Implementasi Algoritma Convolutional Neural Network (CNN) Untuk Klasifikasi Kerapihan Ruangan

Mahameru, Irfan Andito
Ravly Dwi Septian
Dwi Rolliawati
Mujib Ridwan

Jurnal Komputer Teknologi Informasi Sistem Komputer (JUKTISI)
Vol. 4 No. 2 (2025): September 2025

This study implements a Convolutional NeurallNetwork (CNN) to classify room images into two categories: messy and clean. The model utilizes VGG16 as a feature extractor, followed by fully connected layers and a sigmoid activation function in the output layer. This approach is simpler compared to the softmax scheme, which is commonly used for multi-class classification. The dataset was augmented to enhance the model's generalization. Evaluation results show a validation accuracy of 98,63%, indicating the effectiveness of the model in binary classification tasks