JuTISI (Jurnal Teknik Informatika dan Sistem Informasi)
Vol 8 No 3 (2022): JuTISI

Model Convolutional Neural Network untuk Mengukur Kepuasan Pelanggan Berdasarkan Ekspresi Wajah

Daru Prasetyawan (UIN Sunan Kalijaga Yogyakarta)
Rahmadhan Gatra (UIN Sunan Kalijaga Yogyakarta)



Article Info

Publish Date
21 Dec 2022

Abstract

Customer satisfaction shows how well the product or service of an organization meets customer expectations. Customers' facial expressions can show their satisfaction with the services provided. Convolution Neural Network (CNN) is a type of neural network algorithm that can be used to recognize an object in an image. CNN utilizes the convolution process to determine and distinguish an object in the image from other objects such as to recognize various facial expressions. This study aims to measure customer satisfaction by utilizing the CNN model by recognizing any changes in facial expressions. From the results of the CNN model training, an accuracy of 90.57% was obtained. Furthermore, the formed model is implemented into a web-based system that records facial expressions and performs a classification (satisfied or dissatisfied) on any detected facial changes. The most dominant expression is the result of measuring customer satisfaction.

Copyrights © 2022






Journal Info

Abbrev

jutisi

Publisher

Subject

Computer Science & IT

Description

Paper topics that can be included in JuTISI are as follows, but are not limited to: • Artificial Intelligence • Business Intelligence • Cloud & Grid Computing • Computer Networking & Security • Data Analytics • Datawarehouse & Datamining • Decision Support System • E-Systems (E-Gov, ...