Application of backpropagation method for quality sorting classification system on white dragon fruit (Hylocereus undatus)

Baskara

Madjid

et al. 2022

JNTE

Pitaya is another name for dragon fruit which is currently a popular fruit, especially in Indonesia. One of the problems related to determining the quality of dragon fruit is the postharvest sorting and grading process. In general, farmers determine the grading system by measuring the weight or just looking at the size of the fruit, of course, this raises differences in grading perceptions so that it is not by SNI. This research is a development of previous research, but we changed the type of dragon fruit from white dragon fruit (Hylocereus undatus) to red dragon fruit (Hylocereus costaricensis). We also adapted the image processing and classification methods in previous studies and then compared them with other classification methods. The number of images in the training data is 216, and the number of images in the testing data is 75. The comparison of the accuracy of the three classification methods is 84% for the KNN method, 85.33% for the Naive Bayes method, and 86.67% for the Backpropagation method. So that the backpropagation method is the best classification method in classifying the quality grading of red dragon fruit. The network architecture used is 4, 8, 3 with a learning rate of 0.3 so that the training accuracy is 98.61% and the testing accuracy is 86.67%.

Section: Methodsmentioning

confidence: 99%

“…Next, we developed the implementation of the backpropagation method for the quality sorting classification system on white dragon fruit (Hylocereus undatus) in 2021. The results of the study showed that the most suitable network architecture on the backpropagation method was 5,8,5,3 with a system accuracy of 86.67% [8].…”

Section: Introductionmentioning

confidence: 99%

Comparison of Classification for Grading Red Dragon Fruit (<i>Hylocereus Costaricensis</i>)

Baskara

Madjid

et al. 2022

JNTE

“…The result of the cropping process is part of the normalization of data that represents the shape of the ARI bacteria. In addition, the cropping process aims to reduce the computational load [12]. The cropped image is an RGB color space image where the color space consists of 3 color components, namely red components, green components, and blue components.…”

Section: Preprocessing Imagesmentioning

confidence: 99%

The The Classification of Acute Respiratory Infection (ARI) Bacteria Based on K-Nearest Neighbor

Sahenda

Puspitasari

et al. 2021

LKJITI

Acute Respiratory Infection (ARI) is an infectious disease. One of the performance indicators of infectious disease control and handling programs is disease discovery. However, the problem that often occurs is the limited number of medical analysts, the number of patients, and the experience of medical analysts in identifying bacterial processes so that the examination is relatively longer. Based on these problems, an automatic and accurate classification system of bacteria that causes Acute Respiratory Infection (ARI) was created. The research process is preprocessing images (color conversion and contrast stretching), segmentation, feature extraction, and KNN classification. The parameters used are bacterial count, area, perimeter, and shape factor. The best training data and test data comparison is 90%: 10% of 480 data. The KNN classification method is very good for classifying bacteria. The highest level of accuracy is 91.67%, precision is 92.4%, and recall is 91.7% with three variations of K values, namely K = 3, K = 5, and K = 7.

“…Supervised learning is a learning model in which the data already has a target, if the classification results do not match the predetermined target, the weight will be updated in each hidden layer. Updates the weights are expected to improve the accuracy of the system [11], [14]. However, apart from using the backpropagation method, the researcher also made comparisons with other neural network methods, for example the Radial Basis Function Neural Network (RBFNN).…”

Section: G Classificationmentioning

confidence: 99%

Comparison of Neural Network Methods for Classification of Banana Varieties (Musa paradiasaca)

Nugroho

Madjid

et al. 2021

JRE

Every region in Indonesia has a very large diversity of banana species, but no system records information about the characteristics of banana varieties. The purpose of this research is to make an encyclopedia of banana types that can be used for learning by classifying banana varieties using banana images. This banana variety classification system uses image processing techniques and artificial neural network methods as classification methods.The varieties of bananas used are pisang merah, pisang pisang mas kirana, pisang klutuk, pisang raja and pisang cavendis. The parameters used are color features (Red, Green, and Blue) and shape features (area, perimeter, diameter, and length of fruit). The intelligent system used is the Backpropagation method and the Radial Basis Function Neural Network. The results showed that both methods were able to classify banana varieties with an accuracy rate of 98% for Backpropagation and 100% for the Radial Basis Function Neural Network.