Identification of Tea Diseases Based on Spectral Reflectance and Machine Learning
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
With the ability to learn rules from training data, the machine learning model can classify unknown objects. Atthe same time, the dimension of hyperspectral data is usually large, which may cause an overfitting problem. In this research, an identification methodology of tea diseases was proposed based on spectral reflectance andmachine learning, including the feature selector based on the decision tree and the tea disease recognizer basedon random forest. The proposed identification methodology was evaluated through experiments. Theexperimental results showed that the recall rate and the F1 score were significantly improved by the proposedmethodology in the identification accuracy of tea disease, with average values of 15%, 7%, and 11%, respectively. Therefore, the proposed identification methodology could make relatively better feature selection and learnfrom high dimensional data so as to achieve the nondestructive and efficient identification of different teadiseases. This research provides a new idea for the feature selection of high dimensional data and the nondestructiveidentification of crop diseases.
Abstract
With the ability to learn rules from training data, the machine learning model can classify unknown objects. Atthe same time, the dimension of hyperspectral data is usually large, which may cause an overfitting problem. In this research, an identification methodology of tea diseases was proposed based on spectral reflectance andmachine learning, including the feature selector based on the decision tree and the tea disease recognizer basedon random forest. The proposed identification methodology was evaluated through experiments. Theexperimental results showed that the recall rate and the F1 score were significantly improved by the proposedmethodology in the identification accuracy of tea disease, with average values of 15%, 7%, and 11%, respectively. Therefore, the proposed identification methodology could make relatively better feature selection and learnfrom high dimensional data so as to achieve the nondestructive and efficient identification of different teadiseases. This research provides a new idea for the feature selection of high dimensional data and the nondestructiveidentification of crop diseases.
참고문헌 (34)
- X. Wan, "Research advance on tea biochemistry", Journal of Tea Science, 35(1), pp.1~10 (2015)
- Z. Luo, "Advanced in research and application of sex pheromone of tea(Camellia sinensis)pest", Journal of Tea Science, 36(3), pp.229~236 (2016)
- P. Peng, "Review and prospect on forecasting of tea pests and diseases", Southwest China Journal of Agricultural Sciences, 23(5), pp.1742~1745 (2010)
- S. Cheng, "Fast detection methods for crop disease infection period using spectral and imaging technology", Ph. D., pp.2014
- Y. Hong, "Progress in real-time quantitative PCR technique", International Journal of Epidemiology and Infectious Disease, 33(3), pp.161~166 (2006)
- Wafaa Benhabib, "A Multi-Objective TRIBES", OC-SVM Approach for the Extraction of Areas of Interest from Satellite Images, 2017, pp.13(2), 321~339[DOI]
- F. Qin, "Image recognition of four different alfalfa leaf diseases based on deep learning and support vector machine", Journal of China Agricultural University, 22(7), pp.123~133 (2017)
- B. Chen, "Image diagnosis algorithm of diseased wheat", Transactions of the Chinese Society for Agricultural Machinery, 40(12), pp.190~195 (2009)
- Y. Tian, "Research on recognition of cucumber disease based on image processing in sunlight greenhouse", Journal of Agricultural Mechanization Research, 28(2), pp.151~153 (2006)
- Y. Chai, "Recognition of greenhouse tomato disease based on image processing technology", Techniques of Automation and Applications, 32(9), pp.83~89 (2013)
- X. Wei, "Study on quality grading of tea by digital image processing techniques", Journal of Anhui Agricultural Sciences, 40(7), pp.4251~4253 (2012)
- S. Chen, "The study of tea-leaf and tea-stalk image recognition and classification based on multi-features and multi-classifiers", M. S., pp.2014
- X. Li, "Research on nondestructive determination of tea quality based on machine vision and spectroscopy techniques", Ph. D., pp.2009
- Q. Chen, "Estimation of tea quality level using hyperspectral imaging technology", Acta Optica Sinica, 28(4), pp.669~674 (2008)
- J. Y. Peng, "Fast detection of Camellia sinensis growth process and tea quality informations with spectral technology : a review", Guang pu xue yu guang pu fen xi(Guang pu), 36(3), pp.775~782 (2016)
- J. Zhao, "Detecting subtle bruises on fruits with hyperspectral imaging", Transactions of the Chinese Society for Agricultural Machinery, 39(1), pp.106~109 (2008)
- C. Bravo, "Early disease detection in wheat fields using spectral reflectance", Biosystems Engineering, 84(2), pp.137~145 (2003)
- D. G. Leckie, "Automated detection and mapping of crown discolouration caused by jack pine budworm with 2. 5 m resolution multispectral imagery", International Journal of Applied Earth Observation & Geoinformation, 7(1), pp.61~77 (2005)
- B. Mojaradi, "Dimensionality reduction of hyperspectral data via spectral feature extraction", IEEE Transactions on Geoscience & Remote Sensing, 47(7), pp.2091~2105 (2009)
- S. Zhang, "Recognition of tea disease spot based on hyperspectral image and genetic optimization neural network", Transactions of the Chinese Society of Agricultural Engineering, 33(22), pp.200~207 (2017)
- Y. Wang, "Analysis of feature selection and its impact on hyperspectral data classification based on Decision Tree Algorithm", Journal of Remote Sensing, 11(1), pp.69~76 (2007)
- X. B. Yang, "Decision tree and its key techniques", Computer Technology and Development, 17(1), pp.43~45 (2007)
- S. F. Ding, "An overview on theory and algorithm of support vector machines", Journal of University of Electronic Science & Technology of China, 40(1), pp.2~10 (2011)
- M. A, "Research and application on naïve Bayes classification algorithm", M. S., pp.2014
- Y. Sang, "Research of classification algorithm based on k nearest neighbor", M. S., pp.2014
- S. Feng, "Research and improvement of decision trees algorithm", Journal of Xiamen University(Natural Science), 46(4), pp.497~500 (2007)
- Y. Zhang, "Decision tree algorithms for big data analysis", Computer Science, 43(6A), pp.374~383 (2016)
- K. Fang, "A review of technologies on random forests", Statistics & Information Forum, 26(3), pp.32~38 (2011)
- L. Breiman, "Random forests", Machine Learning, 45(1), pp.5~32 (2001)
- L. Breiman, "Bagging predictors", Machine Learning, 24(2), pp.123~140 (1996)
- T. K. Ho, "The random subspace method for constructing decision forests", IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(8), pp.832~844 (1998)
- S. Dong, "A brief theoretical overview of random forests", Journal of Integration Technology, 2(1), pp.1~7 (2013)
- O. Russakovsky, "ImageNet large scale visual recognition challengem", International Journal of Computer Vision, 115(3), pp.211~252 (2015)
- T. Y. Lin, "Microsoft coco: common objects in context", Computer Vision – ECCV 2014, pp.740~755 (2014), Springer