Article Per Year (5 Year)
p-Index From 2020 - 2025
0.961
P-Index
This Author published in this journals
All Journal Jurnal Sains Student Research Jurnal of Information Technology and Society (JITS) Jurnal Ilmiah Nusantara JURNAL AKADEMIK EKONOMI DAN MANAJEMEN Mars: Jurnal Teknik Mesin, Industri, Elektro dan Ilmu Komputer
Arvi Pramudyantoro
Unknown Affiliation
Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Languange, Linguistic, Communication & Media Social Sciences Other

Published : 6 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 6 Documents
Search

 1 
PENGENALAN POLA KASUS POTENSI BANJIR DI PANGKALPINANG DENGAN ALGORITMA RANDOM FOREST DAN XGBOOST MENGGUNAKAN GOOGLE EARTH ENGINE Randi Atul Aufa; Eka Altiarika; Arvi Pramudyantoro; Yudistira Bagus Pratama; Zikri Wahyuzi
Jurnal Teknologi Informasi dan Masyarakat Vol 3 No 1 (2025): Journal of Information Technology and Society (JITS)
Publisher : Universitas Muhammadiyah Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35438/jits.v3i1.1415

Abstract

Banjir merupakan bencana yang sering terjadi di Kota Pangkalpinang dan menimbulkan dampak sosial serta ekonomi yang signifikan. Setiap tahun, curah hujan tinggi dan elevasi wilayah yang rendah menyebabkan genangan air di berbagai titik, mengganggu aktivitas masyarakat dan infrastruktur kota. Oleh karena itu, diperlukan sistem peringatan dini yang efektif berbasis teknologi untuk mengenali pola potensi banjir secara akurat dan cepat. Penelitian ini bertujuan untuk mengenali pola kasus banjir dengan menggabungkan data historis lingkungan dan iklim menggunakan algoritma pembelajaran mesin melalui platform Google Earth Engine (GEE). Metode yang digunakan dalam penelitian ini meliputi pengumpulan data spasial dan klimatologis dari GEE, seperti curah hujan, kelembapan tanah, suhu permukaan, tutupan lahan, dan elevasi. Data selanjutnya diproses menggunakan Google Colab, termasuk tahapan preprocessing dan feature engineering. Algoritma Random Forest dan XGBoost digunakan dalam pendekatan ensemble learning dengan metode soft voting. Data dibagi menjadi 80% untuk pelatihan dan 20% untuk pengujian. Evaluasi model dilakukan menggunakan metrik Accuracy, Precision, Recall, dan F1 Score. Hasil penelitian menunjukkan bahwa model memiliki performa tinggi dengan Accuracy 0.98, Precision 0.97, Recall 0.99 dan F1 Score 0.98. Prediksi potensi banjir tahun 2025–2030 menunjukkan tren perubahan jumlah titik banjir dengan probabilitas tinggi setiap tahunnya. Visualisasi pengenalan pola potensi banjir dalam bentuk peta interaktif di GEE mempermudah analisis spasial dan mendukung pengambilan keputusan mitigasi. Penelitian ini diharapkan dapat menjadi solusi praktis dalam peringatan dini dan strategi adaptasi terhadap bencana banjir.
Perbandingan Sentimen Komentar Youtube pada Video Promosi Bisnis Kuliner di Bangka Belitung Menggunakan Algoritma Machine Learning Al Ahfaz Reza Ramdani; Yudistira Bagus Pratama; Arvi Pramudyantoro; Eka Altiarika; Zikri Wahyuzi
Jurnal Teknologi Informasi dan Masyarakat Vol 3 No 1 (2025): Journal of Information Technology and Society (JITS)
Publisher : Universitas Muhammadiyah Bangka Belitung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35438/jits.v3i1.1416

Abstract

Penelitian ini membandingkan sentimen komentar youtube pada video promosi bisnis kuliner di Bangka Belitung menggunakan algoritma machine learning. Penelitian ini bertujuan untuk memahami persepsi masyarakat terhadap bisnis kuliner lokal yang tersebar di platform youtube, serta mengetahui algoritma mana yang lebih efektif dalam mengklasifikasikan sentimen komentar. Metode yang digunakan adalah analisis sentimen dengan pendekatan kualitatif. Algoritma machine learning yang digunakan adalah Support Vector Machine (SVM) dan Naïve Bayes. Data diperoleh melalui proses web scraping terhadap 27 video kuliner khas Bangka Belitung, seperti lempah kuning, mie Koba, otak-otak, dan martabak Bangka, yang kemudian dikumpulkan menjadi 13.692 komentar. Komentar-komentar tersebut diproses melalui tahapan preprocessing, seperti case folding, penghapusan simbol dan angka, tokenisasi, stopword removal, serta stemming. Setelah itu, dilakukan pelabelan sentimen secara manual dan otomatis untuk mengklasifikasikan komentar ke dalam kategori positif, negatif, dan netral. Model klasifikasi kemudian dibangun menggunakan algoritma SVM dan Naïve Bayes, dan dilakukan evaluasi menggunakan metrik akurasi, presisi, recall, dan f1-score. Hasil evaluasi menunjukkan bahwa SVM memiliki akurasi lebih tinggi (86.55%) dibandingkan Naïve Bayes (84.63%). Hasil penelitian menunjukkan bahwa mayoritas komentar memiliki sentimen netral, dengan sedikit komentar positif dan negatif. Penelitian ini memberikan wawasan tentang sentimen masyarakat terhadap bisnis kuliner di Bangka Belitung, yang dapat bermanfaat bagi pelaku bisnis kuliner dalam meningkatkan strategi pemasaran dan pelayanan mereka.
PERBANDINGAN PERFORMA ALGORITMA NAIVE BAYES DAN SVM UNTUK ANALISIS SENTIMEN KOMENTAR YOUTUBE TERHADAP INDUSTRI ESPORTS DI INDONESIA Tito Dian Permana; Yudistira Bagus Pratama; Zikri Wahyuzi; Eka Altiarika; Arvi Pramudyantoro
JURNAL ILMIAH NUSANTARA Vol. 2 No. 6 (2025): Jurnal Ilmiah Nusantara
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jinu.v2i6.6753

Abstract

The esports industry in Indonesia is rapidly growing and gaining significant attention on social media, particularly YouTube, where comments reflect public perceptions. This study compares the performance of Naive Bayes and Support Vector Machine (SVM) in classifying sentiments from YouTube comments and explores key themes using Latent Dirichlet Allocation (LDA). Data were collected via the YouTube Data API v3, labeled with TextBlob and manually verified into positive, negative, and neutral categories. After preprocessing and TF-IDF representation, class imbalance was handled with SMOTE, and models were trained and evaluated using accuracy, precision, recall, F1-score, and confusion matrix. Results indicate that Naive Bayes achieved 73.85% accuracy with an F1-score of 0.71, while SVM slightly outperformed with 73.97% accuracy and the same F1-score. SVM showed better consistency in classifying negative and neutral comments, whereas Naive Bayes was more effective for positive ones. LDA revealed dominant discussion topics such as appreciation, enthusiasm, community interaction, criticism, and support for esports development. These findings highlight SVM’s superior overall performance and the value of LDA in uncovering public discourse, providing both academic contribution and practical insights for the esports industry in understanding public sentiment.
Pengembangan Virtual Assistant menggunakan Teknologi NLP dengan Metode Algoritma Machine Learning untuk Layanan Informasi Akademik di SMA Negeri 1 Parittiga Berbasis Web Yuniarni Yuniarni; Yudistira Bagus Pratama; Arvi Pramudyantoro
Mars : Jurnal Teknik Mesin, Industri, Elektro Dan Ilmu Komputer Vol. 3 No. 5 (2025): Oktober: Jurnal Teknik Mesin, Industri, Elektro Dan Ilmu Komputer
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/mars.v3i5.1152

Abstract

This study aims to develop a web-based Virtual Assistant to improve the efficiency of academic information services at SMA Negeri 1 Parittiga. The research was motivated by the delays and inaccuracies in information delivery caused by the manual system still used in the school. The system development was carried out using the Research and Development approach with the Waterfall model, which includes the stages of needs analysis, design, implementation, and evaluation. The main technologies used are Natural Language Processing (NLP) and the Long Short-Term Memory (LSTM) machine learning algorithm, which allow the assistant to understand and respond to user questions in natural language in a contextual way. The system architecture uses Flask as the backend, Vue.js as the frontend, and Laravel for administrative data management. The testing results show that the system has an accuracy level of 88.4% in providing correct answers and a user satisfaction level of 92%, surpassing the target success rate of 80%. These findings prove that integrating NLP and LSTM can enhance the system's ability to understand conversational context and speed up the distribution of academic information. The study concludes that a web-based Virtual Assistant is an effective solution for the digitalization of school information services and has the potential to support the implementation of artificial intelligence technology in secondary education in Indonesia.
ANALISIS DATA PELANGGAN DENGAN ALGORITMA K-MEANS UNTUK PENINGKATAN PENJUALAN LAYANAN ICONNET DI BANGKA BELITUNG Muhamad Mustaqim; Yudistira Bagus Pratama; Arvi Pramudyantoro
JURNAL AKADEMIK EKONOMI DAN MANAJEMEN Vol. 2 No. 4 (2025): Desember
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jaem.v2i4.7106

Abstract

Sales increase is an essential factor for telecommunication service providers, including ICONNET, a subsidiary of PLN, amid intense market competition. Companies face the challenge of designing effective marketing strategies without structured customer data analysis. This study aims to apply the K-Means Machine Learning algorithm to analyze and cluster ICONNET customer data in Bangka Belitung, with the expected results supporting strategic sales increase decisions. The methodology employed is Data Mining with the CRISP-DM framework, where the modeling process implements the K-Means algorithm. The determination of the optimal number of clusters (K) was consistently performed using the Elbow Method and Silhouette Score, yielding an optimal value of K=2. The clustering results successfully divided customers into two main groups: Cluster 0, dominated by users of low-value packages (Package 1 and 2), and Cluster 1, consisting of users of higher-value packages (specifically Package 5). This segmentation provides a basis for ICONNET to formulate differentiated service strategies and targeted marketing offers tailored to the characteristics and preferences of each customer segment, which directly supports operational efficiency and long-term business growth.
Identifikasi Pola Perubahan Tutupan Lahan (Land Cover) Akibat Penggunaan Lahan (Land Use) Menggunakan Algoritma Random Forest Di Kabupaten Bangka Tengah Ari Ardiansyah; Yudistira Bagus Pratama; Zikri Wahyuzi; Arvi Pramudyantoro; Andesta Granitio Irwan
JOURNAL SAINS STUDENT RESEARCH Vol. 3 No. 6 (2025): Jurnal Sains Student Research (JSSR) Desember
Publisher : CV. KAMPUS AKADEMIK PUBLISING

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61722/jssr.v3i6.7072

Abstract

Central Bangka Regency has been facing growing environmental pressures resulting from the expansion of oil palm plantations, mining operations, and accelerated urban development. These activities have caused considerable changes in land cover, posing a threat to the sustainability of local ecosystems. This study aims to examine land cover dynamics between 2019 and 2022 and to forecast future conditions for 2030 as a basis for sustainable spatial planning. Sentinel-2A satellite imagery was processed using the Google Earth Engine(GEE) platform, employing the Random Forest(RF) algorithm to classify land cover into five categories: forest, water, built-up, oil palm plantations, and barren. Model validation through the Overall Accuracy metric demonstrated strong classification performance, reaching 0.90297 in 2019 and 0.90849 in 2022. The analysis showed a 21.63% reduction in forest area, alongside significant increases in oil palm and built-up land. The projection for 2030 suggests that forest cover may decline to just 3.35% of the total area, with oil palm plantations and built-up land becoming dominant. These results emphasize the necessity of implementing sustainable land-use management strategies to maintain a balance between economic growth and environmental conservation in Central Bangka Regency.
Co-Authors Al Ahfaz Reza Ramdani Andesta Granitio Irwan Ari Ardiansyah Eka Altiarika Muhamad Mustaqim Randi Atul Aufa Tito Dian Permana Yudistira Bagus Pratama Yuniarni Yuniarni Zikri Wahyuzi