cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mustakim
Contact Email
Mustakim
Phone
-
Journal Mail Official
ijaidm@uin-suska.ac.id
Editorial Address
-
Location
Kab. kampar,
Riau
INDONESIA
Indonesian Journal of Artificial Intelligence and Data Mining
Published by Universitas Islam Negeri Sultan Syarif Kasim Riau
ISSN : 26143372     EISSN : 26146150     DOI : -
Core Subject : Science,
Computer Science & IT
Indonesian Journal of Artificial Intelligence and Data Mining (IJAIDM) is an electronic periodical publication published by Puzzle Research Data Technology (Predatech) Faculty of Science and Technology UIN Sultan Syarif Kasim Riau, Indonesia. IJAIDM provides online media to publish scientific articles from research in the field of Artificial Intelligence and Data Mining. IJAIDM will be published 2 (two) times a year, in March and September, each edition contains 7 (seven) articles. Articles may be written in English or Indonesia.
Arjuna Subject : -
Articles 233 Documents
 19   20   21   22   23 
Implementation of Single Moving Average Method for Fashion Forecasting Musthofa Br. Butar-Butar, Yulia Syahfitri; Helmiah, Fauriatun; Syahputra, Abdul Karim
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.36181

Abstract

Toko Mazaya is a business engaged in the sale of clothing, celada and bags. During its sales, there is often a shortage or accumulation of the number of products to be marketed, not in accordance with the number of requests from customers, there is no computerized system for trading. This research aims to implement the single moving average method for forecasting the stock of products to be provided to support proper decision making. By using historical sales data from January 2024 to January 2025 to forecast 6 month ahead. the results of forecasting clothes for the next 6 months to July 2025 with the smallest MAPE level of 9.52 in May 2025 with a forecast amount of 55. While the results of pants forecasting for the next 6 months to July 2025 with the smallest MAPE level of 9.41 in June 2025 with a forecast amount of 47.50 and the results of bag forecasting for the next 6 months to July 2025 with the smallest MAPE level of 8.89 in February 2025 with a forecast amount of 40.00. 
Evaluating Entropy-Based Feature Selection for Sales Demand Forecasting Using K-Means Clustering and Naive Bayes Classification Wulandari, Fadhilah Dwi; Lindawati, Lindawati; Fadhli, Mohammad
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.37046

Abstract

Sales demand forecasting is crucial for inventory optimization in retail, especially for Micro, Small, And Medium Enterprises (MSMEs). This study examines the effect of entropy-based feature selection on the performance of a two-stage machine learning framework comprising K-Means clustering and Naive Bayes classification. The research was conducted on transactional data collected from a footwear MSME in Palembang, Indonesia, covering January to December 2024. Shannon Entropy and Information Gain were applied to identify and retain the most informative features before clustering and classification tasks. Two experimental scenarios were investigated: (1) using all features without selection and (2) applying entropy-based feature selection with Information Gain thresholds of 0.4 and 0.5 for category-based and quantity-based targets, respectively. The first scenario yielded moderate performance, with a Silhouette Score of 0.5747 and a classification accuracy of 96.97%. In contrast, the second scenario demonstrated superior results, achieving a Silhouette Score of 0.6261 and a classification accuracy of 99.49% when quantity sold was used as the target variable. These findings indicate that entropy-based feature selection reduces data dimensionality, enhances clustering compactness, and improves classification accuracy. This research contributes to the field by presenting a practical framework for sales demand forecasting in retail environments. Future work will focus on integrating additional contextual variables, such as seasonal trends and promotions, and validating the system in real-world retail settings
Synergy Analysis on Cryptocurrency Returns and Investor Sentiment Using Bidirectional Encoder Representations from Transformers (BERT) Hardiyanto, Reynaldy; Husodo, Zaäfri Ananto
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.33315

Abstract

Cryptocurrencies have become prominent alternative investments. Unlike traditional financial assets, their intrinsic value is a subject of ongoing debate since they do not have a tangible backing asset. As a result, investor sentiment heavily influences price volatility and serves as a key indicator of perceived value based on collective investor beliefs. However, major events such as the FTX scandal can severely weaken investor confidence. Social media drives market discussions, making sentiment analysis vital for understanding behavior and predicting price movements. This study examined sentiment analysis techniques to construct an investor sentiment index and investigate its relationship with cryptocurrency returns during the FTX collapse. We employed DistilBERT and the AFINN lexicon method to develop sentiment index, finding that DistilBERT achieves an F1-score of 76.49%, significantly outperforming AFINN's 30.65%. Furthermore, our results indicate a positive correlation between investor sentiment and cryptocurrency returns during the FTX collapse. Our findings indicate that deep learning models can be more effective than lexicon-based approaches for sentiment analysis in financial markets
Development of EfficientNet Model on Broad and Needles Leaved Species Tree Crowns with Forest Health Monitoring Method Hernani, Livia Ayu Istoria; Andrian, Rico; Safei, Rahmat; Tristiyanto, Tristiyanto
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.37463

Abstract

Forest Health Monitoring (FHM) is a method for monitoring forest health conditions using various ecological indicators, such as tree canopy density and transparency. This research aims to evaluate the performance of the EfficientNet model in classifying the density and transparency values of broadleaf and coniferous tree canopies. The dataset consists of 3,956 tree canopy images collected from Tahura Wan Abdul Rachman (WAR), a conservation forest in Lampung, and is divided into 10 classes based on magic cards. Magic cards are a learning medium in the form of picture cards containing values of density and transparency. This research uses the EfficientNet-B0 architecture with certain training parameters. The results show that the EfficientNet-B0 model provides the best performance with an accuracy of 90.00%, a precision of 97.00%, a recall of 97.00%, and an F1-score of 97.00%. This research shows that EfficientNet can be used effectively to assist decision making related to automatic visual monitoring of forest health.
Student Behavior Monitoring System in Classroom Environment Using YOLOv8 Sepulau, Ifroh Intan; Kusumanto, Kusumanto; Husni, Nyayu Latifah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.37086

Abstract

Student ethics in an academic environment is an important element in creating an orderly and professional learning environment. One form of ethical violation that is still often found in the lecture environment is eating and drinking activities in the classroom. This study's objective is to develop an automatic detection system for unethical student behavior in the classroom, especially eating and drinking activities, utilizing one of the newest Real-time deep learning approaches object recognition on a Raspberry Pi device, The algorithm known as You Only Look Once version 8 (YOLOv8). A special dataset was developed through a manual annotation process in the form of images and videos showing students with various activities in the classroom. This system is expected to be an additional solution in monitoring student ethics automatically, efficiently, and in real-time in a modern learning environment. The test findings demonstrate that the model can identify eating and drinking activities with a respectable degree of precision indicating that the system is able to detect target activities with an accuracy level of up 95% with fairly stable performance in good lighting conditions and certain viewing angles
Sentiment Analysis of BCA Mobile App Reviews Using K-Nearest Neighbour and Support Vector Machine Algorithm Zandroto, Yosefin Yuniati; Vitianingsih, Anik Vega; Maukar, Anastasia Lidya; Hikmawati, Nina Kurnia; Hamidan, Rusdi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.37773

Abstract

The rapid evolution of digital technology has significantly transformed the financial services landscape, especially in the realm of mobile banking. BCA Mobile stands among the most popular apps for digital banking in Indonesia. Despite its widespread adoption, user reviews reflect diverse viewpoints and sentiments about the app. The objective of this research is to examine the user sentiments regarding the BCA Mobile app, based on reviews sourced from the Google Play Store and App Store. Two classification models, namely Support Vector Machine (SVM) and K-Nearest Neighbour (K-NN), are used in the analysis process. The collected review data undergoes several pre-processing stages and is labeled automatically using a Lexicon-Based technique. For feature weighting, the TF-IDF (Term Frequency-Inverse Document Frequency) approach is used.. Sentiment classification is then carried out using both K-NN and SVM, with performance evaluated through a matrix of confusion based on measurements like F1-score, recall, accuracy, and precision.  The findings show that the SVM algorithm outperforms K-NN in terms of performance, with an accuracy of 94%, while K-NN achieves an accuracy of 82%. This study offers valuable insights for BCA management in understanding user sentiment and enhancing service quality through the application of artificial intelligence
The Ensemble Supervised Machine Learning for Credit Scoring Model in Digital Banking Institution Prahastiwi, Narita Ayu; Lubis, Muharman; Fakhrurroja, Hanif
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 2 (2025): July 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i2.37677

Abstract

The digital transformation of the banking industry requires credit scoring systems that are both accurate and adaptable to complex, diverse data. This study aims to develop and evaluate a credit scoring model using ensemble supervised learning to predict credit risk for a consumer loan service (Product X) at Bank XYZ. Ensemble algorithms such as Random Forest, AdaBoost, LightGBM, CatBoost, and XGBoost were compared to a single classification method, Decision Tree. Model performance was assessed using precision, recall, F1-score, and ROC-AUC. The results show that XGBoost outperformed other models, achieving the highest ROC-AUC score of 0.803, indicating strong generalization and low risk of overfitting. SHAP analysis revealed key features influencing the model, including loan tenor, loan amount (plafond), income, and Days Past Due (DPD) history. Compared to the baseline Decision Tree model (ROC-AUC 0.573), XGBoost significantly improved classification accuracy. It also showed the potential to reduce the Non-Performing Loan (NPL) rate from 4% to below 3% and increase the approval rate from 65% to over 70%, aligning with Product X’s KPIs. These findings confirm that ensemble learning models especially XGBoost offer strategic value in enhancing credit portfolio quality and decision-making in digital banking.
Real-Time Access Control System with YOLOv11-Based Face and Blink Detection Rifani, Namira Nur; Kusumanto, RD.; Husni, Nyayu Latifah
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i3.36812

Abstract

This study presents a real-time smart access control system that combines facial recognition with blink-based liveness detection to strengthen security and reduce spoofing risks. The main purpose is to provide a lightweight and efficient method that verifies both identity and physical presence in real time. The system employs two YOLOv11 models: one for detecting facial regions and another for distinguishing eye states through “open” and “closed” transitions. Identity verification is carried out by comparing facial embeddings using Euclidean distance. A private dataset was collected for facial images, while blink data was obtained from a public source, both annotated in YOLO format. After 100 epochs, the face detection model achieved 0.999 precision, 1.000 recall, 0.995 mAP50, and 0.868 mAP50–90, while the blink detection model recorded 0.959 precision, 0.962 recall, 0.967 mAP50, and 0.678 mAP50–90. These outcomes confirm that the objectives were achieved, demonstrating a practical and reliable biometric authentication solution with integrated liveness verification. The system also offers scalability for future multi-modal applications.
Carbon Emission Trends (1999–2022): Forecasting Association of Southeast Asian Nations (ASEAN)'s Future Using a Hybrid Approach to Support Zero-Emission Policies Dhika, Muhammad Rama; Lestari, Sri
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i3.36685

Abstract

Carbon Dioxide (CO₂) emissions are a primary driver of global climate change, with the energy sector being the dominant contributor. Southeast Asia, experiencing rapid economic growth, faces significant increases in CO₂ emissions due to high energy consumption. This study proposes a hybrid Autoregressive Integrated Moving Average (ARIMA)-XGBoost approach to predict CO₂ emissions in Association of Southeast Asian Nations (ASEAN) countries from 2023 to 2035, overcoming limitations of traditional linear models by combining machine learning (XGBoost) and time-series analysis ARIMA. Results demonstrate high accuracy (R² = 0.98) with the identification of key factors, including Gross Domestic Product (GDP), population, and total greenhouse gas (GHG) emissions. For instance, Indonesia's emissions are predicted to rise from 841.84 MtCO₂ (2023) to 2197.36 MtCO₂ (2035), while Brunei's emissions decrease from 10.86 MtCO₂ to 9.57 MtCO₂. Residual analysis and k-fold cross-validation confirm model robustness. These findings underscore the need for differentiated policies, such as renewable energy transitions in high-growth emission countries (Indonesia, Philippines) and regulatory strengthening in stable-trend nations (Brunei, Laos). The study provides methodological contributions to data-driven emission forecasting and evidence-based policy recommendations for the Association of Southeast Asian Nations (ASEAN) climate change mitigation.
Discovering Prescription Patterns in Type 2 Diabetes Based on Demographic Attributes Using Association Rules Yani, Putri; Hikmah, Maulida; Mahdiana, Deni
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i3.38082

Abstract

Type 2 diabetes mellitus (T2DM) is a chronic disease that requires effective long-term therapeutic management. Appropriate and continuous treatment is crucial to prevent complications and improve patients’ quality of life. In clinical practice, prescription patterns vary significantly and are influenced by demographic and clinical characteristics. This study aimed to analyze prescription patterns of T2DM patients based on demographic and clinical attributes, and to identify frequently co-prescribed drug combinations using the Apriori algorithm. A total of 3,500 prescription records were obtained from RSUD H. Damanhuri Barabai. The analysis was conducted in two stages: (1) association between demographic factors (age, gender, blood pressure) and prescribed drugs, and (2) association among drugs regardless of patient demographics. With minimum support of 3%, confidence thresholds of 60% and 35%, and lift greater than 1.5, fifteen valid rules were identified in the demographic-to-drug analysis, and nine rules in the drug combination analysis. Strong patterns were observed, such as the prescription of Empagliflozin and Insulin Degludec for hypertensive patients aged 40–49, and the co-prescription of Acarbose and Glimepiride. These findings demonstrated that the Apriori algorithm was effective in identifying meaningful prescription patterns. Beyond methodological contributions, the results provide practical value for hospitals by supporting pharmacy managers in drug procurement planning, optimizing stock management, and designing distribution strategies that anticipate patient needs based on prescription trends.

Page 21 of 24 | Total Record : 233

 19   20   21   22   23 

Filter by Year

2018 2025


Reset
Filter By Issues
All Issue Vol 8, No 3 (2025): November 2025 Vol 8, No 2 (2025): July 2025 Vol 8, No 1 (2025): March 2025 Vol 7, No 2 (2024): September 2024 Vol 7, No 1 (2024): March 2024 Vol 6, No 2 (2023): September 2023 Vol 6, No 1 (2023): Maret 2023 Vol 5, No 2 (2022): September 2022 Vol 5, No 1 (2022): March 2022 Vol 4, No 2 (2021): September 2021 Vol 4, No 1 (2021): March 2021 Vol 3, No 2 (2020): Spetember 2020 Vol 3, No 1 (2020): March 2020 Vol 2, No 2 (2019): September 2019 Vol 2, No 1 (2019): March 2019 Vol 1, No 2 (2018): September 2018 Vol 1, No 1 (2018): March 2018 More Issue