Identification of bent-double galaxies: Our first data set was from the FIRST (Faint Images of the Radio Sky at Twenty Centimeters) astronomy survey, where we considered the task of identifying galaxies with a bent-double morphology. Working with the FIRST catalog, which had been created by fitting elliptic Gaussians to the brighter image ‘blobs’, we extracted representative features for each galaxy for use in machine learning algorithms. This data set also formed a key test bed for our research in classification algorithms.
Select publications (available from Google Scholar):
- Kamath, C., E. Cantu-Paz, I.K. Fodor, N. Tang, “Classification of bent-double galaxies in the FIRST survey,” IEEE Computing in Science and Engineering, July/August 2002, pp 52-60.
- Fodor, I. K., and C. Kamath, “Dimension reduction techniques and the Classification of Bent Double Galaxies,” Computational Statistics and Data Analysis journal, Volume 41, pp. 91-122, 2002.
- Kamath, C., E. Cantu-Paz, I. K. Fodor, N. Tang, “Using data mining to find bent-double galaxies in the FIRST survey,” Proceedings, Astronomical Data Analysis, at the SPIE Annual Meeting, San Diego, July-August 2001.
- Kamath, C, E., Cantu-Paz, I. K. Fodor, N. Tang, “Searching for Bent-Double Galaxies in the FIRST Survey,” book chapter in Data Mining for Scientific and Engineering Applications, eds. R. Grossman, C. Kamath, W. Kegelmeyer, V. Kumar, and R. Namburu, Kluwer, pp. 95-114, 2001.
Analysis of coherent structures: Coherent structures are a collection of neighboring points (grid points in a simulation or pixels in an image) that behave as a coherent whole. Analysis of the behavior of these structures over time can shed light on the phenomenon being simulated or observed. Our work in this area has focused on the definition and evolution of these structures in both experimental data from the NSTX and simulation data of the Rayleigh-Taylor instability. The latter comprised two of the largest data sets we analyzed at 30TB and 80TB.
Select publications (available from Google Scholar):
- C. Kamath, A. Gezahegne, and P. L Miller, “Identification of coherent structures in three-dimensional simulations of a fluid-mix problem,” International Journal of Image and Graphics, Volume 9, No. 3, pp. 389-410, July 2009.
- A. Gezahegne and C. Kamath, “Tracking non-rigid structures in computer simulations,” IEEE International Conference on Image Processing, San Diego, October 2008, pp. 1548-1551.
- N. S. Love and C. Kamath, “Image Analysis for the Identification of Coherent Structures in Plasma,” Applications of Digital Image Processing, XXX, SPIE Conference 6696, San Diego, August 2007.
Classification of orbits in a Poincare plot: One of the analysis tasks in magnetic fusion is the classification of orbits in a Poincare plot into one of four types – quasiperiodic, island chain, separatrix, and stochastic – based on the shape of the orbit. Each orbit is represented by the (x,y) coordinates of the points, with an orbit consisting of a few thousand points, making this the smallest data set we analyzed. It was also the most challenging, making us realize that while our eyes can easily discern a pattern created by a few points, automating the identification of this pattern in code is far from trivial.
Select publications (available from Google Scholar):
- A. Bagherjeiran and C. Kamath, “Graph-based Methods for Orbit Classification,” Sixth SIAM International Conference on Data Mining, Bethesda, April 2006.