cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Usman Ependi
Contact Email
dr.u.ependi@gmail.coom
Phone
+6281271103018
Journal Mail Official
journal@adsii.or.id
Editorial Address
Street AMD, Tanjung Harapan Alley, Taman Kavling Mandiri Sejahtera B11, Palembang, South Sumatra, Indonesia, 30151
Location
Unknown,
Unknown
INDONESIA
International Journal of Artificial Intelligence and Science
Published by Asosiasi Doktor Sistem Informasi Indonesia
ISSN : -     EISSN : 30642728     DOI : https://doi.org/10.63158/IJAIS
Core Subject : Science,
Computer Science & IT
The International Journal of Artificial Intelligence and Science (IJAIS) is independently organized and managed by the Asosiasi Doktor Sistem Informasi Indonesia (ADSII). IJAIS is an open-access journal designed for researchers, lecturers, and students to publish their findings in the fields of Artificial Intelligence and Science. IJAIS serves as a platform for sharing innovative and original research, showcasing the latest advancements and technological developments in Artificial Intelligence and Science.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 12 Documents
 1   2 
Mobile Ad Hoc Network (MANET) Performance in Disaster Recovery Mabina, Alton
International Journal of Artificial Intelligence and Science Vol. 2 No. 2 (2025): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v2i2.16

Abstract

This study evaluates the performance of Mobile Ad Hoc Networks (MANETs) in disaster recovery, addressing the gap in existing research that primarily focuses on network performance metrics. The study aims to provide a comprehensive evaluation using the Balanced Scorecard (BSC) framework, considering financial, user, process, and innovation perspectives. A quantitative approach is employed, synthesizing data from existing literature, case studies, and empirical research on MANET deployments in disaster scenarios. Key performance indicators (KPIs) are categorized into the four BSC dimensions: network efficiency (process), cost-effectiveness (financial), usability (user), and innovation capacity. The study finds that MANETs significantly enhance communication resilience during disasters but face challenges in scalability, energy consumption, and security. The BSC framework identifies high deployment feasibility and operational efficiency but highlights limitations in long-term sustainability and integration with satellite/terrestrial networks. Unlike previous studies focused solely on technical parameters, this research offers a holistic evaluation by integrating the BSC framework, providing a more comprehensive analysis. The findings suggest that adaptive routing, AI-driven optimizations, and hybrid MANET-Satellite models could improve network performance. Future research should explore real-world deployments, energy-efficient protocols, and enhanced security models using blockchain.
Web-Based Electric Bicycle Fault Diagnosis Using the Backward Chaining Method Nugroho, Satrio Wicaksono; Dwi Nor Amadi; Pradityo Utomo; Candra Budi Susila
International Journal of Artificial Intelligence and Science Vol. 2 No. 2 (2025): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v2i2.35

Abstract

This study aims to develop a web-based expert system for diagnosing electric bicycle faults using the backward chaining method. It addresses the limitation of previous systems that did not support user input of fault hypotheses. The research stages include literature review, data collection (31 faults and 5 symptoms), implementation of web-based inference, and black box testing. The results demonstrate that the system successfully accommodates user-input hypotheses and related symptoms, then matches them with rules to generate diagnoses. Functional testing confirms all features operate as intended. The research novelty lies in: (1) the first comprehensive knowledge base for electric bicycles (31 faults), (2) an interactive web interface supporting hypothesis input, and (3) dynamic database storage for rule updates.
Optimizing Arduino-Based Laser Cut Machine Settings for Home Industry Subagyo, Ibnu Rivansyah; Prasetyaningrum, Putri Taqwa
International Journal of Artificial Intelligence and Science Vol. 1 No. 1 (2024): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v1.i1.3

Abstract

The rapid development of laser technology has significantly impacted various industrial sectors, particularly through the use of CNC laser cutting machines. These machines offer distinct advantages and limitations, making them suitable for processing a wide range of materials. This study aims to identify the most effective and efficient settings for a diode-based CNC laser cutting machine, specifically for cutting plywood. An experimental approach was employed, involving the design, creation, and testing of the machine. The research focused on optimizing the focus point and operational settings to achieve precise cuts. The results indicate that the optimal focus point is 12.6 mm, with the best cutting performance achieved at a speed of 500 mm/min, 30% laser power, and 7 passes. The findings suggest that this CNC laser machine is highly efficient for small-scale industries, offering affordability, ease of production, and reduced labor costs by automating multiple machines with a single computer. However, its application is limited in large-scale manufacturing due to constraints related to the Arduino-based control system and the maximum work area size.
Vehicle Detection on The Traffic Using Detection Transformer (DETR) Algorithm Khoiriyah, Rofiatul; Hendrawan, Aria
International Journal of Artificial Intelligence and Science Vol. 1 No. 1 (2024): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v1.i1.4

Abstract

Object detection is a computer vision technique aimed at detecting and identifying objects in images or videos. In recent years, with advancements in Machine Learning and Deep Learning, object detection has made significant progress in various fields such as healthcare, security, and transportation. The DETR algorithm is a novel approach in object detection that combines transformer architecture with attention techniques to address object detection challenges. This research applies the DETR algorithm with ResNet backbone for vehicle detection on the roads, involving 6 object classes: Car, Truck, Bus, Motorcycle, Pickup Car, and Truck Box. Four training experiments were conducted: DETR-ResNet50, DETR-ResNet101, DETR-DC5-ResNet50, and DETR-DC5-ResNet101. The implementation results show that DETR-DC5 improves the accuracy of vehicle detection. DETR-DC5 with ResNet-101 achieved the highest score for AP50, which is 0.957. However, it should be noted that DETR-DC5 with ResNet-50 managed to maintain overall AP stability, with a lower parameter of 35.5. The model's outcomes in this study can be effectively applied for vehicle detection on the roads.
Traffic Vehicle Detection Using Faster R-CNN: A Comparative Analysis of Backbone Architectures Hakim, Luqman; Hendrawan, Aria; Khoiriyah, Rofiatul
International Journal of Artificial Intelligence and Science Vol. 1 No. 1 (2024): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v1.i1.5

Abstract

Object detection is a crucial task in computer vision, where advanced deep learning models have shown significant improvements over traditional methods. In this study, the Faster R-CNN algorithm is applied to a traffic dataset containing six vehicle categories: Bus, Car, Motorcycle, Pick Up Car, Truck, and Truck Box. The novelty of the research lies in the comparison of four backbone architectures ResNet50, ResNet50V2, MobileNetV3 Large, and MobileNetV3 Large 320 evaluated for their performance in vehicle detection at IoU thresholds of 0.5 and 0.75. The results reveal that ResNet50 provided the best overall performance, achieving mAP scores of 0.966 at IoU 0.5 and 0.887 at IoU 0.75, offering a balanced trade-off between precision and recall. ResNet50V2 and MobileNetV3 Large also performed well, with mAP scores of 0.945 and 0.870 for ResNet50V2, and 0.969 and 0.843 for MobileNetV3 Large, respectively. However, MobileNetV3 Large 320 showed the lowest detection performance, with mAP scores of 0.857 at IoU 0.5 and 0.551 at IoU 0.75. These findings provide useful insights into the suitability of different architectures for vehicle detection tasks, particularly in traffic surveillance applications.
BBCA Stock Price Prediction Using Linear Regression Method Saputra, Shannon Dominique; Widiantoro, Albertus Dwiyoga
International Journal of Artificial Intelligence and Science Vol. 1 No. 1 (2024): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v1.i1.7

Abstract

This study focuses on predicting the stock price of Bank Central Asia (BBCA) using linear regression techniques, a widely utilized statistical method in financial forecasting. Stock price prediction is critical for investors, particularly in volatile markets like Indonesia. This research analyzes the relationship between key variables, such as adjusted closing prices and trading volume, based on historical data. The methodology includes data collection, preprocessing, model construction, and evaluation using metrics like Root Mean Square Error (RMSE) to assess the model's accuracy. The results indicate that linear regression can effectively predict BBCA stock prices with reasonable accuracy, providing a practical and interpretable tool for investors. These findings contribute to financial forecasting by demonstrating the utility of linear regression in stock price prediction, particularly in emerging markets.
A Comparative Study of Logistic Regression and Support Vector Machine for COVID-19 Symptom Prediction Ferdiansyah, Ferdiansyah; Putra, Briandy Tri; Yulianingsih, Evi; Fatmasari, Fatmasari; Idham, Muhammad
International Journal of Artificial Intelligence and Science Vol. 1 No. 1 (2024): September
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v1.i1.8

Abstract

The rapid spread of COVID-19 has created a critical need for accurate and efficient tools to predict symptoms and aid in early diagnosis. This study aims to compare the effectiveness of two machine learning models, Logistic Regression and Support Vector Machine (SVM), in predicting COVID-19 symptoms based on patient data. The dataset used contains key COVID-19 symptoms, which were processed and modeled using both techniques. Logistic Regression was evaluated alongside SVM using three different kernels: Linear, Sigmoid, and Radial Basis Function (RBF). The models' performance was measured using the Confusion Matrix to assess accuracy. Logistic Regression achieved an accuracy of 96.78%, while the SVM with the RBF Kernel slightly outperformed it with an accuracy of 96.85%. The SVM with the Sigmoid Kernel performed the least effectively, with an accuracy of 95.19%. These findings suggest that both models are highly effective for symptom prediction, with the RBF Kernel showing the best overall performance in handling complex, non-linear data patterns.
Classification of Aquatic Species in Cultivation Ponds via Image Processing and Machine Learning Setiawan, Arif; Wahyu Wibowo, Angga; Setiaji, Pratomo; Agus Triyanto, Wiwit; Arifin, Muhammad
International Journal of Artificial Intelligence and Science Vol. 2 No. 1 (2025): March
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v2.i1.9

Abstract

Fish cultivation is a vital economic activity for coastal communities, yet traditional farming methods often face challenges such as environmental instability, feeding inefficiencies, and water pollution. Effective monitoring of underwater environments is essential to improve fish quality and farming efficiency. A crucial part of this process is the accurate classification of fish and non-fish objects. This study proposes a method for underwater classification using morphometric feature extraction and machine learning techniques. The research process involves six main steps: (1) preparation of Region of Interest (ROI) detection data, (2) extraction of morphometric features—length (L) and width (W), (3) feature computation, (4) data partitioning for training and testing, (5) classification using Support Vector Machine (SVM), Random Forest (RF), and K-Nearest Neighbor (KNN), and (6) evaluation using a confusion matrix. Among all models tested, the Random Forest algorithm yielded the highest accuracy at 93%, with classification results showing True Positive = 349, False Positive = 28, True Negative = 223, and False Negative = 0. The findings highlight RF’s potential for enhancing automated fish monitoring in smart aquaculture systems.
Enhancing Security Protocols for MANETs in 5G-Enabled Smart Healthcare Systems Mabina, Alton
International Journal of Artificial Intelligence and Science Vol. 2 No. 1 (2025): March
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v2.i1.15

Abstract

Mobile Ad Hoc Networks (MANETs) and 5G technologies offer transformative capabilities for healthcare systems, especially in developing countries like Botswana. MANETs provide decentralized, flexible connectivity, while 5G ensures high-speed, low-latency communication—together enabling critical services such as telemedicine, real-time patient monitoring, and emergency response. However, their integration introduces significant security risks, including data breaches, unauthorized access, and system vulnerabilities. This paper proposes a Comprehensive Multi-Layer Security Framework to address these challenges, combining encryption, secure MANET routing protocols, 5G network slicing, blockchain authentication, and AI-driven intrusion detection. The framework aims to secure patient data at every network layer, enhancing system integrity, confidentiality, and availability. Implementation strategies include phased infrastructure development, workforce training, and the creation of data protection regulations. The study also emphasizes the importance of international cooperation and technology adaptation for resource-constrained environments. By adopting this model, Botswana can establish a secure, scalable healthcare infrastructure that supports innovation and improves access to quality care.
A Hybrid Image Processing Approach for Real-Time Face Recognition in Attendance Monitoring Agho, Davit Cany; Hendrawan, Aria
International Journal of Artificial Intelligence and Science Vol. 2 No. 1 (2025): March
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/IJAIS.v2.i1.17

Abstract

In the era of digital transformation, institutions are increasingly adopting automation to enhance administrative efficiency, particularly in human resource management. At Tanggirejo Village Hall, a critically low employee attendance rate of 46.45% in January 2024 exposed the limitations of manual attendance systems, which are prone to errors and manipulation. This study proposes a face recognition-based attendance system utilizing OpenCV’s Haar Cascade Classifier for face detection and the Local Binary Pattern Histogram (LBPH) for face recognition. A total of 500 grayscale facial images from 10 employees were collected and processed to train and test the system. Evaluation using a Confusion Matrix revealed an accuracy of 72%, precision of 93%, and recall of 75%. While a 27% error rate was observed—primarily due to lighting inconsistencies and limited training data—the system performed reliably in real-time scenarios. The integration of these lightweight algorithms allows for fast and accurate identification, suitable for resource-constrained environments. This solution not only addresses the local attendance challenges but also presents a scalable, automated model that can be adopted by similar institutions seeking to improve productivity and operational transparency through real-time employee monitoring.

Page 1 of 2 | Total Record : 12

 1   2 

Filter by Year

2024 2025


Reset
Filter By Issues
All Issue Vol. 2 No. 2 (2025): September Vol. 2 No. 1 (2025): March Vol. 1 No. 1 (2024): September