Prof. Wenfeng Wang

International Academy of Visual Art and Engineering, London, UK

Professor Dr. Wenfeng Wang is currently the editor in chief of International Journal of Electrical and Electronics Engineering (IJEEE) and International journal of Applied Nonlinear Science (IJANS). He is also a professor in Shanghai Institute of Technology. He is the director of International Academy of Visual Art and Engineering in London and the JWE Technological Research Center in Shanghai. He is also a tenured professor in IMT Institute in India and the director of Sino-Indian Joint research center of artificial intelligence and robotics. He was selected in 2018 as a key tallent in Ningbo Institute of Materials Technology and Engineering, Chinese Academy of Sciences. He is a reviewer of many SCI journals, including some top ones - Water Research, Science China-Information Sciences, Science of the Total Environment, Environmental Pollution, IEEE Transactions on Automation Science and Engineering and etc. He served as a keynote speaker of AMICR2019, IACICE2020, OAES2020, 3DIT-MSP&DL2020, NAMSP2021, ICCAES 2021, CSAMCS 2021 and etc.

Title: Extension Prototypical Network for Few-shot Learning

Abstract: In this paper, we proposed a novel method based on extension distance for unsupervised meta-learning learning. Compared with previous algorithms, the network can also learn new classes and correctly classify them, and each class only requires a few shots for training. Among them, extension distance emerged as a new distance measurement method, which has obvious advantages over the previous Euclidean distance. This paper compares it with the prototypical network based on Euclidean distance and compares and analyzes the experimental results, the experiment that works best is the Miniimagenet dataset which improves accuracy by about 2.36%. The meta-learning method based on metric space is further explored, and experiments are carried out on three data sets and achieved good experimental results on MNIST, miniimagenet, and omniglot data sets.

Prof. Dr. Ying-Ren Chien

National Ilan University, China
Prof. Ying-Ren Chien received his Ph.D. degree in Communication Engineering from National Taiwan University (2009). He was a communication engineering in Chunghwa Telecom (2000-2009), which is the largest integrated telecommunication service provider in Taiwan. From 2009 to 2010, he joined the with the Research Center for Information Technology Innovation, Academia Sinica, as a postdoctoral fellow. Then, Dr. Chien serves as an Assistant Research Fellow in National Chung-Shan Institute of Science & Technology since 2010 to 2012. Since 2012, Dr. Chien joined the Department of Electrical Engineering, National Ilan University, Yilan City, Taiwan. Since 2018, he we promoted as a Full Professor and served the Chair. His research interests are consumer electronics, multimedia denoising algorithms, adaptive signal processing theory, active noise control, machine learning, Internet of things, and interference cancelation. 
Since 2022, he has servered as the vice chair of IEEE CESoc Virtual Reality, Augmented Reality and Metaverse (VAM). He received Best Paper Awards including ICCCAS 2007, Conference on Computational Linguistics and Speech Processing (ROCKLING2017), and IEEE ISPAS 2021. Dr. Chien was presented with IEEE CESoc/CTSoc Service Awards (2019), NSC/MOST Special Outstanding Talent Award (2021), excellent research-teacher award (2018 and 2022), and excellent teaching award (2021). Prof. Chien was listed the world’s top 2% of top scientists through Scopus’s paper influence data (2020, 2021 Science Impact Rankings). He is an IEEE Senior Member and IEICE Senior Member. He has published +70 journal/conference papers.

Title: An Introduction to Data Selective Adaptive Filtering Algorithms
Abstract: In recent years, the amount of data generated by various sources, such as social media, sensors, and the internet, has grown exponentially. This explosion in data volumes has spurred a widespread interest in data-selective adaptive algorithms. These algorithms can reduce computational overhead by avoiding weight updates for adaptive filters when the magnitude of the error signals is too small or too large. In this context, the conventional error-based data selection scheme has been extensively studied and implemented. However, recent developments in the field have introduced a novel correntropy-based data selection scheme that offers advantages over the conventional method. During this talk, we will cover both error-based and correntropy-based data selection schemes. We will discuss the theoretical foundations, practical implementations, and their respective strengths and limitations. We will also demonstrate the effectiveness of these techniques using an active noise control problem as an example. Active noise control is a field that aims to reduce the noise levels in an environment by generating an anti-noise signal that cancels out the original noise. This problem requires the use of adaptive filters, which can be computationally expensive. Therefore, data-selective adaptive algorithms can significantly reduce the computational burden of the process while maintaining the quality of the output. Overall, this talk aims to provide a comprehensive overview of data-selective adaptive algorithms and their applications in active noise control. Attendees will gain a deep understanding of the theoretical foundations, practical considerations, and real-world applications of these techniques.

Prof.Matthias F. Carlsohn

ENGINEERING & CONSULTANCY DR. CARLSOHN, Germany

Dr. Carlsohn has a track record in scientific and commercial image processing and communication with 40+ years of experiences in this field gathered from affiliations in large consumer and in defense industry, as co-founder of related start-ups as well as from several universities in Germany, France and Austria where he was appointed. In his Engineering and Consultancy for Computer Vision and Image Communication he is dealing with related commercial and industrial developments and applications and has driven the past 16 years Springer’s Journal of Real-Time Image Processing as co-editor-in-chief.

Prof.Jon Hall

Open University, UK

I am a leading research scientist in computing, requirements engineering, formal methods and problem solving with over 100 scientific publications and extensive experience through the design, management and evaluation of problem solving research programmes in many domains. I have successfully contributed value through my research and scholarship to many organisations, and academic, scientific and leadership committees and boards, and provided business evaluations for many companies.