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 33 Documents
 1   2   3   4 
Search results for , issue "Vol 5, No 2 (2025): June" : 33 Documents clear
Analisis Sentimen Pengguna Media Sosial Terhadap Pemilihan Presiden 2024 Dengan Metode Naive Bayes Classifier Rumini, Rumini
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.v5i2.6679

Abstract

Dengan semakin berkembangnya penggunaan media sosial sebagai sarana komunikasi publik, banyak opini, komentar, dan sentimen yang disampaikan secara terbuka. Namun, volume data yang besar serta penggunaan bahasa informal di platform ini menimbulkan kesulitan dalam memahami sentimen secara efektif. Dampak dari permasalahan ini adalah kurangnya pemahaman yang akurat tentang preferensi politik masyarakat, yang dapat memengaruhi strategi kampanye dan kebijakan publik. Oleh karena itu, diperlukan sebuah metode untuk mengklasifikasikan sentimen secara lebih efektif dari data yang tidak terstruktur. Untuk menyelesaikan masalah tersebut, penelitian ini menggunakan algoritma Naive Bayes Classifier untuk mengklasifikasikan sentimen tweet menjadi tiga kategori: positif, netral, dan negatif. Dengan menggunakan dataset yang terdiri dari 1.945 data hasil crawling dan melalui representasi teks menggunakan Bag of Words (BoW) serta TF-IDF, penelitian ini menunjukkan bahwa algoritma Naive Bayes berhasil mengklasifikasikan sentimen positif, netral, dan negatif secara efektif, terutama pada ulasan negatif dan netral. Model Naive Bayes dengan BoW terbukti memiliki akurasi keseluruhan sebesar 90,15%, dengan keseimbangan yang lebih baik antara precision dan recall dibandingkan model dengan TF-IDF.
Temporal Pattern Recognition: A BiLSTM-based Framework for Churn Prediction Zulman, Muhammad Reza; Mahmudah, Rifa’atun; Arhami, Muhammad; Davi, Muhammad
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.v5i2.6952

Abstract

Industri telekomunikasi menghadapi tantangan besar dalam mempertahankan basis pelanggannya, di mana churn atau perpindahan pelanggan ke penyedia layanan pesaing menjadi isu krusial yang secara langsung memengaruhi kinerja finansial, efisiensi operasional, serta daya saing perusahaan dalam jangka panjang. Untuk menjawab tantangan ini, diperlukan pendekatan analitik yang mampu memprediksi kemungkinan churn secara akurat. Penelitian ini bertujuan untuk mengevaluasi efektivitas jaringan saraf Bidirectional Long Short-Term Memory (BiLSTM) dalam memprediksi churn pelanggan PT Medianusa Permana melalui analisis data sekuensial temporal. Dataset yang digunakan mencakup data pelanggan dari April 2020 hingga Mei 2023, dengan berbagai variabel prediktif seperti jenis layanan, media transmisi, alokasi bandwidth, status langganan, status kemitraan, ketentuan kontrak, serta riwayat keluhan. Arsitektur BiLSTM yang diterapkan terdiri dari tiga lapisan LSTM bidirectional, dirancang untuk memaksimalkan pengenalan pola temporal sekaligus mengurangi overfitting guna meningkatkan akurasi model. Validasi dilakukan melalui teknik cross-validation dan confusion matrix, yang menunjukkan bahwa model mampu mencapai akurasi rata-rata sebesar 89% serta performa klasifikasi yang tinggi dalam mengidentifikasi pelanggan yang churn maupun tidak churn. Hasil penelitian ini menegaskan bahwa BiLSTM efektif dalam menangkap indikator perilaku halus yang mendahului churn, dan dapat menjadi dasar yang kuat dalam pengembangan strategi retensi pelanggan yang lebih proaktif dan berbasis data.
Smartphone Photos Categorization Using Markov Model with Limited Training Data Hatala, Zulkarnaen; Hudzaly, Muhammad
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.v5i2.6943

Abstract

This writing investigates the classification of images taken using a smartphone. Due to the large number of photos and the large number of photo categories, it is necessary to automatically categorize these photos. Photos are classified using two different approaches. The first method uses Hidden Markov Model (HMM) and the second technique employs Siamese Network from Convolutional Neural Network (CNN) architecture. The same data are used for training and testing for both models. For HMM we use Discrete Cosine Transform (DCT) to extract salient features of images. The number of training examples is very small compared to the test set. Here we carried out few-shot classification method. For recognition of the HMM, Viterbi algorithm is applied. Performances of both procedures were measured. For only 109 test samples HMM achieve 98% accuracy, while twin network achieves 90%. The use of HMM has advantage over Siamese in term of faster computation. HMM opens the opportunity of the smartphone with low computation capability to categorize photos automatically.
Laplacian Kernel and Deep Learning for Palmprint Classification Duli, Sirlus Andreanto Jasman; Wisesa, Bradika Almandin; Faristasari, Evvin; Peprizal, Peprizal; Putri, Vivin Mahat; Fadila, Resma
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.v5i2.6978

Abstract

Palmprint classification is a robust biometric method for personal identification due to its uniqueness and stability. This study explores the use of deep learning combined with the Laplacian Kernel and Deep Morphological Processing Network (DMPN) for palmprint classification. We trained the proposed system on a dataset of palmprint images collected from 10 participants, each contributing 10 palm images. The results demonstrated that the model achieved an accuracy of 90%, with weighted precision, recall, and F1-score all at 0.9007, indicating a well-balanced classification performance. Additionally, the model achieved a weighted precision of 0.9045, emphasizing its ability to minimize false positives. The average Equal Error Rate (EER) of 0.0917 indicates an effective balance between the false acceptance rate (FAR) and false rejection rate (FRR). The system was tested under various conditions, including different orientations, lighting, and backgrounds, demonstrating its robustness in real-world scenarios. This study also compares the results with recent palmprint classification techniques, such as deep learning, GANs, and few-shot learning, and discusses potential improvements, including incorporating multi-spectral data fusion and few-shot learning to enhance performance in real-world applications.
Sentiment Analysis of Service and Facility Satisfaction at Computer Lab of Universitas Bumigora Using Indobert Mundika, Eko; Martono, Galih Hendro; Rismayati, Ria
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.v5i2.6798

Abstract

Computer laboratories have a strategic role in supporting the technology-based learning process at Bumigora University. To understand the extent to which the available services and facilities meet students' expectations, this study conducted a sentiment analysis of student reviews using the IndoBERT model, an artificial intelligence-based Natural Language Processing (NLP) approach. Data was obtained from a questionnaire focusing on aspects of laboratory services and facilities, then analyzed to classify opinions into positive, negative, and neutral sentiments. The analysis results show the dominance of positive sentiments, indicating that computer laboratories have generally met student expectations, especially in supporting practicum activities. The IndoBERT model used was able to achieve 85% accuracy, demonstrating its effectiveness in reliably identifying opinion trends. These findings provide a comprehensive picture of student perceptions, and serve as an important basis for managers in formulating strategies to improve the quality of laboratory services and facilities so that a conducive and relevant learning experience can be maintained.
Application of Shapley Additive Explanations (SHAP) in Deep Learning for Lung Disease Detection Using X-ray Images Muliani, Sarifah; Negara, Benny Sukma; Irsyad, Muhammad; Jasril, Jasril; Iskandar, Iwan
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.v5i2.7044

Abstract

Pemeriksaan menggunakan citra x-ray merupakan metode yang efektif dalam membantu deteksi penyakit paru-paru, seperti COVID-19, dan pneumonia. Seiring dengan perkembangan teknologi yang meningkat, proses diagnosis kini dapat dilakukan secara lebih akurat dengan memanfaatkan sistem berbasis kecerdasan buatan. Salah satu metode yang banyak digunakan adalah deep learning namun metode ini bersifat black-box, sehingga hasil prediksi sulit dipahami dengan alasan dibalik keputusan model. Tujuan penelitian ini adalah untuk membangun sistem klasifikasi citra x-ray menggunakan model deep learning berbasis Convolutional Neural Network (CNN) dengan arsitektur VGG-16, serta menerapkan metode Shapley Additive Explanations (SHAP) untuk memberikan penjelasan mengenai visual terkait area citra yang mempengaruhi hasil prediksi. Model dilatih menggunakan beberapa konfigurasi, dan hasil terbaik diperoleh pada rasio data 80% : 20%, learning rate 0.001, batch size 32, dan 50 epoch. Hasil penelitian menunjukkan bahwa model mampu mencapai akurasi sebesar 95,75% pada data training dan 96,00% pada data validasi. Metode SHAP digunakan untuk meningkatkan pemahaman terhadap hasil prediksi. Hasil menunjukkan bahwa kombinasi deep learning dan SHAP mampu memberikan penjelasan visual terhadap hasil prediksi model.
A Real-Time Egg Incubator Monitoring System with ESP32 and Blynk Wijaya, Andi; Aini, Syarifah; Hidayat, Kemas Muhammad Wahyu
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.v5i2.6874

Abstract

Poultry farming, especially chicken, contributes to the provision of world food needs, especially in the provision of chicken meat and eggs to fulfill human protein. However, the productivity of chicken farming is often hampered by traditional egg hatching methods. Egg hatching is traditionally done by the mother hen, which affects the number and quality of chicks produced. The purpose of this research is to increase the productivity of chicken farms which are often hampered by traditional methods of hatching chickens, by applying IoT (Internet of Things) Technology as a solution to more modern egg hatching methods using DHT11 sensors and Lcd 16x2 i2c as temperature and humidity monitoring. It shows that DHT1 is able to maintain temperature in the optimal range of 37°C-39°C with an average difference between DHT11 and thermometer of only 0.3°C - 0.4°C, and humidity that remains stable at a difference of 3% - 4%. The results of this study indicate that the DHT11 is accurate enough to measure air temperature in a stable environment.
Design and Implementation of an Air Pollution Monitoring System in the Campus Area of Politeknik Negeri Lhokseumawe Indrawati, Indrawati; D, Amir
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.v5i2.7306

Abstract

Air pollution is a significant environmental issue that directly affects human health, especially in high-activity areas such as university campuses. This study aims to design and implement a real-time air pollution monitoring system in the campus area of Politeknik Negeri Lhokseumawe. The system utilizes MQ135 and MQ7 gas sensors to detect CO₂ and CO levels in both indoor and outdoor environments. Sensor data are processed using a microcontroller and displayed through a web-based application interface to facilitate user-friendly monitoring. System testing was conducted by recording sensor readings in various environmental conditions over specific time intervals. The test results show that the system can distinguish pollution levels between indoor and outdoor settings and provides data that are relatively stable and responsive to changes in air quality. The implementation of this system is expected to support the campus in monitoring and managing air quality effectively. The normal indoor CO₂ level is 400–800 ppm while the MQ135 shows 325, which means the monitoring system is acceptable and reasonable. For CO . the normal condition is 10 ppm, but the analog MQ7 can show relative values; if it goes up and down according to the trend, it can be accepted as a relative indicator.
Development of a Web-Based Sport Center Reservation System with Dashboard Analytical for Booking Optimization Sa'adah, Muthia Nurul; Minhalina, Sharfina Andzani; Agung, Surya; Prastyo, Ari Dian; Nasir, Muhammad; Wicaksono, Aditya
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.v5i2.6895

Abstract

This research aims to develop a web-based Sports Center reservation system integrated with an analytics dashboard to support decision-making and optimize the booking process. The urgency of this system development is based on the need for digitalization of booking services, which were previously done manually, prone to recording errors, and inefficient. The system is designed to allow real-time self-booking, with an interactive interface to select time slots and automatic detection to prevent double bookings. An additional feature includes a unique QR code provided as proof of booking, which can be scanned for attendance verification. The analytics dashboard presents data such as total revenue, number of bookings, most popular courts, availability rate, and booking trends over time. The development method uses the Waterfall model, consisting of analysis, design, implementation, testing, and maintenance stages. Testing results show that 87.04% of functional scenarios performed as expected, and security testing using OWASP ZAP identified some potential vulnerabilities, serving as a reference for system strengthening. The integration between the reservation system and the analytics dashboard has proven to enhance operational efficiency and the overall quality of the Sports Center's services.This research aims to develop a web-based Sports Center reservation system integrated with an analytics dashboard to support decision-making and optimize the booking process. The urgency of this system development is based on the need for digitalization of booking services, which were previously done manually, prone to recording errors, and inefficient. The system is designed to allow real-time self-booking, with an interactive interface to select time slots and automatic detection to prevent double bookings. An additional feature includes a unique QR code provided as proof of booking, which can be scanned for attendance verification. The analytics dashboard presents data such as total revenue, number of bookings, most popular courts, availability rate, and booking trends over time. The development method uses the Waterfall model, consisting of analysis, design, implementation, testing, and maintenance stages. Testing results show that 87.04% of functional scenarios performed as expected, and security testing using OWASP ZAP identified some potential vulnerabilities, serving as a reference for system strengthening. The integration between the reservation system and the analytics dashboard has proven to enhance operational efficiency and the overall quality of the Sports Center's services.
Development of a Control and Monitoring System for an IoT Rover Based on ESP32 and LoRa in Hazardous Areas Ananda, Naufal Choirul; Maulindar, Joni; Ardiyanto, Marta
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.v5i2.6962

Abstract

This study developed a control and monitoring system for an IoT-based rover using ESP32 and LoRa, designed for hazardous area exploration. The system integrates two wireless communication methods: LoRa for long-range sensor data transmission and NRF24L01 for real-time control. The MQ-6 sensor detects LPG gas, while ultrasonic sensors function as an automatic safety system. A web-based interface built with Next.js and Supabase displays real-time sensor data. The system was developed using a prototyping method that includes requirement analysis, system design, hardware and software development, and testing. Test results show that LoRa transmits data reliably up to 15 meters without obstructions, and NRF24L01 supports stable control up to 100 meters. The MQ-6 sensor accurately detects gas presence, and ultrasonic sensors consistently stop the rover when obstacles are detected within 30 cm. The monitoring website successfully presents real-time data for operator decision-making. Overall, the system is effective and responsive for remote operation in high-risk environments, with strong potential for deployment in scenarios such as gas leaks, disaster zones, or other dangerous areas.

Page 2 of 4 | Total Record : 33

 1   2   3   4 

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