Near Infrared Spectrum Detection of Soybean Fatty Acids Based on GA and Neural Network
This paper represented a way to build mathematical model on genetic multilevel forward neural network. Building the relationship between chemistry measurement values and near infrared spectrum datum. The near infrared spectrum data was input in this network, five kinds of content of fatty acids, which measured by chemistry method, were output. Training the weight of multilevel forward neural network by genetic algorithms, building the soybean fatty acids neural network detection model, and exploring the network model which can realize near infrared spectrum detection exactly and efficiently. The authors designed a multilevel forward neural network trained by genetic algorithms. Test showed that relative coefficient in five fatty acids of soybean can be round about 0.9, and can satisfy init detection of soybean breeding.
Keywordsnear infrared multilevel forward neural network genetic algorithms soybean fatty acids
- Srinivas M, Patnail L M. Adaptive Probabilities of Crossover and Mutations in Gas [J]. IEEE Trans on SMC, 1994, 24(4):656-667.Google Scholar
- Williams P C, Norris K, Gehrke C W and Bernstein K. 1983. Comparison of near-infrared methods for measuring protein and moisture in wheat. Cereal Foods Worle . 150:149-152.Google Scholar
- Morgan J E and Williams P C. 1995. Starch damage in wheat flours: A comparison of enzymic, iodometric and near-infrared reflectance techniques. Cereal Chemistry. 72 (2): 209-212.Google Scholar
- Murray L and Williams P C. 1987. Chemical principles of near-infrared technology. In Williams P C and Norris K ed. Near-infrared Technology. AACC St. Paul, MN.Google Scholar
- Norris K H. 1984. Multivariate analysis of raw material. In: Schmilt L W, ed. Chemistry and world food supplies. Manila: Reihold Publisher, 155-164.Google Scholar