Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Building of Informatics, Technology and Science

Sistem Pendukung Keputusan Pemilihan Biji Kopi Arabika Terbaik Menggunakan Metode SMART Supiyandi Supiyandi; Chairul Rizal; Muhammad Noor Hasan Siregar; Eka Putra; Rusmin Saragih
Building of Informatics, Technology and Science (BITS) Vol 4 No 2 (2022): September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i2.2118

Abstract

Arabica coffee beans are one of the main varieties of coffee beans developed in Indonesia. In making decisions to determine quality Arabica coffee beans, an appropriate system is needed to analyze problems in solving and efficient and accurate data presentation. Therefore, a computer-based system or method is needed to facilitate the selection of the best Arabica coffee beans. This study uses the Simple Multi Attribute Rating Technique (SMART) method. The SMART method is a decision-making method to solve the problem of choosing a multi-objective choice among several criteria, so that later it will be able to produce an effective and efficient analysis. The input criteria that are the priority in selecting the best Arabica coffee beans are aroma with a weight of 25, color with a weight of 25, taste with a weight of 25, dirt content with a weight of 15, and price with a weight of 10. Of the 25 alternatives tested in this system, Gayo Avatara Natural Arabica coffee beans were the best first alternative, followed by Aceh Gayo Wet Hull, Java Ijen Natural, Java Ijen Honey, and Kintamani Natural. This decision support system for selecting the best Arabica coffee beans provides speed, accuracy, and data accuracy in selecting the best Arabica coffee beans which will be used by coffee lovers to provide coffee with a delicious taste. So the results of the decision from 25 types of Arabica coffee, there are 11 types of Arabica coffee with a rating of "Very Good", 10 types of Arabica coffee with a rating of "Good", and 4 types of Arabica coffee with a rating of "Quite Good".
Penerapan Pemilihan Model Arsitektur Terbaik pada Neural Network pada Prediksi Jumlah Siswa SD di Kecamatan Siantar Barat Ramadhani, Cerah Fitri; Siregar, Muhammad Noor Hasan; Rahadjeng, Indra Riyana; Windarto, Agus Perdana
Building of Informatics, Technology and Science (BITS) Vol 4 No 3 (2022): December 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i3.2676

Abstract

The use of the artificial neural network (Backpropagation) method can be used in determining the best architectural model for predicting the number of elementary school students in the Siantar Barat District. The dataset used is a dataset on the number of Elementary School (SD) students in West Siantar District, Pematang Siantar City in 2017-2021 obtained from the Website of the Ministry of Education, Culture, Research and Technology of the Republic of Indonesia (https://dapo.kemdikbud.go.id /pd/3/076303). The dataset is then divided into 2 parts, namely the training and testing dataset. In the training datasets, attribute X1 is a dataset for 2017, X2 is the dataset for 2018, X3 is a dataset for 2019, and attribute Y (target) is the dataset for 2020. For the test datasets, attribute X1 is the dataset for 2018, attribute X2 is a dataset for 2019, attribute X3 is a dataset for 2020 and attribute Y (target) is a dataset for 2021. The results obtained from the analysis of the Backpropagation and virtualization methods using the MatLab application can be generated with a valid dataset and produce an accuracy rate of 87.5% in architectural models 3-9-1. So that the Backpropagation method can be used as a prediction method that makes it very easy to find predictions.