02057nas a2200229   4500000000100000000000100001008004100002260001200043653003100055653001000086653001000096653002700106100002500133700002900158700001700187245006300204856009900267300001000366490000600376520143100382022001401813       2020                            d  c03/202010aArtificial Neural Networks10aFuzzy10aFruit10aSupport Vector Machine1 aMojtaba Mohammadpoor1 aMohadese Gerami Nooghabi1 aZahra Ahmedi00aAn Intelligent Technique for Grape Fanleaf Virus Detection  uhttps://www.ijimai.org/journal/sites/default/files/files/2020/02/ijimai20206_1_7_pdf_85267.pdf  a62-670 v63 aGrapevine Fanleaf Virus (GFLV) is one of the most important viral diseases of grapes, which can damage up to 85% of the crop, if not treated at the right time. The aim of this study is to identify infected leaves with GFLV using artificial intelligent methods using an accessible database. To do this, some pictures are taken from infected and healthy leaves of grapes and labeled by technical specialists using conventional laboratory methods. In order to provide an intelligent method for distinguishing infected leaves from healthy ones, the area of unhealthy parts of each leaf is highlighted using Fuzzy C-mean Algorithm (FCM), and then the percentages of the first two segments area are fed to a Support Vector Machines (SVM). To increase the diagnostic reliability of the system, K-fold cross validation method with k = 3 and k =5 is applied. After applying the proposed method over all images using K-fold validation technique, average confusion matrix is extracted to show the True Positive, True Negative, False Positive and False Negative percentages of classification. The results show that specificity, as the ability of the algorithm to really detect healthy images, is 100%, and sensitivity, as the ability of the algorithm to correctly detect infected images is around 97.3%. The average accuracy of the system is around 98.6%. The results imply the ability of the proposed method compared to previous methods.  a1989-1660