Abstract：Based on stepwise linear regression, and according to the theory of near infrared absorbption, spectrum(1 000-2 500 nm) obtained by detector was divided into three ranges, which were Ⅰ(1 000-1 400 nm) and Ⅱ(1 400-1 860 nm) and Ⅲ(1 860—2 500 nm). In each range the regression wavelengths of different wavelength gaps were picked up stepwise. Regression coefficients and parameters were calculated by Matlab5.3 Program. Regression models were built up in different ranges with different wavelength gaps. Best models could be determined． Prediction results of protein content of ground wheat were displayed in scatter plots. Different results were discussed and compared，which has referencemeaning for application.
郑咏梅1，张 军2，陈星旦2，申铉国1，张铁强1 . 基于逐步回归法的近红外光谱信息提取及模型的研究 [J]. 光谱学与光谱分析, 2004, 24(06): 675-678.
ZHENG Yong-mei1, ZHANG Jun2, CHEN Xing-dan2, SHEN Xuan-guo1, ZHANG Tie-qiang1 . Research on Model and Wavelength Selection of Near Infrared Spectral Information . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2004, 24(06): 675-678.
[1] ZHU Er-yi, YANG Peng-yuan(朱尔一，杨芃原). Application and Technique of Chemertric(化学计量学技术及应用). Beijing： Science Press(北京：科学出版社)，2001. 11. [2] Phil Williams Kari Norris. Near-Infrared Technology in the Agricultural and Food Industries. Minnesota： The American Association of Cereal Chemists, Inc.，1987.
