EKATERINA RAPINCHUK (MERKURJEV)

Research Interests

Graph-based methods, semi-supervised learning, image processing. Applications include classification of high-dimensional data.

Publications

[23] Bhusal, G., Merkurjev, E., Wei, G.-W, Persistent Laplacian-enhanced Algorithm for Scarcely Labeled Data Classification, submitted.

[22] Zhu, Z., Dou, B., Merkurjev, E., Ke, L., Chen, L., Jiang, J., Zhu, Y., Liu, J., Zhang, B., Wei, G.-W., Machine Learning Methods for Small Data Challenges in Molecular Science, Chemical Reviews, 123(13), pp. 8736-8780, 2023. link

[21] Hayes, N., Merkurjev, E., Wei, G.-W., Integrating Transformer and Autoencoder Techniques with Spectral Graph Algorithms for the Prediction of Scarcely Labeled Molecular Data, Computers in Biology and Medicine, Volume 153, February 2023 issue, Article 106479, 2023. link

[20] Merkurjev, E., Efficient Graph-based Spectral Techniques for Data with Few Labeled Samples, International Journal of Data Science and Analytics, published online July 1, 2023. link

[19] Merkurjev, E., Similarity Graph-based Max-flow and Dual Approaches to Semi-supervised Data Classification and Image Segmentation, International Journal of Machine Learning and Cybernetics, published online June 21, 2023. link

[18] Merkurjev, E., Nguyen, D., Wei, G.-W., Multiscale Laplacian Learning, Applied Intelligence, 53(12), pp. 15727-15746, 2023, published online November 28, 2022. link

[17] Balaji, A., Rapinchuk (Merkurjev), E., Similarity Graph-based Semi-Supervised Methods for Multiclass Data Classification, Journal of Emerging Investigators, 2021, with high school student Ashwin Balaji at Novi High School in Michigan.

[16] Merkurjev, E., A Graphical Approach for Multiclass Classification and for Correcting the Labeling Errors in Mislabeled Training Data, Intelligent Data Analysis, 25(4), pp. 879-906, 2021. link

[15] Merkurjev, E., A Fast Graph-Based Classification Method Applied to Unsupervised Classification of 3D Point Clouds, Pattern Recognition Letters, 136, pp. 154-160, 2020. link

[14] Bertozzi, A.L., Merkurjev, E., Graph-based Optimization Approaches for Machine Learning, Uncertainty Quantification and Networks, chapter in Handbook of Numerical Analysis: Processing, Analyzing and Learning of Images, Shapes, and Forms: Part 2, vol. XX, p. 503-532, 2019. link

[13] Waters, A., Merkurjev, E., Asymptotics for Optimal Design Problems for the Schrodinger Equation with a Potential, Journal of Optimization, 2018(3), pp. 1-16, 2018. link

[12] Jacobs, M., Merkurjev, E., Esedoglu, S., Auction Dynamics: A Volume Constrained MBO Scheme, Journal of Computational Physics, 354, pp. 288-310, 2018. link

[11] Merkurjev, E., Bertozzi, A.L., Chung, F., A Semi-Supervised Heat Kernel Pagerank MBO Algorithm for Data Classification, Communications in Mathematical Sciences, 16(5), pp. 1241-1265, 2018. link

[10] Bae, E. and Merkurjev, E., Convex Variational Methods on Graphs for Multiclass Segmentation of High-Dimensional Data and Point Clouds, Journal of Mathematical Imaging and Vision, 58(3), pp. 468-493, 2017. link

[9] Meng, G., Merkurjev, E., Koniges, A., Bertozzi, A.L., Hyperspectral Image Classification Using Graph Clustering Methods, Image Processing On Line, 7, pp. 218-245, 2017. link

[8] Merkurjev, E., Bertozzi, A.L., Lerman, K., Yan, X., Modified Cheeger and Ratio Cut Methods Using the Ginzburg-Landau
Functional for Classification of High-Dimensional Data, Inverse Problems, 33(7), pp. 074003, 2017. link

[7] Merkurjev, E., Bae, E., Bertozzi, A.L., and Tai, X.-C., Global Binary Data Optimization on Graphs for Data Segmentation,
Journal of Mathematical Imaging and Vision, 52(3), pp. 414-435, 2015. link

[6] Merkurjev, E., Sunu, J. and Bertozzi, A.L., Graph MBO Method for Multiclass Segmentation of Hyperspectral Stand-off Detection
Video, IEEE International Conference on Image Processing, pp. 689-693, Paris, France, October 27-30, 2014. link

[5] Merkurjev, E., Garcia-Cardona, C., Bertozzi, A.L., Flenner, A. and Percus, A., Research Announcement: Diffuse Interface Methods
for Multiclass Segmentation of High-Dimensional Data, Applied Mathematics Letters, 33, pp. 29-34, 2014. link

[4] Garcia-Cardona, C., Merkurjev, E., Bertozzi, A.L., Percus, A., Flenner, A., Multiclass Segmentation Using the Ginzburg-Landau
Functional and the MBO Scheme, IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(8), pp. 1600-1614, 2014. link

[3] Gerhart, T., Sunu, J., Lieu, L., Merkurjev, E., Chang, J.-M., Gilles, J., Bertozzi, A.L., Detection and Tracking of Gas Plumes
in LWIR Hyperspectral Video Sequence Data, SPIE Conference on Defense Security and Sensing, 87430J, Baltimore, April 29-May 3, 2013. link

[2] Merkurjev, E., Kostic, T. and Bertozzi, A.L., MBO Scheme on Graphs for Segmentation and Image Processing, SIAM Journal on Imaging Sciences, 6(4), pp. 1903-1930, 2013. link

[1] Peterson, G.E., Campbell, E.T., Balbas, J., Ivy, S., Merkurjev, E., Rodriguez, P., Relative Performance of Lambert Solvers
1: 0-Revolution Methods, Advances in the Astronautical Sciences, 136 (1), pp. 1495-1510, presented at 20th AAS/AIAA Space Flight Mechanics Meeting, San Diego, CA, February 14-17, 2010. link