Prof. Yang Yue
SPIE Fellow 、IEEE Senior Member
Xi'an Jiaotong University, China
BIO: Yue Yang, Professor, PhD, SPIE Fellow, IEEE / Optica Senior Member, National Young Talents Program Candidate, Founder and Current PI of iPatLab, School of Information and Communication Engineering, Xi 'an Jiaotong University. It is devoted to the basic and applied research in the field of intelligent photonics such as optical communication, optical sensing and optical chip. He received a bachelor 's degree in electronic information science and technology and a master 's degree in optics from Nankai University in 2004 and 2007, respectively, and a doctorate in electronic engineering from the University of Southern California in 2012. After graduation, he worked in Silicon Valley Semiconductor Company and Network Equipment Company. In 2021, he was selected into the " Young Top Talent Support Program " of Xi 'an Jiaotong University. He has published more than 270 papers ( including Science ), including nearly 20 invited papers, more than 60 applications and authorization patents ( including 25 U.S. patents, 9 European patents, more than 30 authorizations ), 6 English books, 2 chapters of English books, more than 12,000 Google academic citations, and more than 200 invited reports ( including 1 Tutorial, more than 30 Plenary and more than 70 Keynote ). Presided over the national, provincial and ministerial level and enterprise horizontal
Title: Learning-based Performance Monitoring for Multiple Parameters in Optical Communications Channels
Abstract: In recent years, machine learning has come to the forefront as a promising technology to aid in multiple-parameter performance monitoring for optical communications channels. In this talk, we will introduce CNN-based techniques to effectively monitor multiple system performance parameters of optical channels using eye diagram measurements. Experimental results demonstrate this method achieves a prediction accuracy >98% when tasked with identifying the modulation format (QPSK, 8-QAM, or 16-QAM), as well as the optical signal-to-noise ratio (OSNR), roll-off factor (ROF), and timing skew for 32 GBd coherent channels. For PAM-based intensity-modulation direct detection (IMDD) channel eye-diagram-based CNN method maintain>97% identification accuracy for 432 classes under different combinations of probabilistic shaping (PS), ROF, baud rate, OSNR, and chromatic dispersion (CD) by each modulation format. Furthermore, we undertake on an extensive comparison of ResNet-18, MobileNetV3 and EfficientNetV2. Our designed VGG-based model of reduced layers, alongside the lightweight MobileNetV3, demonstrates enhanced cost-effectiveness while maintaining high accuracy.
Prof. Wen Liu
Winner of the Provincial Outstanding Youth Fund Project
Wuhan University of Technology, China
BIO: Liu Wen, Professor, Visiting Scholar at the School of Computer and Software, Shenzhen University, Visiting Scholar at the Institute of High Performance Computing, Singapore Science and Technology Research Bureau, Selected Member of the "Chutian Scholar Program" in Hubei Province, and Leader of the Science and Technology Entrepreneurship Leading Team of the "5313" Action Plan in Zhoushan City; In 2009, he graduated from Wuhan University of Technology with a bachelor's degree in Information and Computing Science, and in 2015, he received a Ph.D. degree from the Chinese University of Hong Kong, and was a visiting student of the Institute of Automation of the Chinese Academy of Sciences. In response to the application needs of ship navigation safety supervision, intelligent navigation assistance, and maritime intelligent transportation systems, focusing on basic research issues such as maritime multi-source information perception and computing, we will focus on theoretical and technical research on computer vision, data mining, machine learning, and information fusion. In recent years, I have published over 50 papers (including 2 highly cited ESI papers) in important academic journals such as IEEE Internet of Things Journal, IEEE Transactions on Intelligent Transportation Systems, IEEE Transactions on Industrial Informatics, Information Sciences, Ocean Engineering, and The Journal of Navigation, as well as important academic conferences such as IEEE CVPR, ICASSP, ITSC, ICPR, and ICIP; 5 authorized invention patents (2 have been converted to enterprises); The research results won the first prize of the Science and Technology Award of the China Water Transport Construction Industry Association in 2018, the second prize of the Chinese Maritime Science and Technology Journal Paper Award in 2017-2018, and the Excellent Report Award of the International Conference on Machine Learning and Computing (ICMLC) in 2019. The research paper on image dehazing was selected as the Top 10% Papers of IEEE ICIP-2019, an important international conference in the field of artificial intelligence. Served as Deputy Editor in Chief of the SCI Journal International Journal on Semantic Web and Information Systems (CCF-C); SCI Journal of Advanced Transportation, Lead Guest Editor for Sensors; Editorial board member of special issues of Chinese academic journals "Journal of Intelligent Science and Technology", "Computer Science", and "Journal of Earth Information Science"; Youth editorial board member of Journal of Transportation Engineering (EI search) and Computer Engineering; Expert in reviewing funding projects from the Israeli Ministry of Science and Technology and the National Natural Science Foundation of China.
Title: Low-Visibility Enhancement and Beyond
Abstract: The captured visible-light images inevitably suffer from the color distortion, contrast reduction, or loss of fine details under severe weather conditions (such as haze, low-lightness, rain, and snow). The quality-degraded visual information will lead to the limited perceptual accuracy and range, resulting in the increased navigation risk for intelligent marine vehicles. To suppress the influences of severe imaging conditions on navigation safety, this talk will introduce the specific-purpose and general-purpose low-visibility enhancement methods to improve the visual perception for marine surface vehicles under different weather scenarios. In addition, the asynchronous trajectory matching-based multimodal maritime data fusion method will be introduced to promote the maritime situational awareness.
