On Sept. 14-15, SBMI will host a 24-hour Machine Learning Hackathon. This coding Hackathon is designed to be an interactive and engaging challenge for undergraduate, master’s or PhD students.
The Hackathon objective is to detect the onset of slow activity after seizures with time series EEG input data (measured from 13 electrodes). The duration between the start of the seizure and the end of postictal generalized EEG suppression (PGES) characterized by the onset of slow activity is believed to be an important risk factor to Sudden Unexpected Death in Epilepsy (SUDEP).
The Hackathon organizers are Assistant Professor Yejin Kim, PhD (Yejin.Kim@uth.tmc.edu) and Professor Xiaoqian Jiang, PhD (Xiaoqian.Jiang@uth.tmc.edu). If any students have questions about the Hackathon, they are asked to contact Drs. Kim or Jiang.
Visit the SBMI website to learn more about or register for the Hackathon: https://sbmi.uth.edu/hackathon
published on 09/03/2019 at 10:15 a.m.