Current research topics (looking for additional/new researchers):

  • AI: Representation 
    • Generalization, Regularization
    • Compression, Knowledge distillation
    • Shapeability
  • AI: Information theory
    • Encoding/Decoding
    • Mutual information
    • Generalization
  • AI: Interpretability
    • Visualization
    • Path-wise analysis
    • Mutual information
  • AI
    • Hyper-Parameter Optimization (HPO) of DNN
    • Meta-learning
    • Graph Convolutional Network
    • Adversarial attack and defense
    • DNN architecture for spatio-temporal data

Completed research topics in data science, machine learning, and AI:

  • Connected-X
    • Optimization and diagnostics of networks with big data (commercial result: http://www.assia-inc.com)
    • IoT
    • Connected-Car
  • An Information-Theoretic Study of Stress during Real-World Electric Vehicle Driving Using Physiological and Operational Data (with http://true.kaist.ac.kr/)
  • Analysis of Demand Response Experiments using High Quality IoT Sensor Data (with http://www.encoredtech.com/)
  • Connecting Online Education and Offline Education with Online Activity Data (O2O in education)
  • Value of High-Quality Data for Energy Saving: A Case Study in a University Building (with http://www.encoredtech.com/)
  • Churn Prediction of Mobile and Online Casual Games Using Play Log Data
  • ML based static and dynamic yaw misalignment correction of wind turbines (with http://romaxtech.com/wind-farm-solutions/)
  • Applying Energy Disaggregation to Real-World Services (with http://www.encoredtech.com/, http://taesupmoon.me )
  • Application of classification algorithms for analysis of road safety risk factor dependencies (with http://true.kaist.ac.kr/)
  • An Analysis of Social Features Associated with Room Sales of Airbnb (with http://hcc.snu.ac.kr/)
  • N-polar Visualization: A Radial Layout with Multiple Interactive Anchors (with http://hcc.snu.ac.kr/)
  • Vi-Bros: Tactile Feedback for Indoor Navigation with a Smartphone and a Smartwatch (with http://hcc.snu.ac.kr/)
  • Data re-purposing and opportunistic research
  • Creative approaches on data (Exploratory Data Analysis)

Past research topics (samples):

  • Convex optimization + network information theory + dynamic programming – “Iterative water-filling for Gaussian vector multiple-access channels” (with http://www.comm.utoronto.ca/~weiyu/http://stanford.edu/~boyd/http://web.stanford.edu/group/cioffi/)
  • Extension of iterative water-filling to broadcast channel problems in information theory – “Sum power iterative water-filling for multi-antenna Gaussian broadcast channels”
  • Multiuser Diversity – “Increase in capacity of multiuser OFDM system using dynamic subchannel allocation”
  • Multiuser MIMO – “On the capacity of multiuser wireless channels with multiple antennas”