KLASIFIKASI RAS MANUSIA MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK BERBASIS TELEGRAM BOT

Arya Danu Setyadi

JURNAL TEKNIK INFORMATIKA DAN SISTEM INFORMASI
Vol 10 No 2 (2023): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)

There are four major races in human populations: Caucasian, Mongoloid, Negroid, and Australoid. The lack of knowledge about human races has become a problem in recent times. Therefore, this research was conducted to increase public knowledge about the different races found in humans. The research used Convolutional Neural Network (CNN) and a 50-layer architecture called ResNet-50, also known as a Residual Network, classification model are using Chat Bot feature in Telegram App.. The trained CNN model was tested with a test dataset and resulted in an accuracy score of 84%. The Recall score was 84%, and the Precision score was 85%.