2023 3rd International Conference on Internet of Things and Machine Learning(IoTML 2023)





Prof. Nikolaos M. Freris

University of Science and Technology of China (USTC), China

Nick Freris is Professor in the School of Computer Science at USTC, and Vice Dean of the International College. He received the Diploma in Electrical and Computer Engineering from the National Technical University of Athens (NTUA), Greece, in 2005, and the M.S. degree in Electrical and Computer Engineering, the M.S. degree in Mathematics, and the Ph.D. degree in Electrical and Computer Engineering all from the University of Illinois at Urbana-Champaign (UIUC) in 2007, 2008, and 2010, respectively. 

His research lies in AIoT/CPS/IoT: machine learning, distributed optimization, data mining, wireless networks, control, and signal processing, with applications in power systems, sensor networks, transportation, cyber security, and robotics. Dr. Freris has published several papers in high-profile conferences and journals held by IEEE, ACM, and SIAM and holds three patents. His research has been sponsored by the Ministry of Science and Technology of China, Anhui Dept. of Science and Technology, Tencent, and NSF, and was recognized with the National High-level Talent award, the USTC Alumni Foundation Innovation Scholar award, and the IBM High Value Patent award. Previously, he was with the faculty of NYU and, before that,he held senior researcher and postdoctoral researcher positions at EPFL and IBM Research, respectively.  Dr. Freris is a Senior Member of ACM and IEEE, and a member of CCF and SIAM.

Title:Adaptive Compression of Deep Neural Networks

Abstract:Model compression is crucial for accelerating deep neural networks while maintaining high prediction accuracy. In this talk, I will present a lightweight compression method termed Adaptive SensiTivity-basEd pRuning (ASTER) which dynamically adjusts the filter pruning threshold concurrently with the training process. This is accomplished by computing the sensitivity of the loss to the threshold on the fly (without re-training), as carried with minimal overhead on the Batch Normalization (BN) layers. ASTER then proceeds to adapt the threshold so as to maintain a fine balance between pruning ratio and model accuracy. Extensive experiments on numerous neural networks and benchmark datasets illustrate a state-of-the art trade-off between FLOPs reduction and accuracy, along with formidable computational savings. 

Dr. Cheng Chin

Newcastle University in Singapore, Singapore

Dr Cheng Siong Chin is a Chair Professor in Intelligent Systems Modelling and Simulation at Newcastle University and an Adjunct Professor at Chongqing University, School of Automotive Engineering. He received his Ph.D. in Applied Control Engineering at Research Robotics Centre at Nanyang Technological University (NTU) in 2008 and his M.Sc. (Distinction) in Advanced Control and Systems Engineering from The University of Manchester in 2001. He also received a B.Eng. (Hons) degree in Mechanical and Production Engineering from Nanyang Technological University (NTU) in 2000. Before moving into academia, he worked in the consumer electronics industry for a few years. He obtained 6 Economic Development Board (EDB)-Industrial Postgraduate Programme (IPP) and 2 Singapore Maritime Institute (SMI) grants from the Singapore government in intelligent systems design, simulation, and predictive analytics. He has achieved over 150 publications, 5 authored books, 2 Singapore Patent Applications, and 3 US Patents. He also received DCASE2019 Judges' Award in IEEE AASP Challenge on DCASE2019. He is an Associate Editor for IEEE Access Journal, Applied Artificial Intelligence, IEEE Transportation Electrification Community (TEC) eNewsletter, and editorial board member of Electronics. He has served as General Chair, Keynote Speaker, Session Chair, and Technical Committee at numerous international conferences.

Abstract: Water is a precious resource that should be managed carefully. However, due to leakages in Water Distributed Networks (WDNs), a large amount of water is lost each year, suggesting a reliable and robust leak detection and localization system. We will review the current technologies for leakage detection in WDN and several proposed intelligent methodologies. The current methods and their limitations are discussed. Uncertainties involved in the implementation of WDN leakage detection are presented. Suggestions to overcome such uncertainties are provided.