Researcher

Center for Computational Center (CCS) 

University of Tsukuba

Research interests: Data mining, outlier detection, boundary point detection, deep neural networks, data stream mining.

Contact: khalique.vijdan@kde.cs.tsukuba.ac.jp

This is my personal webpage mainly for sharing my professional and research profile. 

I am a researcher at the Center for Computational Center (CCS) at the University of Tsukuba, Japan. 

I did my Ph.D. in Computer Science from the University of Tsukuba as a member of the Knowledge and Data Engineering (KDE) lab. I am interested in research areas related to knowledge and data engineering and my Ph.D. research is about Outlier Detection, Cluster Boundary Points Detection, and Data Stream Mining. 

Today, the world is data-driven! The amount and the speed at which the data is being produced is unprecedented. Extracting useful and actionable knowledge from this tremendous amount of data can be advantageous in numerous fields such as health, science, and business. 

Mining outlying data points commonly known as outlier detection may represent some anomalous behavior of the system generating this data. Similarly, the data points occurring near the boundary of the dense cluster of data points may represent some useful information. Hence, algorithms that can mine such data points can have useful applications, and many research papers address these problems. This is my motivation to contribute scientifically in this particular research area. Furthermore, I am also interested in exploring and contributing to the knowledge and data engineering-related research fields such as clustering and pattern detection. 

Another research interest is in the application of Deep Neural Networks (DNNs) for data analysis. DNNs have been shown to be effective in learning and representing the complex structure of data and have less or no reliance on the cumbersome task of feature selection. This capability of DNNs makes them useful for the task of data analysis. My interest is to explore the capability of DNNs for the analysis of different kinds of data e.g. time series.