Prediction of Wine Alcohol Concentration Based on Sample Selection and PSO-ANN

doi:10.12068/j.issn.1005-3026.2018.07.012

Abstract

Abstract: In order to improve the accuracy and robustness of the quantitative analysis model， a new sample selection algorithm named KM was proposed. In the experiment， 40 samples of wine were used as the analysis objects， and the KM algorithms was compared with traditional sample selection algorithms， such as RS， KS and SPXY. The experimental results show that |RMSEP-RMSEC| obtained by KM algorithm is superior to the other three algorithms， and there are significant differences in RPD， which indicates that KM method has good prediction accuracy. In order to overcome the neural network training algorithms drawbacks that BP neural networks converge slowly and is easy to fall into local optimum， the particle swarm optimization algorithm was used to optimize the parameters of artificial neural network (PSO-ANN). The results show that PSO-ANN algorithm can improve the convergence velocity of training， robustness and the accuracy of classification than genetic algorithm， artificial fish swarm algorithm， and shuffled frog-leaping algorithm.

Key words: sample selection algorithm, swarm intelligence algorithm, BP neural network, Raman spectroscopy, wine, particle swarm optimization

CLC Number:

O657.37

WANG Qiao-yun， ZHENG Nian-zu. Prediction of Wine Alcohol Concentration Based on Sample Selection and PSO-ANN[J]. Journal of Northeastern University Natural Science, 2018, 39(7): 970-975.

References

[1]叶向晖，沈于兰，申兰慧，等.拉曼光谱法在食品药品分析中的应用与进展［J］.中国药业，2017，26(1):1-5.(Ye Xiang-hui，Shen Yu-lan，Shen Lan-hui，et al.Raman spectroscopy in the application of food and drug analysis and progress ［J］.China Pharmaceutical，2017，26 (1):1-5.)
[2]文军.拉曼光谱和表面张力用于水质检测与分析［J］.物理实验，2014，34(5):9-12.(Wen Jun.Raman spectroscopy and surface tension for water quality detection and analysis ［J］.Physical Experiment，2014，34 (5):9-12.)
[3]Rocha R A D，Paiva I M，Anjos V，et al.Quantification of whey in fluid milk using confocal Raman microscopy and artificial neural network ［J］.Journal of Dairy Science，2015，98(6):3559-3567.
[4]詹雪艳，赵娜，林兆洲，等.校正集选择方法对于积雪草总苷中积雪草苷NIR定量模型的影响［J］.光谱学与光谱分析，2014 (12):3267-3272.(Zhan Xue-yan，Zhao Na，Lin Zhao-zhou，et al.Effect of algorithms for calibration set selection on quantitatively determining asiaticoside content in centella total gluecosides by near infrared spectroscopy ［J］. Spectroscopy and Spectral Analysis，2014(12):3267-3272.)
[5]靳召晰，张秀娟，罗付义，等.近红外光谱建模样本选择方法研究［J］.光谱学与光谱分析，2016，36(12):3920-3925.(Jin Zhao-xi，Zhang Xiu-juan，Luo Fu-yi，et al.Study of modeling samples selection method based on near infrared spectrum［J］.Spectroscopy and Spectral Analysis，2016，36(12):3920-3925.)
[6]Zhao C H，Guo F R，Wang F L.Spectra data analysis and calibration modeling method using spectra subspace separation and multiblock independent component regression strategy ［J］.AIChE Journal，2011，57(5):1202-1215.
[7]Liu F，Xie L，Li B J，et al.Multi-sense swarm intelligence algorithm and its application in feed-forward neural networks training［J］.Journal of University of Science and Technology Beijing，2008，30(9):1061-1066.
[8]Saptoro A，Tade M O，Vuthaluru H.A modified Kennard-Stone algorithm for optimal division of data for developing artificial neural network models［J］. Chemical Product and Process Modeling，2012，7(1):1-14.
[9]Zhan X M，Zhu X R，Shi X Y，et al.Determination of hesperidin in tangerine leaf by near-infrared spectroscopy with SPXY algorithm for sample subset partitioning and monte carlo cross validation［J］.Spectroscopy and Spectral Analysis，2009，29(4):964-968.
[10]Bezborah A.A hardware architecture for training of artificial neural networks using particle swarm optimization［C］ // The Third International Conference on Intelligent Systems Modelling and Simulation.Kota Kinabalu:IEEE Computer Society，2012:67-70.
[11]Lilichenko M，Kelley A M.Application of artificial neural networks and genetic algorithms to modeling molecular electronic spectra in solution［J］.Journal of Chemical Physics，2001，114:7094-7102.
[12]Hai M J，Xie K，Wang Y F.Optimization of pump parameters for gain flattened Raman fiber amplifiers based on artificial fish school algorithm［J］.Optics Communications，2011，284:5480-5483.
[13]Eusuff M，Lansey K，Pasha F.Shuffled frog-leaping algorithm:a memetic meta-heuristic for discrete optimization［J］.Engineering Optimization，2006，38:129-154.
[14]Diamond P，Fomenko I V.Robustness and universal approximation in multilayer feedforward neural networks［R］.Sydney:Sydney University，1992.
[15]Bengio Y，Simard P，Frasconi P.Learning long-term dependencies with gradient descent is difficult［J］.IEEE Transactions on Neural Networks，1994，5(2):157-166.