Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Dinamik INFOKUM Journal of Computers and Digital Business
Donni Nasution
Universitas Prima Indonesia
Computer Science & IT Decision Sciences, Operations Research & Management

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

Found 3 Documents
Search

 1 
COMPARISON OF EXPONENTIAL SMOOTHING AND MULTIPLICATIVE SEASIONALITY METHODS FOR FORECASTING STUDENT GRADUATION BASED ON SEMESTER ACHIEVEMENT INDEX Muhammad Angga Prasetyo; Diana Krisdianti Hutagalung; Donni Nasution
INFOKUM Vol. 10 No. 02 (2022): Juni, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (507.247 KB)

Abstract

Forecasting is an important tool in effective and efficient planning. This method is a continuous improvement procedure for forecasting the latest observation objects. This forecasting method focuses on the exponential decrease in priority on the object of observation that is longer. This forecasting method can only predict from data in the form of horizontal data patterns. In this study, the authors will compare the Exponential Smoothing and Winter Multiplicative Seasonality methods, where the authors will use a sample in the form of a student achievement index, so that a conclusion will be drawn from the comparison of the two methods which is better in forecasting.
Analisis Kinerja Metode Support Vector Machine dalam Mengukur Tingkat Kepuasan Pengguna QRIS di Pasar Kuliner Pajak USU Tita Yunala Mashita Purba; Mariapuli Br Bukit; Anggiat Mangihut Parulian Sihite; Donni Nasution
Journal of Computers and Digital Business Vol. 5 No. 2 (2026)
Publisher : PT. Delitekno Media Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56427/jcbd.v5i2.1007

Abstract

Transformasi pembayaran digital di Indonesia mendorong penggunaan Quick Response Code Indonesian Standard (QRIS) sebagai sistem transaksi non-tunai yang efisien dan inklusif, khususnya pada sektor Usaha Mikro, Kecil, dan Menengah (UMKM). Pasar Kuliner Pajak Universitas Sumatera Utara (USU) merupakan salah satu lokasi dengan tingkat adopsi QRIS yang tinggi, namun kepuasan penggunanya belum banyak dianalisis secara komprehensif. Tujuan penelitian ini adalah menganalisis kinerja metode Support Vector Machine (SVM) dalam mengukur tingkat kepuasan pengguna QRIS melalui analisis sentimen. Penelitian ini mengadopsi pendekatan kuantitatif dengan pengumpulan data melalui kuesioner berbasis Google Form kepada 559 responden. Data diolah menggunakan Python melalui tahapan preprocessing, normalisasi data, dan klasifikasi menggunakan metode SVM dengan kernel linear. Hasil penelitian menunjukkan bahwa metode SVM mampu mengklasifikasi tingkat kepuasan pengguna QRIS dengan tingkat akurasi mencapai 98,21%. Nilai precision pada kelas "Tidak Puas" mencapai 1,00 dengan recall 0,97, sedangkan kelas "Puas" memperoleh precision 0,95 dan recall 1,00. Melalui hasil penelitian ini, metode SVM dinilai efektif dalam melakukan klasifikasi tingkat kepuasan penggunaan QRIS pada lingkungan UMKM kuliner.
ANALISIS PREDIKSI TINGKAT KECEMASAN PADA PASIEN IGD DENGAN CATBOOST CLASSIFIER BERDASARKAN PARAMETER MEDIS Muhammad Ayub Al Farizi; Dedi Kaldo Malau; Steven Lee; David Ronaldo Sibarani; Donni Nasution
Dinamik Vol 31 No 2 (2026)
Publisher : Universitas Stikubank

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35315/dinamik.v31i2.10498

Abstract

The anxiety levels of patients in the Emergency Department (ED) have a significant impact on medical management and care, making accurate early detection crucial. This study aims to develop and evaluate a machine learning-based classification model to predict patient anxiety levels into four categories: Normal (0), Mild (1), Moderate (2), and Severe (3), using the CatBoost Classifier algorithm. This approach utilizes physiological parameters such as systolic and diastolic blood pressure, heart rate, respiratory rate, as well as demographic variables and hypertension history. The data were trained and validated through appropriate dataset splitting, with comprehensive evaluation using accuracy, precision, recall, F1-score metrics, and learning curve analysis to assess model generalization. The evaluation results showed very high performance, with an overall accuracy reaching 99%. The model provides remarkable consistency across all classes: for the Normal class (0), precision, recall, and F1-score reached 1.00; the Mild class (1) achieved 0.98, 0.99, and 0.99; the Moderate class (2) each reached 0.98; and the Severe class (3) reached 1.00, 0.99, and 0.99. The learning curve indicates no overfitting and the model's ability to learn effectively as the amount of training data increases. Feature importance analysis confirms that both systolic and diastolic blood pressure are dominant predictors of anxiety levels, in line with observed patient physiological responses. Overall, the CatBoost model is proven to be highly reliable and holds great potential as a clinical decision support system that can assist healthcare professionals in the early detection and management of patient anxiety in a dynamic ER environment.
Co-Authors Anggiat Mangihut Parulian Sihite David Ronaldo Sibarani Dedi Kaldo Malau Diana Krisdianti Hutagalung Mariapuli Br Bukit Muhammad Angga Prasetyo Muhammad Ayub Al Farizi Steven Lee Tita Yunala Mashita Purba