Title: Application of the common vector approach on identification of winter rapeseed (Brassica napus L.) cultivars and their yield characters

Authors: Zehra Aytaç; Nurdilek Gülmezoğlu; M. Bilginer Gülmezoğlu

Addresses: Department of Field Crops, Faculty of Agriculture, Eskişehir Osmangazi University, 26480, Eskişehir, Turkey ' Department of Soil Science and Plant Nutrition, Faculty of Agriculture, Eskişehir Osmangazi University, 26480, Eskişehir, Turkey ' Department of Electrical and Electronics Engineering, Faculty of Engineering and Architecture, Eskişehir Osmangazi University, 26480, Eskişehir, Turkey

Abstract: In this study, five winter rapeseed cultivars (Ceres, Zorro, Falcon, Express, and Samourai) growing over two years were classified by using the common vector approach (CVA), Fisher's linear discriminant analysis (FLDA) and support vector machine (SVM). For this purpose, seven yield characters (plant height, number of branches per plant, number of pods per plant, number of pods on main stem, number of seeds per pod, pod length and thousand seed weight) of each cultivar were used. Cultivars grown in the years 2003 and 2005 were classified separately by using seven yield characters each of which has 20 samples. Then cultivars were also classified by using seven yield characters each of which has 40 samples obtained by combining the plant samples belonging to the years 2003 and 2005. Furthermore, the seven and six yield characters taken from five cultivars grown in 2005 were classified by using only CVA. When CVA is used in all studies, 100% classification rate is guaranteed for the training set of all studies. For the test set, the classification of five cultivars has low performance, but the classification of seven and six yield characters gave satisfactory results. It is concluded that the CVA method was more successful in the classification of different varieties belonging to any plant and/or of different characters belonging to any variety.

Keywords: yield character classification; common vector approach; CVA; Fisher's LDA; linear discriminant analysis; FLDA; support vector machines; SVM; rapeseed classification; identification; winter rapeseed; Brassica napus L.; rapeseed cultivars; crop yield.

DOI: 10.1504/IJSAMI.2016.077271

International Journal of Sustainable Agricultural Management and Informatics, 2016 Vol.2 No.1, pp.66 - 78

Received: 16 Nov 2015
Accepted: 18 Feb 2016
Published online: 25 Jun 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article