Browsing by Subject "Nearest-neighbors"

Now showing 1 - 2 of 2

Open Access
A classification learning algorithm robust to irrelevant features
(Springer, 1998-09) Güvenir, H. Altay
Presence of irrelevant features is a fact of life in many realworld applications of classification learning. Although nearest-neighbor classification algorithms have emerged as a promising approach to machine learning tasks with their high predictive accuracy, they are adversely affected by the presence of such irrelevant features. In this paper, we describe a recently proposed classification algorithm called VFI5, which achieves comparable accuracy to nearest-neighbor classifiers while it is robust with respect to irrelevant features. The paper compares both the nearest-neighbor classifier and the VFI5 algorithms in the presence of irrelevant features on both artificially generated and real-world data sets selected from the UCI repository.
Open Access
Theoretical and spectroscopic investigations on the structure and bonding in B-C-N thin films
(2009) Bengu, E.; Genisel, M. F.; Gulseren, O.; Ovali, R.
In this study, we have synthesized boron, carbon, and nitrogen containing films using RF sputter deposition. We investigated the effects of deposition parameters on the chemical environment of boron, carbon, and nitrogen atoms inside the films. Techniques used for this purpose were grazing incidence reflectance-Fourier-transform infrared spectroscopy (GIR-FTIR), X-ray photoelectron spectroscopy (XPS), transmission electron microscopy (TEM) and electron energy loss spectroscopy (EELS). GIR-FTIR experiments on the B-C-N films deposited indicated presence of multiple features in the 600 to 1700 cm- 1 range for the infrared (IR) spectra. Analysis of the IR spectra, XPS and the corresponding EELS data from the films has been done in a collective manner. The results from this study suggested even under nitrogen rich synthesis conditions carbon atoms in the B-C-N films prefer to be surrounded by other carbon atoms rather than boron and/or nitrogen. Furthermore, we have observed a similar behavior in the chemistry of B-C-N films deposited with increasing substrate bias conditions. In order to better understand these results, we have compared and evaluated the relative stability of various nearest-neighbor and structural configurations of carbon atoms in a single BN sheet using DFT calculations. These calculations also indicated that structures and configurations that increase the relative amount of C-C bonding with respect to B-C and/or C-N were energetically favorable than otherwise. As a conclusion, carbon tends to phase-segregate in to carbon clusters rather than displaying a homogeneous distribution for the films deposited in this study under the deposition conditions studied.