will be on the computational challenges involved in the processing of big datasets and the building of efficient software pipelines to overcome them. The latest advances in medical image processing and their practical applications in improving diagnostic workflows will be shared with the participants.