cover
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
husein_ismail@uinsu.ac.id
Editorial Address
Department of Mathematic Faculty Of Science and Technology Univesitas Islam Negri Sumatera Utara IAIN St. No.1 Medan
Location
Kota medan,
Sumatera utara
INDONESIA
Zero : Jurnal Sains, Matematika, dan Terapan
ISSN : 2580569X     EISSN : 25805754     DOI : 10.30829
Arjuna Subject : -
Articles 184 Documents
IoT-Based Automatic Fire Protection System (SIPEKA) with Android Application for Fast Monitoring and Response Sundari, Jenie; Yunita, Yunita; Handayani, Popon; Fauziah, Sifa; Hardiyan, Hardiyan
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26162

Abstract

Fire hazards cause serious damage, especially in densely populated areas lacking rapid-response systems. This study introduces SIPEKA, an IoT-based automatic fire suppression system integrated with an Android application for real-time monitoring and control. The system uses DHT22 and MQ-2 sensors connected via Wi-Fi to detect fire indicators and activate suppression devices such as pumps or sprinklers. Testing was conducted in a controlled 3×3 m residential-like environment. Results show an average fire detection time of 2.8 s, a notification delay of 1.5 s, and a suppression success rate of 94.7%. The Android interface provides reliable manual override and remote monitoring with 99% uptime. Unlike conventional IoT fire systems that only issue alerts, SIPEKA combines automatic suppression, mobile control, and real-time monitoring, offering an effective, low-cost, and intelligent solution to improve household fire safety.
Egg Quality Classification Using Support Vector Machine Based on Image and Non-Image Fusion Abrolillah, Faizal; Santoso, Irwan Budi; Chamidy, Totok
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26263

Abstract

Egg production and consumption in Indonesia continue to rise, highlighting the need for accurate egg quality assessment. This study evaluated egg quality using a Support Vector Machine (SVM) model that integrates image and non-image features through feature-level fusion. A total of 750 eggs were analyzed based on external characteristics (shell color, cleanliness, texture, weight, and images) and internal characteristics (odor, albumen, yolk, black spots, images). Image data were reprocessed through grayscale conversion, resizing, and texture extraction using the Gray Level Co-occurrence Matrix (GLCM). Both linear and polynomial SVM kernel with varying degrees were tested, and the polynomial kernel (degree 6) achieved the best, with 86% accuracy, 91% precision, and 87% recall. These results demonstrate that integrating image and non-image features significantly enhances egg quality classification compared to using either data type alone. These findings provide valuable insights for developing automated egg grading system in the poultry industry.
Hybrid GSTAR-Machine Learning Model for Forecasting Tourists Numbers in Yogyakarta Sohibien, Gama Putra; Azmi, Annisa Nurul; Sofa, Wahyuni Andriana; Sumarni, Cucu; Prasetyo, Rindang Bangun; Putri, Christiana Anggraeni
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26381

Abstract

Tourism management in DI Yogyakarta is vital to ensure tourism benefits local communities. A key challenge lies in the uncertainty and spatial interdependence of tourist visits among neighboring regions. While the GSTAR model captures spatial relationships, its accuracy decreases with outliers, non-linearity, and assumption violations. To overcome these issues, this study integrates GSTAR with machine learning. Using 168 observations of tourist visits across DI Yogyakarta’s regencies/cities (January 2010–December 2023), GSTAR-GLS-XGBoost model achieved 22–34% lower RMSE than other models. Tourist numbers fluctuate greatly, with peaks in May, June, July, and December. Practically, these findings can help local governments and stakeholders optimize resource allocation, plan promotions, and prepare facilities during peak seasons for sustainable tourism management in DI Yogyakarta. 
Constructing Efficient Frontiers in Cryptocurrency Market Using Long-Run GARCH Volatility Ginting, Josep; Staenly, Staenly
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.25928

Abstract

Cryptocurrency portfolio optimization faces challenges from persistent volatility. This study aims to construct efficient frontiers using long-run GARCH (1,1) volatility estimates to improve portfolio stability in crypto markets. Daily prices of Bitcoin (BTC), Ethereum (ETH), and Solana (SOL) from January 2023 to December 2024 are analyzed. After confirming stationarity and modeling conditional volatility, GARCH-based risks are applied in portfolio optimization. Results show BTC is the least volatile (25.54%), SOL the most (43.56%), and ETH exhibits strong volatility persistence but a weaker risk-adjusted return. The maximum Sharpe ratio portfolio favors BTC and SOL (Sharpe ratio = 3.692), while the minimum variance portfolio concentrates on BTC. Compared with traditional variance-based methods, the GARCH approach produces more stable and realistic efficient frontiers. These findings suggest that volatility-aware modeling enables investors to design more resilient crypto portfolios under persistent structural risk.
Oil Spill Detection and Verification in Nothern Bintan Putri Suhendi, Brigitta Aurelia; Marsisno, Waris
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.25942

Abstract

The Riau Islands Province, particularly northern Bintan Island, is strategically located near countries such as Singapore, making it a gateway to regional and international markets but also vulnerable to oil spills. This study aims to detect oil spill areas using GLCM texture analysis, adaptive thresholding, and various machine and deep learning models, followed by look-alike verification. The XGBoost model achieved the best performance with an accuracy of 0.9772, detecting oil spill areas of 5,400,241 m² and look-alike regions covering 1,333,045 m² on March 23, 2024. The findings also indicate that inland waters are often misidentified as spills, highlighting the importance of verification. This study is the first to integrate several of these methods for Sentinel-1 based oil spill detection in Bintan waters, as a new approach to accurate and efficient regional monitoring.
Spectral Clustering-Based Segmentation Framework for TikTok Influencer Classification Saputra, Rizky Ageng; Purwadi, Joko
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26396

Abstract

This study presents a data-driven segmentation model for TikTok influencers using Spectral Clustering on 120 verified beauty influencers from FastMoss TikTok Analytics (2024–2025). Five engagement metrics views, likes, comments, shares, and followers were selected via variance thresholding, explaining 92.6% of behavioral variance. A similarity graph with a Radial Basis Function (RBF) kernel (σ = 0.5) and k = 3 clusters yielded a Silhouette Score of 0.9473, indicating highly cohesive and well-separated clusters. Compared to K-Means and Hierarchical Clustering, Spectral Clustering achieved 7.8% higher cohesion, capturing complex, nonlinear engagement patterns. Principal Component Analysis (PCA) confirmed clear distinctions among Micro–Mid, Macro, and Mega influencers. Results show that influencer impact depends more on interaction dynamics than follower count, offering a graph-based approach to optimize brand strategies effectively.
Distribution Models of Claim Frequency and Claim Severity in Determining the Pure Premium of Car Insurance with the Application of a Deductible Manurung, Tohap
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26257

Abstract

The objective of this study is to determine the pure premium value based on a car damage claim data model from car insurance company X, using data that applies a deductible value. The data used comprises car damage claims with deductibles applied during a year period. Determining the distribution model for insurance claims is one of the relevant techniques for measuring operational risk in insurance companies. In this context, historical claim data is tested against existing distribution models, enabling the calculation of pure premium values for the insurance company. The results show that the claim frequency data follows a Negative Binomial distribution with an expected value of E(N) = 0.0107, and the claim severity data follows a Log-logistic distribution with E(X) = 12,037,950. Therefore, the calculated pure premium value is E(S) = Rp129,205.19. The pure premium obtained serves as the basis for determining the actual premium charged to policyholders, with the addition of loadings.
Prediction of Heart Disease Risk Based on Patient Health History Using the Support Vector Machine (SVM) Algorithm Simatupang, Septian; Ramadhansyah, Rizki; Tumanggor, Rustianna; Tan, Eric Pratama; Fajar, Syafrizal Amri
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26087

Abstract

Heart disease remains the leading cause of death worldwide, with early detection being critical to improving patient outcomes. This study develops a heart disease risk prediction model using the Support Vector Machine (SVM) algorithm. A dataset of 303 patient records with 14 clinical attributes was used, including age, blood pressure, cholesterol, and chest pain type. Data preprocessing, normalization, and feature selection were performed to optimize the model. Evaluation metrics such as accuracy (92%), precision (90%), recall (96%), and F1-score (93%) demonstrated significant improvements over the baseline model. These results highlight the SVM model’s effectiveness as a tool for early heart disease detection, offering potential for enhanced predictive healthcare, particularly in Indonesian clinical settings. 
Modeling of the Stunting Cases Using GWPR Incorporating Exposure in Central Java Province Triyanto, Triyanto; Fitriana, Laila; Pramesti, Getut; Pambudi, Dhidhi
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.26348

Abstract

Geographically Weighted Poisson Regression (GWPR) is a local form of Poisson regression that accounts for cases of spatial heterogeneity. Many studies have been conducted on GWPR models; however, these models do not account for the population size in each region. In this study, GWPR incorporating exposure was applied for the modeling of stunting cases in Central Java Province, Indonesia. The exposure in this model is the number of toddlers in each regency/city.The results of the empirical study showed that the percentage of low birth weight has a significant effect on the stunting cases in all regencies/cities, with the exception of Purworejo and Wonosobo. Meanwhile, other independent variables that have a significant effect on stunting cases vary across regencies/cities. The GWPR model incorporating exposure yields lower MSE values than the GWPR model without exposure, which were 4871 and 5730, respectively. The lower MSE indicates that the GWPR incorporating exposure has better accuracy in modeling the number of stunting cases.
Modeling Student Organizational Engagement in Higher Education Using an Adapted SIR Dynamic System Fathoni, M. Ivan Ariful; Mufidah, Izzatul
ZERO: Jurnal Sains, Matematika dan Terapan Vol 9, No 2 (2025): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v9i2.25834

Abstract

Student involvement in organizations is essential for developing leadership, collaboration, and broader competencies in higher education. This study analyzes the dynamics of student organizational engagement using an adapted SIR (Susceptible–Infective–Recovered) mathematical model, where the three compartments respectively represent non-members (S), active members (I), and former members (R). Parameters including recruitment rate , disengagement rate , and reactivation rate  were selected and calibrated based on prior studies in educational and social diffusion modeling. Numerical simulations conducted in MATLAB indicate convergence toward a stable equilibrium with approximately 52% non-members, 35% active members, and 13% former members, depending on parameter variation. The results also show that increasing recruitment by 50% or reducing disengagement by half accelerates system stabilization and raises the equilibrium proportion of active members by up to 20%. These findings provide quantitative insight into how organizational participation evolves dynamically and offer practical implications for universities to design data-informed policies that enhance recruitment, sustain engagement, and improve student leadership development over time.