Long-term prediction of hydraulic system dynamics via structured recurrent neural networks

Long-tailed graphical model and frequentist inference of the model parameters for biological networks AĞRAZ, MELİH; Purutçuoğlu Gazi, Vilda (Informa UK Limited, 2020-03-12) The biological organism is a complex structure regulated by interactions of genes and proteins. Various linear and nonlinear models can define activations of these interactions. In this study, we have aimed to improve the Gaussian graphical model (GGM), which is one of the well-known probabilistic and parametric models describing steady-state activations of biological systems, and its inference based on the graphical lasso, shortly Glasso, method. Because, GGM with Glasso can have low accuracy when the syst...
Long-time behaviour of solutions to a singular heat equation with an application to hydrodynamics Kitavtsev, Georgy; Taranets, Roman M. (European Mathematical Society Publishing House, 2020-01-01) In this paper, we extend the results of [8] by proving exponential asymptotic H-1-convergence of solutions to a one-dimensional singular heat equation with L-2-source term that describe evolution of viscous thin liquid sheets while considered in the Lagrange coordinates. Furthermore, we extend this asymptotic convergence result to the case of a time inhomogeneous source. This study has also independent interest for the porous medium equation theory.
Fast Computation of Sommerfeld Integrals in Planar Multilayered Media Özgün, Özlem; Li, C.; Kuzuoğlu, Mustafa; Mittra, Raj (2021-08-28)
Fast simulation and modeling of scattering from targets in MIMO imaging systems Gül , Yunus Emre; Alatan, Lale; Department of Electrical and Electronics Engineering (2022-5-11) The forward model analysis in a multiple input multiple output (MIMO) system requires the computation of the signals received by receiver antennas when various targets are illuminated by a transmitter antenna. The full wave analysis of such systems provides accurate results with high computational cost. Fast analysis of the system can be achieved by simple models based on several approximations which limits the accuracy. In this thesis, a modeling technique that provides better accuracy compared to simple m...
Rigorous Analysis of Double-Negative Materials with the Multilevel Fast Multipole Algorithm Ergül, Özgür Salih (2012-02-01) We present rigorous analysis of double-negative materials (DNMs) with surface integral equations and the multilevel fast multipole algorithm (MLFMA). Accuracy and efficiency of numerical solutions are investigated when DNMs are formulated with two recently developed formulations, i.e., the combined tangential formulation (CTF) and the electric and magnetic current combined-field integral equation (JMCHE). Simulation results on canonical objects are consistent with previous results in the literature on ordin...

Citation Formats

E. KILIÇ, M. Dölen, and A. B. Koku, “Long-term prediction of hydraulic system dynamics via structured recurrent neural networks,” 2011, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/43028.