Immune Algorithm for the Singular Sample of Near Infrared Spectroscopy

Abstract:

This paper proposes a method to identify the singular sample with near infrared spectroscopy based on immune algorithm. T The immune algorithm and genetic algorithm for the same NIR spectral data sets are singular sample identification and comparison of the two methods. Remove the singular sample, immune algorithm is better than the genetic algorithm are used to PRESS of PLS model of water, fat, the protein increased by 25.8%, 32.1%, 21.7%.Experiments show that, artificial immune algorithm is not only suitable for near infrared spectra of singular sample, but also can improve the model prediction accuracy and robustness.

• Periodical: Applied Mechanics and Materials (Volumes 427-429)
• Pages: 770-773
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.427-429.770
• Online since: September 2013
• Authors: Fan Yu*, Ji Xin Li
• Keywords: Clonal Selection, Immune Algorithm, Near Infrared Spectroscopy (NIRS), Singular Sample

References

[1] XU Guang-Tong, YUAN Hong-Fu, LU Wan-Zhen. Development of Modern Near Infrared Spectroscopic Techniques and Its Applications. Spectroscopy and Spectral Analysis, 2000, 02: 134.

[2] CHU Xiao-Li, YUAN Hong-Fu, LU Wan-Zhen. The On-line Near Infrared Spectroscopy Process Analytical Technique and Its Applictions. Modern Scientific Instruments, 2004, 02: 3.

[3] Cummins D J, Andrews C W. Iteratively reweighted partial least squares: A performance analysis by Monte Carlo simulation. Journal of Chromatography . (1995).

DOI: 10.1002/cem.1180090607

[4] YANG Hui-hua, Tan Feng, WANG Yi-Ming, LUO Guo-AN. lsomap-PLS Nonlinear Modeling Method for Near Infrared Spectroscopy[J]. Spectroscopy and Spectral Analysis, 2009, 02: 321.

[5] XU Guang-tong, YUAN Hong-Fu, LU Wan-Zhen. Study of Quantitative Calibration Model Suitability in Nera infrared Spectroscopy Analysis[J]. Spectroscopy and Spectral Analysis, 2001, (04): 459.

[6] BAO Xin. Robust Regression and Its Application in Spectral Analysis[D]. ZheJiang: ZheJiang University, (2010).

[7] ZHU Shi-Ping. Sample selection methods for building calibration model of Near infrared Spectroscopy based on Principal Component Analysis and genetic Gligorithms[J]. Transactions of the Chinese Society of Agricultural Engineering, 2008, 09: 126.

[8] CAO Hui, ZHOU Yan. Multi-Population Elitists Shared Genetic Algorithm for Outlier Detection of Spectroscopy Analysis[J]. Spectroscopy and Spectral Analysis, 2011, 07: 1847.