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 16 Documents
 1   2 
Search results for , issue "Vol 5, No 2 (2025): Juni On-Progress" : 16 Documents clear
Edge Implementation of Vehicle Plate Identification using Haar Classifier and Convolutional Neural Networks Wibowo, Risky Ari; Muhammad, Fadil; Ahendyarti, Ceri; Alimuddin, Alimuddin; Muttakin, Imamul
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.v5i2.6570

Abstract

The increase in vehicle ownership every year causes a lack of information monitoring on each vehicle. As one of the methods used to find vehicle information, recognizing each number plate is a solution for recognizing vehicles. Utilizing object detection techniques using computer vision in recognizing vehicle number plates can simplify the plate recognition process. The process of identifying and classifying the characters on the plates is conducted simultaneously with a simple implementation which is a benefit of using computer vision in recognizing vehicle plates. The use of the Haar cascade classifier algorithm in this research overcomes the problem of plate detection combined with the Convolutional Neural Networks (CNN) to conduct Optical Character Recognition (OCR) on vehicle plates. The results of vehicle plate recognition in-situ experiments in four real-time tests obtained an average accuracy value of 42.67%.
Instagram Influencer Recommendation System Based On Content-Based Filtering To Support Digital Marketing Strategy Az Zahra, Erika Oktaviana; Pramono, Pramono; Suryani, Fajar
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.v5i2.6939

Abstract

Influencer marketing is a popular promotional strategy on Instagram that involves influential individuals or public figures to promote products. However, there are problems where companies still find it difficult to find the right influencers. This research aims to build a Content-Based Filtering-based Instagram influencer recommendation system to support digital marketing strategies. The system development method used is Rapid Application Development (RAD) with 4 stages, namely requirements planning, system design, development, and implementation. With this system, users can recommend other influencers who have similar characteristics such as number of followers, average likes, and comments, engagement rate, and growth rate. System testing was conducted on 10 test data with different inputs. The results showed that 9 out of 10 tests matched the user input, indicating a system accuracy of 90% and has the potential to assist users in selecting relevant influencers.
Clustering of Accounts Receivable Billing Data Based on Customer Tariff Categories at PT PLN UP3 Palembang Ramadhan, Dimaz Gymnastiar; Yulistia, Yulistia
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.v5i2.6511

Abstract

The purpose of writing this final assignment is to group customers based on late payment patterns by applying the K-Means Clustering algorithm. The data used are late receivables and arrears of PT PLN Palembang customers. The results of writing this final assignment show that Cluster 1 has 10 data, Cluster 2 has 36 data, and Cluster 3 has 326 data on late payments. While in the risky payment arrears, Cluster 1 has 26 data, Cluster 2 has 36 data, and Cluster 3 has 312 data. From the evaluation results using Silhouette Score, it shows that there are 3 clusters with a value of 0,880 (Highest), which means that the clustering that was formed was successful and can be used.
Implementation Of Web-based Digital Library To Improve Learning Resource Access Services With RAD Method Approach Risyda, Fitria; Gardenia, Yulisa; Awaludin, Muryan
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.v5i2.6993

Abstract

The advancement of digital technology opens up opportunities for libraries to improve their services, including at the Universitas Dirgantara Marsekal Suryadarma (UNSURYA) Library. Fast, flexible, and integrated access are the main needs of the academic community. However, the system at the UNSURYA library currently has limitations such as limited operating hours and physical constraints in managing digital collections such as e-books, digital books, theses, and dissertations. This study aims to develop a digital library that can improve accessibility and user experience in accessing learning resources at the UNSURYA campus library. Application development using the Rapid Application Development (RAD) method, functional testing of the application using blackbox testing and usability testing to see user responses to the application that has been developed. The results of the usability testing questionnaire using the System Usability Scale (SUS) Score calculation showed a value of 80, the conversion of this value shows the "Good" category which indicates that the digital library application that has been built is considered good by users and has met the usability criteria to improve learning resource access services and workflows at the UNSURYA Library
Comparison of the Performance of Fuzzy Tsukamoto and Fuzzy Mamdani in an Internet of Things Based Grape Greenhouse Control System Rusadi, Athirah; Ula, Munirul; Daud, Muhammad; Nurdin, Nurdin; Hasibuan, Arnawan
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.v5i2.6936

Abstract

The application of Internet of Things in agriculture, particularly in grape greenhouses, enables automated environmental control to enhance efficiency and crop yield. This study compares the performance of two fuzzy logic methods, Fuzzy Mamdani and Fuzzy Tsukamoto, in a temperature and humidity control system based on IoT using the DHT22 sensor. The system is designed to automate irrigation via actuators based on sensor data. Performance evaluation was conducted using RMSE, MAE, and standard deviation metrics. The results show that the Tsukamoto method achieved lower RMSE 2.6928, MAE 2.2625, and standard deviation 1.1080 compared to the Mamdani method, which recorded RMSE of 2.9039, MAE of 2.3947, and standard deviation of 1.9268. However, a paired t-test yielded a p-value of 0.0690 0.05, indicating no statistically significant performance difference. Thus, while Fuzzy Tsukamoto appears superior in metrics, both methods are considered equally effective for controlling environmental conditions in grape greenhouses.The application of Internet of Things in agriculture, particularly in grape greenhouses, enables automated environmental control to enhance efficiency and crop yield. This study compares the performance of two fuzzy logic methods, Fuzzy Mamdani and Fuzzy Tsukamoto, in a temperature and humidity control system based on IoT using the DHT22 sensor. The system is designed to automate irrigation via actuators based on sensor data. Performance evaluation was conducted using RMSE, MAE, and standard deviation metrics. The results show that the Tsukamoto method achieved lower RMSE 2.6928, MAE 2.2625, and standard deviation 1.1080 compared to the Mamdani method, which recorded RMSE of 2.9039, MAE of 2.3947, and standard deviation of 1.9268. However, a paired t-test yielded a p-value of 0.0690 0.05, indicating no statistically significant performance difference. Thus, while Fuzzy Tsukamoto appears superior in metrics, both methods are considered equally effective for controlling environmental conditions in grape greenhouses.
Implementation of Random Forest Algorithm in Lecturer Performance Evaluation System Sufina, Sufina; Wati, Lidya
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.v5i2.6975

Abstract

Lecturer performance evaluation is a crucial process in improving the quality of education in higher education institutions. However, one of the main challenges in evaluating lecturer performance is analyzing large amounts of data objectively and efficiently. This study applies the Random Forest algorithm to automatically evaluate lecturer performance data based on the Employee Performance Target (SKP). The method used is Rapid Application Development (RAD), which includes requirements planning, design, construction, and system implementation. The results of the study show that the implementation of the algorithm in the developed system is capable of classifying lecturer performance with an accuracy rate of 72.73% for main performance assessment and 81.82% for behavioral performance. These results indicate that the Random Forest algorithm can be used as a supporting tool in data-driven lecturer performance evaluation.Lecturer performance evaluation is a crucial process in improving the quality of education in higher education institutions. However, one of the main challenges in evaluating lecturer performance is analyzing large amounts of data objectively and efficiently. This study applies the Random Forest algorithm to automatically evaluate lecturer performance data based on the Employee Performance Target (SKP). The method used is Rapid Application Development (RAD), which includes requirements planning, design, construction, and system implementation. The results of the study show that the implementation of the algorithm in the developed system is capable of classifying lecturer performance with an accuracy rate of 72.73% for main performance assessment and 81.82% for behavioral performance. These results indicate that the Random Forest algorithm can be used as a supporting tool in data-driven lecturer performance evaluation.
Implementation and Evaluation of a Barcode-Based Motorcycle Spare Parts Stock Opname Application Using the Spiral Model Indrayana, Didik; Prajoko, Prajoko
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.v5i2.6469

Abstract

Using a barcode-based application, this study aims to make the stock-taking process for motorcycle spare parts at PT XYZ faster and more accurate. The traditional method currently used, which involves manual recording on paper and re-entering data into spreadsheets, takes up to two weeks and is prone to human error. This research proposes a solution by developing an application that enables real-time data input, inter-branch data synchronization, and automatic report generation. The system development employs the Spiral model with a quantitative approach to measure improvements in efficiency and accuracy. The research was conducted over six months (September 2024-February 2025) at PT XYZ, covering the head office and 14 branches in Sukabumi City. Data were collected through observation, interviews, and analysis of previous stok opname documents. The results show that the application implementation reduced the processing time from two weeks to one day and significantly decreased error rates. These findings demonstrate that the barcode-based application can enhance the accuracy and efficiency of the stok opname process, providing an important contribution to optimizing inventory management of spare parts in the automotive industry.
Applying Local Interpretable Model-agnostic Explanations (LIME) for Interpretable Deep Learning in Lung Disease Detection Ananda, Sherly; Negara, Benny Sukma; Irsyad, Muhammad; Jasril, Jasril; Iskandar, Iwan
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.v5i2.7042

Abstract

Artificial Intelligence (AI) semakin banyak diterapkan dalam bidang kesehatan melalui model Machine Learning (ML) dan Deep Learning (DL). Namun, kompleksitas model modern yang bersifat black-box menimbulkan kebutuhan akan metode interpretasi yang transparan. Explainable AI (XAI) hadir untuk menjembatani hal tersebut, dengan memberikan pemahaman yang lebih baik terhadap kinerja model. Penelitian ini mengimplementasikan metode Local Interpretable Model-agnostic Explanations (LIME) untuk memvisualisasikan hasil klasifikasi model DL berbasis arsitektur ResNet18 terhadap citra Chest X-ray (CXR) pada tiga kelas: normal, COVID-19, dan pneumonia. Model mencapai precision, recall, dan F1-score rata-rata sebesar 97%, serta Accuracy sebesar 98%. Visualisasi LIME menunjukkan area citra yang berkontribusi signifikan terhadap klasifikasi, serta mampu membedakan ketiga kelas dengan baik. Hasil ini mendukung penggunaan XAI untuk meningkatkan interpretabilitas model DL dalam diagnosis medis.
Multi-Label Emotion Detection for Mental Health Monitoring Using Deep CNN and Visual Attention Hadi, Muhammad Nur; Sari, Ratri Wulan
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.v5i2.6961

Abstract

Mental health is a crucial aspect of modern human life that requires continuous monitoring. This research aims to develop a multi-label classification system to automatically detect various human emotional expressions through facial images, serving as a supportive approach for AI-based mental health monitoring. The proposed system leverages a Convolutional Neural Network (CNN) architecture integrated with a visual attention mechanism using the Convolutional Block Attention Module (CBAM). The AffectNet dataset is used as the primary data source, providing multi-label annotations for various emotional states. The model is designed using sigmoid activation and binary cross-entropy loss to handle multiple emotions simultaneously in a single image. Evaluation is conducted using the confusion matrix and metrics such as Precision, Recall, and F1-score. Experimental results demonstrate that the model achieves a Mean Average Precision (mAP) of 89.7%, indicating good performance in multi-label emotion classification. Specifically, the model achieves an F1-score of 100% for the emotions Happy, Fear, Surprise, Disgust, and Neutral, but faces challenges in distinguishing Sad (F1-score 67%) and Angry (F1-score 80%) expressions from others. Incorporating the attention mechanism proves beneficial in enhancing the overall performance of the model. This study contributes to the development of adaptive emotion recognition technologies, potentially applicable in real-time, non-invasive psychological monitoring systems.
Implementation of a Chatbot for Customer Service Integrated into an MSME Website Panca Mukti, M. Thoriq
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.v5i2.7000

Abstract

Penelitian ini berfokus pada implementasi chatbot menggunakan algoritma Artificial Neural Network (ANN) yang terintegrasi ke dalam website UMKM untuk meningkatkan layanan pelanggan secara otomatis. Metodologi yang digunakan adalah CRISP-DM (Cross-Industry Standard Process for Data Mining), yang mencakup tahapan pemahaman bisnis, pemahaman data, persiapan data, pemodelan, evaluasi, dan deployment. Data diproses menggunakan teknik Natural Language Processing (NLP) seperti case folding, tokenizing, dan stemming, kemudian direpresentasikan dengan pendekatan Bag of Words (BoW). Model ANN terdiri dari satu input layer, dua hidden layer dengan fungsi aktivasi ReLU, dan satu output layer dengan fungsi aktivasi softmax. Hasil pengujian menunjukkan akurasi sebesar 98,33%, dengan nilai precision, recall, dan F1-score masing-masing sebesar 98% tanpa indikasi overfitting. Chatbot yang dikembangkan berhasil diintegrasikan ke dalam website berbasis Laravel dan mampu merespons pertanyaan pelanggan secara otomatis.

Page 1 of 2 | Total Record : 16

 1   2 

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