Key accomplishments

Assistant Professor, The University of Tennessee, Knoxville

Image Processing
• Developed an image deblurring method based on explicit blur modeling, which was achieved by a mixture of structure-enhanced parameterized kernels.
• Proposed a blur extraction module embedded in a U-Net structure that consisted of cascaded dense dilated convolution (CDDC) and residual integrated pooling (RIP) blocks.

Feature Selection
• Introduced an ensemble model leveraging boosting and stacking with SVM base learners, which enabled an identification of important feature interactions.
• Leveraged XGBoost to apply a gradient boosting search of feature subsets and developed a framework that determined and quantified the importance of feature interactions.

Wind Energy Forecasting
• Proposed a regime-switching ensemble model conforming to wind dynamics by leveraging LSTM and TCN as base learners.
• Analyzed a general input usage of wind power forecasting models established upon an ANN architecture.

 

Postdoctoral Research Associate, Texas A&M University

• Developed a kernel regression method equipped with a k-NN bandwidth selector and quantified the effect of small device installation on wind turbines.
• Created and published an R package, deployed the package to EDP Renewables, provided a user’s manual, and educated users.

 

Researcher, Center for Information Security Technologies, Korea University

• Developed analgorithm for a large-scale vehicle routing problem with time windows (VRPTW), which entailed distance-based clustering, constraint-based sub-clustering, and optimization within each sub-cluster.
• Distributed the software (in Java) to Samsung Electronics Logitech.

 

System Analyst, LG Display

• Analyzed LCDmanufacturing processes by developing programmable logic controller (PLC) level simulation models in AutoMod.
• Accomplished 2% increase on the total productivity of the associated production lines by optimizing PLC logics and delivered the simulation scripts for the company’s usage.

Role 1
Data scientist
Role 2
Machine learning engineer
Test Score
AI, Machine learning, Data Science
100%
Unspecified
full-time 40-hours-per-week
Any
Senior
United States
Any
NA
Hybrid
Willing to work for equity and paid projectsWilling to work for stock and paid projects

Tags

AITechTransportTechEnergyTech

Education

Experience

Expertise

Python
80
R
90
MS Office
90
Latex
90
TensorFlow
70
PyTorch
70
SQL
75
NLP
50
Spark
50
Tableau
60
Jira
50
MLflow
50
Java
50
git
55
GCP
45
AWS
40
C++
35
HTML
35

Languages

English,
Korean

Honors & awards

Go Back
 
Required 'Candidate' login to applying this job. Click here to logout And try again
 
 

Answers

 

Account Activation

Before you can login, you must activate your account with the code sent to your email address. If you did not receive this email, please check your junk/spam folder. Click here to resend the activation email. If you entered an incorrect email address, you will need to re-register with the correct email address.