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 215 Documents
 11   12   13   14   15 
An IoT-Enabled Low Latency Automatic Identification System Using Round-robin Scheduling Algorithm Septian, Belen; Adrianda, Aidil; Misbahuddin, Md.; Ridho, M. Fauzan
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): Juni On-Progress
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6512

Abstract

The Automatic Identification System (AIS) is a vital maritime technology that enhances navigation safety and vessel tracking. This system is integrated with the Internet of Things (IoT) for real-time data transmission. However, due to multiple tasks being employed, the system latency increases. To address this problem, this study proposes an optimized task-scheduling approach using a Round-robin algorithm with an additional task-reshuffling mechanism. The proposed method is implemented on an ESP32 microcontroller, enabling real-time processing of AIS messages while minimizing latency and energy consumption. Experimental results demonstrate that the hybrid Round-robin and Shuffling method achieves the lowest average transmission time of 28.736 seconds, outperforming traditional Priority and standard Round-robin scheduling approaches. The findings of this study contribute to enhancing real-time processing capabilities in embedded vessel tracking systems. Following this, future research should focus on addressing transient fluctuations using adaptive scheduling techniques. 
Enhancing Hoax News Detection Performance through Modified Convolutional Neural Network Architecture Mujilahwati, Siti; Reknadi, Danang Bagus
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): Juni On-Progress
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6953

Abstract

The spread of fake news (hoaxes) on the internet is increasingly widespread, along with the increasing use of the internet in Indonesia. To detect hoaxes automatically, this study proposes a Convolutional Neural Network (CNN) model based on data from the Detik.com and TurnBackHoax.id sites. The data includes various categories such as politics, religion, and technology. The model was developed through several optimization stages: tokenization and text padding, utilization of pre-trained Word2Vec as embedding weights, stratified data division, handling class imbalance with class weights, and implementing a multilevel CNN architecture with dropout. Training was carried out using the Adam optimizer with a small learning rate and an early stopping technique. The evaluation results showed that the proposed model achieved an accuracy, precision, recall, and F1-score of 96%, with the fastest training time of 100.42 seconds. The model was also evaluated with the ROC_AUC model, with a score of 98.91%. This performance outperformed the CNN-1D and Augmentasi-CNN models. This approach has proven to be effective and efficient in detecting Indonesian hoax news.
Machine Learning Approaches For Classification Of Infectious Diseases Using Smote Shofwan, Ari; Sulistianingsih, Neny; Rismayati, Ria
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): Juni On-Progress
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v%vi%i.6960

Abstract

Infectious diseases such as acute nasopharyngitis, acute pharyngitis, and acute tonsillitis remain major public health issues, especially in primary healthcare facilities with limited resources like Puskesmas Gunungsari. This study aims to develop a machine learning-based classification model to detect infectious diseases using patient medical data. The evaluated models include Random Forest, Decision Tree, Support Vector Machine (SVM), and Neural Network, with performance assessed using k-fold cross-validation ranging from 5 to 10 folds. Evaluation results show that the Decision Tree consistently achieved the best performance, with an accuracy of approximately 91.7% to 91.9% and an F1-score ranging from 91.9% to 92.3% on cross-validation data, as well as a test accuracy of 94.7% and an F1-score of 95.0%. The Random Forest model also demonstrated good and stable performance, with accuracy between 90.5% and 90.7%. Meanwhile, SVM and Neural Network produced lower results, with maximum accuracy of around 77.0% and 71.7%, respectively. Overall, the findings demonstrate that the Decision Tree model is the most effective for supporting early diagnosis of infectious diseases at Puskesmas Gunungsari, providing superior classification capabilities compared to other models.
Application of Naive Bayes Algorithm in Analyzing Public Sentiment towards Coretax on Platform X Wijaya, Egi Putu; Rifqo, Muhammad Husni
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): Juni On-Progress
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6949

Abstract

Taxation is the main state data, to make it easier for people to pay taxes, an integrated application called coretax is used. However, there are many differences because it has many problems in its use. Therefore, the study was conducted to find out public sentiment towards the coretax application using a naïve Bayes algorithm. The methods used range from data collection, data cleaning, data pre-processing, classification with textblob to classification and evaluation with naïve Bayes algorithms. Of the total 2858 total data used, the results were 782 positive sentiment data, 479 negative sentiments and 1597 neutral sentiments. The results showed that the accuracy of the model could reach 81% with an f1-score value of 80%, as well as a precision and recall value of 81%. This shows that the naïve bayes algorithm is quite good at classifying public sentiment towards the coretax application.
Optimization of Stunting Risk Prediction Using a Hybrid Genetic-Machine Learning Model Heryati, Agustina; Terttiaaivini, Terttiaavini; Marcelina, Dona; Romli, Harsi
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6988

Abstract

Stunting is a chronic nutritional problem that remains a national priority issue in Indonesia. According to the 2022 Indonesian Nutrition Status Survey (SSGI), the national stunting prevalence reached 21.6%, with a target reduction to 14% by 2024. Accurate prediction of stunting risk remains a challenge, particularly in regions like Palembang City, which exhibit diverse socio-economic conditions and complex anthropometric characteristics. This study develops a hybrid machine learning model for stunting risk prediction by integrating classification algorithms with a Genetic Algorithm (GA) for feature selection. The hybrid approach aims to enhance predictive accuracy and efficiency based on numerical and socio-economic data. A total of 6,000 samples were used, and after preprocessing (trimming, winsorization, normalization, and SMOTE), 5,366 clean data samples were obtained. Four classification algorithms were tested: Decision Tree, K-Nearest Neighbor, Random Forest, and XGBoost. The best performance was achieved by the XGBoost model, with an accuracy of 84.08%, recall of 93%, and F1-score of 0.91 for the majority class. By integrating the Genetic Algorithm, optimal accuracy reached 95.34% in the third generation of feature selection. This study contributes a hybrid machine learning-based predictive framework that can be adopted by local health institutions for more targeted early detection of stunting risk.
Design and Construction of an Internet of Things-Based Landslide Early Detection System in Landslide-Prone Areas Prasetyo, Sidik; Susanto, Rudi; Pramono, Pramono
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6847

Abstract

Landslides are one of the natural disasters that often occur in Indonesia due to the geographical conditions dominated by mountainous and hilly areas, coupled with high rainfall. Landslides can cause huge losses and casualties due to the absence of a system that can provide real-time warnings as a preventive measure. This research aims to design and build an Internet of Things (IoT)-based landslide early detection system that is able to detect environmental conditions that have the potential for landslides in real-time. The system uses an ESP32 microcontroller as the control center connected with a rain sensor (YL-83), a tilt sensor (MPU6050), and a soil moisture sensor (Capacitive Soil Moisture). Data from the sensors is sent via RESTful API and WebSocket with WiFi connection to the monitoring website. The system is also equipped with a buzzer and RGB LED as a warning indicator if environmental conditions are detected that have the potential for landslides. For a power source, a rechargeable 18650 battery is used and combined with a Step-Up and Charger Module J5019 to maintain voltage stability. The test results conducted in the test environment obtained 40 experimental data with stable sensor readings, and all components can function properly and can display data on the monitoring website. This system offers a practical solution to support disaster mitigation in landslide-prone areas.
Interpreting Lung Disease Detection from Chest X-rays Using Layer-wise Relevance Propagation (LRP) Fauziyyah, Laila Nurul; Negara, Benny Sukma; Irsyad, Muhammad; Iskandar, Iwan; Yanto, Febi
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.7043

Abstract

Penelitian ini mengusulkan pendekatan klasifikasi penyakit paru berbasis citra X-ray menggunakan arsitektur VGG16 yang dilengkapi metode interpretabilitas Layer-wise Relevance Propagation (LRP). Dataset terdiri dari tiga kelas: COVID-19, pneumonia, dan normal, yang diproses melalui augmentasi dan normalisasi. Model dilatih dengan rasio data 70:30, learning rate 0.001, batch size 32, dan optimizer Adam. Hasil pelatihan menunjukkan akurasi tinggi sebesar 96,78% dengan nilai precision, recall, dan F1-score yang seimbang. Metode LRP digunakan untuk menyoroti area penting pada citra yang berkontribusi terhadap prediksi model, sehingga meningkatkan transparansi keputusan. Kontribusi utama penelitian ini adalah integrasi VGG16 dengan LRP dalam klasifikasi multi-kelas citra X-ray, yang memberikan hasil akurat sekaligus interpretasi visual yang mendukung kepercayaan dalam aplikasi medis.
Development of the Shortest Path Navigation Feature in a 360° Virtual Campus Tour Using Dijkstra's Algorithm Alifi, Muhammad Riza; Hodijah, Ade; Setijohatmo, Urip Teguh; Wulan, Sri Ratna; Hayati, Hashri
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6839

Abstract

A 360° virtual campus tour allows users to independently explore all available scenes in the form of 360° panoramic photos through a self-guided navigation feature. However, not all navigation tools provided are capable of generating route recommendations for users to follow. This presents a challenge, as users may feel overwhelmed when deciding where to begin and end the tour—particularly when the number of scenes reaches into the hundreds. In certain scenarios, prolonged interaction within a virtual reality environment may lead to discomfort due to motion sickness. Implementing a shortest path algorithm offers a potential solution by guiding users through recommended routes, thereby improving exploration efficiency and reducing interaction time. This study integrates a shortest path-based navigation feature into a virtual campus tour using Dijkstra’s algorithm, consisting of: (1) a front-end navigation component for the user interface of route searching, and (2) a back-end routing component that processes pathfinding using a graph-based structure. The implemented navigation feature demonstrates high efficiency, with an average execution time of only 4.94 ms and low memory consumption, as measured by a resident set size of 710.47 KB and used heap memory of 668.61 KB.
Usability Testing Analysis of Bank Aceh Mobile Action Applications Using Human Centered Design and Heuristic Evaluation Methods Amalia, Fatihah Indah; Fitria, Rahma; Ulva, Ananda Faridhatul
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

One of the efforts to improve regional digital banking services is through the development of Bank Aceh Syariah's Action Mobile application. This application is designed to facilitate customers in conducting various transactions online, such as transfers, payments, and mutation checks. However, despite being available on the Google Play Store and receiving favorable ratings, the usage of this application is still relatively low compared to other regional banks' mobile banking applications. Some of the problems found are related to user experience, including limited e-commerce payment features and digital wallet top-up services that only support certain platforms such as OVO, GoPay, and LinkAja. In addition, the information displayed in the transaction mutation section is also considered incomplete, resulting in complaints from users. This problem has the potential to hinder comfort in using the application and affect the level of customer satisfaction. To overcome these challenges, an evaluation of the application's usability was conducted using the Human Centered Design approach and the Heuristic Evaluation method. The evaluation involved users and experts who provided feedback based on Nielsen's ten heuristic principles. The results showed some weaknesses in the application design, such as navigation that was not fully intuitive, information delivery that was not clear, and inadequate service features. Based on these findings, a solution was designed in the form of a new application prototype that was more responsive and user-friendly. The design was carried out using the Figma application, focusing on improving the interface and adding the required features. With these improvements, it is expected that Action Mobile Bank Aceh Syariah can be more competitive in the midst of the rapid development of digital banking services. This technology is also part of a strategic step in supporting digital banking transformation in the region, as well as increasing customer satisfaction and loyalty.
Optimisation of Employee Attendance System Using Face Recognition and Geotagging Based on Mobile Android Fitria, Rahma; Sahputra, Ilham; Maulana, Riki
Journal of Artificial Intelligence and Software Engineering Vol 5, No 2 (2025): June
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i2.6892

Abstract

The growth of technology is developing very rapidly in various fields, ranging from industry, offices, government, to education. One interesting innovation is the application of facial recognition to an Android-based attendance system. This system allows attendance to be carried out by scanning employee faces using Android devices in certain areas such as offices or companies. By using this technology, the attendance process which is usually done manually or using fingerprints can be optimized, thereby reducing the risk of long queues when employees are present together. In some offices, attendance is still done manually by filling in attendance books or using fingerprints. This method often causes problems, especially when many employees come at the same time. The queues that form will of course interfere with their productive time. Therefore, to overcome this problem, an Android-based attendance application is needed that integrates facial recognition technology. This application is designed so that it can only be accessed in an office environment, with certain area coverage settings. This study uses the Convolutional Neural Network (CNN) algorithm which is effective for image processing in facial recognition. In addition, researchers also apply the GPS Locking or Geotagging method to ensure that attendance can only be carried out in predetermined areas, thereby increasing the security and accuracy of attendance data. The dataset used in this study consists of facial images, where each individual is photographed in five different angles to improve the accuracy of the system. The results of this study are expected to create a more efficient and effective attendance system. By simplifying the attendance process, this technology not only saves time but also increases employee satisfaction, because they no longer have to face long queues. This is a step forward in utilizing technology to improve human resource management in the digital era.

Page 13 of 22 | Total Record : 215

 11   12   13   14   15 

Filter by Year

2021 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): June Vol 5, No 2 (2025): Juni On-Progress Vol 5, No 1 (2025): Maret Vol 5, No 1 (2025): March 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