This event is endorsed
and organized by

4th EAI International Conference on e-Learning e-Education and Online Training

April 5–7, 2018 | Shanghai, People's Republic of China

Guanglu Sun

Short biography

Guanglu Sun is currently a professor and deputy dean in the School of Computer Science and Technology, and a director in the Center of Information Security and Intelligent Technology at Harbin University of Science and Technology, China. He received his B.S., M.S. and Ph.D. from Harbin Institute of Technology. He entered into Post-doctoral mobile station of Computer Science Department at Tsinghua University, as an assistant researcher from 2008 to 2011. He visited Northwestern University in the U.S.A. as the visiting scholar from 2014 to 2015. He is a senior member of China Computer Federation and the member of IEEE and ACM. He is also the Co-leader of Heilongjiang Provincial Talent Research Team, the New Century Excellent Talent of Universities in Heilongjiang, and the Innovative Talent of the university. He is the chair, the publication chair, session chair and PC member of IEEE Globecom, ICC, ICYCSEE, ADHIP conferences. He has published more than 60 papers which are indexed by SCI and EI. He also has been in charge of more than 20 projects as PI or co-PI, with more than 20 patent applications and authorization in China. His research interests include computer networks and security, machine learning, and intelligent information processing.

Title of Keynote speech:Traffic Classification based on Machine Learning Methods


The present era is the era of artificial intelligence. Machine learning is the pearl on the AI crown. Machine learning methods have already been deployed widely in many fields, such as natural language processing, image processing, bioinformatics, etc. In computer networks and information security, machine learning based methods have also played a important role. In Internet traffic classification, machine learning based methods identify encrypted traffic and proprietary protocols effectively based on statistical features of traffic flows. However, changes of network environment lead to performance degradation of traffic classification based on traditional machine learning models. To tackle these problems, incremental learning methods and transfer learning have attracted increasing attention as they both achieve the state of art performance in traffic classification and have their own characteristics compared with other machine learning methods. Incremental SVMs model is introduced to reduce the high training cost of memory and CPU, and to realize traffic classifier's high-frequency and quick updates. TrAdaBoost for multi-class task is utilized to transfer the knowledge from source domain into target domain in traffic classification.  

Prof. Dr. Xiao-Jun Yang 

Short biography

Prof. Dr. Xiao-Jun Yang is currently Professor of Applied Mathematics and Mechanics at State Key Laboratory for Geomechanics and Deep Underground Engineering, China University of Mining and Technology.  His research interests are wide-ranging and include the study of  viscoelasticity, analytical, approximate, numerical and exact solutions for ODEs and PDEs, integral transforms and their applications, nonlinear dynamics, continuous mechanics, rock mechanics, fluid mechanics, heat transfer, and traffic flow, wavelet, signal processing, biomathematics, mathematical physics, general calculus and applications, fractional calculus and applications, local fractional calculus and applications, general fractional calculus and applications, and variable order fractional calculus and applications. He has 4 books, 9 Chapters and more than 160 publications. He is currently the editorial board member of more than 10 ISI journals. In 2018, he is awarded as the 2017 Elsevier Most Cited Chinese Researchers in Mathematics.  

Title of keynote speech: Local fractional calculus applied to model the mathematical problems in fractal engineering


In this talk, we mainly introduce the concepts and properties of local fractional derivative and local fractional integral. The local fractional diffusion equation in the fractal heat-transfer is discussed in detail. The computational methods for the model, such as local fractional Fourier series, local fractional Laplace type integral transforms and local fractional Fourier type integral transforms are considered to handle the above problem and the solutions of the model with are obtained in detail. The local fractional calculus is accurate and efficient for modelling the mathematical problems in fractal engineering.