For the Benefit of All

“We will find a way. We always have.” - Joseph A. Cooper, Interstellar (2014)

Recent Posts

More Posts

5 min read

Understand/refresh the key backgrounds of RNN and learn how to apply RNN to healthcare data with PyTorch.

CONTINUE READING

5 min read

Understand/refresh the key backgrounds of CNN and learn how to apply CNN to healthcare data with PyTorch.

CONTINUE READING

2 min read

Understand/refresh the key backgrounds of general neural networks and learn how to implement feed-forward neural networks by using PyTorch.

CONTINUE READING

2 min read

Learn basic usage of PyTorch, a deep learning framework on Python.

CONTINUE READING

2 min read

Deep Learning for Healthcare, a new lab series for CSE6250.

CONTINUE READING

Selected Publications

We analyzed longitudinal claims data from 1,376,756 patients with epilepsy from 2006 to 2015 to determine whether information in medical and pharmacy claims data can predict, at the time of prescribing the first antiepileptic drug (AED), which patients with epilepsy will become resistant to AEDs. Our models created from large claims data using machine learning methods can accurately predict which patients with epilepsy will become drug resistant at the time of the first AED prescription. In addition, our model predicts drug resistance on average 2.26 years earlier than waiting for 2 AED failures as the standard clinical definition of drug resistance.
In Neurology, submitted, 2017.
Project

Recent Publications

. Big Data Analytics of Medical Claims Data for Early Prediction of Drug Resistant Epilepsy. In Neurology, submitted, 2017.

Project

. Decentralized Task Re-planning Approaches with en Route Information Rewards. In RiTA, 2012.

PDF Project

. A Track Before Detect Approach for Strap-Down Image IR Seekers in Dual-Mode-Guided Interceptors. In APISAT, 2012.

Project

. SDAT: Simultaneous detection and tracking of humans using Particle Swarm Optimization. In IEEE ICMA, 2011.

PDF Project

. Fast human detection using Gaussian Particle Swarm Optimization. In IEEE DEST, 2011.

PDF Project

Patents

  • Method and System for Predicting Refractory Epilepsy Status
    • U.S. Patent Application 15/412,806, Filed Jan 2017, Patent Pending
  • Method and System for Predicting Optimal Epilepsy Treatment Regimes
    • U.S. Patent Application 15/415,758, Filed Jan 2017, Patent Pending

Projects

All Deep Learning Healthcare Robotics Computer Vision

Adversarial Attacks and Defenses in Healthcare

Crafting adversarial examples and developing robust models toward them, especially for healthcare data.

Machine Learning aided Epilepsy Treatment

Machine learning with big data analysis on epilepsy patients data.

Internship - Bosch

Autonomous Driving Research Intern.

RGB-D SLAM with IMU

Information fusion between a RGB-D camera and an Inertial Measurement Unit.

Tactical System of Unmanned Networked Airborne Autonomy and Multi-role Intelligence

Robotics in national defense.

Pedestrian Detection and Tracking

Detection and tracking of pedestrians in video frames.

Teaching

I have served as a teaching assistant for the following courses at Georgia Tech:

Also, I had served as a teaching assistant for the following courses at KAIST:

  • MAE285: Software Application in Aerospace Engineering, Fall 2012
  • MAE260: Elementary Mathematics for Aerospace Mechanics, Spring 2012
  • EE405: Electronics Design Lab, Spring 2011

Tags

Contact

  • stan84@gatech.edu
  • KACB Room 1211, Georgia Institute of Technology, 266 Ferst Drive, Atlanta, GA, 30332-0765, USA
  • Tuesday 10:00 to 13:00 or email for appointment