# Graduate Students Seminar

## Online on Blackboard Collaborate

Wednesday, April 27, 2022

11:00 AM – 12:00 PM

11:00 AM – 12:00 PM

Online

Session Chair: | John Eustaquio |

Discussant: | Dr. Yi Huang |

###### Speaker 1: Ji Li

**Title***Effect of lipid fractions on subclinical atherosclerosis using CARDIA data***Abstract**- The burden of subclinical atherosclerosis is the strongest predictor of future cardiovascular events (CVEs) in diabetic individuals with chronic kidney disease (CKD). To evaluate the effect of cumulative LDL/ lipid fractions on total atherosclerotic burden, first I usedrandom forest to do variable selection. Then multinomial logistic regression and proportional odds model are fitted. Some significant effects such as Cholesterol and BMI are detected.

###### Speaker 2: Ehsan Shakeri

**Title***Probability Density Function Control through Fokker-Planck Equations***Abstract**- For nonlinear systems faced with Gaussian distributed noise, the output and state variables are not Gaussian. For such stochastic systems, mean and variance control is not sufficient and the higher order of moments of the process must be controlled. by shaping the PDF of the process, we can control all its moments. To control the PDF of a process, we need a PDF simulator. The Fokker-Planck (FP) equation describes the time evolution of the PDF of a stochastic process so that by solving the FP equation, the PDF of the process can be obtained at any instance of time. In this talk, we introduce two industrial processes for which a controller has been designed to shape the output PDF and review a Fokker-Planck control framework for stochastic differential equations. Moreover, we study the path integral method to solve the FP equations.