Deteksi Ekspresi Wajah Untuk Mengukur Tingkat Kepuasan Pelanggan Dengan Menerapkan Metode Convolutional Neural Network

Wulansari, Tanti (2024) Deteksi Ekspresi Wajah Untuk Mengukur Tingkat Kepuasan Pelanggan Dengan Menerapkan Metode Convolutional Neural Network. Undergraduate thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (7kB)
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (85kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Share Alike. Download (143kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf - Submitted Version Restricted to Registered users only Download (5MB) | Request a copy

Abstract

The primary focus on enhancing customer satisfaction and service quality lies in the customer satisfaction system using Convolutional Neural Network (CNN). This method enables the real-time detection of customers facial expression to evaluate their satisfaction levels. Three types of datasets are utilized in this research to train various CNN models: primary, secondary, and mixed datasets. The results of multiple trials conducted reveal that the CNN From the Scratch 3 model, trained on a mixed dataset divided into an 80:20 ratio for training and testing data respectively, achieves an accuracy of 90,43% for training and 90,46% for testing. User Acceptance Testing (UAT) trials of the customer facial expression detection website demonstrated a success rate of 88%, indicating a relatively high level of acceptance among users for the customer expression detection website. The time required to detect customer facial expression is 30 seconds, as directly tested in the shop

Actions (login required)

View Item