• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.4
• /
• pp.21-26
• /
• 2011

Feature ranking is useful to gain knowledge of data and identify relevant features. In this study, we proposed a use of feature ranking for classification of neuro-degeneration and vascular dementia in micro-Raman spectra of platelet. The entire region of the spectrum is divided into local region including several peaks, followed by Gaussian curve fitting method in the region to be modeled. Local minima select from the subregion and then remove the background based on the position by using interpolation method. After preprocessing steps, significant features were selected by feature ranking method to improve the classification accuracy and the computational complexity of classification system. PCA (principal component analysis) transform the selected features and the overall features that is used classification with the number of principal components. These were classified as MAP (maximum a posteriori) and it compared with classification result using overall features. In all experiments, the computational complexity of the classification system was remarkably reduced and the classification accuracy was partially increased. Particularly, the proposed method increased the classification accuracy in the experiment classifying the Parkinson's disease and normal with the average 1.7 %. From the result, it confirmed that proposed method could be efficiently used in the classification system of the neuro-degenerative disease and vascular dementia of platelet.

• Journal of Korean Ophthalmic Optics Society
• /
• v.15 no.3
• /
• pp.219-225
• /
• 2010

Purpose: Usefulness in predicting the power of spherical rigid gas-pearmeable (RGP) lenses prescription using dioptric power matrices and arithmetic calculations was evaluated in this study. Noncycloplegic refractive errors and over-refractions were performed on 110 eyes of 55 subjects (36 males and 19 females, aged $24.60{\pm}1.55$years) in twenties objectively with an auto-refractometer (with keratometer) and subjectively. Tear lenses were calculated from keratometric readings and base curves of RGP lenses, and the power of RGP lenses were computed by a dioptric power matrix and an arithmetic calculation from the manifest refraction and the tear lens, and were compared with those by over-refractions in terms of spherical (Sph), spherical quivalent (SE) and astigmatic power. Results: The mean difference (MD) and 95% limits of agreement (LOA=$MD{\pm}1.96SD$) were better for SE (0.26D, $0.26{\pm}0.70D$) than for Sph (0.61D, $0.61{\pm}0.86D$). The mean difference and agreement of the cylindrical power between matrix and arithmetic calculation (-0.13D, $-0.13{\pm}0.53D$) were better than between the others (-0.24D, $0.24{\pm}0.84D$ between matrix and over-refraction; -0.12D, $0.12{\pm}1.00D$ between arithmetic calculation and over-refraction). The fitness of spherical RGP lenses were 54.5% for matrix, 66.4% for arithmetic calculation and 91.8% for over-refraction. Arithmetic calculation was close to the over-refraction. Conclusions: In predicting indications and powers of spherical RGP lens fitting, although there are the differences of axis between total (spectacle) astigmatism and corneal astigmatism, Spherical equivalent using an arithmetic calculation provides a more useful application than using a dioptric power matrix.