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 248 Documents
 21   22   23   24   25 
Comparison of Adaptive Boosting and Categorical Boosting in Heart Attack Diagnosis Amran, Ali; Suryani, Suryani; Fathinah, Nadiva Azro; Desiani, Anita; Ramayanti, Indri
Journal of Artificial Intelligence and Software Engineering Vol 6, No 1 (2026): Maret
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i1.9051

Abstract

Heart disease is one of the leading causes of death worldwide, and therefore, accurate early detection methods are needed to help reduce mortality rates. One approach that can be applied is machine learning using classification techniques based on ensemble boosting algorithms. This study aims to compare the performance of two ensemble algorithms, namely Adaptive Boosting (AdaBoost) and Categorical Boosting (CatBoost), in classifying heart attack disease. The labels used in this study are positive and negative. The evaluation process was conducted using two testing techniques: percentage split with a ratio of 80% training data and 20% testing data, and 10-fold cross-validation. Model performance was evaluated based on accuracy, precision, and recall to comprehensively measure classification capability. The results show that in the percentage split method, CatBoost achieved the highest accuracy of 98.88%, while in k-fold cross-validation it reached 98.43%. Nevertheless, AdaBoost also demonstrated good performance, with all evaluation metrics exceeding 90%. Therefore, the best-performing model in this study is CatBoost with the k-fold cross-validation technique on the heart attack dataset.
Product Sales Analysis based on sales level using the K-Means Clustering method Kinasih, Aisha Bethary; Christianto, Paminto Agung; Amalia, Nurul
Journal of Artificial Intelligence and Software Engineering Vol 6, No 1 (2026): Maret
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i1.7710

Abstract

Micro, Small, and Medium Enterprises (MSMEs) play a highly strategic role in driving Indonesia’s economic growth. Nevertheless, most business actors have not yet utilized digital technology to its full potential. One such example is Toko Nabila Daster, which recorded 475 sales transactions during the period of January–June 2025, but has not conducted an analysis to identify products with high, medium, or low sales levels. This situation may result in stock accumulation and ineffective promotional strategies. The objective of this study is to group products based on their sales levels using the K-Means Clustering method. The optimal number of clusters is determined through the Elbow Method, while the quality of clustering is assessed using the Davies-Bouldin Index (DBI). The results of the analysis indicate the formation of product clusters that distinguish best-selling, moderately selling, and low-selling categories. These findings are expected to serve as a foundation for business decision-making, particularly in designing promotional strategies and managing inventory more efficiently.
Implementation of WebSocket in an IoT-Based Smart Home Door Security System Using ESP32-CAM with Face Recognition Safriadi, Safriadi; Nasir, Muhammad; Erdiansyah, Umri
Journal of Artificial Intelligence and Software Engineering Vol 6, No 1 (2026): Maret
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i1.9052

Abstract

The advancement of Internet of Things technology, especially in the field of information technology, opens up opportunities in the development of smarter, more efficient, and flexible home security systems. Frequently used systems such as fingerprints and RFID still have limitations in flexibility, scalability, and effectiveness against threats. To overcome these problems, an IoT-based home door security system was developed using ESP 32 - CAM and face recognition technology. This system utilizes the Haar Cascade Classifier algorithm for face detection and the Local Binary Pattern Histogram for face recognition. Test results show a fast response, communication stability, and an increase in accuracy of 66.07% with 10 datasets, 86.07% with 50 datasets, and 93.03% with 100 datasets. This shows that the more datasets used, the higher the system's accuracy in recognizing user faces.
A-Star and SMART Methods for Islamic Boarding School Recommendations in North Aceh and Lhokseumawe Fuzna Febriani; Dahlan Abdullah; Rini Meiyanti
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.8928

Abstract

Advances in information technology have increased the public’s need for systems capable of providing information quickly and easily, including in searching for Islamic boarding schools. This study developed a web-based Geographic Information System (GIS) to recommend Islamic boarding schools in North Aceh and Lhokseumawe using the Simple Multi-Attribute Rating Technique (SMART) method and the A-Star algorithm. The SMART method determines rankings based on four criteria: location, accreditation, number of students, and type of boarding school through weighting, min-max normalization, and utility calculation. A-Star is applied to find the shortest route using the Haversine formula. The dataset consists of 361 verified boarding schools from the Dayah Education Office. Black box testing confirms all system functions are valid. Results show Dayah Darul Yaqin achieved the highest SMART score of 81.44 with a distance of 0.3 km, followed by Imam Syafi’i with 80.66 and 0.88 km, demonstrating that the SMART-A-Star integration produces objective and efficient recommendations.
Web-Based Village Public Service Information System in Nambangan Selogiri Village Wonogiri Fahriza Wahyu Akbar; Wijiyanto Wijiyanto; Hanifah Permatasari
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.9500

Abstract

Digital transformation at the village government level has become a crucial aspect of realizing efficient, transparent, and responsive public services. However, Nambangan Village currently faces administrative bottlenecks due to its reliance on a conventional service system. The process of issuing various certificates, such as the Certificate of Inability (SKTM), domicile letters, and cover letters, requires residents to physically visit the village hall. This practice leads to crowded queues, potential errors in population data recording, and low time efficiency in service delivery. This study aims to design and develop a web-based Village Public Service Information System that adapts to the operational needs of both village officials and the community of Nambangan Village. The system development method applied is the Software Development Life Cycle (SDLC) using the Waterfall model, which encompasses the stages of requirements analysis, system design, implementation, testing, and maintenance. The system is built using PHP, HTML, CSS, and JavaScript programming languages, supported by a MySQL database for integrated data management. The primary features implemented include online document submission, population data management, service tracking for village officials, public village information delivery, and a public grievance reporting system. Software quality assurance was functionally evaluated through the Black Box Testing method. The final outcome of this research is expected to provide an applicable technological solution for Nambangan Village to optimize public administrative governance and provide accessible services for the community without spatial or temporal constraints.
Application of the Random Forest Algorithm for Classifying Children's Nutritional Status Rahma Jihan Ananta; Nurdin Nurdin
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.8655

Abstract

Status gizi yaitu suatu kondisi terkait gizi yang bisa diukur dan merupakan hasil dari adanya keseimbangan kebutuhan gizi pada tubuh dengan asupan gizi dari makanan. Klasifikasi yaitu teknik yang digunakan dalam data mining, untuk menganalisis data yang kemudian dijadikan kedalam beberapa kategori sesuai dengan variabel-variabel yang terkait. Pada Metode yang akan digunakan merupakan Algoritma Random Forest digunakan untuk klasifikasi klasifikasi status gizi anak berdasarkan data Dinas Kesehatan Lhokseumawe. Tujuan penelitian adalah untuk menerapkan Algoritma Random Forest untuk melakukan klasifikasi status gizi anak serta mengetahui tingkat akurasi dan efektivitas Random Forest dalam melakukan klasifikasi status gizi anak. Metode penelitian yang digunakan dalam penelitian ini adalah metode pengumpulan data dan metode perancangan sistem, dalam metode pengumpulan data penulis mengumpulkan sample data, observasi, wawancara, dan studi literatur, kemudian dalam metode perancangan sistem penulis melakukan analisa kebutuhan sistem, dan analisa metode perancangan sistem. Sistem klasifikasi status gizi balita di Dinas Kesehatan Kota Lhokseumawe menggunakan algoritma Random Forest berhasil dikembangkan dengan dataset antropometri 2185 sampel yang terdiri dari variabel jenis kelamin (L0, P1), usia bulan, berat badan, tinggi badan, dan indeks massa tubuh (IMT) yang telah melalui preprocessing lengkap berupa label coding dan normalisasi Min-Max Scaling ke rentang, menghasilkan kinerja sebesar 97,89% pada dashboard produksi yang konsisten dengan perhitungan manual 75,51% menggunakan bootstrap sampling dan mayoritas voting dari 3 pohon ansambel. Tahapan pemodelan data mencakup transformasi kategorikal status_gizimenjadi numerik (obesitas0, stunting1, underweight2, wasting3) serta pembagian dataset 80:20 (350 data latih, 87 data uji) dengan stratified sampling yang mempertahankan proporsi kelas realistis sesuai prevalensi gizi buruk di Indonesia, di mana underweight dominan diikuti stunting dan wasting minoritas
Decision Support System for Motorcycle Credit Eligibility Assessment Using the Simple Multi-Attribute Rating Technique Sri Kurnia; Dahlan Abdullah; Nurdin Nurdin
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.8963

Abstract

Sistem Pendukung Keputusan (SPK) merupakan sistem berbasis komputer yang digunakan untuk membantu proses pengambilan keputusan dengan memanfaatkan data, model analisis, dan antarmuka pengguna secara terintegrasi. Penerapan SPK diperlukan dalam proses evaluasi kelayakan kredit sepeda motor agar keputusan yang dihasilkan lebih objektif dan akurat. Pada PT XYZ Kota Lhokseumawe, proses penilaian kelayakan kredit masih dilakukan secara manual sehingga memerlukan waktu yang lama dan berpotensi menimbulkan kesalahan dalam pengambilan keputusan. Penelitian ini bertujuan untuk menerapkan metode SMART (Simple Multi-Attribute Rating Technique) dalam sistem pendukung keputusan untuk menentukan kelayakan kredit sepeda motor. Metode penelitian meliputi pengumpulan data, penentuan kriteria dan bobot, perhitungan nilai utility, serta perhitungan nilai preferensi untuk menentukan tingkat kelayakan calon pelanggan. Hasil penelitian menunjukkan bahwa dari 103 calon pelanggan, sebanyak 45 pelanggan (44%) dinyatakan layak memperoleh kredit dengan nilai preferensi ≥ 0,60, sedangkan 58 pelanggan (56%) dinyatakan tidak layak. Metode SMART mampu membantu perusahaan dalam meningkatkan akurasi evaluasi kredit.
Predicting Household Food Insecurity Status in Langsa City Using Double Random Forest and EasyEnsemble Algorithms Rizqi Ananda; Munirul Ula; Fadlisyah Fadlisyah
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.9116

Abstract

Accurately identifying food-insecure households is challenging because the condition is inherently multidimensional. This study compares three machine-learning approaches — Random Forest (RF), Double Random Forest (DRF), and RF combined with EasyEnsemble class balancing — for predicting household food insecurity in Langsa City. Data from the 2024 SUSENAS survey cover 2,057 households with 13 predictor variables. A berat_count ≥ 3 threshold on the FIES indicators defines the target variable, yielding 755 food-insecure (36.7%) and 1,302 food-secure (63.3%) households. Fifty repetitions with a 70:30 train-test split yield stable performance estimates. RF + EasyEnsemble achieves the best results with a mean AUC of 0.8398 and sensitivity of 79.84%, far surpassing DRF at 2.62%. ANOVA (F = 191.899; p 0.001) and Tukey HSD tests confirm statistically significant differences. Feature importance reveals social-assistance participation (54.78%) and physical housing conditions (28.89%) as the dominant predictors.
An Analysis Of User Awareness Regarding Data Privacy In The Use Of Artificial Intelligence-Based Applications Khalimin Khalimin; Dwinanto Rivaldo Pramudya; Vernando Septian; Tomi Defisa
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.9173

Abstract

Penelitian ini dilatarbelakangi oleh meningkatnya penggunaan aplikasi berbasis Artificial Intelligence (AI) yang memberikan berbagai kemudahan digital, tetapi juga memunculkan persoalan mengenai privasi dan keamanan data pribadi pengguna. Tujuan penelitian ini adalah menganalisis tingkat kesadaran pengguna terhadap privasi data serta mengidentifikasi perilaku pengguna dalam melindungi data pribadi saat menggunakan aplikasi AI. Penelitian dilakukan dengan pendekatan kuantitatif melalui penyebaran kuesioner daring kepada 70 responden yang aktif menggunakan aplikasi AI. Data dianalisis menggunakan statistik deskriptif dan analisis persentase. Hasil penelitian menunjukkan bahwa tingkat kesadaran privasi pengguna berada pada kategori tinggi dengan persentase sebesar 83,4%. Mayoritas responden memahami bahwa aplikasi AI mengumpulkan data pengguna dan memiliki risiko penyalahgunaan data pribadi. Meskipun demikian, pengguna tetap memanfaatkan aplikasi AI karena dinilai praktis, efisien, dan bermanfaat dalam kehidupan sehari-hari. Kondisi ini menunjukkan adanya fenomena privacy paradox, yaitu ketika pengguna menyadari risiko privasi, tetapi tetap menggunakan layanan tersebut. Penelitian ini menegaskan pentingnya literasi digital dan kesadaran privasi data dalam penggunaan aplikasi AI di Indonesia.
Implementation of SMOTE and Information Gain Feature Selection in Learning Vector Quantization for Asthma Disease Classification Diah Ayu Kinanti; Fitri Insani; Novi Yanti; Muhammad Affandes
Journal of Artificial Intelligence and Software Engineering Vol 6, No 2 (2026): Juni (OnProgress)
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v6i2.9354

Abstract

Asma adalah penyakit pernapasan akibat peradangan saluran udara di paru-paru yang menyebabkan penyempitan dan kesulitan bernapas. Prevalensinya terus meningkat secara global, sehingga diperlukan metode deteksi dini yang akurat. Masalah yang ditemukan dalam proses pengklasifikasian penyakit asma adalah distribusi kelas yang tidak seimbang pada dataset. Penelitian ini menerapkan algoritma Learning Vector Quantization (LVQ) yang dioptimalkan dengan seleksi fitur Information Gain dan teknik penyeimbangan data SMOTE untuk klasifikasi penyakit asma. Dataset penelitian mencakup 2.392 data pasien dengan 28 fitur dan 1 kelas target yang diperoleh dari platform Kaggle. Pengujian dilakukan pada lima skenario dengan tiga fungsi jarak Euclidean , Chebyshev, Manhattan, learning rate 0,001–0,005, dan rasio pembagian data 90:10, 80:20, serta 70:30. Hasil terbaik diperoleh pada skenario SMOTE, Information Gain, dan LVQ menggunakan fungsi jarak Euclidean  dengan learning rate 0.004 dan rasio 90:10, menghasilkan akurasi 77.97%, precision  73.61%, recall  87.22% dan F1-score 79.84%. Penerapan SMOTE menjadi komponen penting karena tanpa SMOTE model gagal mengenali kelas asma, terbukti pada percobaan tanpa menggunakan SMOTE menghasilkan precision , recall , dan F1-score bernilai 0% meskipun akurasi mencapai 94–95%.

Page 23 of 25 | Total Record : 248

 21   22   23   24   25 

Filter by Year

2021 2026


Reset
Filter By Issues
All Issue Vol 6, No 2 (2026): Juni (OnProgress) Vol 6, No 1 (2026): Maret Vol 5, No 4 (2025): Desember 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