• Asian Journal of Turfgrass Science
• /
• v.23 no.1
• /
• pp.77-90
• /
• 2009

Near Infrared Reflectance Spectroscopy(NIRS) is a quick, accurate, and non-destructive method to measure multiple nutrient components in plant leaves. This study was to acquire a liner regression equation by evaluating the nutrient contents of 'CY2' creeping bentgrass rapidly and accurately using NIRS. In particular, nitrogen fertility is a primary element to keep maintaining good quality of turfgrass. Nitrogen, moisture, carbohydrate, and starch were assessed and analyzed from 'CY2' creeping bentgrass clippings. A linear regression equation was obtained from accessing NIRS values from NIR spectrophotometer(NIR system, Model XDS, XM-1100 series, FOSS, Sweden) programmed with WinISI III project manager v1.50e and ISIscan(R) (Infrasoft International) and calibrated with laboratory values via chemical analysis from an authorized institute. The equation was formulated as MPLS(modified partial least squares) analyzing laboratory values and mathematically pre-treated spectra. The accuracy of the acquired equation was confirmed with SEP(standard error of prediction), which indicated as correlation coefficient($r^2$) and prediction error of sample unacquainted, followed by the verification of model equation of real values and these monitoring results. As results of monitoring, $r^2$ of nitrogen, moisture, and carbohydrate in 'CY2' creeping bentgrass was 0.840, 0.904, and 0.944, respectively. SEP was 0.066, 1.868, and 0.601, respectively. After outlier treatment, $r^2$ was 0.892, 0.925, and 0.971, while SEP was 0.052, 1.577, and 0.394, respectively, which totally showed a high correlation. However, $r^2$ of starch was 0.464, which appeared a low correlation. Thereof, the verified equation appearing higher $r^2$ of nitrogen, moisture, and carbohydrate showed its higher accuracy of prediction model, which finally could be put into practical use for turf management system.

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1535-1543
• /
• 2015

The brain-computer interface obtains a user's electroencephalogram as a replacement communication unit for the disabled such that the user is able to control machines by simply thinking instead of using hands or feet. In this paper, we propose a feature extraction method based on a non-selected filter by SBCSP to classify motor imagery EEG. First, we divide frequencies (4~40 Hz) into 4-Hz units and apply CSP to each Unit. Second, we obtain the FLD score vector by combining FLD results. Finally, the FLD score vector is projected onto the optimal plane for classification using PCA. We use BCI Competition III dataset IVa, and Extracted features are used as input for LS-SVM. The classification accuracy of the proposed method was evaluated using $10{\times}10$ fold cross-validation. For subjects 'aa', 'al', 'av', 'aw', and 'ay', results were $85.29{\pm}0.93%$, $95.43{\pm}0.57%$, $72.57{\pm}2.37%$, $91.82{\pm}1.38%$, and $93.50{\pm}0.69%$, respectively.