Back Propagation-Artificial Neural Network Model for Prediction of the Quality of Tea Shoots through Selection of Relevant Near Infrared Spectral Data via Synergy Interval Partial Least Squares

Wang, Shengpeng;Zhang, Zhengzhu;Ning, Jingming;Ren, Guangxin;Wan, Xiaochun;et.al.
(2012) Analytical Letters — Vol. 46, n° 1, p. 184-195 (2012)

Files

No attached file found for this publication.

Details

Authors
  • Wang, Shengpeng
    Author
  • Zhang, Zhengzhu
    Author
  • Ning, Jingming
    Author
  • Ren, Guangxin
    Author
  • Wan, Xiaochun
    Author
Show more
Abstract
Near-infrared spectroscopy and back propagation-artificial neural network (BP-ANN) model in conjunction with synergy interval partial least squares (siPLS) algorithm were used to evaluate tea shoots quality. The near-infrared spectra regions relevant to tea quality (12493 cm<sup>-1</sup> to 11645 cm<sup>-1</sup>, 9087.5 cm<sup>-1</sup> to 8242.7 cm<sup>-1</sup>, 8238.9 cm<sup>-1</sup> to 7394.2 cm<sup>-1</sup>, and 6541.7 cm<sup>-1</sup> to 5697 cm<sup>-1</sup>) were selected using siPLS algorithm. The two principal components that explained 99.46% of the variability in this spectral data were then used to calibrate the BP-ANN quality index (QI) model. The performance of this model [the coefficient of determination for prediction (r<inf>pre</inf> <sup>2</sup>), 0.9680; root mean square error of prediction (RMSEP), 0.0178] was superior to those of the BP-ANN model (r<inf>pre</inf> <sup>2</sup> = 0.9332, RMSEP= 0.0285) and the siPLS model (r<inf>pre</inf> <sup>2</sup> = 0.9230, RMSEP= 0.0360). The predicted QI values of 25 samples highly correlated with the experimental values (r<inf>pre</inf> <sup>2</sup> = 0.9223, RMSEP= 0.0344). The QI model with the combined siPLS-BP-ANN algorithms accurately predicted the quality of tea shoots. © 2013 Copyright Taylor and Francis Group, LLC.

Citations

  • APA
  • Chicago
  • FWB

Wang, S., Zhang, Z., Ning, J., Ren, G., Yan, S., & Wan, X. (2012). Back Propagation-Artificial Neural Network Model for Prediction of the Quality of Tea Shoots through Selection of Relevant Near Infrared Spectral Data via Synergy Interval Partial Least Squares. Analytical Letters, 46(1), 184-195. https://doi.org/10.1080/00032719.2012.706848 (Original work published 2012)