CSNano Seminar Series 15 : Assoc Prof Dr Norma Alias

Seminar Title : “The Classification of Complex Model, Big Data and HPC Platform in Numerical Perspective for the Application of Fourth Industrial Revolution ” Date : 14 Jun 2017 (Thursday) Time : 2.30 pm – 4.30 pm Venue : CSNano Meeting Room, Centre for Sustainable Nanomaterials (CSNano), Ibnu Sina Institute for Scientific & Industrial Research (ISI-SIR), Universiti Teknologi Malaysia, Skudai

Norma Alias
Associate Professor
Department of Mathematics
Universiti Teknologi Malaysia
Skudai, Johor
norma@ibnusina.utm.my

 


“The Classification of Complex Model, Big Data and HPC Platform in Numerical Perspective for the Application of Fourth Industrial Revolution “

Naturally, the mathematical process starts from proving the existence and uniqueness of the solution by the using the theorem, corollary, lemma, proposition, dealing with the simple and non-complex model. Proving the existence and uniqueness solution are guaranteed by governing the infinite amount of solutions and limited to the implementation of a small-scale simulation on a single desktop CPU. Accuracy, consistency and stability were easily controlled by a small data scale. However, the fourth industrial can be described the mathematical process as the advent of cyber-physical systems involving entirely new capabilities for researcher and machines (Xing, 2017). In numerical perspective, the fourth industrial revolution required the transition from a uncomplex model and small scale simulation to complex model and big data for visualizing the real-world application in digital dialectical and exciting opportunity. Thus, a big data analytics and its classification are a problem solving for these limitations. Some applications of fourth industrial revolution will highlight the extension version in terms of models, derivative and discretization, dimension of space and time, behavior of initial and boundary conditions, grid generation, data extraction, numerical method and image processing with high resolution feature in numerical perspective. In statistics, a big data depends on data growth however, from numerical perspective, a few classification strategies will be investigated deals with the specific classifier tool. This paper will investigate the conceptual framework for a big data classification, governing the mathematical modeling, selecting the superior numerical method, handling the large sparse simulation and investigating the parallel computing on high performance computing (HPC) platform. The conceptual framework will benefit to the big data provider, algorithm provider and system analyzer to classify and recommend the specific strategy for generating, handling and analyzing the big data. Numerical analysis and parallel performance evaluation are the indicators for performance investigation of the classification strategy. This research will benefit to obtain an accurate decision, predictions and trending practice on how to obtain the approximation solution for science and engineering applications. As a conclusion, classification strategies for generating a fine granular mesh, identifying the root causes of failures and issues in real time solution. Furthermore, the big data-driven and data transfer evolution towards high speed of technology transfer to boost the economic and social development for the fourth industrial revolution (Xing, 2017; Marwala et al., 2017).

VIEW DETAIL