Fast Measurement of Fruit Tree Nitrogen Status Based on Multi-Color LEDs and BP-ANN

Abstract:

A new optical instrument for fast measurement of fruit tree nitrogen status was designed and fabricated. Multi-color LEDs were used as light source, a portable spectrophotometer as optical detector, and an optic fiber as light signal transmission medium. In the paper, the principle of using multi-color LEDs for the measurement of fruit tree nitrogen status was first introduced. Then, the method of using error back propagation artificial neural network (BP-ANN) for calibration modeling was elaborated. Reflective light intensities of Multi-color LEDs were taken as the incoming signals to BP-ANN. The structure of BP-ANN with three layers has been optimized to minimize its calibration error. In the test, total 200 leave samples picked from Huang-hua pear trees planted in three orchards with different levels of nitrogen fertilizing. Among them, 150 samples were selected randomly out for calibration set with the remaining 50 for prediction set. The result shows that correlation coefficient of R2 between predicted and measured values of nitrogen content reaches 0.93 with maximum prediction error less than 3.36(SPAD). The study suggests that the new optical method integrating multi-color LEDs with BP-ANN is promising for fast diagnosis of fruit tree mineral nutrition status.

• Periodical: Advanced Materials Research (Volumes 179-180)
• Pages: 1364-1367
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.179-180.1364
• Online since: January 2011
• Authors: Hai Qing Yang, Gang Lv
• Keywords: BP ANN, Fruit Tree, Multi-Color LED, Nitrogen Status, Pear, Spectrophotometer

References

[1] Information on http: /www. onfruit. com/pic/photo/3163. html.

[2] H. Yang, J. Yao, Y. He: Spectr. Sp. A Vol. 29 (2009), p.1607.

[3] H. Yang, Y. He, Y. Chen, P. Lin and D. Wu: Spectr. Sp. A Vol. 28 (2008), p.1232.

[4] H. Yang, D. Wu and Y. He, in: MIPPR2007: Pattern Recognition and Computer Vision, edited by S.J. Maybank, volume 6788 of Proceedings of the Society of Photo-optical Instrumentation Engineering (SPIE), SPIE International Society of Optical Engineering Publishers (2007).

[5] H. Yang and Y. He, in: Proceedings of the 9th International Conference for Young Computer Scientists, edited by G.J. Wang, IEEE Computer Society Publisher, CA (2008).

[6] H. Yang and Y. He, in: Computer and Computing Technologies in Agriculture II, edited by D. Li, Volume 293 of International Federation for Information Processing, Springer (2009).

[7] H. Yang and Y. He, in: Proceedings of 2008 International Conference on Informationization, Automation and Electrification in Agriculture, edited by H. Zhang, Orient Acad Forum, Austrilia (2008).

[8] H. Yang and Y. He, in: 2008 IEEE International Conference on Automation and Logistics, edited by IEEE, NY (2008).

[9] H. Yang, J. Wu, X. Chen and Y. He, in: 2008 7th World Congress on Intelligent Control and Automation, edited by IEEE, NY (2008).

[10] H. Yang and Y. He, in: CISP 2008: 1st International Congress on Image and Signal Processing, edited by D. Li, IEEE Computer Society, CA (2008).

[11] Information on http: /www. camo. com.

[12] Information on http: /www. specmeters. com/Chorophyll_Mete/Minolta_SPAD_502_Meter. html.

[13] Information on http: /www. mathworks. co. uk/products/neuralnet.