Text
IMPLEMENTASI MODEL REGRESI LOGISTIK MULTINOMIAL BERDASARKAN REPEATED K-FOLD CROSS VALIDATION UNTUK KLASIFIKASI HAMA DAN PENYAKIT TANAMAN JAGUNG
One of the food crops used as a source of carbohydrates is corn. However, there are several obstacles in the cultivation of corn plants that cause low productivity of corn yields, namely pests and diseases. The purpose of this study was to obtain an accurate level of accuracy in the classification of pests and diseases of maize, namely grasshoppers, cob borers, Spodoftera frugiperda, downy mildew, leaf rust, and non-pathogens, using multinomial logistic regression, based on repeated k-fold cross validation. The research data was obtained from the RGB color feature extraction process on each image of pests and diseases of corn, , which is in the form of the average value of each layer R, G and B. The dataset obtained was divided into train and test data using repeated k-fold cross validation, with k= 5 and repeated 10 times. Train data is used to generate the model, while test data is used to see the performance of the obtained model.The classification process is carried out using a multinomial logistic regression model, and calculates the level of classification accuracy with a confusion matrix. The results of this study indicate that using multinomial logistic regression with repeated k-fold cross validation, can obtain an accuracy level is 94.75%, macro precision is 69.79%, macro recall is 59.58%, macro F-score is 64, 16%, while for micro precision is 79.99%, micro recall is 79.99%, and micro F-score is 79.99%
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2207004347 | T77828 | T778282022 | Central Library (Referens) | Available but not for loan - Not for Loan |
No other version available