Seminar by Jae Kyoung Kim from Dept. of Math Sciences, KAIST
15 April 2025
KST 16:00
The Seminar is being held in Room 1010 (Jasmin) – Integrated mechanical engineering building. Click here for the campus map.
In this talk, I will present methods for extracting meaningful insights from both static and time-series data. For static data, Principal Component Analysis (PCA) is a widely used technique for identifying signals in noisy datasets. However, determining the optimal number of signals often relies on subjective judgment. To address this, I will introduce a novel approach based on random matrix theory, which provides an objective criterion for selecting the optimal signal count. For time-series data, various statistical and machine learning-based methods have been developed. I will demonstrate how integrating these approaches with mathematical modeling can significantly enhance predictive accuracy (in particular causal detection). As an application, I will illustrate how these methods can be used to analyze the impact of climate change on Dengue incidence.