Title
Data-Driven Machine Learning and Optimization for Industry

Abstract
Today, industrial processes (e.g., in production) generate a significant amount of process data through sensor measurements. In this talk, we will show how data-driven machine learning and optimization algorithms can be enhanced and applied to such processes for optimizing one or multiple objectives, such as product quality criteria and robustness.
To achieve this, a range of methods including supervised learning (regression and/or classification), hyperparameter optimization, and multiple criteria optimization need to be combined and applied, often in an automatic way. Moreover, enhancements of such algorithms need to be developed to fit the requirements of such industrial processes, including the on-line application of predictive models.
In this presentation, we illustrate this approach towards data-driven machine learning in industrial processes by means of some practical examples from the automotive industry. In addition to the supervised learning approach for product quality optimization, we will also show an example of unsupervised learning for anomaly detection in high-dimensional feature spaces.
To make such techniques applicable in industry, algorithmic developments such as a new algorithm (global-local outlier detection in subspaces; GLOSS) for anomaly detection, a new cluster-Kriging approach for Gaussian process modelling, and enhanced imputation algorithms for missing value handling are required. In the talk we will briefly describe some of those new methods.
Combining the machine learning and optimization algorithms, an integrated approach for automatic modeling, prediction, and optimization for industrial production processes (and other machine learning tasks) is defined, which is applicable in a wide range of industries. A sample application in the automotive industry is used to illustrate the general approach.

Biodata
Prof. Thomas Bäck is head of the Natural Computing Research Group and Director of Education at the Leiden Institute of Advanced Computer Science (LIACS). He received his PhD in Computer Science from Dortmund University, Germany, in 1994. He has been Associate Professor of Computer Science at Leiden University since 1996 and full Professor for Natural Computing since 2002.

Prof. Thomas Bäck has more than 250 publications on data science and nonlinear global optimization and decision support, is the author of a book on evolutionary algorithms, entitled Evolutionary Algorithms in Theory and Practice, and co-editor of the Handbook of Evolutionary Computation. He is editorial board member and associate editor of a number of journals on evolutionary and natural computation (Journal of Natural Computing, Theoretical Computer Science C, Evolutionary Computation), co-editor of the Natural Computation Book Series (Springer), and has served as program chair for all major conferences in evolutionary computation. He received the best dissertation award from the Gesellschaft für Informatik (GI) in 1995 and is an elected fellow of the International Society for Genetic and Evolutionary Computation for his contributions to the field. In 2015, he received the prestigious IEEE Evolutionary Computation Pioneer Award for his contributions in synthesizing evolutionary algorithms. Thomas’ research interests are also in applications of data science and optimization to the life sciences, and in industrial applications in areas such as industry 4.0, process optimization, and product development. In his research projects, he collaborates with companies such as BMW, Honda Research, Tata Steel, and many others.

Title
Data Analytics Using Intelligent Techniques Inspired from Nature

Abstract
This talk highlights some of our recent research results in data analytics using intelligent techniques inspired from nature. Our algorithms include compact radial-basis-function (RBF) neural networks, incrementally-generated fuzzy neural network, granular support vector machines, semi-exhaustive search and class-dependent feature selection algorithms. We demonstrate our algorithms in various challenging data analytics problems, such as chip fault detection, glaucoma diagnosis, EEG signal classification, stock trading and time series prediction, fighter jet response tactics, scanning acoustic microscope image analysis, action recognition in videos, content-based image retrieval, gene selection in microarray data, and face recognition.

Biodata
Dr. Lipo Wang received the Bachelor degree from National University of Defense Technology (China) and PhD from Louisiana State University (USA). His research interest is intelligent techniques with applications to optimization, communications, image/video processing, biomedical engineering, and data mining. He is (co-)author of 300 papers, of which 100 are in journals. He holds a U.S. patent in neural networks and a patent in systems. He has co-authored 2 monographs and (co-)edited 15 books. He was/will be keynote/panel speaker for 30 international conferences. He is/was Associate Editor/Editorial Board Member of 30 international journals, including 3 IEEE Transactions, and guest editor for 10 journal special issues. He was a member of the Board of Governors of the International Neural Network Society (for 2 terms), IEEE Computational Intelligence Society (CIS, for 2 terms), and the IEEE Biometrics Council. He served as CIS Vice President for Technical Activities and Chair of Emergent Technologies Technical Committee, as well as Chair of Education Committee of the IEEE Engineering in Medicine and Biology Society (EMBS). He was President of the Asia-Pacific Neural Network Assembly (APNNA) and received the APNNA Excellent Service Award. He was founding Chair of both the EMBS Singapore Chapter and CIS Singapore Chapter. He serves/served as chair/committee members of over 200 international conferences. Selected publications can be downloaded at his website.

Title
The Linguistic Model of Music

Abstract
We human beings speak language though we still possess music at the same time, though these two are considered to share the common origin. In this talk, we discuss the applicability of techniques on natural language processing for the music information processing. Within this talk, we will make two important digressions. One is what is the communication. Language seems a meaningful, communicative part of the common origin; then, what is the meaning of music. The other digression is what works in infant's language acquisition. Thereafter, we present our formalization of music in syntactic tree, where we define the distance among trees and present several applications. Finally, we close the talk by the open discussion on whether artificial intelligence come to obtain musical aesthetics.

Biodata
Satoshi Tojo received degrees of Bachelor of Engineering, Master of Engineering, and Doctor of Engineering from University of Tokyo, Japan. He joined Mitsubishi Research Institute, Inc. (MRI) in 1983, and Japan Advanced Institute of Science and Technology (JAIST), Ishikawa, Japan, as associate professor in 1995; professor from 2000. His research interest is in formal semantics of natural language, logic in artificial intelligence including knowledge and belief of rational agents, and grammar acquisition, as well as linguistic model of music.

Title
Approaching to a global bibliometric database

Abstract
World scientific database is huge. World-class bibliometric databases, such as Web of Science (ISI) and Scopus are well-known, however, they have been able to cover a part of it only. Sciencetometrics performed on the base of each bibliometric database thus can not reflect the true information for the scientific amount and productivity of individual scientists, institutions as well as nations. In higher education and/or research institution rankings, for instance, either ISI or Scopus data has been taken into account. In addition, national and/or local bibliometric databases are still rather poor. They are usually absent in annual reports.
This work presents the Vietnam Citation Gateway - a bibliometric database, which can provide an integrated simultaneous statistics from ISI, Scopus as well as local scientific databases. The approach is rather promising for a global bibliometrics.

Biodata
Professor Nguyen Huu Duc, earned a bachelor's degree in Physics from the University of Hanoi in 1980. He obtained his Ph.D Degree in the same group in 1988, received the French Habilitation (DHR) in Physics at the Joseph Fourier University of Grenoble in 1997. He became a Full Professor of the Vietnam National University (VNU), Hanoi in 2004 and Professor of Merit in 2008. He has also been nominated as an associate and/or visiting professor at French Universities, such as the University of Rouen in the period 1997-2001 and the Joseph Fourier University of Grenoble in 2003. Prof. Duc is author of 100 scientific ISI papers in various international journals and of 10 monographs published in volumes of the Handbook of Magnetic Materials and the Handbook on the Physics and Chemistry of Rare Earths (Elsevier Science Publisher) and recent Handbook of Advanced Magnetism and Magnetic Materials (VNU Press). The Third Chen Ning Yang Award of the Association of Asia Pacific Physical Societies (in 2004) and the State Prize for S&T of Vietnam (in 2017) were given to Prof. N.H. Duc for excellent contributions to the study of rare earth – transition metal intermetallic compounds. In 2014, N.H. Duc obtained the Palm Academic Medal of French Republic. Prof. N.H. Duc is the Editor in Chief of the VNU-Elsevier Journal of Science: Advanced Materials and Devices, the Advisory Editorial Board member for the Journal of Magnetism and Magnetic Materials (2009-2012) and IOP Advances in Natural Sciences: Nanoscience and Nanotechnology (since 2010). Since 2008, Prof. Duc has been serving as the Vice-President of VNU Hanoi – a leading Vietnamese university with over hundred years history.