April 6, 2019, Florida Atlantic University
May 19-24, 2019, Bahia Mar Fort Lauderdale Beach
July 29-August 2, 2019, Harold and Marleen Forkas Alumni Center, Florida Atlantic University
Saturday, February 9, 2019, Florida Atlantic University
February 15 & 16, 2019, Florida Atlantic University, Science and Engineering Complex
March 4-8, 2019, Florida Atlantic University, Student Union
Need to improve your mathematical skills? Check out the Math Boot Camp! New sessions open throughout the semester!
Thursday, March 28, 2019; SE 215, 11:00 a.m.
Speaker: Professor Louis Menzer, Chemistry and Physics, Npva Southeastern University
Title: Seizure Prediction with Machine Learning using Real and Simulated Electrocorticography Data
Epilepsy is the most common chronic neurological disorder, affecting approximately one percent of people worldwide. Patients with symptoms not well controlled with medication often suffer significantly reduced quality of life due to the unpredictable nature of seizures, which are periods of pathological synchronization of neural activity in the brain. Using a surgically-implanted intracranial electrode grid, electrocorticography (ECoG) provides better spatial and temporal resolution of brain electrical activity, compared with conventional scalp electroencephalography (EEG). We combine this patient data with simulated output from a full Hodgkin-Huxley calculation using in silico neurons connected with a small-world network topology. Supervised Machine Learning, a set of powerful and flexible artificial intelligence techniques that allow computers to classify complex data without the need for explicit programming, along with topological data analysis methods, are employed with a goal of developing an algorithm that can be used for the real-time clinical prediction of seizure risk.
All are cordially invited. Coffee and donuts will be served.
Wednesday, April 3, 2019; SE 215, 2:30 p.m.
Speaker: Ziyu Hu
Title: The HARQ model for Realized Volatility
Among models for the realized volatility (RV) and RV-based forecasting, the issue of measurement errors has been largely ignored, while in the others the errors are treated as homoskedastic. In this presentation, we introduce a new family of models by Bollerslev et al. which allows the parameters to vary explicitly with the (estimated) degree of measurement error. The models exhibit stronger persistence, and in turn generate more responsive forecasts when the measurement is relatively low. The HARQ model is one from the family that adds time-varying components to the popular Heterogeneous Autoregression (HAR) model of Corsi. Significant improvements in the accuracy of the resulting forecasts are documented implementing the new class of models for the S&P 500 equity index and the individual constituents of the Dow Jones Industrial Average, as compared to the models that ignore the temporal variation in the magnitude of the realized volatility measurement errors.
All are cordially invited.