IMPLEMENTASI METODE CONVOLUTIONAL NEURAL NETWORK UNTUK IDENTIFIKASI PENYAKIT PADA TANAMAN POHPOHAN
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
Shaputra, Irwan
Agtriadi, Herman Bedi
Cahyaningtyas, Rizqia
Agtriadi, Herman Bedi
Cahyaningtyas, Rizqia
Subject
Teknik Informatika
Datestamp
2022-09-20 03:03:50
Abstract :
Pohpohan plant or called in scientific language Pilea trinervia Wight is a wild plant that lives in wild forests. And includes one of the indigenous vegetable plants or plants that are cultivated in a certain area that can be consumed as vegetables. Pohpohan plants can also be used as traditional or herbal medicines, and pohpohan plants are often also used in certain communities as traditional or herbal medicines. Convolutional Neural Network (CNN) is a method that can be used to detect and recognize an object in an image. CNN is also a type of neural network that can work well on an image. In this study, the classification class used by the author consisted of four classes of disease types, which included four (4) classes of disease types, namely healthy leaves, Budug disease, Blonde disease, Perforated Leaf disease. The amount of data processed is 387 images with testing data and 310 images for validation with a total of 15 epochs. Furthermore, the image data will be used to form a model or model fitting that will be used for the testing process. The parameters used in this study to measure the success rate. In this system model, the highest accuracy and lowest loss are the 15th diepoch, which is 0.9406 with a loss of 0.2112, for the highest val_accuracy and the lowest val_loss there is the 15th diepoch, namely val_accuracy 0.9836 with a val_loss of 0.0989.
Pohpohan plant or called in scientific language Pilea trinervia Wight is a wild plant that lives in wild forests. And includes one of the indigenous vegetable plants or plants that are cultivated in a certain area that can be consumed as vegetables. Pohpohan plants can also be used as traditional or herbal medicines, and pohpohan plants are often also used in certain communities as traditional or herbal medicines. Convolutional Neural Network (CNN) is a method that can be used to detect and recognize an object in an image. CNN is also a type of neural network that can work well on an image. In this study, the classification class used by the author consisted of four classes of disease types, which included four (4) classes of disease types, namely healthy leaves, Budug disease, Blonde disease, Perforated Leaf disease. The amount of data processed is 387 images with testing data and 310 images for validation with a total of 15 epochs. Furthermore, the image data will be used to form a model or model fitting that will be used for the testing process. The parameters used in this study to measure the success rate. In this system model, the highest accuracy and lowest loss are the 15th diepoch, which is 0.9406 with a loss of 0.2112, for the highest val_accuracy and the lowest val_loss there is the 15th diepoch, namely val_accuracy 0.9836 with a val_loss of 0.0989.
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
