Article Per Year (5 Year)
p-Index From 2021 - 2026
0.751
P-Index
This Author published in this journals
All Journal BAREKENG: Jurnal Ilmu Matematika dan Terapan Prosiding Seminar Nasional Official Statistics PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND OFFICIAL STATISTICS E-Jurnal Akuntansi
Permatasari, Novia
Unknown Affiliation
Humanities Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Energy Engineering Mathematics Mechanical Engineering Physics Social Sciences Transportation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
PREDICTING DIABETES MELLITUS USING CATBOOST CLASSIFIER AND SHAPLEY ADDITIVE EXPLANATION (SHAP) APPROACH Permatasari, Novia; Asy Syahidah, Shafiyah; Leofiro Irfiansyah, Aldo; Al-Haqqoni, M. Ghozy
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 2 (2022): BAREKENG: Jurnal Ilmu Matematika dan Terapan
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (468.484 KB) | DOI: 10.30598/barekengvol16iss2pp615-624

Abstract

Diabetes mellitus as a metabolic disease characterized by hyperglycemia can be dangerous if it cannot be handled properly. Early detection of existing symptoms can reduce the impact of delays in treatment. This study aims to carry out early-detection patients with diabetes mellitus using a machine learning approach through data from MIT’s GOSSIS (Global Open Source Severity of Illness Score). By using Shapley Additive Explanation (SHAP) which enables prioritization of feature that determine compound classification, this study shows that the CatBoost classifier has 14 features that significantly can be used for classification with feature ‘d1_glucose_max’ or the highest glucose concentration of the patient in their serum or plasma during the first 24 hours of their unit stay has the highest impact to classify diabetes mellitus patients, then followed by age and glucose APACHE. The selected features are then classified and get the validation AUC score of 86.86%.
Analysis of Artificial Intelligence (AI) Technology Acceptance Among Accounting Employees: A Model Based on UTAUT-3 Permatasari, Novia; Rahmawati, Mia Ika
E-Jurnal Akuntansi Vol. 35 No. 9 (2025)
Publisher : Fakultas Ekonomi dan Bisnis Universitas Udayana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24843/EJA.2025.v35.i09.p18

Abstract

This study aims to analyze the factors that influence the acceptance and use of artificial intelligence (AI) technology by accounting employees using the UTAUT-3 model. Using a quantitative approach, data were collected from 162 accounting employees of an Internet Service Provider (ISP) company in East Java via a questionnaire and analyzed using PLS-SEM via SmartPLS 4. The results indicate that performance expectations, effort expectations, and social impact positively influence behavioral intention, while facility conditions, hedonic motivation, habit, and personal innovation do not have a significant effect. Habit influences actual usage behavior, but behavioral intention does not have a significant effect. These findings indicate the dominance of functional factors over pleasure or infrastructure in driving AI adoption. This study enriches the behavioral accounting literature and provides managerial implications for organizations in strategically adopting AI in financial reporting.
Studi Implementasi Estimasi Luas Area Panen Padi Melalui Satellite Imagery Time Series dan Machine Learning Firmansyah, Achmad Fauzi Bagus; Permatasari, Novia; Utami, Nasiya Alifah
Seminar Nasional Official Statistics Vol 2025 No 1 (2025): Seminar Nasional Official Statistics 2025
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/semnasoffstat.v2025i1.2389

Abstract

Rice data is essential for policymakers in designing food security strategies in Indonesia. Currently, harvested area estimates are produced monthly using the Area Sampling Frame (ASF), although this method faces operational and cost-related limitations. Satellite Imagery Time Series (SITS) data, particularly from Sentinel-1, offers an alternative for identifying rice growth stages through machine learning-based modelling. This study applies that approach in South Sulawesi Province to estimate harvested rice area. The workflow includes regional clustering, satellite data integration, preprocessing, growth stage modelling using XGBoost, and phase area estimation. The results show that most clusters achieved high classification accuracy. Moreover, the predicted harvest area patterns closely match those from the ASF method. These findings demonstrate that using SITS data combined with machine learning offers an effective and practical alternative, especially in modernizing agricultural statistics systems in major rice-producing regions like South Sulawesi.
Enhancing Poverty Rates Reliability Using Small Area Estimation Permatasari, Novia
Proceedings of The International Conference on Data Science and Official Statistics Vol. 2025 No. 1 (2025): Proceedings of 2025 International Conference on Data Science and Official St
Publisher : Politeknik Statistika STIS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34123/icdsos.v2025i1.695

Abstract

This study systematically compares the performance of three Small Area Estimation(SAE) methods—Empirical Best Linear Unbiased Predictor (EBLUP), Hierarchical Bayes (HB)Beta, and HB Flexible Beta—using two different auxiliary data sources-Village Potential(Podes) and Socio-Economic Registration data (Regsosek). The SAE methodologies wereapplied in a case study focusing on Java Island, Indonesia. Direct estimates remain has highRelative Standard Errors (RSE) above 25%, indicating low reliability. EBLUP methodsimproved estimate reliability but still produced some unreliable estimates. The HB Beta methodfurther reduced RSE values, while the HB Flexible Beta model achieved the lowest RSE,eliminating all unreliable estimates. Moreover, Socio-Economic Registration data consistentlyresulted in lower RSE values compared to Village Potential data, particularly when used withthe HB Flexible Beta model. These result highlight that integrating advanced SAE models suchas HB Flexible Beta with high-quality administrative data such as Socio-Economic Registrationdata is crucial for producing reliable and precise poverty estimates for more targeted andeffective poverty alleviation policies.
Co-Authors Al-Haqqoni, M. Ghozy Asy Syahidah, Shafiyah Firmansyah, Achmad Fauzi Bagus Leofiro Irfiansyah, Aldo Rahmawati, Mia Ika Utami, Nasiya Alifah