Wu JIANG, Billur Barshan ÖZAKTAŞ, Nitin MANTRI, Zhengming TAO, Hongfei LU

Classification of Camellia species from 3 sections using leaf anatomical data with back-propagation neural networks and support vector machines

Leaf characteristics provide many useful clues for taxonomy. We used a back-propagation artificial neural network (BP-ANN) and C-support vector machines (C-SVMs) to classify 47 species from 3 sections of genus Camellia (16 from sect. Chrysanthae, 16 from sect. Tuberculata, and 15 from sect. Paracamellia). The classification model was constructed based on 7 leaf anatomy attributes including, area of adaxial epidermal cell, thickness of adaxial epidermal cell, thickness of palisade parenchyma, thickness of total leaf, thickness of spongy parenchyma, thickness of abaxial epidermal cell, and area of abaxial epidermal cell. Model parameters of C-SVM, comprising regularization parameter (C) and kernel parameter (g), were optimized by cross-validation. The best classification accuracy of the 3 Camellia sections was achieved by the radial basis function SVM classifier (with parameters C = 32, g = 0.13), as well as the sigmoid SVM classifier (with parameters C = 32, g = 0.13), which was up to 84.00% in the training set and 90.91% in the prediction set, respectively. Compared with BP-ANN, SVM yields slightly higher prediction accuracy, which indicates that it is feasible to accurately classify the 3 sections of Camellia using SVMs based on leaf anatomy data.

Anahtar Kelimeler:

Key words: BP-ANN, Camellia, leaf anatomy, plant numerical taxonomy, supervised pattern recognition, SVM

Classification of Camellia species from 3 sections using leaf anatomical data with back-propagation neural networks and support vector machines

Keywords:

Key words: BP-ANN, Camellia, leaf anatomy, plant numerical taxonomy, supervised pattern recognition, SVM,

PDF

___

Bila S, Harkouss Y, Ibrahim M, Rousset J, N’Goya E, Baillargeat D, Verdeyme M, Aubourg M, Guillon P (1999). An accurate wavelet neural-network-based model for electromagnetic optimization of microwave circuits. Int J RF Micro CE 93: 297–306.
Burges CJC (1998). A tutorial on support vector machines for pattern recognition. Data Min Knowl Disc 2: 121–167.
Chang HT (1998). Camellia. In: Zhengyi W, Raven PH, editors. Flora of China. Beijing, China: Science Press, pp. 367–412.
Chen QS, Zhao JW, Fang CH, Wang DM (2007). Feasibility study on identification of green, black and Oolong teas using nearinfrared reflectance spectroscopy based on support vector machine (SVM). Spectrochim Acta Part A 66: 568–574.
Chen QS, Zhao JW, Lin H (2009). Study on discrimination of roast green tea (Camellia sinensis L.) according to geographical origin by FT-NIR spectroscopy and supervised pattern recognition. Spectrochim Acta Part A 72: 845–850.
Cortes C, Vapnik V (1995). Support-vector networks. Mach Learn 20: 273–297.
Cybenco G (1989). Approximation by superposition of a sigmoidal function. Math Control Signal 2: 303–314.
Dogan A, Demirpence H, Cobaner M (2008). Prediction of groundwater levels from lake levels and climate data using ANN approach. Water SA 34: 1–10.
Giacomini M, Ruggiero C, Calegari L, Bertone S (2000). Artificial neural network based identification of environmental bacteria by gas-chromatographic and electrophoretic data. J Microbiol Meth 43: 45–54.
Guyer D, Yang X (2000). Use of genetic artificial neural networks and spectral imaging for defect detection on cherries. Comput Electron Agr 29: 179–194.
Hagan MT, Menhaj MB (1994). Training feed forward networks with the Marquardt algorithm. IEEE T Neural Networks 6: 861–867
Hornik K, Stinchombe M, White H (1989). Multilayer feed forward network are universal approximator. Neural Networks 2: 359– 3
Jiang B, Peng QF, Shen ZG, Moller M, Pi EX, Lu HF (2010). Taxonomic treatments of Camellia (Theaceae) species with secretory structures based on integrated leaf characters. Plant Syst Evol 290: 1–20.
Jiang W, Nitin M, Jiang B, Zheng YP, Hong SS, Lu HF (2012). Floral morphology resolves the taxonomy of Camellia L. (Theaceae) sect. Oleifera and sect. Paracamellia. Bangl J Plant Taxon 19(2): 155–165.
Kong HZ (2001). Comparative morphology of leaf epidermis in the Chloranthaceae. Bot J Linn Soc 136: 279–294.
Kumar V, Kodandaramaiah J, Rajan MV (2012). Leaf and anatomical traits in relation to physiological characteristic in mulberry (Morus sp.) cultivars. Turk J Bot 36: 683–689.
Li ZX, Yang XM (2008). Damage identification for beams using ANN based on statistical property of structural responses. Comput Struct 86: 64–71.
Lin XY, Peng QF, Lv HF, Du YQ, Tang BY (2008). Leaf anatomy of Sect. Oleifera Chang and Sect. Paracamellia Sealy and its taxonomic significance. J Syst Evol 46: 183–193.
Lu H, Jiang W, Ghiassi M, Lee S, Nitin M (2012). Classification of Camellia (Theaceae) species using leaf architecture variations and pattern recognition techniques. PLoS ONE 7: e29704.
Lu HF, Jiang B, Shen ZG, Shen JB, Peng QF, Cheng CG (2008). Comparative leaf anatomy, FTIR discrimination and biogeographical analysis of Camellia section Tuberculata (Theaceae) with a discussion of its taxonomic treatments. Plant Syst Evol 274: 223–235.
Lu HF, Pi EX, Peng, QF, Wang LL, Zhang CJ (2009). A particle swarm optimization-aided fuzzy cloud classifier applied for plant numerical taxonomy based on attribute similarity. Expert Syst Appl 36: 9388–9397.
Lu HF, Shen JB, Lin XY, Fu JL (2008). Relevance of Fourier transform infrared spectroscopy and leaf anatomy for species classification in Camellia (Theaceae). Taxon 57: 1274–1288.
Lu HF, Zheng H, Lou HQ, Jiang LL, Chen Y, Fang SS (2010). Using neural networks to estimate the losses of ascorbic acid, total phenols, flavonoid, and antioxidant activity in asparagus during thermal treatments. J Agr Food Chem 58: 2995–3001.
Luo D, Hosseini HG, Stewart JR (2004). Application of ANN with extracted parameters from an electronic nose in cigarette brand identification. Sensors Actuat B 99: 253–257.
Ming TL (2000). Monograph of the Genus Camellia. Kunming, Yunnan, China: Science and Technology Press.
Mitchell TM (1997). Machine Learning. Boston: WCB/McGraw-Hill.
Moshou D, Wahlen S, Strasser R, Schenk A, De Baerdemaeker J, Ramon H (2005). Chlorophyll fluorescence as a tool for online quality sorting of apples. Biosyst Eng 91: 163–172.
Pi EX, Lu HF, Jiang B, Huang J, Peng QF, Lin XY (2011). Precise plant classification within genus level based on simulated annealing aided cloud classifier. Expert Syst Appl 38: 3009–3014.
Pi EX, Peng QF, Lu HF, Shen JB, Du YQ, Huang FL, Hu H (2009). Leaf morphology and anatomy of section Camellia (Theaceae). Bot J Linn Soc 3: 456–476.
Pontil M, Verri A (1998). Support vector machines for 3-D object recognition. IEEE T Pattern Anal 20: 637–646.
Roggo Y, Duponchel L, Huvenne LP (2003). Comparison of supervised pattern recognition methods with McNemar’s statistical test: Application to qualitative analysis of sugar beet by near-infrared spectroscopy. Anal Chim Acta 477: 187–200.
Sadeghi BHM (2000). A BP-neural network predictor model for plastic injection molding process. J Mater Process Tech 103: 411–416.
Shen JB, Lu HF, Peng QF, Zheng JF, Tian YM (2008). FTIR spectra of Camellia sect. Oleifera, sect. Paracamellia, and sect. Camellia (Theaceae) with reference to their taxonomic significance. J Syst Evol 46: 194–204.
Turhan K, Serdar B (2013). Support vector machines in wood identification: the case of three Salix species from Turkey. Turk J Agric For 37: 249–256.
Vapnik VN (1989). Statistical Learning Theory. New York: Wiley.
Vapnik VN (1995). The Nature of Statistical Learning Theory. New York: Springer.
Vasic PS, Dubak DV (2012). Anatomical analysis of red Juniper leaf (Juniperus oxycedrus) taken from Kopaonik Mountain, Serbia. Turk J Bot 36: 473–479.
Vijayan K, Zhang WJ, Tsou CH (2009). Molecular taxonomy of Camellia (Theaceae) inferred from nrITS sequences. Am J Bot 96: 1348–1360.
Yang ZR, Qi L (2005). Comparative morphology of the leaf epidermis in Schisandra (Schisandraceae). Bot J Linn Soc 148: 39–56.
Yuan SF, Chu FL (2007). Fault diagnostics based on particle swarm optimization and support vector machines. Mech Syst Signal Pr 21: 1787–1798.
Zheng H, Fang SS, Lou HQ, Chen Y, Jiang LL, Lu HF (2011). Neural network prediction of ascorbic acid degradation in green asparagus during thermal treatments. Expert Syst Appl 38: 5591–5602.
Zheng H, Lu HF, Zheng YP, Lou HQ, Chen CQ (2010). Automatic sorting of Chinese jujube (Zizyphus jujuba Mill. cv. ‘hongxing’) using chlorophyll fluorescence and support vector machine. J Food Eng 101: 402–408.