Implementation Of Convolutional Neural Network (Cnn) Based On Mobile Application For Rice Quality Determination
The purpose of this study is to design and build a CNN deep learning program modeling for a mobile application for rice quality classification and analyze the performance of a mobile application-based classification program as a means of halal information in real time. The method applied is an exper...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Khairun University, Faculty of Engineering, Department of Electrical Engineering
2025-01-01
|
| Series: | Protek: Jurnal Ilmiah Teknik Elektro |
| Subjects: | |
| Online Access: | https://ejournal.unkhair.ac.id/index.php/protk/article/view/9396 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The purpose of this study is to design and build a CNN deep learning program modeling for a mobile application for rice quality classification and analyze the performance of a mobile application-based classification program as a means of halal information in real time. The method applied is an experimental method that utilizes machine learning technology by using many rice images that are used as datasets. The data of these images is classified by their shape, color and background. This image is used as a reference for the training dataset. After the CNN training model is formed, it is then set up in a web editor p5.js then an interface is created to connect to a server such as Google Cloud using FastAPI, which can be accessed using a mobile application or a web server such as Chrome. In the mobile application, create an interface to connect with the camera system and data base on the cloud server. The results of the study were obtained that CNN deep learning modeling can be used in real time. In web browser usage, the data shown is also affected by lighting. The accuracy level of the built model reached above 99.8 percent with a validation accuracy rate of 99.7 percent in the data training process. When testing, the average accuracy of the data was around 99.9 percent. This clearly proves that CNNs can be used to classify objects properly and accurately. |
|---|---|
| ISSN: | 2354-8924 2527-9572 |