Article Per Year (5 Year)
p-Index From 2021 - 2026
1.908
P-Index
This Author published in this journals
All Journal Pythagoras: Jurnal Matematika dan Pendidikan Matematika Statistika JURNAL MATEMATIKA STATISTIKA DAN KOMPUTASI JMPM: Jurnal Matematika dan Pendidikan Matematika Journal of Data Analysis Amerta Nutrition Journal of Applied Data Sciences Narra J Jurnal Natural Transcendent Journal of Mathematics and Applications Leuser Journal of Environmental Studies Ekonomikalia Journal of Economics Journal of Educational Management and Learning Indonesian Journal of Case Reports
Asep Rusyana
Department Of Statistics, Faculty Of Mathematics And Natural Sciences, Universitas Syiah Kuala
Agriculture, Biological Sciences & Forestry Astronomy Biochemistry, Genetics & Molecular Biology Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Energy Environmental Science Health Professions Immunology & microbiology Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Mathematics Medicine & Pharmacology Neuroscience Nursing Physics Public Health Other

Published : 20 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 20 Documents
Search

 1   2 
A generalized linear mixed model for understanding determinant factors of student's interest in pursuing bachelor's degree at Universitas Syiah Kuala ASEP RUSYANA; KHAIRIL ANWAR NOTODIPUTRO; BAGUS SARTONO
Jurnal Natural Volume 21 Number 2, June 2021
Publisher : Universitas Syiah Kuala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/jn.v21i2.19325

Abstract

Generalized Linear Mixed Model (GLMM) is a framework that has a response variable, fixed effects, and random effects. The response variable comes from an exponential family, whereas random effects have a normal distribution. Estimating parameters can be calculated using the maximum likelihood method using the Laplace approach or the Gauss-Hermite Quadrature (GHQ) approach. The purpose of this study was to identify factors that trigger student's interest to continue studying at Universitas Syiah Kuala (USK) using both techniques.  The GLMM is suitable for the data because the variable response has a Bernoulli distribution, and the random effects are assumed to be having a normal distribution. Also, the model helps identify the relationship between the dependent variable and the predictors. This study utilizes data from six high schools in Banda Aceh city drawn using a two-stage sampling technique. Stage 1, we randomly chose six out of sixteen public senior high schools in Banda Aceh. Stage 2, we selected students from each school from four different major classes. The GLMM model includes one binary response variable, five numerical fixed-effects, and two random effects. The response variable is the interest of high school students to continue study at USK (yes or no). The five fixed effects in the model including scores of collaboration (C), Action (A), Emotion (E), Purposes (P), and Hope (H).  Finally, the random effects are schools (S) and majors (M). In this study, both Laplace and GHQ techniques produce identical results. The predictors that can explain student interest are A, E, and H. These predictors have a positive effect. The random effects of schools and majors are not significantly different from zero. The model with three significant predictors is better than the complete predictor model.
Optimizing antimicrobial synergy: Green synthesis of silver nanoparticles from Calotropis gigantea leaves enhanced by patchouli oil Kemala, Pati; Khairan, Khairan; Ramli, Muliadi; Helwani, Zuchra; Rusyana, Asep; Lubis, Vanizra F.; Ahmad, Khairunnas; Idroes, Ghazi M.; Noviandy, Teuku R.; Idroes, Rinaldi
Narra J Vol. 4 No. 2 (2024): August 2024
Publisher : Narra Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52225/narra.v4i2.800

Abstract

Silver nanoparticles (AgNPs) synthesized from plant extracts have gained attention for their potential applications in biomedicine. Calotropis gigantea has been utilized to synthesize AgNPs, called AgNPs-LCg, and exhibit antibacterial activities against both Gram-positive and Gram-negative bacteria as well as antifungal. However, further enhancement of their antimicrobial properties is needed. The aim of this study was to synthesize AgNPs-LCg and to enhance their antimicrobial and antifungal activities through a hybrid green synthesis reaction using patchouli oil (PO), as well as to characterize the synthesized AgNPs-LCg. Optimization was conducted using the response surface method (RSM) with a central composite design (CCD). AgNPs-LCg were synthesized under optimal conditions and hybridized with different forms of PO—crude, distillation wastewater (hydrolate), and heavy and light fractions—resulting in PO-AgNPs-LCg, PH-AgNPs-LCg, LP-AgNPs-LCg, and HP-AgNPs-LCg, respectively. The samples were then tested for their antibacterial (both Gram-positive and Gram-negative bacteria) and antifungal activities. Our data indicated that all samples, including those with distillation wastewater, had enhanced antimicrobial activity. HP-AgNPs-LCg, however, had the highest efficacy; therefore, only HP-AgNPs-LCg proceeded to the characterization stage for comparison with AgNPs-LCg. UV-Vis spectrophotometry indicated surface plasmon resonance (SPR) peaks at 400 nm for AgNPs-LCg and 360 nm for HP-AgNPs-LCg. The Fourier-transform infrared spectroscopy (FTIR) analysis confirmed the presence of O-H, N-H, and C-H groups in C. gigantea extract and AgNP samples. The smallest AgNPs-LCg were 56 nm, indicating successful RSM optimization. Scanning electron microscopy (SEM) analysis revealed spherical AgNPs-LCg and primarily cubic HP-AgNPs-LCg, with energy-dispersive X-ray spectroscopy (EDX) confirming silver's predominance. This study demonstrated that PO in any form significantly enhances the antimicrobial properties of AgNPs-LCg. The findings pave the way for the exploration of enhanced and environmentally sustainable antimicrobial agents, capitalizing on the natural resources found in Aceh Province, Indonesia.
Biocomposite Innovation: Assessing Tensile and Flexural Performance with Maleated Natural Rubber Additives Fatra, Warman; Anuar, Kaspul; Oktriyono, Febri Dwi; Fernando, Rivo; Helwani, Zuchra; Rusyana, Asep; Zul Amraini, Said
Leuser Journal of Environmental Studies Vol. 1 No. 2 (2023): November 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ljes.v1i2.98

Abstract

Fiberglass is the most common reinforcing fiber used in composites, with polymer matrices having high tensile strength and chemical resistance, including an excellent insulating property; however, they are non-degradable. Natural fiber reinforced polymer composites have advantageous properties such as lower density and price, when compared to synthetic composite products. In addition, hybrid composites may be obtained depending on various properties such as the fibers' length, structure, content and orientation, matrix bonding and arrangement. This study was carried out to determine the effect of adding Maleated Natural Rubber (MNR) from natural rubber as a coupling agent, in order to produce the highest tensile and flexural strength. The hand lay-up and vacuum bag methods with the Response Surface Method-Central Composite Design (RSM). -CCD) were used. The composite arrangement pattern was E-glass/OPEFB/E-glass, the volume fraction of OPEFB (oil palm empty fruit bunches):E-glass was 40:60, 50:50 and 60:40, the fraction volume of OPEFB + E-glass:matrix was 40:60, 50: 50, 60: 40 and the coupling agent were added by 9, 10 and 11% of the total epoxy resin used. Furthermore, the composite mold was made of glass with dimensions of 200mm x 50mm x 50mm. The results showed that the composite product obtained from both methods had a tensile strength value, which was influenced by the variable OPEFB fiber and epoxy resin. Meanwhile, the flexural strength was influenced by the OPEFB fiber and the quadratic factor of the epoxy-MNR resin.
Deep Learning-Based Bitcoin Price Forecasting Using Neural Prophet Noviandy, Teuku Rizky; Maulana, Aga; Idroes, Ghazi Mauer; Suhendra, Rivansyah; Adam, Muhammad; Rusyana, Asep; Sofyan, Hizir
Ekonomikalia Journal of Economics Vol. 1 No. 1 (2023): July 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/eje.v1i1.51

Abstract

This study focuses on using the Neural Prophet framework to forecast Bitcoin prices accurately. By analyzing historical Bitcoin price data, the study aims to capture patterns and dependencies to provide valuable insights and predictive models for investors, traders, and analysts in the volatile cryptocurrency market. The Neural Prophet framework, based on neural network principles, incorporates features such as automatic differencing, trend, seasonality considerations, and external variables to enhance forecasting accuracy. The model was trained and evaluated using performance metrics such as RMSE, MAE, and MAPE. The results demonstrate the model's effectiveness in capturing trends and predicting Bitcoin prices while acknowledging the challenges posed by the inherent volatility of the cryptocurrency market.
Leveraging Artificial Intelligence to Predict Student Performance: A Comparative Machine Learning Approach Maulana, Aga; Idroes, Ghazi Mauer; Kemala, Pati; Maulydia, Nur Balqis; Sasmita, Novi Reandy; Tallei, Trina Ekawati; Sofyan, Hizir; Rusyana, Asep
Journal of Educational Management and Learning Vol. 1 No. 2 (2023): December 2023
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/jeml.v1i2.132

Abstract

This study explores the application of artificial intelligence (AI) and machine learning (ML) in predicting high school student performance during the transition to university. Recognizing the pivotal role of academic readiness, the study emphasizes the need for tailored interventions to enhance student success. Leveraging a dataset from Portuguese high schools, the research employs a comparative analysis of six ML algorithms—linear regression, decision tree, support vector regression, k-nearest neighbors, random forest, and XGBoost—to identify the most effective predictors. The dataset encompasses diverse attributes, including demographic details, social factors, and school-related features, providing a comprehensive view of student profiles. The predictive models are evaluated using R-squared, Root Mean Square Error, and Mean Absolute Error metrics. Results indicate that the Random Forest algorithm outperforms others, displaying high accuracy in predicting student performance. Visualization and residual analysis further reveal the model's strengths and potential areas for improvement, particularly for students with lower grades. The implications of this research extend to educational management systems, where the integration of ML models could enable real-time monitoring and proactive interventions. Despite promising outcomes, the study acknowledges limitations, suggesting the need for more diverse datasets and advanced ML techniques in future research. Ultimately, this work contributes to the evolving field of educational AI, offering practical insights for educators and institutions seeking to enhance student success through predictive analytics.
Explainable Artificial Intelligence in Medical Imaging: A Case Study on Enhancing Lung Cancer Detection through CT Images Noviandy, Teuku Rizky; Maulana, Aga; Zulfikar, Teuku; Rusyana, Asep; Enitan, Seyi Samson; Idroes, Rinaldi
Indonesian Journal of Case Reports Vol. 2 No. 1 (2024): June 2024
Publisher : Heca Sentra Analitika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.60084/ijcr.v2i1.150

Abstract

This study tackles the pressing challenge of lung cancer detection, the foremost cause of cancer-related mortality worldwide, hindered by late detection and diagnostic limitations. Aiming to improve early detection rates and diagnostic reliability, we propose an approach integrating Deep Convolutional Neural Networks (DCNN) with Explainable Artificial Intelligence (XAI) techniques, specifically focusing on the Residual Network (ResNet) architecture and Gradient-weighted Class Activation Mapping (Grad-CAM). Utilizing a dataset of 1,000 CT scans, categorized into normal, non-cancerous, and three types of lung cancer images, we adapted the ResNet50 model through transfer learning and fine-tuning for enhanced specificity in lung cancer subtype detection. Our methodology demonstrated the modified ResNet50 model's effectiveness, significantly outperforming the original architecture in accuracy (91.11%), precision (91.66%), sensitivity (91.11%), specificity (96.63%), and F1-score (91.10%). The inclusion of Grad-CAM provided insightful visual explanations for the model's predictions, fostering transparency and trust in computer-assisted diagnostics. The study highlights the potential of combining DCNN with XAI to advance lung cancer detection, suggesting future research should expand dataset diversity and explore multimodal data integration for broader applicability and improved diagnostic capabilities.
Profil Sensori Minuman Jeli Ekstrak Air Daun Salam Kombinasi Jus Jambu Menggunakan Quantitative Descriptive Analysis: Sensory Profiling of Jelly Drink Made from a Combination of Bay Leaf Water Extract and Guava Juice Using a Quantitative Descriptive Analysis Putri, Sefanadia; Marliyati, Sri Anna; Setiawan, Budi; Rimbawan, Rimbawan; Yunianto, Andi Eka; Rusyana, Asep
Amerta Nutrition Vol. 8 No. 3 (2024): AMERTA NUTRITION (Bilingual Edition)
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/amnt.v8i3.2024.452-460

Abstract

Background: The profiling of a drink made from bay leaves combined guava juice has not been previously reported despite the positive health aspects of both plants. Objectives: To analyze the sensory characteristics of jelly drink bay leaf water extract with guava juice combination using the Quantitative Analysis Descriptive (QDA) sensory evaluation method. Methods: The QDA carried out of three stages, namely the panelist preparation stage, Forum Group Discussion (FGD), and quantitative descriptive test. QDA was carried out on four jelly drink product formulas, namely F0 (standard), F1 (75:25), F2 (50:50), F3 (25:75) from the ratio of bay leaf extract:guava juice. Results: Sensory attributes consist of 17 attributes, namely appearance (particle aggregation size, viscosity, homogeneity), aroma (bay leaf, guava, sweet), texture (gritty, ease of spreading), taste (guava, sweet, sour, bay leaf), mouthfeel (gritty, jelly-like consistency, viscosity), aftertaste (astringent and bitter). The results of the one-way ANOVA analysis showed significant differences between the formula and the control product (p<0.05). Formula 1 and 3 not accepted by consumers because there are weaknesses, such as the inhomogeneous appearance and the strong aroma of bay leaf obtained the highest value in formula 1. In contrast, formula 3 has the highest value in astringent and bitter aftertaste, gritty texture and mouthfeel. Conclusions: The selected treatment is formula two of jelly drink with a ratio of bay leaf water extract: guava juice = 50:50. A description like this will assist food technology in developing new products.
Application of the ARIMAX Model in Assessing the Impact of Global Stock Price Index on Forecasting Indonesia's IHSG Marzuki, Marzuki; Riswanda, Muhammad; Nurhasanah, Nurhasanah; Rusyana, Asep
Transcendent Journal of Mathematics and Applications Vol 3, No 1 (2024)
Publisher : Syiah Kuala University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24815/tjoma.v3i1.38775

Abstract

Time series analysis can be classified into two parts when viewed based on the analysis data variables, namely univariate and multivariate time series analysis. The ARIMAX model is the development of the ARIMA model. The ARIMAX model is a multivariate time series analysis method consisting of exogenous and endogenous variables. This study aims to forecast the Composite Stock Price Index (IHSG) using the ARIMAX model, by looking at the influence of global stock price indices, namely the American stock price index (DJIA), Japanese stock price index (N225), and Chinese stock price index (SSEC). The results of the study show that the model used to forecast the 2019 IHSG is the ARIMAX model (4,1,4). The results of the 2019 IHSG forecast produce fluctuating data. The highest IHSG share price of 6,958.419 occurred in November, while the lowest share price of 6.591.566 occurred in January. Forecast accuracy measured using RMSE and MAPE obtained results of 144.5387 and 2.5121 respectively.
Analisis Korespondensi Pada Korban Kecelakaan Lalu Lintas Berdasarkan Provinsi di Indonesia Mahmudi, Mahmudi; Fahmi, Mulkan; Elfurqany, Nuwairy; Sarah, Siti; Rusyana, Asep
JMPM: Jurnal Matematika dan Pendidikan Matematika Vol 4 No 1: March - August 2019
Publisher : Prodi Pendidikan Matematika Universitas Pesantren Tinggi Darul Ulum Jombang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/jmpm.v4i1.1617

Abstract

Penelitian ini bertujuan untuk melihat hubungan mengenai tingkat kecelakaan lalu lintas berdasarkan provinsi di Indonesia. Penelitian ini menggunakan data sekunder yaitu data kecelakaan lalu lintas 4 bulan pertama tahun 2019 di Indonesia dengan jumlah sampel sebanyak 31 provinsi. Analisa data dalam penelitian ini menggunakan analisis deskriptif, uji Chi-Square, analisis profil baris dan kolom, analisis nilai inersia baris dan kolom, serta grafik Korespondensi. Berdasarkan hasil penelitian, diketahui bahwa kecelakaan luka ringan merupakan tingkat kecelakaan dengan jumlah terbesar di Indonesia, dengan persentase sebesar 21,4% korban kecelakaan lalu lintas terdapat di provinsi Jawa Timur, sebesar 17,7% terdapat di provinsi Jawa Tengah. Berdasarkan grafik korespondensi korban kecelakaan luka ringan dan meninggal dunia dominan terjadi di provinsi Jawa Timur, Jawa Tengah, dan Jawa Barat. Korban kecelakaan luka berat dominan di provinsi Sumatera Utara dan Lampung.
Hybrid Ensemble Learning with SMOTEENN and Soft Voting for Stunting Risk Prediction: A SHAP-Based Explainable Approach Furqany, Nuwairy El; Subianto, Muhammad; Rusyana, Asep
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.829

Abstract

Stunting remains a critical public health concern in Indonesia, with long-term consequences for physical growth, cognitive development, and human capital. This study introduces a hybrid machine learning framework to predict household-level stunting risk by integrating Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTEENN), soft voting ensemble, and SHapley Additive exPlanations (SHAP). The objective is to enhance both predictive accuracy and interpretability in identifying high-risk households. A dataset of 115,579 household records from West Sumatra, comprising 20 demographic, socioeconomic, health, and housing predictors, was utilized. Preprocessing steps included handling missing values, categorical encoding, and applying SMOTEENN exclusively on the training set to mitigate class imbalance. The baseline models demonstrated limited sensitivity, with XGBoost performing best at 74.56% accuracy and 71.08% F1-score on imbalanced data. After applying SMOTEENN, performance improved substantially, with XGBoost achieving 91.82% accuracy and 91.74% F1-score. Further improvements were obtained through hybridization, where the Random Forest and XGBoost soft voting ensemble reached 91.95% accuracy and 92.46% F1-score, representing a notable gain over individual classifiers. SHAP analysis added interpretability by identifying family members, education level, diverse food consumption, occupation, and drinking water source as dominant predictors of stunting risk. The novelty of this study lies in the integration of SMOTEENN with ensemble learning and SHAP, providing not only robust performance but also transparency in feature contributions. The findings demonstrate that the proposed framework improves sensitivity to minority classes, delivers superior predictive accuracy compared to baseline models, and offers interpretable insights to guide targeted interventions. By combining methodological rigor with explainability, this research contributes a practical decision-support tool for policymakers, supporting early detection of at-risk households and accelerating stunting reduction efforts in Indonesia.
Co-Authors Abd. Rasyid Syamsuri Ahmad, Khairunnas Akhyar Wijaya Anuar, Kaspul Bagus Sartono Budi Setiawan Dwi Astiti Syahbani Elfurqany, Nuwairy Elvitra Mutia Ulfa Enitan, Seyi Samson Fahmi, Mulkan Fara Inka Durrah Fernando, Rivo Fitriana AR Fitriana AR Furqany, Nuwairy El Ghazi Mauer Idroes Hizir Sofyan Idroes, Ghazi M. Inas Salsabila Ira Julita Januaria Douw Kemala, Pati Khairan Khairan Lathifah Setiawan Latifah Rahayu Lubis, Vanizra F. Mahmudi Mahmudi Marzuki Marzuki Marzuki Marzuki Maulana, Aga Maulydia, Nur Balqis Mira Suci Yana Muhammad Adam, Muhammad Muhammad Iqbal Muhammad Subianto Muliadi Ramli Muzamil Muzamil Nanny Salwa Nany Salwa Noviandy, Teuku R. Nurhasanah Nurhasanah Nurhasanah Nurhasanah Oktriyono, Febri Dwi Ridha Ferdhiana Rimbawan , Rinaldi Idroes Riswanda, Muhammad Romi Rosadi Sasmita, Novi Reandy Siti Rusdiana Siti Sarah, Siti Sri Anna Marliyati Suhendra, Rivansyah Tessa Prihartina Parhusip Teuku Rizky Noviandy Teuku Zulfikar TRINA EKAWATI TALLEI Warman Fatra, Warman Yulia Yulia Yunianto, Andi Eka Zuchra Helwani, Zuchra Zul Amraini, Said Zurnila Marli Kesuma