About Me
Hi, my name is Woojae Kim, an engineer and a machine learning enthusiast. I have over 6 years of experience as an engineering consultant, based in New York (Arup) and in Seoul.
Throughout my professional & academic life, my focus has been computational modeling of real-world problems. Oddly though, my interest and coursework in optimization methods have naturally led me to pursue further study in computer science. I have recently earned a M.S. in CS from Georgia Tech with concentration in Machine Learning (ML). Throughout the years, I have gained experience in Python, Java, MySQL and R. In terms of ML packages, I have extensively used: Numpy, Pandas, Matplotlib, Scikit-Learn, Pytorch, Tensorflow, Keras and BURLAP(Java)
I have also tried to compelment my academic knowledge with more practical aspects of machine learning by completing various MOOCS:
- Machine Learning by Stanford University (Prof. Andrew Ng)
- Structuring Machine Learning Projects by Coursera (Prof. Andrew Ng)
- Neural Networks and Deep Learning by Coursera
- Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization by Coursera
- Convolutional Neural Networks by Coursera
- Sequence Models by Coursera
- Deep Learning Specialization by Coursera
Projects
Training Lunar Lander with Deep Reinforcement Learning
https://github.com/wkim300/dqn_lunarlanderThis work (see write-up here) presents a Deep Q-network (DQN) with experience replay to solve Open AI Gym’s Lunar Lander environment. The core algorithm replicates that of the legendary Atari paper by Minh et al. in 2013. The trained DQN successfully controls the space fleet in a continuous state-space, enabling safe landings. The DQN utilizes three fully connected layers with rectifier nonlinearities to approximate the optimal action-value function. Experience replay and bootstrapping method through network duplication were utilized to improve the network’s performance. Extensive grid search was performed to fine-tune the network’s hyperparameters and study their effects on the agent’s performance
Analysis of Adult Income & Wine Quality Dataset through Machine Learning Methods
https://github.com/wkim300/ml_analysis_wine-adultThis work (see write-up here) explores data-driven machine learning techniques; five classification algorithms—decision tree, neural networks, AdaBoosted decision trees, support vector machines, k-nearest neighbors—were implemented on two different datasets: adult income dataset and wine quality dataset. After some data preprocessing, the algorithms were trained on both datasets through k-fold (k=10) cross-validation method. During the training, learning curves and complexity curves were plotted. Then the trained models were tested on the unseen, held-out testing sets (20% of the entire datasets), and the resulting performances were analyzed utilizing various metrics, such as precision, recall and f1-score.
Yuikhan Air-purifying Robot
https://yuikhan.lifeI have teamed up with my former classmates at UIUC to design and prototype an air-purifying robot, Yuikhan (유익한 로봇). Yuikhan is a smarter version of robotic vacuum-for air quality control. It autonomously creates map of the living space using LiDAR and SLAM technology. After recogizing your space, it then purifies the space based on indoor air quality map that it has generated. We have built the robot from scratch using a 3D-printer and off-the-shelf components. We then integrated the hardware to and the cleaning algorithm through Robotic Operating System (ROS). We have a working protype of the device which syncs with a mobile application for direct control. See our landing page for more information.
Experience
As part of military service (병역특례), I am working as a research scientist to develop & deploy Building Energy Management Systems (BEMS).
BEMS is a software for monitoring, analyzing and controlling energy-consuming equipments in buildings, such as heating, ventilation and air conditioning (HVAC), lighting and power systems. Due to its multidisciplinary nature, BEMS engineering requires understanding and knowledge in various areas, including software engineering, electrical engineering, computer network and mechanical engineering. I have generatedmachine learning models to predict building energy consumption based on its historical data and attributes (e.g. location, usage, floor area, etc.) I collaborated with Samsung Electronics and Samsung SDS to test & deploy their BEMS software in various buildings in South Korea, as part of government-funded research project.
University of Illinois at Urbana-Champaign (UIUC)
Research Asistant & Teaching Assitant
August 2015 - July 2017
As an research assistant, performed research in computational mechanics under professor Martin Ostoja-Starzewski.
Research Topic: Modeling of heat-transfer in nonlinear materials. Used hyperbolic heat conduction equation (Maxwell-Cattaneo) to model heat conduction in various types of tissues. The goal of the project was to have better control of electrosurgical process by developing an active control-feedback system for assisted robotic electrosurgery. Designed and conducted experiments to validate superposition of thermal waves in biological tissues (pork meat) and compared the experimental results with analytical models.
As a teaching assistant, taught & supervised lab sessions for ME330:Engineering Materials.
As part of Facade & Building Physics team at Arup, performed numerical analysis (CFD and FEA) on complex facade systems to validate their thermal & structural performances.
Proficient in various engineering softwares, including:
- MATLAB
- Mathematica
Education
Georgia Institute of Technology
M.S., Computer Science
January 2018 - May 2020
Master of Science in Computer Science (non-thesis option), concentration in Machine Learning with emphasis on AI and Visual Analytics.
Coursework in ML & AI:
- Machine Learning (CS 7641)
- Machine Learning for Trading (CS 7646)
- Artificial Intelligence (CS 6601)
- Artificial Intelligence for Robotics (CS 7638)
- Knowledge-Based Artificial Intelligence - Cognitive Systems (CS 7637)
- Reinforcement Learning and Decision Making (CS 7642)
Others:
University of Illinois at Urbana-Champaign (UIUC)
PhD, Mechanical Engineering
August 2015 - June 2017 (on a leave)
At UIUC, performed research under professor Martin Ostoja-Starzewski, concentration in Computational Mechanics and Numerical Methods.
Coursework includes, but not limited to:
- Intro to Optimization (ECE 490)
- Mathematical Methods II (TAM 542)
- Numerical Fluid and Thermodynamics (ME 412)
The Cooper Union
M.Eng., Mechanical Engineering
August 2013 - May 2015
Master of Engineering in Mechannical Engineering, concentration in Computational Fluid Dynamics (CFD) and Finite Element Analysis (FEA).
Thesis: Investigatinng Thermal Performance of Double-skin Perforated-sheet Facade Using Multi-scale Approach
The Cooper Union
B.S., Mechanical Engineering
August 2009 - May 2013
Bachelor of Mechanical Engineering from Cooper Union in NY, NY
A Little More About Me
In my free time, I enjoy basketball, weight training and cycling…