cover
Contact Name
Bahtiar Imran
Contact Email
bahtiarimranlombok@gmail.com
Phone
+6285337626083
Journal Mail Official
bahtiarimranlombok@gmail.com
Editorial Address
Perumahan Green Asia Blok I2-04, Kecamatan Labuapi, Kabupaten Lombok Barat Nusa Tenggara Barat, Indonesia
Location
Kab. lombok barat,
Nusa tenggara barat
INDONESIA
Jurnal Kecerdasan Buatan dan Teknologi Informasi
ISSN : 29636191     EISSN : 29642922     DOI : https://doi.org/10.69916
Core Subject : Science,
Jurnal Kecerdasan Buatan dan Teknologi Informasi or abbreviated JKBTI is a national journal published by the Ninety Media Publisher since 2022 with E-ISSN : 2964-2922 and P-ISSN : 2963-6191. JKBTI publishes articles on research results in the field of Artificial Intelligence and Information Technology. JKBTI is committed to becoming the best national journal by publishing quality articles in Indonesian and English and becoming the main reference for researchers. All submissions are blind and reviewed by peer reviewers. All papers can be submitted in BAHASA INDONESIA or ENGLISH. Scope : Neural Networks, Machine Learning, Deep Learning, Data Mining, Big Data, Decision-Making System, Information System, Mobile Application, Data Warehouses, Database, Internet of Thing, Expert System.
Articles 170 Documents
Polynomial Regression Model for Predicting PVC Ceiling Sales Based on Historical Data: A Case Study at CV. Kilaw Maju Bersama M. Ilham Akbar; Herri Setiawan; Zaid Romegar Mair
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.597

Abstract

The growth of the building materials industry, particularly PVC ceilings, requires accurate sales forecasting to support production stability, distribution efficiency, and inventory management. CV. Kilaw Maju Bersama, a PVC ceiling distributor, faces weekly sales fluctuations based on 104 weekly observations from January 2023 to December 2024. This study develops a Polynomial Regression model to forecast PVC ceiling sales using average selling price, number of retail stores, and promotional activities as independent variables. A quantitative approach was applied through data collection, data cleaning, exploratory data analysis (EDA), chronological time-series train-test splitting without shuffling, Z-score standardization, polynomial degree selection using TimeSeriesSplit, and model evaluation using MAPE, RMSE, and R 2 . The results show that the degree-1 Polynomial Regression model achieved a training MAPE of 3.12%, RMSE of 129.741, and R 2 of 0.643, while the testing set achieved a MAPE of 4.57%, RMSE of 187.311, and R 2 of 0.380. These results indicate low prediction error and satisfactory generalization to unseen data. The model therefore provides a practical decision-support tool for weekly sales forecasting, inventory planning, and data-driven business decision-making in the building materials industry.
Implementation of a Web-Based Rule-Based System for Determining Goat Health Status from Clinical Symptoms and Feeding Patterns Azka Naufal El Rumi; Mulkan Azhari
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.598

Abstract

Goat farmers frequently rely on direct observation and personal experience to assess animal health, while similar clinical signs and limited access to veterinary personnel can delay initial handling. This study develops a web-based expert system using a rule-based system and forward chaining to determine goat health status from clinical symptoms, feeding patterns, and additional observable conditions. Knowledge was represented as 45 IF–THEN rules stored in a MySQL database. The application was implemented with PHP and provides modules for consultation, health-status recommendations, administration of symptoms, feeding patterns, additional conditions, health categories, diagnostic rules, and diagnosis history. The inference process begins with facts selected by the user and matches them against the knowledge base until a conclusion is obtained. The system generates four health-status outcomes: healthy, unhealthy, sick, and indicated mild illness, together with initial handling recommendations. Black-box testing covered the public interface, consultation form, forward-chaining process, result page, and administrator functions. All tested functions produced the expected outputs. The implementation demonstrates that integrating clinical signs and feeding behavior within a transparent rule-based workflow can support structured initial health assessment for goats. The system is intended as decision support and does not replace examination by a veterinarian.
Design of an Augmented Reality Learning Application for Three-Dimensional Trigonometry Using Marker-Based Tracking Nurul Zakiah; Khairunnisa
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.599

Abstract

Three-dimensional trigonometry requires students to understand relationships among points, lines, planes, distances, and angles in spatial objects, yet conventional two-dimensional explanations often provide insufficient visual support. This study designed and evaluated an Android-based augmented reality learning application using marker-based tracking to present interactive models of a cuboid, cube, triangular prism, and pyramid. The application was developed with Unity 2022 LTS, Vuforia SDK, C#, and Blender. Its functions include marker scanning, three-dimensional object visualization, explanatory content, an interactive quiz, score feedback, usage guidance, and printable flashcard markers. Functional testing used eleven black-box scenarios on two Android devices, while user evaluation involved 20 students who completed a ten-item questionnaire. All functional scenarios produced the expected output, resulting in a 100% success rate. The Vuforia image targets achieved a four-star rating; the effective detection distance was 17–50 cm, with usable viewing angles between 45 and 90 degrees. Student evaluation produced an average score of 95.1%, classified as good according to the study criteria. The findings indicate that marker-based augmented reality can provide stable spatial visualization, straightforward navigation, and an engaging supplementary medium for learning three-dimensional trigonometry. Future development should expand the learning material, increase the question bank, optimize performance on lower-specification devices, and examine markerless tracking.
Employee Performance Classification Using Optimized Random Forest with Max Depth and N-Estimators at PT Bringin Gigantara M. Imam Saputra; Rendra Gustriansyah; Dwi Asa Verano
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.602

Abstract

Employee performance assessment is a crucial component of human resource management because it supports strategic decisions such as contract renewal, incentives, and competency development. This study proposes an optimized Random Forest model for employee performance classification at PT Bringin Gigantara by tuning the max_depth and n_estimators hyperparameters. The dataset consists of monthly performance evaluation records from 100 contract employees during January–December 2024, including ten performance variables. During model development, hyperparameter optimization was conducted exclusively on the training set using Stratified 5-Fold Cross-Validation to evaluate parameter combinations and select the most stable and accurate configuration. The optimization results indicate that the best-performing configuration was n_estimators = 50 and max_depth = 10, achieving a mean cross-validation accuracy of 98%. The optimized model achieved 98.75% accuracy on the training set and 95% accuracy on the test set, with corresponding precision, recall, and F1-score values demonstrating good classification performance. The findings indicate that the optimized Random Forest model can provide a practical, objective, and data-driven decision-support tool for human resource personnel in evaluating employee performance and supporting contract renewal decisions. Nevertheless, the model is intended to support, rather than replace, managerial judgment.
MyOLC: An Intelligent Learning Ecosystem with Automated Multi-Role Tracking for Non-Formal Education in the Society 5.0 Era Zaeniah Zaeniah; Ahmad Subki
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.603

Abstract

Technological developments have brought significant changes in various fields, including education. Optima Mataram Tutoring is one of the non-formal educational institutions that is required to adapt to technological developments to improve the quality of learning services. Optima Mataram Tutoring is an educational institution that provides learning assistance services for students at various levels of education. However, the learning management process is still carried out conventionally, such as manual attendance recording, delivery of materials via instant messaging, and the collection of assignments that are not yet integrated, causing various obstacles to the effectiveness and efficiency of the teaching and learning process at Optima Mataram Tutoring. This condition causes difficulties in monitoring student progress and managing academic data, as well as slow and inaccurate information delivery. Therefore, in this study, a Learning Management System application was developed at Optima Mataram Tutoring that is able to support an integrated and effective learning process that is easy to access. The method used in developing this LMS is the waterfall method. This LMS is expected to meet the needs of students in receiving learning materials, the needs of teachers in conducting assessments, and the needs of parents in monitoring their children's activities during the learning process at Optima Mataram Tutoring.
Android-Based Markerless Augmented Reality for Interactive Visualization of Lava Tour Merapi (Case Study: Amtra Journey) Farid Panjasela Ramadhani; Dita Danianti; Ahmad Subhan Yazid; Dhina Puspasari Wijaya
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.605

Abstract

The Lava Tour Merapi is a key tourist destination located in Sleman Regency, providing educational experiences about the history of Mount Merapi's eruptions. However, most tourism information is still primarily provided by tour guides, which restricts visitors’ ability to access information on their own. This study aimed to create an Android-based markerless Augmented Reality (AR) application to offer interactive tourism information for the Lava Tour Merapi. Using a Research and Development (R&D) approach with the Waterfall software development model, the study included stages such as requirements analysis, system design, implementation, testing, and maintenance. The application was developed with Unity and Blender, and it implemented markerless AR combined with the Global Positioning System (GPS) to show three-dimensional virtual objects based on the user's location, eliminating the need for physical markers. Functional testing was conducted utilizing the Black Box Testing method. The results indicated that all features of the application such as package selection, route selection, destination information, interactive maps, 3D visualizations, and audio playback functioned correctly according to the specified requirements. The application ultimately provides an interactive service for location-based tourism information, allowing visitors to access destination details more easily and improving their overall tourism experience.
Implementation of Simple Additive Weighting Algorithm for Student Skill Evaluation in SMK Cahaya Otomotif 2 Abi Nanda Septiansyah; Anita Ratnasari
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.606

Abstract

Skill evaluation processes at SMK Cahaya Otomotif 2 are currently conventional, resulting in unintegrated assessment data and difficulties in real-time monitoring. This study aims to develop a web-based e-learning system implementing the Simple Additive Weighting (SAW) algorithm to automate objective student skill assessments. The system was developed using the Waterfall model with the PHP programming language and CodeIgniter framework. Assessments are based on six main criteria: quizzes, forum engagement, practical tasks, attendance, mid-term exams, and final exams. Results indicate that the system accurately generates preference scores and automatically classifies student competencies into categories ranging from "Highly Competent" to "Needs Remedial". Validation using student operational data proves a perfect alignment between system and manual calculations, as shown in the 91.75 score sample. Black Box testing confirmed that all functional features operate validly. This implementation successfully enhances grading transparency for students and facilitates the school management in monitoring skill development measurably.
Web-Based Inventory Information System for Asset and Consumable Management at Ratumbuysang Mental Hospital Faith Nathaniel Alexander; Chriestie E. J. C. Montolalu; Wisard Kalengkongan; Christian Alderij Soewoeh; Mahardika Inra Takaendengan; Stephano C.W. Ngangi
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.613

Abstract

This study aimed to design and develop a web-based Inventory Information System for Ratumbuysang Mental Hospital to address inventory management that was previously performed manually. Manual recording made inventory searching, asset tracking, and report preparation less efficient and increasedthe risk of recording errors. The system was developed using the Waterfall method through requirements analysis, system design, implementation, testing, and maintenance. The application uses React.js for the frontend, Node.js and Express.js for the backend, PostgreSQL for data management,and Prisma ORM as the database interface. The implemented functions include item master-data management, incoming assets, outgoing assets, consumable items, user management, report generation, and QR Code-based asset identification. Black Box Testing was conducted using 27 functional scenarios and showed that all tested functions operated according to the expectedresults. User Acceptance Testing (UAT) involved 24 statements using a five-point Likert scale. The overall mean score was 4.68, equivalent to 93.50%, and was categorized as Very Good in the original evaluation. These findings indicate that the developed system was accepted by users and can support structured inventory management at Ratumbuysang Mental Hospital.
Enhancing Micro-Retail Inventory Management through Dynamic Reorder Point Algorithm: System Development, ISO/IEC 25010 Performance Evaluation, and Usability Assessment Dina Widiastuti; Isti Sholikah; Clarissa Rahmawati; Alka Osy Ramadhasari
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.614

Abstract

Manual inventory management in basic necessity retail stores frequently leads to data discrepancies, inefficient stock monitoring, and high risks of stockouts. Toko AS Sembako faces these challenges, relying on manual logbooks that severely hinder daily operational efficiency and accurate decision making. To address this, this study develops a Web Based Inventory Information System utilizing the Rapid Application Development method and the robust Yii2 framework. The core novelty lies in integrating a dynamic Reorder Point algorithm to generate proactive minimum stock notifications, shifting the inventory paradigm from reactive manual checks to automated, data driven procurement. The developed system was rigorously evaluated using a comprehensive, multidimensional framework. Functional reliability testing utilizing Boundary Value Analysis yielded an exceptional 98 percent success rate, ensuring strict input validation. Performance efficiency, assessed under ISO 25010 standards, achieved an optimal average Largest Contentful Paint of 1.325 seconds, guaranteeing rapid data access. Furthermore, usability evaluation using the System Usability Scale resulted in an Excellent score of 82.5, proving the interface intuitiveness for non technical users despite algorithmic complexity. Crucially, operational impact analysis demonstrated a massive 94 percent reduction in daily administrative time, compressing manual tasks from 135 minutes down to just 8 minutes. Ultimately, this research delivers a robust, fast, and user centric digital solution that successfully prevents stockouts and significantly streamlines retail operations. These empirical findings confirm that advanced algorithmic features can be successfully abstracted into a simple interface, offering a scalable model for digital transformation in the retail sector today.
Analysis of Shopee App User Behavior Patterns Using the K-Means Algorithm and RFM Model (Case Study: ZR Store) Nafiah; Pamela Kareen
Jurnal Kecerdasan Buatan dan Teknologi Informasi Vol. 5 No. 3 (2026): September 2026
Publisher : Ninety Media Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69916/jkbti.v5i3.622

Abstract

The rapid growth of e-commerce in Indonesia has led to an increase in transaction volumes and user activity on online shopping platforms, such as the Shopee app. Large-scale transaction data can be leveraged to understand user behavior patterns, enabling companies to formulate more effective and targeted marketing strategies. This study aims to analyze the behavior patterns of Shopee app users using the Recency, Frequency, Monetary (RFM) method and the K-Means clustering algorithm. The RFM method is employed to assess customer characteristics based on the time of the last transaction (Recency), transaction frequency (Frequency), and total customer expenditure (Monetary). Subsequently, the K-Means algorithm is applied to segment users based on similarities in their transaction behavior. The dataset comprises 200 customers, with attributes including customer code, transaction date, age, gender, quantity of items purchased, shipping type, product category, and payment method. Using the K-Means algorithm, customers were grouped into three clusters: C1 (Loyal Customers), C2 (Less Loyal Customers), and C3 (New Customers). The results indicate that 90 customers fell into category C1, 39 into category C2, and 71 into category C3. Regarding rankings, the maximum rank (RRank_max) was 50 with an obtained rank value of 12.0; for Frequency (Frank), the value was 2 with a maximum rank (Frank_max) of 12.29; and an Mrank of 48.8 was obtained.