OPTIMALISASI HYPERPARAMETER RANDOM FOREST MENGGUNAKAN ALGORITMA GENETIKA PADA KLASIFIKASI KANKER PARU-PARU

Dhiyaussalam, NIM.: 21206051004 (2023) OPTIMALISASI HYPERPARAMETER RANDOM FOREST MENGGUNAKAN ALGORITMA GENETIKA PADA KLASIFIKASI KANKER PARU-PARU. Masters thesis, UIN SUNAN KALIJAGA YOGYAKARTA.

Preview	Text (OPTIMALISASI HYPERPARAMETER RANDOM FOREST MENGGUNAKAN ALGORITMA GENETIKA PADA KLASIFIKASI KANKER PARU-PARU) 21206051004_BAB-I_IV-atau-V_DAFTAR-PUSTAKA.pdf - Published Version Download (2MB) | Preview
	Text (OPTIMALISASI HYPERPARAMETER RANDOM FOREST MENGGUNAKAN ALGORITMA GENETIKA PADA KLASIFIKASI KANKER PARU-PARU) 21206051004_BAB-II_sampai_SEBELUM-BAB-TERAKHIR.pdf Restricted to Registered users only Download (991kB) | Request a copy

Abstract

Lung cancer is a type of cancer with the highest death rate compared to other cancers. Cancer can be classified using histopathological methods obtained using a biopsy. Manually classifying cancer on histopathological images is intensive work and very prone to human error. Classification of cancer from histopathological images can be done with the help of a computer using computer vision and machine learning. In this study to obtain the desired model, the steps taken were data collection, feature extraction from images, feature selection, Random Forest model development, hyperparameter optimization using Genetic Algorithms, and performance evaluation of the model. The histopathological images collected were extracted for color features and texture features with the results divided into 9 RGB features and 9 HSV features for color features and texture features which were divided into 6 types of features namely dissimilarity, correlation, homogeneity, contrast, ASM, and energy which were then searched for the value of the four different angles resulting in 24 texture features. In total there are 42 features which are then selected using the correlation coefficient and the remaining 24 features will be used to build a classification model using Random Forest. The classification model that has been built is then optimized by performing hyperparameter tuning which is done automatically so that the resulting model is reliable and better than the general model. The optimized hyperparameters are n estimators, max depth, max features, and criterion. By using a Genetic Algorithm, all of these hyperparameters are set automatically to get the hyperparameter with the best model performance. The Random Forest model with hyperparameters with default values managed to get an accuracy of 98.82% and a 10-fold cross-validation value of 99.39%. While the model that has been optimized using the Genetic Algorithm with the best hyperparameter n estimators = 300, max depth = 100, max features = log2, and criterion = entropy produces an accuracy of 98.83% and a 10-fold cross-validation value of 99.50%. The Random Forest model with hyperparameters optimized using the Genetic Algorithm managed to outperform the Random Forest model with default hyperparameters.

Share this knowledge with your friends :

Actions (login required)

View Item