Perbandingan Akurasi CNN dan SVM Untuk Deteksi dan Klasifikasi Aktivitas Merokok

Galih Purbo Danu Kisowo

Router : Jurnal Teknik Informatika dan Terapan
Vol. 2 No. 3 (2024): September : Router : Jurnal Teknik Informatika dan Terapan

This study compares the performance of Convolutional Neural Network (CNN) and Support Vector Machine (SVM) algorithms in detecting and classifying smoking activities. Using an image dataset containing two classes, Smoking and Non-Smoking, this research implements transfer learning using the InceptionResNetV2 model for CNN and the SVM method. Evaluation results show that CNN has higher accuracy compared to SVM in detecting smoking activities. This research contributes to the development of surveillance systems for smoke-free areas in smart cities.