Dongyoung Kim, born at 1987.05.26, received his Ph.D. degree in Biomedical Engineering at Texas A&M University in 2016 .
He worked as a researcher in Electrical Engineering and Computer Science at the University of Texas at Dallas for two years after his bachelor’s degree at the University of Texas at Dallas in 2012. He also received a Bachelor of Science degree at Kyungpook National University, Daegu, Republic of Korea.
Dongyoung Kim is currently focusing on developing new artificial intelligence (AI)
modalities for science and engineering applications.
He combined a range of AI technologies including supervised machine learning, deep neural network, generative adversarial network, and unsupervised machine learning to create AI agent performing biomedical research. He was worked on the optimization theory and the image processing in the big data applied for oncology and cell biology.
Dongyoung Kim is currently an Artificial Intelligence Professional at Data Analytics Laboratory, Samsung Life Insurance, Republic of Korea.
He worked at Institute for Basic Science, South Korea as research fellow for three years. He was at Texas A&M University, The University of Southwestern medical center, and the University of Texas at Dallas studying for oncology, antibody engineering, and biomedical optics.
He was a research assistant for the embedded software research center at Kyungpook National University during his bachelor’s degree. He had an internship program for EOS in Australia.
Generative Adversarial Network
Deep Neural Network
AI-powered transmitted light microscopy uses a range of AI technologies to make:
In-silico fluorescence staining using generative adversarial network (GAN).
Identify cancer types from blood driven particles using deep neural networks (variational encoder-decoder conjugated with convolutional neural networks).
Breast cancer prediction from blood driven particles using machine learning algorithms.
Classifying urinary tract infection from the diagnostic kit photograph using convolutional neural network.
Finding extremely rare cancer event from blood using generative adversarial network.
In-silico histology labeling using generative adversarial network.
Recovering high definition medical image from the low resolution using generative adversarial network.
High resolution medical image recovery from a small subset of acquisition using generative adversarial network.