cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Putu Yudia Pratiwi
Contact Email
putuyudia.pratiwi@undiksha.ac.id
Phone
+6281916579014
Journal Mail Official
insert@undiksha.ac.id
Editorial Address
Kampus Tengah Undiksha, Jl. Udayana No. 11 Singaraja, Bali, Indonesia
Location
Kota denpasar,
Bali
INDONESIA
INSERT: Information System and Emerging Technology Journal
Published by Universitas Pendidikan Ganesha
ISSN : -     EISSN : 27228207     DOI : http://dx.doi.org/10.23887/insert.v1i1
Core Subject : Science, Engineering,
Computer Science & IT Engineering
INSERT: Information System and Emerging Technology Journal is an independent, quarterly basis online & print version, open access, peer-reviewed, non-profit journal that publishes original research, short communications, review articles or essays, and book reviews relevant to Information System and Computer Technology.
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 98 Documents
 6   7   8   9   10 
Integration of IndoBERT as a Feature Extractor with Machine Learning and Deep Learning Algorithms for Quality Management System Audit Findings Classification I Ketut Agus Sanjaya; Aniek Suryanti Kusuma; I Putu Agus Eka Darma Udayana; Ayu Manik Dirgayusari
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.110286

Abstract

The SNI ISO 9001:2015 audit process faces significant challenges in accurately classifying non-conformity findings due to the standard's complexity. Misclassification leads to ineffective corrective actions and recurring quality issues. This study aims to develop an Artificial Intelligence-based text classification model to automate the mapping of Indonesian-language audit findings to their respective clauses, leveraging IndoBERT's linguistic capabilities. This research adopts a quantitative approach by integrating the IndoBERT Pre-trained Language Model as a feature extractor with two modelling approaches, the traditional Machine learning algorithms such as Support Vector Machine (SVM), XGBoost, Random Forest and the Long Short-Term Memory (LSTM) Deep learning architecture. IndoBERT generates contextual semantic representations from the finding texts, which are then used as input features for two modelling approaches, traditional Machine learning algorithms such as SVM, XGBoost, and Random Forest and the Long Short-Term Memory (LSTM) Deep learning architecture, aimed at capturing sequential dependencies within the text. Model performance was evaluated and compared against conventional (SVM) and pure Deep learning (LSTM) baselines. The experimental results definitively show that the IndoBERT integration strategy is significantly superior. The IndoBERT - LSTM model was established as the absolute best model, achieving the highest Accuracy of 0.90 and an F1-Score of 0.90. This performance represents an improvement of 45.16% over the pure LSTM baseline and 26.76% over the SVM baseline. Overall, the IndoBERT - LSTM model provides the most accurate and consistent solution for automating the classification of audit findings.
Unemployment Forecasting in North Sulawesi Using a Long Short-term Memory (LSTM) Algorithm Melati Roring; Gladly Caren Rorimpandey; Kristofel Santa
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.111436

Abstract

Unemployment remains a key socio-economic indicator that reflects both economic performance and human development conditions at the regional level. In North Sulawesi Province, unemployment levels have shown noticeable fluctuations over the past two decades, driven by changes in labour market structure, workforce characteristics, and development outcomes. This study aims to forecast the number of unemployed people in North Sulawesi by applying a multivariate Long Short-Term Memory model capable of capturing long-term temporal dependencies in time-series data. The analysis uses annual data published by Statistics Indonesia for the period 2000–2025. Several explanatory variables are selected through Pearson correlation analysis, including the Open Unemployment Rate, the number of unemployed women, the population that has never been employed, and the Human Development Index. All variables are normalised and transformed into five-year sliding windows to preserve temporal relationships. The model is constructed using a single hidden layer with 32 units and a dropout rate of 0.2 and is trained using the Adam optimisation algorithm. The evaluation results indicate that the proposed model achieves satisfactory predictive accuracy, with a Mean Absolute Error of 2,960 persons, a Root Mean Square Error of 3,454 persons, and a Mean Absolute Percentage Error of 3.56 percent. Forecasting results for the 2026–2030 period show a gradual decline in unemployment levels. These findings suggest that the model provides reliable unemployment projections and supports data-driven employment policy planning in North Sulawesi.
Design and Implementation of An ETL-Based Data Management Pipeline Using a Semi-Kimball Approach for Business Intelligence in Boarding House and Laundry MSMEs: English I Made Yoga Sattwika Darma; Luh Gede Astuti
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.113448

Abstract

Micro, small, and medium enterprises (MSMEs) in the service sector, particularly boarding house and laundry businesses, often face challenges in managing operational data in an integrated and structured manner to support effective decision-making. In practice, most business owners rely on fragmented records and experiential judgment, resulting in limited ability to identify operational patterns and optimize business performance. This study proposes the design and implementation of a lightweight data management pipeline based on Extract, Transform, Load (ETL) and a data mart using a semi-Kimball approach to support Business Intelligence in MSMEs. The research adopts a Design Science Research (DSR) methodology, focusing on the development of a practical system artifact. The dataset consists of a combination of internal operational data, data from similar businesses, and simulated data reflecting realistic operational conditions. The system is implemented using Python for ETL processes, SQLite as a lightweight data warehouse, and Flask for backend and API services. The results demonstrate that the proposed system successfully integrates multi-source data—including occupancy, laundry transactions, and operational activities—into a structured and consistent data model. The system further enables the delivery of interactive dashboards that support descriptive and diagnostic analytics, facilitating the identification of operational patterns and improving data-driven decision-making.
Harnessing Machine Learning for Financial Inclusion: SVM Vs. Logistic Regression in Microfinance Credit Eligibility Classification Ni Putu Noviyanti Kusuma; Ni Wayan Nanik Suaryani Taro Putri
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.113782

Abstract

Village Credit Institutions, known locally as Lembaga Perkreditan Desa (LPD), play a fundamental role in Bali's financial inclusion ecosystem by integrating formal credit evaluations with the socio-cultural considerations of indigenous communities. As the volume of credit applications escalates, relying on subjective manual assessments becomes susceptible to inconsistency, potentially triggering non-performing loan risks while simultaneously hindering capital access for potential borrowers. This comparative study empirically evaluates the performance of Support Vector Machine (SVM) and Logistic Regression (LR) algorithms in classifying customer creditworthiness at LPD Sibetan, Karangasem Regency. Utilizing 4,000 historical credit application records from January 2020 to December 2024, both models were extensively optimized using a Grid Search approach with 5-fold cross-validation. The results demonstrate that the SVM model with a linear kernel consistently outperforms Logistic Regression across all evaluation metrics. SVM achieved a classification accuracy of 90.00%, precision of 90.91%, recall (sensitivity) of 96.77%, and an Area Under the Curve (ROC-AUC) score of 98.92%. Conversely, the Logistic Regression model with L1 regularization recorded an accuracy of 86.12% and an ROC-AUC of 97.52%. An anatomy of the confusion matrix reveals that SVM is vastly superior in suppressing both False Positives (financial risk) and False Negatives (opportunity cost). By comparing the robustness of SVM and Logistic Regression, this study contributes to financial inclusion by providing a more accurate credit scoring model for microfinance institutions, ensuring that communities previously deemed high-risk can be reassessed more fairly and gain access to capital.
Developing IT Strategic Plan for Mangrove Conservation Using TOGAF ADM: A Case Study of the M4CR Loan Project Putu Raditya Astika Putra; Dana Indra Sensuse; Raden Trimanadi
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.115211

Abstract

The Mangrove for Coastal Resilience (M4CR) Loan Project is a national initiative supported by a USD 400 million World Bank loan targeting the rehabilitation of 600,000 hectares of degraded mangroves in Indonesia. Loan disbursement is governed by Performance-Based Conditions (PBC), demanding a reliable, integrated ICT system. However, the project suffers from fragmented ICT development, absence of a strategic plan, and post-institutional transition challenges following the dissolution of BRGM in 2024. This study aims to develop an ICT Master Plan (RITIK) for M4CR using the TOGAF Architecture Development Method (ADM). A qualitative interpretive approach combining case study and action research was employed. Data was collected through in-depth interviews with three key informants (PPK, IT Expert, IT Assistant), observation, and document review. TOGAF ADM was applied from the Preliminary Phase through Opportunities, Solutions, and Migration Planning (Phases E–F), with ArchiMate 3.2 as the modeling notation. Results include: (1) a five-module integrated IS architecture (SI_DMPM, SI_KONTRAK, SI_OPERASIONAL, SI_EKSEKUTIF, SI_PENGETAHUAN) built on an open-source infrastructure stack (PostgreSQL/PostGIS, GeoServer, containerization); (2) a technology architecture shifting from fragmented SaaS dependency to a centralized, organization-owned server; and (3) a four-phase technical implementation roadmap (2026–2027) within a broader 2026–2030 ICT strategic planning horizon designed to ensure post-project governance continuity validated through internal FGD. The RITIK provides strategic guidance for ICT governance continuity across institutional transitions and PBC target acceleration.
An Internet of Things-Based Drinking Water Quality Monitoring Using Support Vector Machine and Support Vector Regression Dea Putri Amanda; Lindawati; Mohammad Fadhli
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.117294

Abstract

Drinking water quality monitoring is essential to ensure compliance with water quality standards and protect public health. However, conventional monitoring methods often relied on periodic inspections and laboratory testing, making continuous supervision difficult. This study aimed to develop an Internet of Things-based drinking water quality monitoring system integrated with machine learning to classify water quality and predict the remaining filter lifetime. The system utilized pH, turbidity, and Total Dissolved Solids sensors connected to an ESP32 microcontroller for real-time data acquisition. Measurement data were transmitted, stored in a MySQL database, and processed using Support Vector Machine for water quality classification and Support Vector Regression for filter lifetime prediction. Machine learning models were evaluated using metrics for classification and regression, while sensor performance was tested by comparing measurement results with reference equipment. The results show that the developed sensors achieve average error values of 3.94% for pH, 5.26% for turbidity, and 1.82% for Total Dissolved Solids measurements. The Support Vector Machine model achieves an accuracy of 94.85% in classifying water quality, while the Support Vector Regression model obtains low prediction errors and a coefficient of determination of 0.9977. The integrated system successfully performs real-time monitoring, water quality classification, and filter lifetime prediction. These findings indicate that the proposed system provides an effective approach for drinking water quality monitoring and predictive filter maintenance.
Information Systems Success and User Acceptance in Digital Tax Transformation: A Systematic Literature Review Gede Angga Ardiana; Milla Sepliana Setyowati
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.117399

Abstract

Digital transformation in tax administration often faces structural challenges due to the fragmentation between information system success and user acceptance research. This study aims to synthesize the existing literature and develop an integrative conceptual framework for digital tax administration transformation. Using a Systematic Literature Review (SLR) approach, 26 Scopus-indexed articles published between 2021 and 2026 were analyzed following the PRISMA protocol and quality assessment procedures. The findings indicate that system quality, information quality, service quality, and trust are key factors shaping perceived usefulness, user satisfaction, and technology adoption. The literature further suggests that sustained system use is associated with improved tax compliance, organizational benefits, and broader digital transformation outcomes. In addition, digital literacy, organizational readiness, top management support, and change management were identified as important contextual factors. The study concludes that digital tax system success cannot be understood solely from either technical or behavioral perspectives. Its primary contribution is the development of an Integrated Framework of Digital Tax Transformation Success that conceptually links system success, user acceptance, tax compliance, and digital transformation outcomes within a unified framework.
Development Of a YOLOV4-Based Orange Fruit Detection Model for Orange Counting Using the Coco Dataset I Gusti Ngurah Surya Ardika Dinataputra; Kadek Yota Ernanda Aryanto; Anak Agung Gede Yudhi Paramartha; I Made Gede Sunarya
INSERT : Information System and Emerging Technology Journal Vol. 7 No. 1 (2026)
Publisher : Information System Study Program, Faculty of Engineering and Vocational, Undiksha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/insert.v7i1.117660

Abstract

Orange counting during harvest season is important because pricing decisions depend on estimated yield, and miscalculation can disadvantage both farmers and traders. This study developed an orange fruit detection model using YOLOv4 and training data derived from the Microsoft COCO dataset. The problem context was established through interviews with Siam orange farmers in Belantih, Kintamani, Bangli, where counting errors were reported to reduce expected income. For model development, two training configurations were compared: a one-class model trained only on orange images and a two-class model trained on orange and apple images. Field testing images were collected in an orchard in Penikit, Badung, using the same Siam orange type targeted in the study. Evaluation was divided into three subsets: 30 orange-only images for one-class mAP evaluation, 60 mixed orange-apple images for two-class mAP evaluation, and 20 orange images for final manual counting validation. At IoU 0.50, the one-clas model achieved 85.78% mAP, whereas the two-class model achieved 33.52%. Manual counting on 20 images yielded 82% accuracy for the one-class model and 55% for the two-class model. These results show that a focused one-class formulation is more suitable for orchard-side orange counting under the constraints of this study.

Page 10 of 10 | Total Record : 98

 6   7   8   9   10 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 1 (2026) Vol. 6 No. 1 (2025) Vol. 5 No. 2 (2024) Vol. 5 No. 1 (2024) Vol. 4 No. 2 (2023) Vol. 4 No. 1 (2023) Vol. 3 No. 2 (2022) Vol. 3 No. 1 (2022) Vol 2, No 2 (2021) Vol. 2 No. 2 (2021) Vol. 2 No. 1 (2021) Vol 2, No 1 (2021) Vol 1, No 2 (2020) Vol. 1 No. 2 (2020) Vol. 1 No. 1 (2020) Vol 1, No 1 (2020) More Issue