Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jupiter: Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika Buffer Informatika
Augie Sugiarto Nunka
Unknown Affiliation
Aerospace Engineering Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Metode Regresi Linier Berganda Untuk Prediksi Pemakaian Bbm Pt. Kalonica Bara Kusuma Augie Sugiarto Nunka; Wawan Joko Pranoto
Jupiter: Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika Vol. 2 No. 1 (2024): Januari : Publikasi Ilmu Keteknikan Industri, Teknik Elektro dan Informatika
Publisher : Asosiasi Riset Ilmu Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/jupiter.v2i1.56

Abstract

PT. Kalonika Bara Kusuma is a company operating in the mining sector located in the city of Samarinda, East Kalimantan province. To achieve maximum profits, PT. Kalonika Bara Kusuma adds or subtracts units according to the amount of turnover obtained in the previous month. However, after being evaluated, it turned out that this method was not effective. Because you only see at a glance the fluctuations in historical data. Sometimes when you have reduced units, it turns out that demand in the following month actually increases. This results in less than optimal profits because they cannot serve existing customer requests. Vice versa. This is what causes PT. Kalonika Bara Kusuma experienced difficulty in making a decision to add or subtract units. From this problem, the author created an application that can predict the amount of turnover in the next month and provide recommendations for deciding which camera units should be increased or decreased in number. To predict the amount of turnover using the Multiple Linear Regression method. After obtaining the predicted results for the amount of turnover, a test was carried out using the Mean Absolute Percentage (MAPE) with a result of 200%, which means that the Multiple Linear Regression method is not suitable to be used to predict the amount of turnover in the next period. Production forecasting is a form of decision making that is used as a basis in many manufacturing and service industries. Therefore, companies that are able to produce products on time and in the right quantities are companies that are able to survive the competition. This demand forecasting is used to forecast demand for products that are independent (not dependent), such as forecasting finished products. The multiple linear regression method is an analytical technique that tries to explain the relationship between two or more variables, especially between variables that contain cause and effect, called regression analysis. So in relation to the description above, this research aims to determine production forecasting using the multiple linear regression method at PT. Kalonica Bara Kusuma.The mining industry is a series of activities that have a long period of time and costs a lot of money, a series of industrial activities, namely mining activities which include digging, loading and hauling to obtain optimal profits from activities. One of the mining industries needs to be a study of operational costs for transportation equipment
Analisis Sentimen Ulasan Pengguna Aplikasi Game Sky Childern Of The Light Menggunakan Metode Algoritma Naive Bayes (Studi Kasus Tingkat Kepuasan Pengguna) Hafidz Syauqie; Augie Sugiarto Nunka; Mu. Aldi Rahmad Fahrozi
Merkurius : Jurnal Riset Sistem Informasi dan Teknik Informatika Vol. 2 No. 4 (2024): Juli: Merkurius: Jurnal Riset Sistem Informasi dan Teknik Informatika
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/merkurius.v2i4.140

Abstract

This research use the Naive Bayes algorithm to classification of user reviews of the Sky Childern Of The Light application from the Google Play Store. The Sky Childern Of The Light application is a popular online game, because it offers a unique and immersive playing experience. This method was chosen because of its simplicity, speed, ease of interpretation, and suitability for high-dimensional data. The advantages of Naive Bayes are the accuracy and efficiency of calculations, fast results and presentation. The data collected was 1500 data with a classification ratio of 8:2 with an accuracy value of 87% using the Naïve Bayes algorithm. This method is very good at analyzing the sentiment of the Sky Children Of The Light application.
Optimasi Seleksi Fitur BERT Menggunakan GA Pada Metode KNN Dalam Menentukan Opini Publik Terkait Keberlanjutan IKN Augie Sugiarto Nunka; Yulianto, Fendy; Rudiman
Buffer Informatika Vol. 12 No. 1 (2026): Buffer Informatika
Publisher : Department of Informatics Engineering, Faculty of Computer Science, University of Kuningan, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/buffer.v12i1.482

Abstract

Penelitian ini berfokus pada optimasi klasifikasi opini publik terkait keberlanjutan Ibu Kota Nusantara (IKN) yang beragam di media sosial. Tujuan utama dari penelitian ini adalah untuk meningkatkan performa klasifikasi sentimen dengan mengintegrasikan model Bidirectional Encoder Representations from Transformers (BERT) untuk ekstraksi fitur, Algoritma Genetika (Genetic Algorithm) untuk seleksi fitur, dan K-Nearest Neighbors (KNN) sebagai metode klasifikasi. Metode penelitian diawali dengan pengumpulan 1.274 data komentar dari YouTube, diikuti oleh pelabelan pakar, pra-pemrosesan data, dan ekstraksi fitur menggunakan IndoBERT yang menghasilkan 768 fitur. Algoritma Genetika kemudian diterapkan untuk menyeleksi fitur-fitur paling relevan. Hasil penelitian menunjukkan bahwa model tanpa seleksi fitur mencapai akurasi sebesar 76,56%. Sementara itu, model yang menggunakan seleksi fitur Algoritma Genetika berhasil mereduksi jumlah fitur menjadi 371 dan memperoleh akurasi sebesar 75,00%. Meskipun terjadi sedikit penurunan akurasi sebesar 1,56%, seleksi fitur terbukti mampu meningkatkan efisiensi komputasi secara signifikan dengan mengurangi dimensi fitur hingga 51,7% tanpa mengorbankan kinerja secara drastis, meskipun kedua model gagal dalam mengklasifikasikan kelas netral secara efektif.
Co-Authors Fendy Yulianto Hafidz Syauqie Mu. Aldi Rahmad Fahrozi Rudiman Wawan Joko Pranoto