cover
Contact Name
Akim Manaor Hara Pardede
Contact Email
jaiea@ioinformatic.org
Phone
+6281370747777
Journal Mail Official
jaiea@ioinformatic.org
Editorial Address
Jl. Gunung Sinabung Perum. Grand Marcapada Indah. Blok. F1. Kota Binjai. Sumatera Utara
Location
Unknown,
Unknown
INDONESIA
Journal of Artificial Intelligence and Engineering Applications (JAIEA)
Published by Yayasan Kita Menulis
ISSN : -     EISSN : 28084519     DOI : https://doi.org/10.53842/jaiea.v1i1
The Journal of Artificial Intelligence and Engineering Applications (JAIEA) is a peer-reviewed journal. The JAIEA welcomes papers on broad aspects of Artificial Intelligence and Engineering which is an always hot topic to study, but not limited to, cognition and AI applications, engineering applications, mechatronic engineering, medical engineering, chemical engineering, civil engineering, industrial engineering, energy engineering, manufacturing engineering, mechanical engineering, applied sciences, AI and Human Sciences, AI and education, AI and robotics, automated reasoning and inference, case-based reasoning, computer vision, constraint processing, heuristic search, machine learning, multi-agent systems, and natural language processing. Publications in this journal produce reports that can solve problems based on intelligence, which can be proven to be more effective.
Articles 430 Documents
Operational Data Analysis and Visualization of PT XYZ Using Business Intelligence Approach with Microsoft Power BI M. Frizky Feri Setiawan; Yekti Condro Winursito
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.722

Abstract

The study aims to analyze and visualize operational data at PT XYZ, a furniture manufacturing company, utilizing Business Intelligence methods with Microsoft Power BI. A systematic approach was employed, encompassing data import, transformation, cleaning, and visualization, to develop an interactive dashboard that enhances decision-making. Key findings indicate that certain production sections consistently met or exceeded their targets, while others revealed opportunities for improvement. Insights into service wage distribution, standard time requirements, and target realizations were derived from the dashboard. The research identified sections with high service wages and highlighted areas with elevated standard times, suggesting a need for efficiency enhancements. Recommendations include focusing on underperforming sections and optimizing operations to reduce service wages. The study concludes that the developed dashboard supports data-driven decision-making, ultimately contributing to improved operational performance within the companys.
Designing a Web-Based Student Attendance System for Madrasah Ibtidaiyah Al Hikmah Debong Moh. Rival Ghulam Khadiri; Wahyu Krishantoro
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.723

Abstract

Monitoring student attendance at school is a shared responsibility between the school and parents or guardians. However, the manual attendance system currently in use often leads to issues, such as students being absent without permission and going unnoticed. For instance, a student may inform their parents that they are going to school but fail to attend classes. This situation raises serious concerns for both the school and parents, as it impacts student discipline and supervision. To address these issues, a web-based student attendance system is required to monitor attendance more effectively and in real time. This system is designed with the primary goal of enhancing the efficiency of attendance data management, minimizing human errors in attendance recording, and providing convenience for parents and school administrators in monitoring student attendance. This study aims to contribute to the field of education by developing a modern, efficient, and integrated attendance tracking technology. The proposed web-based attendance system not only automatically records student attendance but also generates accurate attendance reports that can be accessed anytime by relevant stakeholders. Therefore, this system is expected to improve transparency, effectiveness, and accountability in supervising student attendance at Madrasah Ibtidaiyah Al Hikmah Debong.
Design of a Web-Based Inventory Management System for the Nutrition Installation at Harapan Sehat Hospital, Jatibarang Yuniarti, Deni; Jaka Subrata
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.725

Abstract

The rapid development of information technology has had a significant impact on various sectors, particularly in business and economics. In the context of data management within companies, inventory systems play a crucial role in minimizing the potential manipulation of company assets. The inventory management system, which was originally handled manually, has now evolved into a website-based system. The main goal of this development is to reduce human error and increase efficiency in recording the flow of goods in and out. This system, designed specifically for the Nutrition Installation at Harapan Sehat Hospital in Jatibarang, aims to assist staff in efficiently recording and managing inventory while generating accurate reports based on the required data. The website is built using MySQL as the database for storing inventory information, with CSS and HTML for the interface, and PHP as the programming language to implement the system's functionality. This research employs a qualitative analysis approach, with data collection techniques including observations and interviews for primary data, as well as notes, books, and documents related to inventory as secondary data. It is expected that this inventory management system will effectively support inventory management needs at Harapan Sehat Hospital in Jatibarang, facilitating more efficient and accurate inventory control.
Improving Regional Clustering Based on Tuberculosis Cases using the K-Means Algorithm of the Cirebon City Health Office Wilda Rusmiati Rahayu; Purnamasari, Ade Irma; Bahtiar, Agus; Kaslani
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.727

Abstract

Tuberculosis (TB) is a highly infectious disease prevalent in Indonesia, including Cirebon City. This study utilizes the K-Means algorithm to optimize the clustering of areas based on TB case data from the Cirebon Health Office. By analyzing the number of cases, population density, and other factors, the study aims to identify regional clusters with similar TB case characteristics. The research employed Rapid Miner software and the Knowledge Discovery Database (KDD) methodology. The K-Means analysis categorized the study area into two clusters. Cluster_0, representing 20 areas, had lower TB risk, characterized by higher population density, smaller geographic size, and fewer TB cases. Cluster_1, representing two areas, exhibited higher TB risk, marked by lower population density, larger area, and more TB cases. The clustering quality was evaluated using the Davies-Bouldin Index (DBI), which yielded an optimal value of 0.189 at K=2K = 2. Additionally, the Avg within Centroid Performance Vector Analysis supported the clustering validity the clusters with value of 19851032.925.The results demonstrate that this clustering approach effectively identifies TB risk areas, aiding targeted interventions. The findings provide the Cirebon Health Office with a framework for better resource allocation, focusing intensive programs in high-risk regions and preventive measures in low-risk areas.
Comparison of Sentiment Analysis Models Enhanced by Naïve Bayes and Support Vector Machine Algorithms on Mobile Banking BRImo Reviews Ramadan, Muhamad Firly; Martanto; Dikananda, Arif Rinaldi; Rifa'i, Ahmad
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.732

Abstract

This study compares the effectiveness of the Support Vector Machine (SVM) and Naïve Bayes algorithms in classifying user sentiment regarding the BRImo application. User reviews were obtained from the Google Play Store platform and underwent a text preprocessing stage to clean and prepare the data. Subsequently, the SVM and Naïve Bayes algorithms were applied for sentiment analysis, using evaluation metrics such as accuracy, precision, recall, and F1-score. The results show that SVM achieved a training accuracy of 95.67% and a testing accuracy of 83.11%, with its best performance on positive sentiment (precision 92.26%, recall 91.79%, F1-score 92.02%) and moderate performance on negative sentiment (precision 62.81%, recall 62.81%, F1-score 62.81%). Meanwhile, Naïve Bayes recorded a training accuracy of 95.23% and a testing accuracy of 82.77%, with its highest performance on positive sentiment (precision 90.12%, recall 93.38%, F1-score 91.72%) but lower performance on negative sentiment (precision 65.07%, recall 60.06%, F1-score 62.46%). In terms of sentiment distribution, SVM was more effective in handling sentiment variations, particularly in detecting negative and neutral sentiments. These findings indicate that SVM outperforms Naïve Bayes in sentiment analysis of user reviews for the BRImo application.
House Price Prediction Analysis Using a Comparison of Machine Learning Algorithms in the Jabodetabek Area Ningsih, Indah Ratna; Faqih, Ahmad; Rinaldi, Ade Rizki
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.733

Abstract

Jabodetabek, as the largest metropolitan area in Indonesia, has complex property price dynamics, making it difficult for developers and buyers to determine house prices. This study aims to analyze and compare the performance of the Multiple Linear Regression and Random Forest Regression algorithms in predicting house prices in the region. The data was obtained through scraping techniques from the rumah123.com website in October 2024, covering 999 data points with variables such as price, location, building area, land area, number of bedrooms, bathrooms, and garages. A comparative approach with cross-validation was applied to evaluate the performance of both algorithms using the metrics MAE, MSE, RMSE, MAPE, and R². The research results show that Random Forest Regression using GridsearchCV has better predictive performance, with an MAE value of Rp.645,764,815, MAPE of 28.12%, and R² of 0.864. The main factors influencing house prices in Jabodetabek include building size, land size, number of bedrooms, bathrooms, garages, and location. This finding emphasizes the superiority of Random Forest Regression in capturing complex data patterns and the significant role of these variables in determining house prices.
Application of Neural Network to Predict Rupiah Exchange Rate Against Korean Won Saeful, Agung; Dwilestari, Gifthera; Rinaldi, Ade Rizki
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.734

Abstract

This study investigates the application of neural networks for predicting the exchange rate of the Indonesian Rupiah against the Korean Won, addressing the challenges posed by currency fluctuations in international trade and investment. The research employs a data mining approach utilizing historical exchange rate data, which allows the neural network to identify complex patterns that traditional forecasting methods may miss. The model is developed using RapidMiner software, facilitating data preprocessing, transformation, and evaluation. The outcomes show that the predictions were quite accurate, as indicated by a low prediction error rate. The findings suggest that the neural network model not only provides reliable forecasts but also maintains consistent performance over time. This research contributes to the growing field of artificial intelligence in finance, highlighting the potential of advanced predictive models to enhance decision-making processes in the context of global economic interactions. The study underscores the importance of integrating technology with economic analysis to better navigate the complexities of currency exchange and its implications for financial risk management.
Design of a Web-Based Computer Sales Information System at Tend Komputer Veri Rizqiyanto; Mutiara Handayani Ujianti
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.736

Abstract

The rapid advancement of technology has significantly influenced trading systems and facilitated business operations such as offering, purchasing, and selling goods and services via the internet. Alongside the development of computer technology, the internet has emerged as an effective solution to address various challenges in commerce. Business transactions can now be conducted electronically without requiring physical contact or face-to-face meetings. In the realm of online business, e-commerce plays a pivotal role in enhancing the efficiency and effectiveness of electronic business activities, offering numerous benefits for both companies and consumers. The presence of e-commerce is expected to improve services by providing comprehensive information about the offered products.This study employed data collection methods including observation, interviews, and library research. Data analysis was conducted through four stages: system survey, survey findings analysis, information needs identification, and system requirements specification. The system design utilized the Waterfall model with Unified Modeling Language (UML) tools. Furthermore, the MySQL database was applied to facilitate the processing of goods data for sales, ensuring swift, accurate, and efficient marketing efforts. The outcome of this web-based sales information system design is anticipated to enhance operational efficiency in the sales process. This system provides an integrated platform to streamline product management and improve customer access to information. Additionally, the system contributes to optimizing sales processes by reducing manual workloads and increasing data management accuracy. The implementation of this system is expected to support the effectiveness of sales activities at TEND Komputer while offering a competitive edge in an increasingly dynamic market.
Accuracy in Sentiment Analysis of the by.U Application Using Naïve Bayes and SMOTE Techniques Athhar Hafizha Luthfi; Ahmad Faqih; Gifthera Dwilestari
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.737

Abstract

Imbalanced data is a significant challenge in sentiment analysis, as it often impacts the performance of machine learning models. This study applies the Naïve Bayes algorithm, enhanced with the Synthetic Minority Oversampling Technique (SMOTE), to address class imbalance in user reviews of the by.U application. Using the Knowledge Discovery in Databases (KDD) framework, the research involves data selection, preprocessing (text cleaning, normalization, stemming), transformation using TF-IDF, and train-test data splitting. SMOTE is applied to the training data to improve minority class representation, while Naïve Bayes performs sentiment classification. Model evaluation using cross-validation demonstrates that SMOTE increases accuracy from 84.42% to 85.83%. These results underscore the effectiveness of integrating SMOTE with Naïve Bayes in addressing imbalanced data, offering meaningful insights into user sentiment and aiding the development of improved features for the by.U application.
Development of Web and Android Based Employee Attendance Monitoring Application Pratiwi, Heny; Fitriani, Nur; Junirianto, Eko; Sa'ad, Muhammad Ibnu
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.738

Abstract

This research was conducted to develop an Android-based employee attendance monitoring system that can assist the Department of Manpower and Transmigration of East Kalimantan Province in monitoring employee attendance, recapitulating employee attendance, and timely submission of attendance reports. The objective of this research is to simplify employee attendance monitoring and expedite the recapitulation of employee attendance lists at the Department of Manpower and Transmigration of East Kalimantan Province. The system development method used is the prototype model. This method consists of five stages: Communication, Quick Plan, Modeling Quick Design, Construction of Prototype, and Deployment Delivery & Feedback. The result of this research is a web-based information system for Administrators and Direct Supervisors to process data and monitor employee attendance, and an Android-based system for employees to record their check-in and check-out times. In the Android-based system, employees can also input attendance with various remarks such as early leave, absence, sick leave, personal leave, business trips, and external duties. The blackbox testing in this research shows that the system functions as expected, and the betabox testing results in a score of 89.60%.