To enhance the quality of life in diverse ways, we purposely aim at strategic data analytics with an emphasis on Bigdata. In the preparation for the upcoming horizons of fourth industrial revolution, our interests mainly focus on a range of artificial intelligence related techniques including but not limited to conventional data-driven research, and to as by-product implementing software applicable on the site.
shkim1213@konkuk.ac.kr
I am currently looking for graduate students. Prospective students are expected to be proficient in English (i.e., particularly writing) and on competitive computing skills (e.g., python). I highly encourage to knock on the laboratory if your vision is in keeping with the rising AI era.
Send Email
Kim et al. (2018) Meta-analytic Principal Component Analysis, Bioinformatics
Kim et al. (2017) Node-Structured Integrative Gaussian Graphical Model, Computational and Mathematical Methods in Medicine
Kim et al. (2018) Meta-analytic Principal Component Analysis, Bioinformatics
Kim et al. (2017) Node-Structured Integrative Gaussian Graphical Model, Computational and Mathematical Methods in Medicine
Lim et al. (2019) Integrative deep learning DE biomarkers, Computational and Mathematical Methods in Medicine
Kim et al.(2017) Integrative Clustering of Multi-level Omics, Biostatistics
Kim et al.(2016) Meta-Analytic Top Scoring Pair Method, Bioinformatics
Kim et al. (2015) Integrative Phenotyping Framework (iPF), BMC Genomics
Kim et al. (2019) Computer Vision-based Method to Detect Fire Using Color Variation in Temporal Domain, Quantitative Bio-Science
Kim et al. (2019) Predictive Models of Fire via Deep learning Exploiting Colorific Variation, Conference Proceedings of ICAIIC 2019
f
Now that countries in East Asian are undergoing unprecedented air pollution due to fine dust, worries to public heath increasingly aggravated in many ways. Under this circumstance, this project has focused on developing a benchmark to gauge particulates levels in virtue of AI vision-oriented technique.
Kim et al. (2019) Vision-based Models to Predict Particulate Levels via Deep Q-learning Network and Temporal Data, Journal of Sensors.
Kim et al. (2018) Vision-based Predictive Model on Particulates via Deep Learning, Journal of Electrical Engineering & Technology.
In context of public health and environmental study, concerns in South Korea predominantly relate to the water contamination attributed to harmful plastic disposals. Importantly noted, green algae in the river and sea serves as a trustworthy benchmark in gauging water quality on the real-time basis. This project aims to develop the multi-tasks recognition algorithms, enabling simultaneous counts to the estimated organisms and flakes in the blessing of cutting-edge image segmentation techs.
Leaning toward the era of self-driving car, many have proposed a range of the-state-of-the-art vision-based decision rules. This project is designed to provide the automakers with a hint of effective lane-change scenarios prior to heading to the exit. To this end, we fit the reinforcement learning-based model facilitating to implement temporal images, and prove its utility in practice under the virtual simulators.
want to see more amazing works?
[1] "Action recognition models guided by semantic segmentation with the application to monitoring recyclable waste", National Information Society Agency, 125M KRW, Jan 2021–Dec 2021 (중소벤처기업부, 총 1억4000만원/12개월).
[2] "Building AI datasets for training predictive models", National Information Society Agency, 125M KRW, Sep 2020–Dec 2020 (한국정보화진흥원, 총 1억2500만원/4개월).
[3] "Untact identity verification via facial recognition technique paralleled to vision telecommunication", National Research Foundation of Korea Grant, 144M KRW, Sep 2020–Sep 2022 (중소기업청, 총 1억4400만원/2년).
[4] "Statistical artificial intelligence (AI) algorithms to monitor deleterious and infinitesimal environment materials (particulates and microplastics)", National Research Foundation of Korea Grant, 150M KRW, Mar 2020–Feb 2023 (한국연구재단, 총 1억5,000만원/3년).
[5] "Deep learning based image processing techniques to develop a fine dust metering device", Small and Medium Business Administration, 300M KRW, Jan 2020–Dec 2020 (중 소기업청, 총 3억원/1년).
[6] "Techniques to meter particulate matter levels using temporal digital image data", Research Institute of Industrial Science and Technology (RIST), 20M KRW, Dec 2019–Feb 2020 (포스코, 총 2,000만원).
[7] "Integration methods of multi-level omics data via bigdata analytics", National Research Foundation of Korea Grant, 90M KRW, Mar 2017–Feb 2020 (한국연구재단, 총 9,000 만원/3년).
[8] "Development of statistical methodologies for integration of multi-omics data", National Research Foundation of Korea Grant, 34M KRW, Sep 2016–Aug 2017 (한국연구재단, 총 3,400만원/1년).
[1] Jung S., Min J., Jung S., Suh S., Heo S. and Kim S.* (2021) Dental Image Data Generation for Instance Segmentation using Generative Adversarial Networks, in revision, *Corresponding author.
[2] Park Y., Kim S., Chon K., Lee H., Kim J. and Shin J. (2021) Impacts of heavy rain and floodwater on floating debris entering an artificial lake (Daecheong Reservoir, Korea) During the summer, Desalination and Water Treatment.
[3] Suh S., Park Y., Ko K., Yang S., Ahn J., Shin J. and Kim S.* (2020) Weighted Mask R-CNN for Improving Adjacent Boundary Segmentation, ∗Corresponding author. (Datasets)
[4] Kim S., Heo S., Yang S., Han J. and Jung S. (2020) Instance Segmentation Guided by Weight Map with an Application to Tooth Boundary Detection, Quantitative BioScience.
[5] Jung S., Lee E., Lee Y., Ko J., Lee S., Cho J. and Kim S.* (2020) Estimation of Particulate Levels Using Deep Dehazing Network and Temporal Prior, Journal of Sensors, ∗Corresponding author.
[6] Min J., Jung S., Jung S., Yang S. and Kim S.* (2020) Grammatical Error Correction Models for Korean Language via Pre-trained Denoising, Quantitative Bio-Science, ∗Corresponding author.
[7] Kim S., Jung S., Yang S., Han J., Lee B., Lee J. and Han S. (2019) Vision-based Deep Q-learning Network Models to Predict Particulate Matter Concentration Levels using Temporal Digital Image Data, Journal of Sensors (SCIE).
[8] Lim J., Bang S., Kim J., Park C., Cho J. and Kim S.* (2019) Integrative deep learning for identifying differentially expressed(DE) biomarkers, Computational and Mathematical Methods in Medicine (SCIE), ∗Corresponding author.
[9] Han S., Park S., Zhong H., Ryu E., Wang P., Jung S., Lim J., Yoon J.* and Kim S.* (2019) Estimation of joint directed acyclic graphs with lasso family for gene networks, Communications in Statistics - Simulation and Computation (SCIE).
[10] Lim J., Cho J., Kim J., Kim J. and Kim S.* (2019) Deeper Integrative Neural Network Analysis for Multi-level Omics Data, Quantitative Bio-Science, ∗Corresponding author.
[11] Hwang U., Jeong J., Kim J., Cho S. and Kim S.* (2019) Computer Vision-based Method to Detect Fire Using Color Variation in Temporal Domain, Quantitative BioScience, ∗Corresponding author.
[12] Kim S.* and Kim S. (2018) Vision-based Predictive Model on Particulates via Deep Learning, Journal of Electrical Engineering & Technology (SCIE) ∗ Corresponding author.
[13] Lee J., Jhong J., Cho Y., Kim S., Koo J. (2018) Penalized log-density estimation using Legendre polynomials, Communications in Statistics - Simulation and Computation (SCIE).
[14] Lee J., Kim S.*, Jhong J. and Koo J. (2018) Variable Selection and Joint Estimation of Mean and Covariance Models with an Application to eQTL Data, Computational and athematical Methods in Medicine (SCIE), ∗Corresponding author.
[15] Kim S., Kang D. D., Park Y. and Tseng G. C. (2018) Meta-analytic Principal Component Analysis in Integrative Omics Application, Bioinformatics (SCI).
[16] Ma T., Huo Z., Kuo A., Zhu L., Fang Z., Zeng X., Lin C., Liu S., Wang L., Rahman T., Chang L., Kim S. et al. (2018) MetaOmics: Analysis Pipeline and Browser-based Software Suite for Transcriptomic Meta-Analysis, Bioinformatics (SCI).
[17] Kim S., Jhong J., Lee J., Koo J-Y., Lee B. and Han S. (2017) Node-Structured Integrative Gaussian Graphical Models Guided by Pathway Information, Computational and Mathematical Methods in Medicine (SCIE).
[18] Kim S., Oesterreich S., Kim S., Park Y. and Tseng G. C. (2017) Integrative Clustering of Multi-level Omics Data for Disease Subtype Discovery Using Sequential Double Regularization, Received the Distinguished Student Paper Award for ENAR 2015 and ASA Biometrics Section David P Byar Travel Award at JSM 2015, Biostatistics, 18(1):165-179 (SCIE).
[19] Kim S., Lin C. and Tseng G. C. (2016) MetaKTSP: A Meta-Analytic Top Scoring Pair Method for Robust Cross-Study Validation of Omics Prediction Analysis, Bioinformatics, 32:1966-1973 (SCI).
[20] Kim S., Lee J., Jhong J. and Koo J-Y. (2017) Meta-analytic Support Vector Machine for Integrating Multiple Omics Data, BioData Mining, 10:2 (SCIE).
[21] Han S.∗, Kim S.∗, Seok J., Yoon J. and Zhong H. (2017) Estimation of Directed Subnetworks in Ultra High Dimensional Data for Gene Network Problem, Statistics and Its Interface (SCIE), ∗Joint first authors.
[22] Kim S. (2016) Weighted K-means Support Vector Machine for Cancer Prediction, SpringerPlus (section in statistics), 5:1162 (SCIE).
[23] Kim S., Herazo-Maya J. D., Kang D. D., Juan-Guardela B. M., Tedrow J., Martinez F.J., Sciurba F.C., Tseng G.C. and Kaminski N. (2015) Integrative Phenotyping Framework (iPF): Integrative Clustering of Multiple Omics Data Identifies Novel Lung Disease Subphenotypes, BMC Genomics, 16:924 (SCIE).
[24] Jhong J., Lee J., Kim S., Koo J-Y. (2017) Joint Modeling for Mean Vector and Covariance Estimation with l1-Penalty, Quantitative Bio-Science.
[25] Jung H., Kim S., Lee J., Kim J., Han S. (2017) Differential network analysis for Triple positive and Triple negative breast cancer genes, Journal of Breast Cancer (SCIE).
[26] Zhu L., Ding Y., Chen C., Huo Z., Kim S., Oesterreich S. and Tseng G. C. (2016) MetaDCN: meta-analytic framework for differential coexpression network detection with an application to breast cancer, Bioinformatics (SCI).
[27] Hwang H., Kim S. and Kim H. (2016) Reversible Data Hiding Using Sparse Least Square Predictor via the Lasso, EURASIP Journal on Image and Video Processing, 2016:42 (SCIE).
[28] Herazo-Maya J. D.*, Noth I.*, Duncan S. R.*, Kim S., Ma S., Tseng G. C., Feingold E., Juan-Guardela B. M., Richards T. J., Lussier. Y., Huang Y., Vij R., Lindell K. O., Xue J., Gibson K. F., Shapiro S. D., Garcia J. G., and Kaminski N. (2013) Peripheral Blood
Mononuclear Cell Gene Expression Profiles Predict Poor Outcome in Idiopathic Pulmonary Fibrosis, Science Translational Medicine, 5, 205-136 (SCIE).
[29] Liu S., Tsai W., Ding Y., Chen R., Fang Z., Huo Z., Kim S., Ma T., Chang T., Priedigkeit M., Lee A., Luo J., Wang H., Chung I., Tseng G., (2015) Comprehensive evaluation of fusion transcript detection algorithms and a meta-caller to combine top performing methods in paired-end RNA-seq data, Nucleic Acids Research, 17 (SCI).
[30] Schwaderer A., Wang H., Kim S., Kline J., Liang D., Brophy P., et al. (2016) Polymorphisms in α-Defensin-Encoding DEFA1A3 Associate with Urinary Tract Infection Risk in Children with Vesicoureteral Reflux, Journal of the American Society of Nephrology (SCIE).
[31] Suryawanshi S., Budiu R. A., Elishaev E., Zhang L., Kim S., Tseng C. G., MantiaSmaldone G., Ma T., Donnellan N., Lee T., Mansuria S., Edwards R., Huang X. and Vlad A. M. (2014) Complement Pathway Is Frequently Altered in Endometriosis and Endometriosis-Associated Ovarian Cancer, Clinical Cancer Research, 23, 6163-74 (SCIE).
[32] Suh Y., Kim S., Kim S., Park J., Lim H., Park H., Choi H., Ng D., Lee M., and Nam M. (2013) Combined Genome-Wide Linkage and Association Analyses of Fasting Glucose Level in Healthy Twins and Families of Korea, Journal of Korean Medical Science, 28, 415- 423 (SCI).
[1] JMCCM (2017) : An R package to fit a conditional Gaussian graphical model via the joint mean and constant covariance model.
[2] nsiGGM (2017) : Node-structured Integrative Gaussian Graphical Model Guided by Pathway Information.
[3] metaSVM (2017) : Meta-analytic Support Vector Machine for Integrating Multiple Omics Data.
[4] DeepHaze (2017) : Vision-based Predictive Model on Particulates via Deep Learning.
[5] DeepQ-Haze (2018) : Vision-based Models to Predict Particulate levels via Deep Q-learning Network and Temporal Data.
[6] Weighted Mask R-CNN (2020) : Mask R-CNN integrated with the weight in U-Net for Improving Adjacent Boundary Segmentation.
[1] Dashboard to maneuver bridge panels in collaboration with Deep Visions, 2018. 5. 14.
[2] 미세찰칵 freely downloaded on the App Store & Google Play
| Purchase date | Model | Processor | RAM | GPU | Hard drive | Internal name |
|---|---|---|---|---|---|---|
| 2018/05/01 | Workstation | 6 cores / 12 threads (intel i7-7800X) |
128GB (8x16GB) |
Geforce GTX 1080ti 11GB(2EA) | M.2 500GB |
Server1 |
| 2018/05/01 | Workstation | 6 cores / 12 threads (intel i7-7800X) |
128GB (8x16GB) |
Geforce GTX 1080ti 11GB(2EA) | M.2 500GB |
Server2 |
| 2018/11/01 | Workstation | 6 cores / 12 threads (intel i7-7800X) |
128GB (8x16GB) |
Geforce GTX 1080ti 11GB(4EA) | M.2 500GB |
Server3 |
| 2018/11/01 | Workstation | 8 cores / 16 threads (intel i7-9800X) |
128GB (8x16GB) |
Geforce GTX 1080ti 11GB(4EA) | M.2 500GB |
Server4 |
| 2020/05/01 | Workstation | 16 cores / 32 threads (AMD Ryzen9 3950X) |
128GB (4x32GB) |
Geforce GTX 2080ti 11GB(2EA) | M.2 500GB |
Server5 |
| 2020/05/01 | Workstation | 16 cores / 32 threads (AMD Ryzen9 3950X) |
128GB (4x32GB) |
Geforce GTX 2080ti 11GB(1EA) | M.2 500GB |
Server6 |
| 2020/05/01 | Workstation | 16 cores / 32 threads (AMD Ryzen9 3950X) |
128GB (4x32GB) |
Geforce GTX 2080ti 11GB(1EA) | M.2 500GB |
Server7 |
| 2020/10/01 | Workstation | 4 cores / 8 threads (Intel Xeon W-2123) |
128GB (4x32GB) |
Quadro P5000 16GB(2EA) | M.2 500GB |
Server8 |
| 2020/10/01 | Workstation | 4 cores / 8 threads (Intel Xeon W-2123) |
128GB (4x32GB) |
Quadro P5000 16GB(2EA) | M.2 500GB |
Server9 |
| 2020/10/01 | Workstation | 10 cores / 20 threads (Intel i9-10900X) |
128GB (4x32GB) |
Geforce GTX 2080ti 11GB(2EA) | M.2 500GB |
Server10 |
| 2020/10/01 | Workstation | 10 cores / 20 threads (Intel i9-10900X) |
128GB (4x32GB) |
Geforce GTX 2080ti 11GB(2EA) | M.2 500GB |
Server11 |
| 2020/10/01 | Workstation | 18 cores / 36 threads (Intel i9-10900XE) |
128GB (4x32GB) |
Geforce GTX 2080ti 11GB(2EA) | M.2 500GB |
Server12 |
| Purchase date | Model | Hard drive | Internal name |
|---|---|---|---|
| 2018/05/01 | NAS(Synology) | 40TB(4x10TB) | NAS1 |
| 2018/11/01 | NAS(Synology) | 40TB(6x8TB) | NAS2 |
| 2020/10/01 | NAS(Synology) | 20TB(2x10TB) | NAS3 |
| Date | Speaker | Topic | Zoom Link |
|---|---|---|---|
| 2020/12/01 | PIAO LINGNAN | Genetic Algorithm in Stock Market | |
| 2020/11/24 | YongHak Lee | Object Detection in the Context of Mobile Augmented Reality | |
| 2020/11/18 | SungMin Suh | Face Liveness Detection | |
| 2020/11/03 | KyungMin Ko | 3D Point Cloud for Semantic Segmentation | |
| 2020/10/27 | JinHong Min | Action Recognition | |
| 2020/10/20 | SungJun Jung | Instance Segmentation Performance Improvement by Dental Data Generation Using Generative Adversarial Network | |
| 2020/10/13 | SungMin Yang | Unity for Augmented Reality | |
| 2020/09/29 | YongHak Lee | Memory Enhanced Global-Local Aggregation for Video Object Detection | |
| 2020/09/15 | PIAO LINGNAN | Bull Flag Pattern | |
| 2020/09/08 | YongHak Lee | Super-Resolution Based On Deep Learning | |
| 2020/09/01 | SungMin Suh | Weighted Mask R-CNN for Improving Adjacent Boundary Segmentation | |
| 2020/08/24 | KyungMin Ko | CNN Attention for Recognition | |
| 2020/08/18 | SungHwan Kim | Introduction to AI LAB |