Bulletin of the Korean chemical society | |
Determination of Research Octane Number using NIR Spectral Data and Ridge Regression | |
Chi-Hyuck Jun1  Hoeil Chung1  Hyeseon Lee1  | |
关键词: Near infrared spectroscopy; NIR; Multiple linear regression (MLR); Ridge regression; Collinearity; Gasoline; Research octane number (RON).; | |
DOI : | |
学科分类:化学(综合) | |
来源: Korean Chemical Society | |
【 摘 要 】
Ridge regression is compared with multiple linear regression (MLR) for determination of Research Octane Number (RON) when the baseline and signal-to-noise ratio are varied. MLR analysis of near-infrared (NIR) spectroscopic data usually encounters a collinearity problem, which adversely affects long-term prediction performance. The collinearity problem can be eliminated or greatly improved by using ridge regression, which is a biased estimation method. To evaluate the robustness of each calibration, the calibration models developed by both calibration methods were used to predict RONs of gasoline spectra in which the baseline and signal-to-noise ratio were varied. The prediction results of a ridge calibration model showed more stable prediction performance as compared to that of MLR, especially when the spectral baselines were varied. . In conclusion, ridge regression is shown to be a viable method for calibration of RON with the NIR data when only a few wavelengths are available such as hand-carry device using a few diodes.
【 授权许可】
Unknown
【 预 览 】
Files | Size | Format | View |
---|---|---|---|
RO201912010237996ZK.pdf | 85KB | download |