PENERAPAN TUNING HYPERPARAMETER RANDOMSEARCHCV DALAM PROSES KLASIFIKASI PENYAKIT PNEUMONIA
| dc.contributor.author | Reynaldi, Rahmat | |
| dc.date.accessioned | 2025-07-17 | |
| dc.date.available | 2025-07-17 | |
| dc.date.issued | 2024 | |
| dc.identifier.uri | https://jurnal.compartdigital.com/index.php/judis/article/view/38 | |
| dc.description.abstract | Convolutional Neural Network (CNN) is a deep learning method that has been widely applied for image data classification. In the context of using CNN for pneumonia disease classification, hyperparameter settings such as the number of layers, number of filters, and filter size greatly influence model performance. Determining the right combination of model and hyperparameters is often a challenge. Manually selecting optimal parameters for a CNN model can be a very complicated and time-consuming task. Therefore, it is important to perform hyperparameter tuning efficiently to find the most suitable parameter combination so as to produce an accurate CNN model. The hyperparameter tuning process for the CNN method in this research uses RandomSearcCV. The test results of the custom CNN model after being tested using testing data obtained an accuracy score of 81%. Meanwhile, the CNN model with hyperparameter tuning achieved an accuracy score of 90%. This proves that applying hyperparameter tuning to the CNN model using RandomSearchCV can increase the accuracy of the CNN model in the process of classifying pneumonia. Keyword : Hyperparameter, CNN, RandomSearchCV, Pneumonia | en_US |
| dc.language.iso | en | en_US |
| dc.publisher | Universitas Harapan Medan | en_US |
| dc.subject | TUNING HYPERPARAMETER RANDOMSEARCHCV | en_US |
| dc.title | PENERAPAN TUNING HYPERPARAMETER RANDOMSEARCHCV DALAM PROSES KLASIFIKASI PENYAKIT PNEUMONIA | en_US |
| dc.type | Skripsi | en_US |
File In This Item
This item appears in the following Collection(s)
Skripsi [1508]Show Simple Item Record