Keynote Speech 1

Prof. Dr. Mustafa Bin Mat Deris,

Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Malaysia

Abstract – Data Reduction for Information Systems: Issues, Challenges and Future Direction

With the massive data generated daily into computer systems, it is difficult to manage and analyses such massive data size. It is not only causing by the data heterogeneity but also the diverse of dimensionalities in the datasets. For example, social data aggregators, scientific experimental systems, the profiles of internet users, etc., are sparse with high dimensionalities. Thus, it is imperative to reduce the data while retaining the most important and useful data. Data reduction is a process to reduce the volume/size of data to make effective data analysis. It is mainly based on the dimension reduction to reduce the number of features in a dataset without having to lose much information. Dimension reduction techniques are useful to handle the heterogeneity and massiveness of data by reducing variables into manageable size. To some fields, such as data mining, bio-informatics, and machine learning, data sets have huge number of dimensions/attributes that often be encountered. Some attributes are irrelevant or redundant that can complicate the problem and subsequently, degrade the performance and solution accuracy. Thus, some redundant or irrelevant attributes need to be removed which is the main objective of attribute selection. A wide range of dimension reduction approaches are based on classical approaches such as PCA and Bayer’s, and machine learning approaches such as clustering, and feature selection techniques. Rough set theory proposed by Pawlak was successful in the study of soft computing characterized by uncertainty of information, especially in rule extraction, uncertainty reasoning, granular computing, data clustering and data classification. It has been proven to be an efficient mathematical tool as compared with PCA, neural networks and support vector machine methods. Unlike those methods, rough set theory allows knowledge discovering process to be conducted automatically by the data themselves without any dependence on the prior knowledge. The rough set theory however, only be used to solve complete information systems where all available objects in information system have attribute values. It is basically based on the indiscernibility relation that conforms with the reflexive, symmetric and transitive properties. A problem arises when certain attribute values in information systems are missing that cause imprecise answer to some queries, which sometimes happens in the real world. This information system is called incomplete information system (IIS). Because some attribute values are missing in incomplete information systems, such relational properties are difficult to generate, and it is hard to process the incomplete information systems with the indiscernibility relation. There have been many efforts in studying incomplete information systems. Some approaches on attribute selection for IIS have been proposed: tolerance relation approach, and tolerance relation using conditional entropy approach. However, tolerance relation approach leads to poor results in terms of approximation. Therefore, it is important to propose a new approach in order to improve the approximation in the near future.

Speaker Biography:

Prof. Dr. Mustafa Mat Deris received PhD from University Putra Malaysia in 2002. He is a professor of computer science in the Faculty of Computer Science and Information Technology, UTHM, Malaysia. He has successfully supervised Seventeen PhD students and published more than 270 papers in journals and conference proceedings. He has appointed as editorial board member for Journal of Next Generation Information Technology, JNIT, Korea, International Journal of Rough Sets and Data Analysis, IGI-Global, USA and Encyclopedia on Mobile Computing and Commerce, Idea Group, USA.

He was appointed as a keynote speaker from several conferences and served as a program committee member and co-organizer for numerous international conferences/workshops including Grid and Peer-to-Peer Computing, (GP2P 2005, 2006), Autonomic Distributed Data and Storage Systems Management (ADSM 2005, 2006, 2007), and Grid Pervasive Computing Security, organizer for workshops on Rough and Soft Sets Theories and Applications (RSAA 2010, Fukuoka, Japan), Soft Computing and Data Engineering (SCDE) (2010, 2011, Korea ), (2012, Brazil), and for International Conference for Soft Computing and Data Mining (SCDM’14, SCDM’16 and SCDM’18).

He is the recipient of “ICT Excellent Teacher” award in 2006, from Malaysian National Computing Confederation (MNCC). His research interests include distributed databases, rough set theory, soft set theory, and data mining.

Scopus 219 publications, H-index =18 from 1304 citations

http://www.scopus.com/authid/detail.url?authorId=6507331989

Keynote Speech 2

Dr. David Chong

Principal Engineer, TechSource Systems Sdn. Bhd., Malaysia

Abstract – Digital Twins with MATLAB & Simulink

Digital twin technology has moved beyond manufacturing and into the merging worlds of the Internet of Things, artificial intelligence and data analytics. Creating and using digital twins increases intelligence as part of the operational system. Having an up-to-date representation of real operating assets lets us control or optimize the assets and the wider system. The representation not only captures the current state, but often the operating history of the asset. Digital twins enable us to optimize, improve efficiencies, automate, and evaluate future performance

With MATLAB, we can define a model using data from our connected asset. We can also use Simulink to create a physics-based model using multi-domain modeling tools. Both data-driven and physics-based models with MATLAB & Simulink can be tuned with data from the operating asset to act as a digital twin for prediction, anomaly detection, fault isolation, and more.

Speaker Biography:Dr. David Chong Jin Hui is Senior Account Manager for business development at TechSource Systems. He is formerly ASEAN Technical Team Leader & principal application engineer at TechSource Systems. He is specialized in machine learning, deep learning, signal processing, communication and application deployment with MATLAB. Prior joining TechSource Systems, he worked at MIMOS as technical leader, staff researcher & developer, Tunku Abdul Rahman University College as senior lecturer & Intel as senior component engineer. Dr. David Chong holds BEng of Computer & Communication System Engineering and PhD in wireless communication in University Putra Malaysia.