cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Safriadi
Contact Email
safriadi@pnl.ac.id
Phone
+6285262485087
Journal Mail Official
jaise@pnl.ac.id
Editorial Address
Jl. Banda Aceh-Medan Km. 280,3, Buketrata, Mesjid Punteut, Blang Mangat, Kota Lhokseumawe, 24301
Location
Kota lhokseumawe,
Aceh
INDONESIA
Journal Of Artificial Intelligence And Software Engineering
Published by Politeknik Negeri Lhokseumawe
ISSN : 2797054X     EISSN : 2777001X     DOI : http://dx.doi.org/10.30811/jaise
Core Subject : Science,
Computer Science & IT
Artificial Intelligence Natural Language Processing Computer Vision Robotics and Navigation Systems Decision Support System Implementation of Algorithms Expert System Data Mining Enterprise Architecture Design & Management Software & Networking Engineering IoT
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 44 Documents
 1   2   3   4   5 
Search results for , issue "Vol 5, No 3 (2025): September" : 44 Documents clear
Automatic Cat Feeding System Based On The Internet Of Things (IoT) With Time And Feed Weight Control Wijayanti, Sefi Ayuk; Maulindar, Joni; Nurohman, Nurohman
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7538

Abstract

A common problem in pet cat care is irregular feeding, which can affect the animal's nutritional balance and health. To address this issue, an Internet of Things (IoT)-based automatic feeding system utilizing an ESP32 microcontroller has been developed. The system integrates a Passive Infrared (PIR) sensor for cat motion detection, a Load Cell for measuring food weight, and an ultrasonic sensor to monitor food stock levels. Data is stored and displayed through a web-based platform that supports meal scheduling and real-time monitoring. System testing using a blackbox approach shows that all components function properly, including time synchronization via NTP, Wi-Fi communication, and overall sensor functionality. This system is expected to improve feeding consistency and optimally support the health and well-being of cats.
Power Consumption Prediction Using Support Vector Machine and Particle Swarm Optimization Laila, Dwi Nur'aini; Ula, Mutammimul; Yulisda, Desvina
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7433

Abstract

The continuous growth in electricity consumption demands a reliable prediction system to support sustainable energy planning. This study aims to forecast electricity consumption using the Support Vector Machine (SVM) method, in which the parameters are optimized through the Particle Swarm Optimization (PSO) algorithm. PSO is employed to determine the optimal parameters, namely weight and bias, by minimizing prediction errors measured using Mean Squared Error (MSE). The implementation was carried out using Visual Basic for Applications (VBA) in Excel, based on historical electricity usage data from January 2023 to July 2025 The prediction results indicate a high level of accuracy, as evidenced by the lowest Mean Absolute Percentage Error (MAPE) value of 0.006, observed in the Mbt District.. The model was then used to predict electricity consumption until December 2027, revealing a gradual increase in usage across all districts. These findings indicate that the integration of SVM and PSO is effective in producing accurate and reliable prediction models to support decision-making in electricity demand management.
Computer Vision-Based Optical Mark Recognition (OMR) System for Automated Exam Answer Sheet Correction Yusuf, Muhammad; Pradana, Afu Ihsan; Susanto, Rudi
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7142

Abstract

Manual correction of conventional exam answer sheets is a primary problem due to being time-consuming and prone to errors, while commercial OMR devices are costly. This research aims to design and implement an efficient and accurate computer vision-based Optical Mark Recognition (OMR) system for conventional answer sheets. The method employed is an image processing pipeline using OpenCV, which includes preprocessing with Adaptive Thresholding, contour detection, perspective transformation for skew correction, and answer area segmentation for choice extraction based on pixel analysis. Testing results on 30 samples for each condition showed that the system achieved 100% accuracy on thick markings, 99.22% on thin markings, and 86.22% on thin markings with significant scribbles. It is concluded that the developed system is highly effective for answer sheets with clean markings, but its performance degrades when visual noise from scribbles is present, thus offering an affordable OMR alternative with identified performance limitations.
Feature Selection Optimization Using Genetic Algorithm for Naive Bayes-Based Diabetes Mellitus Classification Aris, Nova Arianti; Yuliana, Ade
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7618

Abstract

Diabetes mellitus is a chronic disease with a steadily increasing prevalence each year and poses the risk of severe complications if not addressed early. Therefore, early detection of diabetes risk plays a vital role in prevention efforts. This study aims to enhance feature selection optimization through the use of a genetic algorithm in the classification of diabetes mellitus patients based on the Naive Bayes method. The genetic algorithm was applied to identify the most significant clinical features from patient data, with the expectation of improving the classification model’s accuracy and efficiency. A dataset comprising 1,557 patient records with 29 initial clinical attributes was utilized. Following preparation and selection stages, 7 key features were chosen for model training. Model performance was evaluated using metrics such as accuracy, precision, recall, and F1-score. The results indicated that the model with selected features achieved an accuracy of 80.99%, precision of 80.99%, recall of 100%, and an F1-score of 89.5%. These findings confirm that genetic algorithms are effective in improving Naive Bayes classification performance for diabetes risk identification. This study is expected to serve as a foundation for the development of more accurate and efficient disease risk prediction systems in the future.
Information Systems And Information Technology Strategies In The EMIS (Education Management Information System) Khaidar, Al; Azzanna, Maghriza; Rahmad, Rahmad; Hasibuan, Arnawan; Daud, Muhammad; Nurdin, Nurdin
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7639

Abstract

Perkembangan teknologi informasi telah memengaruhi pengelolaan data pendidikan melalui sistem informasi manajemen, salah satunya Education Management Information System (EMIS). Penelitian ini bertujuan untuk menganalisis efektivitas implementasi EMIS di MAN 1 Aceh Timur serta faktor-faktor yang memengaruhi keberhasilannya. Metode penelitian menggunakan pendekatan kualitatif interaktif dengan studi kasus, melibatkan kepala madrasah, operator EMIS, dan pihak terkait sebagai informan. Analisis dilakukan menggunakan metode SWOT dan value chain untuk mengevaluasi kekuatan, kelemahan, peluang, dan ancaman implementasi sistem. Hasil penelitian menunjukkan EMIS memiliki potensi meningkatkan efektivitas pengelolaan data, integrasi informasi, dan mendukung pengambilan keputusan. Namun, sistem mengalami kendala teknis, terutama gangguan server dengan frekuensi bervariasi setiap bulan, puncaknya terjadi pada Maret dan Juli masing-masing 5 kali, dengan durasi rata-rata meningkat dari 1,8 jam di Januari menjadi 2,5 jam di Juli dan terendah 1,0 jam di April. Evaluasi menekankan perlunya peningkatan infrastruktur, pelatihan operator, dan koordinasi antar pihak terkait untuk mengoptimalkan kinerja EMIS di masa depan.
Goods Management System Using Always Better Control (ABC) Method Prasetyo, Adi Tri; Hasanah, Herliyani; Oktaviani, Intan
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7351

Abstract

This study aims to design and develop a web-based inventory management system utilizing the Always Better Control (ABC) method to assist Toko Didik in managing stock more efficiently. Until now, the inventory process in the store has been carried out manually using conventional record-keeping, which is prone to data entry errors, delays in stock monitoring, and the absence of a classification system to prioritize items based on their sales contribution.To address this problem,  the system was designed using the Waterfall development methodology, involving stages of requirements analysis, system design, implementation, and testing. Data were collected through observation, interviews, and documentation conducted at the store site. The system was built using the Laravel framework and MySQL database, and includes key features such as item recording, automatic item classification using the ABC method, real-time stock monitoring, purchase recommendations, sales transactions, and sales reporting. The results of black-box testing indicate that all system functions operate as expected without errors. The ABC classification method successfully groups items into three categories based on their contribution to total sales, allowing the store owner to prioritize procurement effectively. With this system, inventory management becomes more organized, accurate, and supports data-driven decision-making. This study serve as an alternative solution for small or medium-sized stores in addressing inventory management challenges through the use of information systems.
Modeling Of Centralized Exchange (CEX) Crypto Asset Platform Recommendation System Using Collaborative Filtering Utomo, Diva Reihan Ferdian; Nastiti, Faulinda Ely; Suryani, Fajar
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7179

Abstract

The rapid growth of crypto assets and the variety of Centralized Exchange (CEX) platforms make it difficult for traders to choose a platform that fits their preferences. This research aims to model a recommendation system for CEX platforms using Collaborative Filtering. User rating data for several CEX (Binance, Bybit, Bitget, Tokocrypto, Indodax) were collected via questionnaire. The K-Nearest Neighbors With Means (KNN With Means) method with cosine similarity is used to predict ratings based on the similarity of preferences between users. The model was trained and tested with a 75:25 train-test split. Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) were used as evaluation metrics. Test results show low MAE and RMSE values (around below 1.0 on a 1–5 rating scale), indicating that the recommendations generated are quite accurate. It can be concluded that the Collaborative Filtering approach is effective in recommending CEX platforms according to user needs. This recommendation system is expected to assist traders – especially beginners – in choosing the right exchange more objectively.
Comparison of Random Forest, Decision Tree, and XGBoost Models in Predicting Student Academic Success Nurbaeti, Nurbaeti; Sulistiyaningsih, Neny; Rismayati, Ria
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7138

Abstract

Students' academic success is influenced by various academic and non-academic factors. Machine learning (ML) offers an effective approach to predicting academic outcomes by analyzing complex data patterns. However, most previous studies are limited to graduation prediction and rarely incorporate non-academic features or multiple feature selection techniques. This study aims to compare the performance of three ML algorithms Random Forest, Decision Tree, and XGBoost in classifying students’ academic success using a dataset from the UCI Machine Learning Repository, consisting of 4424 records and 37 features. The data underwent cleaning, label transformation, and feature selection using PCA, SelectKBest, and Variance Threshold. Models were trained using a holdout method (80% training, 20% testing) and evaluated based on accuracy, precision, recall, and F1-score. The results show that Random Forest with Variance Threshold achieved the highest accuracy (0.77) and F1-score (0.84) on majority classes. XGBoost followed with 0.75 accuracy, while Decision Tree showed the lowest performance. All models struggled to classify the minority class, indicating challenges related to data imbalance. This research highlights the importance of algorithm choice and effective feature selection in academic classification tasks. It also emphasizes the need for data balancing strategies to reduce class bias. The findings can help educational institutions design data-driven interventions to improve learning outcomes and reduce dropout rates.
Enhancing Resource Efficiency in Urban Agriculture: A GA-Fuzzy Logic IoT-Based Smart Hydroponic Greenhouse Ula, Munirul; Rusadi, Athirah; Daud, Muhammad
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7799

Abstract

Pertanian presisi berbasis Internet of Things (IoT) menawarkan solusi inovatif terhadap tantangan ketahanan pangan dan keterbatasan lahan di daerah perkotaan. Penelitian ini bertujuan merancang dan mengevaluasi sistem rumah kaca cerdas berbasis hidroponik untuk budidaya tumpang sari anggur dan selada  menggunakan Nutrient Film Technique (NFT). Metodologi penelitian mengintegrasikan Pengendali Logika Fuzzy yang dioptimalkan dengan Algoritma Genetika (GA-FLC) untuk kontrol real-time enam parameter lingkungan: suhu, kelembapan, pH, konduktivitas listrik, intensitas cahaya, dan konsentrasi CO₂. Sistem menggunakan mikrokontroler ESP32 dengan array sensor presisi tinggi dan platform cloud (ThingSpeak, Firebase) untuk monitoring dan kontrol otomatis. Eksperimen dilaksanakan menggunakan Randomized Complete Block Design dengan dua faktor (sistem kontrol GA-FLC vs konvensional; monokultur vs tumpang sari) selama 120 hari di kondisi iklim tropis Bireuen, Aceh. Hasil menunjukkan sistem GA-FLC superior dalam akurasi kontrol dengan Mean Absolute Error suhu 0,7°C (61% lebih baik), response time aktuator 47-53% lebih cepat, dan efisiensi energi 25-30% lebih tinggi. Produktivitas anggur meningkat 27,8% (2,48 kg/tanaman) dan selada 23,7% (245 g/tanaman) dibandingkan sistem konvensional. Efisiensi sumber daya menunjukkan penghematan air 33,3%, energi 32,6%. Water Use Efficiency mencapai 12,4 kg/m³ dengan Energy Productivity 1,85 kg/kWh. Sistem ini memberikan kontribusi signifikan untuk pertanian perkotaan berkelanjutan dengan produktivitas tinggi, efisiensi sumber daya optimal, dan viabilitas ekonomi yang menarik untuk implementasi komersial di daerah tropis.
Comparison of KNN and SVM Performance in 2024 Election Results Sentiment Analysis Bukit, M Iqbal Fahilla; Lubis, Andre Hasudungan
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7659

Abstract

This study compares the performance of the K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) algorithms in sentiment analysis related to the 2024 election results using data from social media. The dataset used consists of 506 public opinion entries categorized into three sentiment labels: positive, negative, and neutral. The data processing involved preprocessing steps such as case folding, tokenization, stopword removal, and stemming, then represented using the Term Frequency–Inverse Document Frequency (TF-IDF) method. The test results showed that both algorithms were able to classify with an accuracy of over 70%. The KNN algorithm produced an accuracy of 75.49%, precision of 71.36%, recall of 75.49%, and an F1-score of 72.88%, while the SVM algorithm showed slightly better performance with an accuracy of 77.45%, precision of 70.59%, recall of 77.45%, and F1-score of 72.15%. Based on the confusion matrix analysis, both models have a high ability to classify positive sentiments, but still face obstacles in recognizing negative and neutral sentiments due to the imbalance in data distribution. Overall, this study indicates that SVM is more suitable for election sentiment analysis on high-dimensional text data.

Page 1 of 5 | Total Record : 44

 1   2   3   4   5 

Filter by Year

2025 2025


Reset
Filter By Issues
All Issue Vol 5, No 4 (2025): Desember (On Progress) Vol 5, No 3 (2025): September Vol 5, No 2 (2025): Juni On-Progress Vol 5, No 2 (2025): June Vol 5, No 1 (2025): March Vol 5, No 1 (2025): Maret Vol 4, No 2 (2024) Vol 4, No 1 (2024) Vol 3, No 2 (2023) Vol 3, No 1 (2023) Vol 2, No 2 (2022) Vol 2, No 1 (2022) Vol 1, No 2 (2021) Vol 1, No 1 (2021) More Issue