Byungkon (Byung) Kang

Research Summary

My research interest spans the area of Artificial Intelligence. In the past, I had been involved in projects that deal with reinforcement learning and stochastic planning algorithms. Through time, my topic gradually shifted over other sub-fields such as unsupervised learning, graph mining, and image processing, although I have managed to remain within the boundary of AI. Currently, I am working on representation learning and natural language processing. 

Courses

• Data structures (Fall'20, Fall'21, Fall'22, Spring'23, Fall'23, Spring'24, Fall'24)

• Machine learning (Fall'19, Fall'20, Fall'21, Spring'23, Spring'24, Fall'24)

• Artificial intelligence (Spring'20, Spring'21, Spring'22, Fall'23)

• Computer science principles (Spring'22, Fall'22)

• Introduction to web design and programming (Spring'21)

Notice

I am looking for RAs. Possible areas of research include, but are not limited to: machine learning, natural language processing, and vision.

Successful  candidates are expected to: 

• Be well-versed in (or at least willing to learn) mathematics and programming,

• Conduct individual/group projects resulting in publishable research papers, and

• Participate in periodic group discussions pertaining to on-going researches.

Exceptional undergraduate interns are also welcome (see below).

If you're interested, please send me an email to arrange for a discussion.

** This offer is valid only to students of SUNY Korea. Prospective students should first be admitted to the university before contacting me.  I do not accept solicitations for admission - I have neither the authority, nor the intention to admit students without proper credentials.

Note to undergraduates looking for research opportunities.

The following are the conditions that I require from research participants from now on:

• You MUST have basic knowledge of the topics that you wish to work on. It's normally advised that you complete either CSE352 or CSE353 with a reasonably good grade, but the exact requirements can be discussed.  I can waive this requirement if you have graduate-level proficiency in mathematics and good programming skills.

• If you're seeking credit for CSE487, then that CSE487 must be the only research course you're taking. I want you to stay focused.

• Also with CSE487: You shouldn't be taking more than two (2) CS courses besides CSE487.

• If you want to work as a paid research intern during the break, then I don't want you working elsewhere. 

Don't get me wrong: Research is loads of fun. But I don't want you to confuse 'fun' with 'easy-going'.

Note on letters of recommendation.

Starting 2024 Fall, I will only write letters of recommendation for those who have actively participated in research with me. 'Active participation' means you have successfully submitted a paper to a conference/journal (regardless of acceptance) in my company. In the past, there have been students who would pretend to engage in research just long enough to get a recommendation from me, after which withdrawing from commitment. 

Publications (Peer-reviewed)

Conferences

• Joonkyu Han, Dennis Wong, Zhoulai Fu, and Byungkon Kang. "AuthZit: Personalized Visual-Spatial and Loci-Tagging Fallback  Authentication", To appear in proceedings of IEEE PRDC 2024.

• Daye Eun and Byungkon Kang. "Accurate Embedding-based Log Determinant Optimization", To appear in proceedings of ACM CIKM 2024.

• Joonkyu Han, Dennis Wong, and Byungkon Kang. "AuthZit: Multi-Modal Authentication with Visual-Spatial and Text Secrets", In proceedings of ACNS 2023 (Poster).

• Jeongmin Yoo, Yeeun Sohn, Yooha Bae, and Byungkon Kang. "Clean Bottle: A reverse vending machine that detects clean PET bottles with machine learning", In proceedings of ICIAE 2022.

• Joonkyu Han, Byungkon Kang, and Dennis Wong. "HWAuth: Handwriting-Based Socially-Inclusive Authentication", In proceedings of SIGGRAPH Asia 2021 (Poster).

• Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn, “Fast, Accurate, and Lightweight Super-Resolution with Cascading Residual Network”, In proceedings of ECCV 2018.

• Seungwon Shin, Dongkyu Kim, Homin Park, Byungkon Kang, and Kyung-Ah Sohn, “Finding Compact Class Sets for Korean Font Image Classification”, In proceedings of ACPR 2017.

• Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn, “Image Distortion Detection using Convolutional Neural Networks”, In proceedings of ACPR 2017.

• Byungkon Kang and Kyung-Ah Sohn, “Embedding Senses via Dictionary Bootstrapping”, In proceedings of UAI 2017.

• Paul K.J. Park, Kyoobin Lee, Jun Haeng Lee, Byungkon Kang, Chang-Woo Shin, Jooyeon Woo, Jun-Seok Kim, Yunjae Seo, Sungho Kim, Saber Moradi, Ogan Gurel, and Hyunsurk Ryu “Computationally Efficient, Real-time Motion Recognition based on Bio-inspired Visual and Cognitive Processing”, In proceedings of ICIP 2015.

• Byungkon Kang “Fast Determinantal Point Process Sampling with Application to Clustering”, In proceedings of NIPS 2013.

• Ruo Ando, Kang Byung, Youki Kadobayashi, “Log Analysis in Cloud Computing Environment using Automated Reasoning”, In proceedings of ICONIP 2010.

Journals

• Hyunwook Koh, Won Gu, Hyo Jung Jang, Byungho Lee, and Byungkon Kang. "MiSurv: An integrative web cloud platform for user-friendly microbiome data analysis with survival responses", Microbiology Spectrum, 2023.

• Hyojung Jang, Hyunwook Koh, Won Gu, and Byungkon Kang. “Integrative web cloud computing and analytics using MiPair for design-based comparative analysis with paired microbiome data”, Scientific Reports, 2022.

• Won Gu, Jeongsup Moon, Crispen Chisina, Byungkon Kang, Taesung Park, and Hyunwook Koh. "MiCloud: A unified web platform for comprehensive microbiome data analysis", PLoS ONE, 2022.

• Namhyuk Ahn, Byungkon Kang, Kyung-Ah Sohn, "Efficient Deep Neural Network for Photo-realistic Image Super-resolution", Pattern Recognition, 2022.

• Byungkon Kang, Jisang Yoon, Ha Young Kim, Sung Jin Jo, Yourim Lee, Hye Jin Kam, "Deep-learning based automated terminology mapping in OMOP-CDM", Journal of the American Medical Informatics Association, 2021

• Garam Lee, Byungkon Kang, Kwangsik Nho, Kyung-Ah Sohn, Dokyoon Kim, “MildInt: Deep learning-based multimodal longitudinal data integration framework”, Frontiers in Genetics, 2019

• Garam Lee, Kwangsik Nho, Byungkon Kang, Kyung-Ah Sohn, Dokyoon Kim, and Alzheimers Disease Neuroimaging Initiative, “Predicting Alzheimers disease progression using multi-modal deep learning approach”, Scientific Reports, 2018.

• Habtamu Minassie Aycheh, Joon-Kyung Seong, Jeong-Hyeon Shin, Duk L. Na, Byungkon Kang, Sang Won Seo, Kyung-Ah Sohn, “Biological Brain Age Prediction using Cortical Thickness Data: A Large Scale Cohort Study”, Frontiers in Aging Neuroscience, 2018.

• Byung Kon Kang and Kee-Eung Kim, “Exploiting Symmetries for Single- and Multi-agent Partially Observable Stochastic Domains”, Artificial Intelligence, 2012.

Workshops

• Eun-Ju Park, Hoyoung Kim, Seonghwan Jeong, ByungKon Kang and YoungMin Kwon, "Keyword-based vehicle retrieval", In proceedings of CVPR Workshops 2021.

• Homin Park, Byungkon Kang, Arnout Van Messem, Wesley De Neve, "3-D deep learning-based item classication for beltconveyors targeting packaging and logistics", In proceedings of ICPR International Workshop on Industrial Machine Learning, 2020.

• Namhyuk Ahn, Byungkon Kang, and Kyung-Ah Sohn, “Image Super-resolution via Progressive Cascading Residual Network”, In proceedings of CVPR Workshop (NTIRE) 2018.

• Byungkon Kang, and Kyomin Jung, “Robust and Efficient Nearest Neighbor Search in Large Data Sets”, NIPS Workshop on Big Learning (BigLearn) 2012.

• Byung Kang, Woosang Lim, and Kyomin Jung, “Scalable Kernel k-Means via Centroid Approximation”, NIPS Workshop on Big Learning (BigLearn) 2011.

• Byung Kon Kang, Kee-Eung Kim, Wook Jung, and Jin-Soo Kim, “Reinforcement Learning for Optimizing Flash Memory Cache Management”, USENIX Workshop on Tackling Computer Systems Problems with Machine Learning Techniques (SysML) 2008. (Invited poster)