Article Per Year (5 Year)
p-Index From 2021 - 2026
4.309
P-Index
This Author published in this journals
All Journal Jurnal Online Mahasiswa (JOM) Bidang Ilmu Sosial dan Ilmu Politik Jurnal Pseudocode Jurnal Informatika dan Teknik Elektro Terapan Jurnal Sistem Informasi dan Bisnis Cerdas Sistemasi: Jurnal Sistem Informasi RABIT: Jurnal Teknologi dan Sistem Informasi Univrab Jurnal Eksplora Informatika Jurnal Nasional Komputasi dan Teknologi Informasi Abdimas Umtas : Jurnal Pengabdian kepada Masyarakat Technologia: Jurnal Ilmiah Jurnal Teknologi Dan Sistem Informasi Bisnis Jurnal Informatika dan Rekayasa Perangkat Lunak Abdimas Galuh: Jurnal Pengabdian Kepada Masyarakat Jurnal Pengabdian Masyarakat Indonesia Jurnal Ilmiah Teknologi Informasi dan Robotika Jurnal Abdi Masyarakat Indonesia International Journal Of Computer, Network Security and Information System (IJCONSIST) Jurnal Pengabdian Mitra Masyarakat (JPMM) Journal of Information System and Artificial Intelligence Journal Research of Social Science, Economics, and Management TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Intechno Journal : Information Technology Journal Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi
Irfan Pratama
Universitas Mercu Buana Yogyakarta
Religion Aerospace Engineering Agriculture, Biological Sciences & Forestry Arts Humanities Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Medicine & Pharmacology Neuroscience Nursing Public Health Social Sciences Transportation Other

Published : 30 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 30 Documents
Search

 1   2   3 
Implementasi Metode Certainty Factor dan Bayesian dalam Sistem Pakar Diagnosa Inkontinensia Urine Lansia Putri Taqwa Prasetyaningrum; Mutaqin Akbar; Agus Sidiq Purnomo; Irfan Pratama; Imam Suharjo
TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akuntansi Vol 4 No 2(SEMNASTIK) (2024): TAMIKA: Jurnal Tugas Akhir Manajemen Informatika & Komputerisasi Akunt
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/tamika.Vol4No2(SEMNASTIK).pp191-199

Abstract

Urinary incontinence is a medical condition commonly experienced by the elderly, requiring prompt and accurate diagnosis for effective treatment. This study aims to develop and compare the performance of two methods in expert systems for diagnosing urinary incontinence in the elderly: Certainty Factor and Bayesian. The developed expert system is web-based and utilizes a symptom dataset collected from the Santa Monika Boro Nursing Home. The findings reveal that the Certainty Factor method excels in diagnostic processing speed, while the Bayesian method offers higher accuracy in diagnostic predictions. This comparison provides valuable insights into selecting appropriate approaches for expert system applications in medical settings.
COMPARISON OF SUPPORT VECTOR MACHINE RADIAL BASE AND LINEAR KERNEL FUNCTIONS FOR MOBILE BANKING CUSTOMER SATISFACTION ANALYSIS Putri Taqwa Prasetyaningrum; Nurul Tiara Kadir; Albert Yakobus Chandra; Irfan Pratama
IJCONSIST JOURNALS Vol 4 No 1 (2022): September
Publisher : International Journal of Computer, Network Security and Information System

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33005/ijconsist.v4i1.75

Abstract

Banking services using mobile banking applications, including Indonesian state bank (called BRI). A study on feedback regarding BRI services based on mobile applications was done. In order to compete with other banks, that is used to enhance and modernize the quality of BRI services provided to clients. Based on phenomena that occur in these situations. This study aims to classify comments from users of the BRI Mobile Banking Application on Google Play services into positive and negative comment sentiments. In this study, the Support Vector Machine (SVM) technique is utilized to determine between positive or negative reviews. The sentiment analysis of BRI google play data was carried out by comparing the Radial Basis Function (RBF) kernel function and the Linear kernel. As well as the experiment of adding feature selection, parameters, and n-grams for a period of two years, from January 1st,, 2017 to December 31st, 2018. The results of the study using the k-fold cross-validation test, the precision value of the SVM kernel linear is 90.80 percent and the SVM kernel RBF is 90.15 percent. In the RBF kernel, there are 1,816 positive classes and 1,455 negative classes. While the Linear kernel obtained a positive class of 1,734 and a negative class of 1,637.
PREDIKSI JUMLAH KEDATANGAN WISATAWAN MANCANEGARA DI INDONESIA BERDASARKAN PINTU MASUK KEDATANGAN UDARA: PREDICTION OF THE NUMBER OF ARRIVALS OF FOREIGN TOURISTS IN INDONESIA BASED ON AIR ARRIVAL ENTRANCES Arya Prayuda; Irfan Pratama
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 9 No 2 (2024): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v9i2.4787

Abstract

Indonesia has diversity and natural wealth that attracts tourism in Indonesia. Tourism is one of the industries that provides the highest foreign exchange for the country because it has a positive impact. However, the existence of COVID-19 has resulted in a decrease in the number of visits due to restrictions on foreign tourists. From January to November 2021, there was a drastic decrease of 61.82% in the number of foreign tourist visits compared to the same period in 2020. In addition to COVID-19, as well as support in building facilities that support the increase in the number of foreign tourists. From these conditions, predictions are needed that are used as a basis for planning and helping decision making. The purpose of this study is to develop a more accurate prediction model in similar studies using the same data in predicting foreign tourist arrivals in Indonesia through air entrances using the XGBoost, Random Forest, and Catboost methods by focusing on the accuracy evaluation results metrics RMSE, MAE, and MAPE and making predictions for the next 12 months. The dataset used is taken from the Central Statistics Agency (BPS), namely data on foreign tourist arrivals based on the arrival entrance in the period January 2017 to November 2021. The data used are time series and non-stationary. From the research results, it can be seen based on the accuracy evaluation results that the XGBoost model of this study gets better accuracy evaluation results than the other two models by getting the results of the RMSE accuracy evaluation value of 671935.2, MAE 648139.1, and MAPE 20985.35. The XGBoost model is better with a smaller accuracy error value than the Random Forest model, Catboost, and similar research using the ARIMA method with an RMSE value of 779670.7, MAE 749030.4, and MAPE 23196.45.
PENANGANAN MISSING VALUES DAN PREDIKSI DATA TIMBUNAN SAMPAH BERBASIS MACHINE LEARNING: HANDLING MISSING VALUES AND PREDICTION OF WASTE PILE DATA BASED ON MACHINE LEARNING Anisa Widianti; Irfan Pratama
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 9 No 2 (2024): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v9i2.4789

Abstract

The issue of increasing waste due to the growing population and human activities presents a serious challenge in waste management in Central Java. One of the main obstacles in waste prediction research is the prevalence of missing data, which can reduce the accuracy of predictive models. This study employs three methods to handle missing values: Mean Imputation, Interpolation, and KNN Imputer. Once the missing values are filled using these methods, the next step is to calculate the prediction values. The study utilizes three predictive models: Random Forest, Gradient Boosting, and KNN. The results indicate that with Mean Imputation, the Random Forest model shows the best performance with an RMSE of 0.349. When using Interpolation for missing values, the Gradient Boosting model becomes the best choice with an RMSE of 0.543. Meanwhile, with KNN Imputer, the Gradient Boosting model again performs the best with an RMSE of 0.188. Based on this research, the most effective approach is using KNN Imputer for handling missing values in conjunction with the Gradient Boosting model. This combination provides the lowest RMSE for similar datasets.
Penerapan Algoritma Latent Dirichlet Allocation (LDA) untuk Pemodelan Topik pada Komentar YouTube tentang KaburAjaDulu Faizah Tri Rezeki; Irfan Pratama
Edutik : Jurnal Pendidikan Teknologi Informasi dan Komunikasi Vol. 6 No. 3 (2026): EduTIK : Juni 2026
Publisher : Jurusan PTIK Universitas Negeri Manado

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67142/edutik.v6i3.453

Abstract

ABSTRAK  Fenomena ‘KaburAjaDulu’ memicu perdebatan mengenai cinta terhadap tanah air dan hilangnya optimisme masyarakat terhadap masa depan di Indonesia. Tren ini menunjukan perubahan pola pikir kritis untuk memperbaiki kualitas hidup yang lebih baik. Untuk menganalisis keresahan tersebut, penelitian ini bertujuan memetakan topik pada komentar YouTube menggunakan algoritma Latent Dirichlet Allocation (LDA) dengan membandingkan model Unigram dan Bigram. Tahapan penelitian meliputi preprocessing seperti case folding & cleansing, stopword removal, normalization, hingga stemming, kemudian dilanjutkan dengan evaluasi kualitas topik berdasarkan nilai Coherence serta visualisasi menggunakan pyLDAvis guna meminimalisir tumpang tindih antartopik. Hasil penelitian adalah LDA mampu memetakan 6 topik utama. Pendekatan Bigram terbukti lebih optimal dibandingkan Unigram. Distribusi topik didominasi oleh wacana Kerja Luar Negeri (23%), yang dipicu langsung oleh tekanan Beban Biaya Hidup (21%) dan Krisis Lapangan Kerja (18%). Selain faktor finansial, penelitian ini berhasil mengungkap kritikan masyarakat yaitu Kritik Pejabat Korup (15%), Dilema Nasionalisme (12%), serta Polemik Pindah Negara (12%). Kesimpulannya, pemodelan Bigram mampu memetakan komentar secara tajam, sekaligus membuktikan bahwa keinginan migrasi dipicu oleh faktor ekonomi dan krisis kepercayaan terhadap pemerintah. ABSTRACT  The “KaburAjaDulu” phenomenon has sparked a debate about patriotism and the public’s loss of optimism regarding Indonesia’s future. This trend reflects a shift in critical thinking aimed at improving the quality of life. To analyze these concerns, this study aims to map topics in YouTube comments using the Latent Dirichlet Allocation (LDA) algorithm by comparing the Unigram and Bigram models. The research stages include preprocessing such as case folding & cleansing, stopword removal, normalization, and stemming, followed by an evaluation of topic quality based on Coherence scores and visualization using pyLDAvis to minimize overlap between topics. The results show that LDA successfully identified 6 main topics. The Bigram approach proved more effective than the Unigram approach. The topic distribution was dominated by the “Kerja Luar Negeri” discourse (23%), directly driven by the pressures of the “Beban Biaya Hidup” (21%) and the “Krisis Lapangan Kerja” (18%). In addition to financial factors, this study successfully uncovered public criticism, namely “Kritik Pejabat Korup” (15%), “Dilema Nasionalisme” (12%), and “Polemik Pindah Negara” (12%). In conclusion, the Bigram model is capable of mapping comments with precision, while also proving that the desire to migrate is triggered by economic factors and a crisis of confidence in the government.
Pengembangan Website Galeri Produk UMKM sebagai Upaya Peningkatan Ekonomi Lokal di Kalurahan Bangunharjo Putry Wahyu Setyaningsih; Albert Yakobus Chandra; Irfan Pratama
Abdimas Galuh Vol 8, No 1 (2026): Maret 2026
Publisher : Universitas Galuh

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25157/ag.v8i1.22244

Abstract

Program pengabdian ini dilaksanakan untuk menjawab kebutuhan penguatan promosi UMKM di Kalurahan Bangunharjo yang belum memiliki platform digital terintegrasi. Melalui pendekatan partisipatif, tim bersama mitra melakukan analisis kebutuhan, pengumpulan konten, perancangan antarmuka, serta pengembangan website galeri produk berbasis domain bangunharjo.id. Proses pengembangan melibatkan dokumentasi produk, penyusunan profil usaha, integrasi Google Maps, serta uji coba berulang guna memastikan kesesuaian dengan kebutuhan UMKM. Hasil implementasi menunjukkan bahwa website berfungsi efektif sebagai etalase digital yang menampilkan informasi UMKM secara terstruktur, sekaligus memperkuat identitas digital melalui elemen branding BUMKal dan penerapan prinsip UI/UX modern. Dampak program meliputi peningkatan kapasitas pemasaran, literasi digital pelaku UMKM, serta kredibilitas usaha lokal. Secara keseluruhan, platform ini menjadi instrumen strategis dalam mendukung penguatan ekonomi desa. Untuk ke depan, disarankan adanya pembaruan konten berkala dan integrasi lebih lanjut dengan media sosial serta fitur pemasaran digital.
Implementasi Data Mining Menggunakan Neural Network Untuk Prediksi Penjualan (Studi Kasus: Burjo Burneo Seturan Raya) Detuer Wonda; Irfan Pratama
Journal of Information System and Artificial Intelligence Vol. 4 No. 1 (2023): Vol. 4 No. 1 (2023): Journal of Information System and Artificial Intelligence
Publisher : Universitas Mercu Buana Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26486/jisai.v4i1.162

Abstract

Abstract Burjo burneo is effort business that sells various type product food and drink with fast serve. distribution process stock product conducted after inventory in warehouse _ _ run out. With supplier Process product like this precisely often affect _ profit targeted profit. Algorithm Neural Network so one solution alternative for manager for predict to sale goods for period time next with using sales data before. Prediction process started make modeling on rapidminer with hidden parameter conditions layer 3 and learning rate 0.03, next the model already formed will continued the running process for produce score desired prediction. _ Destination from prediction this is for look for score root mean square error (RMSE) with performance best for each input data. rmse is level error results regression, meaning the more small score rmse approach digit 0, then results regression will the more accurate. Sehinnga results from study this score accurate performance error _ obtained as big as 0.025.
Sistem Informasi Peramalan Stok Barang di Toko Al Umm Menggunakan Metode Single Moving Average Moch Khoirul Muna Muna; Irfan Pratama
Journal of Information System and Artificial Intelligence Vol. 4 No. 1 (2023): Vol. 4 No. 1 (2023): Journal of Information System and Artificial Intelligence
Publisher : Universitas Mercu Buana Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26486/jisai.v4i1.164

Abstract

Al Umm store is a wholesale and retail store for Muslim clothing that provides various kinds of worship tools such as sarongs, mukena, caps and blankets. With the various kinds of goods available at the Al Umm store, it is difficult for the shop owner to know the stock of goods available in his shop with certainty. To record the stock of these goods, the shop owner still records it manually so the owner does not know for sure how much stock is still available in the store. Therefore, the authors took the initiative to build an application to forecast the stock of goods at the Al-Umm Store using the PHP programming language with the CodeIgniter 3 framework. The author also uses a single moving average forecasting method where this forecasting method is used to determine the amount or number of stock items which needs to be supplied at the Al-Umm shop.
Sentiment Analysis of MyBCA Application User Reviews using Naive Bayes, Random Forest, and Decision Tree Muhammad Rizky Mawandhyka Akbar; Irfan Pratama
SISTEMASI Vol 14, No 5 (2025): Sistemasi: Jurnal Sistem Informasi
Publisher : Universitas Islam Indragiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v14i5.5472

Abstract

In today’s era of globalization, rapid technological advancements are driving innovation across various sectors, including the banking industry. One of the key digital innovations in banking is mobile banking (m-banking), which allows customers to perform transactions via smartphones. This study aims to analyze the sentiment of user reviews on the MyBCA application using three classification methods: Naive Bayes, Random Forest, and Decision Tree. A total of 5,000 user reviews were collected from the Google Play Store through web scraping techniques. The data was preprocessed using the TF-IDF weighting method and processed with Python programming language and the Scikit-Learn library. The dataset was split into 90% training data and 10% testing data. This study also applies the ISO 9126 standard for multi-label classification to assess software quality based on Usability, Efficiency, Functionality, Reliability, and Maintainability. Evaluation results indicate that Random Forest achieved the highest accuracy at 94.09%, outperforming Naive Bayes (81.77%) and Decision Tree (82.38%). This research contributes to the development of a sentiment-based evaluation method for mobile banking applications, integrating user feedback analysis with ISO 9126 quality standards, and offers a useful reference for improving digital banking services.
Implementasi Voice To Text Pada Invoice Checking Berbasis Web Gangsar Swapurba; Irfan Pratama
Intechno Journal : Information Technology Journal Vol. 5 No. 2 (2023): December
Publisher : Universitas AMIKOM Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/intechnojournal.2023v5i2.1391

Abstract

INDOMASCOT adalah perusahaan yang bergerak di bidang konveksi kostum badut maskot. Tim sales-nya seringkali mengalami kerepotan untuk mengirim invoice kepada customer khususnya ketika berada di workshop. Maka dari itu, perlu adanya satu solusi dalam bentuk aplikasi invoice checking yang dapat mengurangi beban pekerjaan tim sales dalam pengiriman invoice kepada customer. Selain itu, sebagai fitur tambahannya baik sekali untuk disematkan pengimplementasian AI dalam bentuk voice-to-text agar customerdapat menginput email & no. invoice-nya dari sumber suara. Dari beberapa kali percobaan, Web Speech APIini kurang memuaskan untuk mengenali alamat email. Namun, memiliki hasil memuaskan untuk mengenali no. invoice yang berbentuk angka. Fitur voice-to-text ini memanfaatkan Web Speech API yang saat tulisan ini dibuat masih dalam status experimental.
Co-Authors Adi Indhito, Tatak Guritno Ahmad Iwan Fadli ahmad subadri Albert Yakobus Chandra Albert Yakobus Chandra Anisa Widianti Ardhi Choiruddin Arya Prayuda Detuer Wonda Eko Suyanto Faizah Tri Rezeki Gangsar Swapurba George Recksy Sandy Pratama I Dewa Putu Nyeneng Kukuh Truna Wijaya Moch Khoirul Muna Muna Muhammad Rizky Mawandhyka Akbar Mutaqin Akbar Nugraha, Anggit Ferdita Nurul Tiara Kadir Nurul Tiara Kadir Ozzi Suria Prasetyaningrum, Putri Taqwa Setyaningsih, Putry Wahyu Sidiq Purnomo, Agus Suharjo, Imam Wahyu Ajitomo Welly Wirman Yoga Pristyanto