Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Ridho Ghiffary Muhammad
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Prediksi Omzet Restoran Haltoy Corner menggunakan Metode Recurrent Extreme Learning Machine (RELM) Ridho Ghiffary Muhammad; Muhammad Tanzil Furqon; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 3 (2021): Maret 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Haltoy Corner Restaurant is a new restaurant in wonosobo city that is famous for its beautiful scenery. Currently, Haltoy Corner is still not able to do the management of the number of employees and the allocation of turnover well. This led to the need for a turnover prediction system for Haltoy Corner to help optimize the number of employees to be employed. Extreme Learning Machine (ELM) is one of the prediction methods that have good accuracy and relatively fast training time, but in ELM the sequence of data has no effect so it can affect the accuracy for dataset timeseries such as Haltoy Corner turnover data. ELM developed a method to overcome this with Recurrent Extreme Learning Machine (RELM), this method adds recurrent to ELM so that it is better for dataset timeseries. The flow to conduct this research starts from data normalization, data training, data testing, data denormalization and finally the calculation of evaluation value. Based on the results of tests conducted using Haltoy Corner turnover data, an error value with Mean Absolute Precentage Error (MAPE) was obtained at the most optimal of 31.677%, with the number of eight features, the number of hidden neurons three, the number of context neurons five, and the comparison of the number of training data with data testing of 90%:10%.
Co-Authors Adinugroho, Sigit Muhammad Tanzil Furqon