Performance of calibration model with different ratio of sample size to the number of wavelength: Application to hemoglobin determination by NIR spectroscopy.


Faculty of Mechanical & Material Engineering, Huaiyin Institute of Technology, Huai'an 223003, China. Electronic address: [Email]


Near infrared spectroscopy is widely used in composition analysis in fields of food, medicines, environment, and so on. The proportion of sample size and the wavelength used is very important for the performance of the calibration model. In this research, we explored the influence of ratio of sample size to the number of wavelength (SWR) on the performance of calibration model, with hemoglobin determination as an example. The results showed that RMSEC increases with the increase of SWR, when SWR is less than 0.5, namely the samples in the calibration set were less than half of the number of wavelengths used in establishing the calibration model, while RMSEP decreases with the increase of SWR. The calibration model was lack of reliability at this range for SWR. RMSEC and RMSEP tend to be stable when SWR value is greater than 0.9. However, in most cases, the samples size was limited, and wavelength selection was commonly used in practical spectroscopy analysis. In order to confirm that the effect of SWR were caused by both sample size and wavelength number, we also studied the performance of calibration model with different WSR. Wavelengths were selected by equidistant combination multiple linear regression (ECMLR) method. The conclusion from results were consistent with the previous part, namely when establishing calibration model, the number of wavelengths used should be less than the twice amount of samples in the calibration set to ensure the validity of the model. We recommend that wavelength selection part was indispensable for small sample size cases. This research can be important evidence and guide for other researches with spectroscopy methods.


Hemoglobin determination,NIR spectroscopy,Sample size,Wavelength number,

OUR Recent Articles