Article Per Year (5 Year)
p-Index From 2021 - 2026
1.203
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah FIFO Building of Informatics, Technology and Science TEKNOKOM : Jurnal Teknologi dan Rekayasa Sistem Komputer JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) JIKA (Jurnal Informatika) Insearch: Information System Research Journal
Riyanto, Umbar
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Social Sciences Other

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search

 1 
ANALISIS PERBANDINGAN ALGORITMA NAIVE BAYES DAN SUPPORT VECTOR MACHINE DALAM MENGKLASIFIKASIKAN JUMLAH PEMBACA ARTIKEL ONLINE Riyanto, Umbar
Jurnal Informatika Vol 2, No 2 (2018): JIKA (Jurnal Informatika)
Publisher : University of Muhammadiyah Tangerang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (545.817 KB) | DOI: 10.31000/.v2i2.1521

Abstract

PT. Linktone Indonesia merupakan salah satu perusahaan yang bergerak dalam bidang portal berita online. Semakin banyaknya portal berita online di Indonesia, para penulis yang ada di PT. Linktone Indonesia harus dapat bersaing, agar artikel yang mereka publish mendapatkan jumlah pembaca yang maksimal. Jumlah pembaca pada sebuah artikel tidaklah menentu, dan sulit untuk diprediksi. Banyaknya jumlah artikel yang dimiliki, maka dapat dilakukan penelitian data mining untuk mengklasifikasi jumlah pembaca artikel. Terdapat beberapa algoritma dalam teknik klasifikasi, akan tetapi tidak semua algoritma memiliki kinerja dan tingkat keakuratan yang baik dalam mengklasifikasi jumlah pembaca artikel. Penelitian ini membandingkan dua algoritma klasifikasi antara Naive Bayes,  Support Vector Machine dan Bagging pada tiap algoritma. Peneliti membagi menjadi 5 dataset dan menggunakan tools WEKA dengan tools options K-Folds Cross Validation dan Confussion Matrix. Hasil penelitian ini, dengan jumlah dataset 7111 record. Bagging kurang memperbaiki hasil klasifikasi dengan jumlah dataset yang besar dan memerlukan waktu pembuatan model yang sangat lama dengan klasifikasi Support Vector Machine. Sementara itu Naive Bayes dalam segi waktu pembuatan model mendapatkan waktu yang paling cepat.
Klasifikasi Citra Jenis Tanaman Jamur Layak Konsumsi Menggunakan Algoritma Multiclass Support Vector Machine Chusna, Nuke L.; Shalahudin, Mohammad Imam; Riyanto, Umbar; Alexander, Allan Desi
Building of Informatics, Technology and Science (BITS) Vol 4 No 1 (2022): June 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (483.267 KB) | DOI: 10.47065/bits.v4i1.1624

Abstract

Mushrooms are plants that have high nutritional content and have various benefits for the health of the human body. However, not everyone knows the types of mushrooms that are suitable for consumption. The types of mushrooms have their own characteristics when viewed from the image. For this reason, a system is needed by utilizing digital image processing to classify types of mushrooms suitable for consumption, so that people can find out which types of mushrooms are suitable for consumption. This research is to classify types of mushrooms suitable for consumption using the Multiclass SVM algorithm with first-order feature extraction, which performs feature extraction based on the characteristics of the image histogram. The result of feature extraction is used as input for classification in Multiclass SVM. Multiclass SVM can map data points to dimensionless space to obtain hyperplane linear separation between each class. The developed method is implemented in Matlab, in order to produce a system in the form of a GUI so that it can be used by general users easily. Based on the test results, the average accuracy is 83%.
Sistem Pendukung Keputusan Pemilihan Platform Investasi P2P Lending Menggunakan Metode Complex Proportional Assessment (COPRAS) Bagir, Muhammad; Riyanto, Umbar; Nuraini, Rini; Kustiawan, Dedi
Building of Informatics, Technology and Science (BITS) Vol 4 No 4 (2023): March 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i4.3246

Abstract

Through technological developments, many fintech P2P lending have emerged which are competing to offer convenience in transactions and offer fast processes. To determine a P2P lending platform as a place to invest, one must know in advance about the company profile or the application and programs offered as a whole. This of course will take a long time to select a P2P lending platform. If you choose an inappropriate P2P lending platform, it will result in losses. The purpose of this research is to build a Decision Support System (DSS) for choosing a P2P lending platform by implementing the Complex Proportional Assessment (COPRAS) approach in order to get the right decision and not take a long time. The COPRAS approach has the ability to produce the best alternative which is limited to alternative analysis through alternative assumptions by providing utility judgment so that the attributes of each alternative are arranged based on intervals. Based on the results of the case studies conducted, the highest utility score was Danamas Lender with a score of 100, then followed by Alami Funding Sharia with a score of 99.2338, Accelerant with a score of 89.8827 and Amartha Microfinance with a score of 83.4988. In addition, based on the results of black box testing, it shows that the software can run as it should.
Penerapan Pendekatan Composite Performance Index Pada Sistem Pendukung Keputusan Pemilihan Supplier Fatmayati, Fryda; Alamsyah, Dedy; Riyanto, Umbar; Dartono, Dartono
Insearch: Information System Research Journal Vol 4, No 02 (2024): Insearch (Information System Research) Journal
Publisher : Fakultas Sains dan Teknologi UIN Imam Bonjol Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15548/isrj.v4i02.9484

Abstract

Pemilihan supplier yang tepat menjadi faktor kunci dalam keberhasilan operasional perusahaan. Supplier yang berkualitas berperan penting dalam menjaga kontinuitas produksi dan kualitas produk akhir. Namun, pemilihan supplier secara manual seringkali menghadapi kendala, seperti proses yang memakan waktu, kesulitan dalam mengintegrasikan berbagai kriteria penilaian, serta potensi kesalahan atau bias dalam penilaian subjektif. Tujuannya penelitian ini dilakukan yakni guna mengembangkan Sistem Pendukung Keputusan (SPK) berbasis pendekatan Composite Performance Index (CPI) yang dapat membantu manajemen dalam mengevaluasi dan memilih supplier dengan lebih tepat. Metode CPI memiliki kelebihan dalam mengintegrasikan berbagai aspek kinerja menjadi satu indeks komposit yang mudah dipahami dan digunakan untuk perbandingan. Studi kasus pemilihan supplier menunjukkan bahwa PT Dikatama Putra Perkasa (A2) memperoleh skor indeks gabungan tertinggi sebesar 116,67. Hasil perhitungan dari SPK yang dikembangkan konsisten dengan hasil hitung secara manual, memperlihatkan perolehan yang sama dan valid. Uji dengan black box testing juga mengonfirmasi bahwa sistem beroperasi sesuai dengan yang diharapkan pada seluruh fitur utama yang diuji.
Klasifikasi Risiko Diabetes Mellitus Menggunakan K-Nearest Neighbors dengan Peningkatan Performa Melalui Teknik Oversampling ADASYN Bagir, Muhammad; Mayatopani, Hendra; Riyanto, Umbar; Alamsyah, Dedy
Journal of Information System Research (JOSH) Vol 6 No 4 (2025): Juli 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i4.7237

Abstract

Diabetes mellitus is a chronic metabolic disease with a continuously increasing global prevalence. Early detection of diabetes risk is crucial to reduce long-term health complications and the associated healthcare costs. However, a major challenge in applying machine learning models to medical data is the issue of class imbalance, which can lead to model bias toward the majority class. This study aims to develop a diabetes risk classification model by integrating the K-Nearest Neighbors (KNN) algorithm with the Adaptive Synthetic Sampling (ADASYN) technique to address the class imbalance problem. The dataset used was obtained from the Kaggle platform, containing 2,000 patient samples with nine predictive features. Data preprocessing was performed through missing value imputation, outlier handling using winsorizing, and feature normalization using StandardScaler. ADASYN was applied to generate adaptive synthetic samples for the minority class, and the KNN model was trained and evaluated using confusion matrix, precision, recall, F1-Score, accuracy, and ROC-AUC metrics. The results indicate that the implementation of ADASYN improved the ROC-AUC Score by 5.48% (from 91.34% to 96.82%) and the overall accuracy by 2.50% (from 81.50% to 84.00%). The F1-Score for the Diabetes class also increased by 0.40%. The integration of KNN and ADASYN has proven effective in enhancing model performance for detecting high-risk diabetes patients and improving sensitivity toward the minority class.
SISTEM PENDUKUNG KEPUTUSAN PEMILIHAN VENDOR IT MAINTENANCE MENGGUNAKAN PENDEKATAN WASPAS Fatmayati, Fryda; Riyanto, Umbar; Rahmadian, Jefri; Pahlevi, Omar
TEKNOKOM Vol. 7 No. 1 (2024): TEKNOKOM
Publisher : Department of Computer Engineering, Universitas Wiralodra

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31943/teknokom.v7i1.199

Abstract

IT maintenance is important for a company because these activities are carried out to maintain and support the optimal performance of a company's IT systems and infrastructure. Generally, selecting an IT maintenance vendor is done by collecting vendor data and then evaluating it based on the desired criteria. This, of course, results in the time it takes to make a choice and makes it difficult to determine the best option. If you choose the wrong IT maintenance vendor, it will result in disrupting the company's stability. This research was conducted with the aim of developing a decision support system that can be used to determine the IT maintenance vendor that best suits their needs and preferences using the WASPAS (Weighted Aggregated Sum Product Assessment) approach. This method is used to determine the best option through weighted addition and multiplication, producing a final value that reflects the extent to which each option can meet the specified criteria. From the existing case studies, the best alternative was obtained, namely: Microsis (A4) got a preference value of 0.8769, followed by ICT Canopy (A1) with a preference value of 0.8613, Pillar IT (A2) with a preference value of 0.8408, Indocom Niaga (A5) with a preference value of 0.8180, and Sasana Digital (A3) with a preference value of 0.7389. The usability test carried out received a score of 88%, which indicates that the system is suitable for use.
Klasifikasi Kepribadian Introvert dan Extrovert Menggunakan Random Forest, Naïve Bayes, dan K-Nearest Neighbor Erkamim, Moh.; Nurhayati, Nurhayati; Heriyani, Nofitri; Riyanto, Umbar
Jurnal Ilmiah FIFO Vol 17, No 2 (2025)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/fifo.2025.v17i2.009

Abstract

Kepribadian merupakan faktor penting yang memengaruhi cara individu berpikir, berperilaku, dan berinteraksi dalam kehidupan sosial. Salah satu dimensi utama dalam model Big Five Personality Traits adalah ekstraversi, yang merepresentasikan kecenderungan seseorang untuk bersosialisasi dan berinteraksi aktif dengan lingkungannya. Penelitian ini bertujuan mengembangkan model klasifikasi kepribadian introvert dan extrovert menggunakan tiga algoritma machine learning, yaitu Random Forest, Naïve Bayes, dan K-Nearest Neighbor (KNN). Dataset yang digunakan berjumlah 2.900 entri dengan delapan atribut perilaku sosial seperti waktu yang dihabiskan sendirian, frekuensi menghadiri acara sosial, ukuran lingkaran pertemanan, dan tingkat aktivitas di media sosial. Proses penelitian meliputi pembersihan data, transformasi variabel kategorikal, pembagian data secara stratifikasi (80:20), pembangunan model, serta evaluasi menggunakan metrik akurasi, precision, recall, F1-score, dan ROC-AUC. Hasil pengujian menunjukkan bahwa model KNN dengan k = 11 memberikan performa terbaik dengan akurasi 92,59% dan nilai ROC-AUC 0,9494, diikuti oleh Naïve Bayes dengan akurasi 92,24% (ROC-AUC 0,8988) dan Random Forest dengan akurasi 90,86% (ROC-AUC 0,9480). Kontribusi utama penelitian ini adalah memberikan analisis komparatif terhadap tiga algoritma yang mewakili paradigma pembelajaran berbeda, yaitu probabilistik, berbasis jarak, dan ensemble pohon keputusan, dalam konteks klasifikasi kepribadian berdasarkan dimensi ekstraversi. Hasil penelitian ini dapat menjadi dasar bagi pengembangan sistem prediksi kepribadian berbasis perilaku sosial yang efisien dan adaptif.
Co-Authors Alamsyah, Dedy Alexander, Allan D Chusna, Nuke L. Dartono, Dartono Fryda Fatmayati Heriyani, Nofitri Kustiawan, Dedi Mayatopani, Hendra Moh. Erkamim Muhammad Bagir Nurhayati Nurhayati Omar Pahlevi Rahmadian, Jefri Rini Nuraini, Rini Shalahudin, Mohammad Imam