CIS Seminar - Frequent Itemset Mining Algorithms for Bioinformatics on a GPU Architecture: A Study
CIS Seminar (PhD Comprehensive Exam Series)
225 Weir Hall
Speaker: Ms. Tina Gui
Title: Frequent Itemset Mining Algorithms for Bioinformatics on a GPU Architecture: A Study
Committee: Dr. Wilkins (committee chair), Dr. Chen, and Dr. Jang
Abstract: Over the last decades, machine learning techniques are being comprehensively deployed to address real world problems in the area of computation biology and bioinformatics. Due to technologies evolution, large-scale data computing is gradually developing at a growing rate. Furthermore, big data mining comes to be a primary challenge in making better, real-time decision in bioinformatics. In recent, an increasing number of data scientists are requiring a higher computing power platform for big data analysis, such as Graphic Processing Units (GPUs), which have multiple cores to transform large volume of data into massively parallel architecture and can process parallel workloads efficiently. Hence, optimally combining these approaches to perform frequent itemset mining on big gene expression data in parallel environments with multi-core processors is a critical challenge to nowadays scientists. In this study, we give an overview of traditional frequent itemset approaches and explain how they can be applied with multi-core GPUs on gene expression datasets. Later, we present our naïve parallel approach combing the systems of machine learning, frequent itemset mining, gene expression data, and GPUs.
Bio: Tina Gui is a Ph.D. student in the Department of Computer and Information Science at the University of Mississippi, who is currently working with Dr. Dawn E. Wilkins and Dr. Yixin Chen. Tina received her bachelor’s in Computer Science from the California State University in 2011 and master’s degree from the University of Mississippi in 2014. Her research interests include machine learning, data mining and bioinformatics.