Event info

IMI Colloquium in July 2024

Wednesday, 10 July 2024 16:45-17:45 seminars

■Date: Wednesday, 10 July 2024 16:45-17:45
■Place: IMI Auditorium(W1-D-413) and Live streaming with ZOOM
■Language: English

■Speaker : Prof. GIM Minjung
(National Institute for Mathematical Sciences/Ajou University Department of Mathematics(Korea))
            Prof. Soon-Sun Kwon
(Ajou University Department of Mathematics(Korea))

Title: Statistical Distances with Mathematical Explanation
by Prof. GIM, Minjung (National Institute for Mathematical Sciences/Ajou University) speaking

Statistical distances measure the difference between distributions or data samples and are employed in various machine learning applications. In this talk, I will introduce several statistical distances and review their mathematical interpretations. We will demonstrate how to use SciPy's statistical distance functions. Using visual illustrations, we will describe the inner workings and properties of several common statistical distances, explaining what makes them both convenient to use and powerful for solving various problems. Additionally, we will present real-life applications and concrete examples.

Title: Statistical Learning Models in Functional structure of Clinical data
by Prof. KWON, Soon-Sun (Ajou University) speaking

In this talk, I introduce two topics about longitudinal data analysis and gait data analysis.
First, longitudinal data are used in statistical studies that accept many repeated measurements as well as the different time spans of the measurements between or within subjects. Furthermore, correct inferences can particularly be obtained by considering the correlation between repeated measurements within subjects. Under the assumption, I propose the clustering method using the Fr'echet distance for multi-dimensional functional data. And I apply the sparse clustering method to multi-dimensional thyroid cancer data collected in South Korea.
Second, motivated by gait data from both the normal and the cerebral palsy (CP) patients group with various gross motor function classification system (GMFCS) levels, I propose a multivariate functional classification method to investigate the relationship between kinematic gait measures and GMFCS levels. The method is generalized to handle multivariate functional data and multi-class classification. The method yields superior prediction accuracy and provides easily interpretable discriminant functions.

※※※ Notes ※※※

meeting ID: 882 4929 0750
passcode: 314361

page top