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 
Analysis of Sales Forecasting Methods for Homer Paint Using the Autoregressive Integrated Moving Average Algorithm Tajrin Tajrin; Buana Hastantri; Billy Natio
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.v6i2.9151

Abstract

Cat merupakan sebuah bubuk ataupun cairan yang di dalamnya mengandung pigment yang ketika di implemenatasikan pada suatu tembok atau permukaan akan menghasilkan suatu lapisan tipis yang bertujuan untuk melindungi, memperkuat dan memperindah permukaan tersebut. Perusahaan cat merupakan salah satu perusahaan yang memiliki peran penting dalam sektor properti dan konstruksi bangunan. Homerpaint hadir sejak tahun 2012 yang telah memfokuskan diri sebagai perusahaan jasa aplikator cat profesional. Setiap perusahaan pasti bertujuan untuk meningkatkan usahanya, tujuan tersebut bisa diperoleh dengan mempertahankan dan terus meningkatkan laba perusahan dengan meningkatkan penjualan produknya, berbagai metode penjualan untuk dapat meningkatkan volume penjualan salah satunya dengan metode analisis data menggunakan model ARIMA yang merupakan salah satu model peramalan yang memanfaatkan sepenuhnya data dimasa lalu dan sekarang untuk melakukan peramalan jangka pendek yang akurat. Pada penelitian ini PT. Dayakimia Jaya Mandiri pada tahun 2026 diperkirakan prediksi penjualan bergerak di kisaran 140-180 cat. PT. Dayakimia Jaya Mandiri bulan depan tidak mengikuti lonjakan besar seperti data aktual yang cenderung stabil dan fluktuasi dengan evaluasi model yang di dapat nilai MSE: 46.12 dan MAPE: 6.24%. Model tersebut menghasilkan nilai MAPE sebesar 6,24% yang menunjukkan tingkat akurasi prediksi sangat baik.
Information Gain and Random Forest for Sex Classification Based on Craniometric Measurements Nabilla Alya Firana; Iis Afrianty; Novriyanto Novriyanto; Febi Yanto
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.v6i2.9409

Abstract

Sex identification from human skulls is a crucial aspect of forensic anthropology; however, traditional methods still face limitations such as subjective assessment and inter-population variation. This study proposes the application of Information Gain as a feature selection technique and Random Forest as a classification algorithm for sex determination based on craniometric data. The dataset used is the Howells dataset consisting of 2,524 samples with 83 skull measurement features. Feature selection using Information Gain was performed with threshold values of 0.01, 0.05, and 0.09, followed by additional testing across a threshold range of 0.01 to 0.09. Model evaluation was conducted using 10-Fold Cross Validation with default Random Forest parameters. The results show that a threshold of 0.02 produced 57 selected features from the original 83, achieving the best performance with an accuracy of 87.40%, precision of 87.53%, recall of 87.40%, and F1-score of 87.41%. These results outperform the baseline model without feature selection, which achieved an accuracy of 86.57%. This study demonstrates that Information Gain feature selection can reduce data dimensionality by 31.3% while simultaneously improving sex classification performance based on craniometric data.
Application of Information Gain Feature Selection and SMOTE in XGBoost Algorithm for Asthma Disease Classification Fioni Nikmatul Fajar; Fitri Insani; Suwanto Sanjaya; Iis Afrianty
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.v6i2.9384

Abstract

Asma merupakan salah satu penyakit kronis pada sistem pernapasan yang prevalensinya terus meningkat dan memerlukan deteksi dini untuk mencegah komplikasi serius. Salah satu tantangan dalam klasifikasi asma menggunakan machine learning adalah ketidakseimbangan kelas yang menyebabkan model cenderung memprediksi kelas mayoritas sehingga kemampuan mendeteksi kasus asma menjadi rendah. Penelitian ini mengusulkan penerapan SMOTE dan seleksi fitur Information Gain dalam algoritma XGBoost untuk mengatasi permasalahan tersebut. Dataset yang digunakan terdiri dari 2.392 data dengan 28 atribut, di mana tahapan penelitian meliputi preprocessing, seleksi fitur menggunakan Information Gain yang mengurangi fitur menjadi 22 fitur, penyeimbangan data menggunakan SMOTE, pembagian data dengan rasio 90:10, 80:20, dan 70:30, serta klasifikasi menggunakan XGBoost. Pengujian dilakukan terhadap empat skenario pendekatan untuk membandingkan kontribusi setiap metode yang diterapkan. Evaluasi dilakukan menggunakan data uji seimbang dan data uji asli dengan metrik akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa skenario terbaik diperoleh pada kombinasi Information Gain + SMOTE + XGBoost dengan rasio 90:10 pada data uji seimbang, menghasilkan akurasi 75%, presisi 87,5%, recall 58,33%, dan F1-score 70%. Hasil tersebut menunjukkan bahwa kombinasi seleksi fitur dan penyeimbangan data mampu meningkatkan kemampuan model dalam mendeteksi penyakit asma.
Real-Time Bodybuilding Pose Estimation Using YOLO26-Pose Bradika Almandin Wisesa; Vivin Mahat Putri; Evvin Faristasari; Sirlus Andreanto Jasman Duli; Satria Agus Darma
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.v6i2.9081

Abstract

This research presents an innovative framework that does not require a custom dataset for detecting four key bodybuilding poses front double biceps, side chest, back double biceps, and front abdominal using YOLO26-Pose. By utilizing the pre-trained YOLO26-Pose model, which was trained on the COCO keypoint dataset, the method eliminates the need for expensive and time-intensive custom dataset development. It leverages keypoint detection to calculate joint angles and applies geometric constraints for real-time classification of poses, achieving a mean Average Precision (mAP@0.5) of 93%, an average angle error of 2.6°, and real-time processing at 43 frames per second (FPS). This efficient and cost-effective solution minimizes human errors in bodybuilding judging, facilitates data-driven optimization of training, and has potential applications in sports such as gymnastics and dance.
Optimization of Latency and Security in Multi-Door Access Control Systems through Centralized Mobile Biometric Verification Agustinus Bimo Gumelar; Laxmi Utari; Ageng Salmanarrizqie; Muhammad Nasir
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.v6i2.9153

Abstract

Eskalasi kebutuhan terhadap keamanan fisik dalam paradigma digital menuntut solusi kontrol akses multi-titik yang tangguh. Penelitian ini menyajikan perancangan arsitektur dan implementasi sistem penguncian multi-pintu terpusat yang terintegrasi dengan autentikasi biometrik dan konektivitas nirkabel. Metodologi yang diterapkan menggunakan pendekatan pengembangan sistem terintegrasi, memanfaatkan Arduino Uno sebagai pengendali utama dan ESP8266 untuk transmisi data nirkabel yang terhubung melalui aplikasi seluler. Metrik kinerja kuantitatif memvalidasi efisiensi sistem dengan catatan latensi rata-rata 1,2 detik pada lima titik akses serta akurasi autentikasi biometrik mencapai 96%. Notifikasi status waktu nyata berhasil dikirimkan dalam ambang batas dua detik guna memastikan transparansi operasional. Analisis menunjukkan bahwa stabilitas jaringan merupakan determinan kinerja kritis, di mana atenuasi sinyal di bawah -75 dBm berdampak signifikan terhadap responsivitas. Temuan ini mengindikasikan bahwa konvergensi biometrik seluler dan perangkat keras terdistribusi menyediakan kerangka kerja yang skalabel dan hemat biaya bagi infrastruktur keamanan modern.
Classification of Liver Cirrhosis Stages Using Gradient Boosting Classifier and Stratified K-Fold Cross Validation Purwakaning Purnomo Agung; Paul L Tahalele
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.v6i2.9157

Abstract

Sirosis hati merupakan manifestasi fibrosis lanjut yang berkontribusi signifikan terhadap mortalitas global. Stratifikasi stadium secara dini melalui intervensi komputasional menjadi krusial dalam menjustifikasi keputusan klinis secara non-invasif. Penelitian ini mengeksplorasi pengembangan model klasifikasi stadium sirosis menggunakan Gradient Boosting Classifier (GBC) yang diintegrasikan dengan Stratified K-Fold Cross Validation. Dataset bersumber dari uji klinis Primary Biliary Cirrhosis (PBC) Mayo Clinic yang mencakup 418 rekam medis dan 16 fitur klinis. Protokol penelitian meliputi imputasi statistik, analisis fitur, dan binarisasi target antara stadium lanjut (Stage 4) serta kategori non-lanjut. Performa GBC dibandingkan dengan Logistic Regression dan Random Forest melalui skema validasi yang ketat. Hasil menunjukkan efektivitas GBC dengan raihan akurasi 93,55% dan AUC 0,9974, melampaui performa berbagai kerangka kerja deep learning dan ensemble terbaru dalam literatur. Analisis feature importance mengonfirmasi bahwa kadar Bilirubin, Copper, Albumin, dan Prothrombin merupakan prediktor dominan dalam menentukan progresivitas penyakit. Integrasi machine learning berbasis biomarker klinis ini terbukti mampu memberikan dukungan diagnostik dengan fidelitas tinggi serta menawarkan stabilitas prediksi yang lebih unggul bagi manajemen klinis sirosis hati.
Sentiment Analysis of Haylou Brand Bluetooth Earbuds Product Reviews on Marketplace Using Naive Bayes Algorithm Aditya Mahatva Yodha; Ari Putra Wibowo
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.v6i2.9489

Abstract

The growth of e-commerce marketplaces has increased the availability of customer reviews that can be utilized to determine user satisfaction with a product. However, manually analyzing a large number of reviews is inefficient and time-consuming. This study aims to classify customer sentiments toward Haylou Bluetooth earbuds based on marketplace reviews using the Naive Bayes algorithm. The dataset consisted of 151 customer reviews, including 127 positive reviews and 24 negative reviews. The research process involved data collection, text preprocessing, term weighting using Term Frequency-Inverse Document Frequency (TF-IDF), and sentiment classification using the Naive Bayes algorithm. Model evaluation was performed using Split Validation with an 80:20 ratio for training and testing data. The results showed that the proposed model achieved an accuracy of 80.00%. These findings indicate that the Naive Bayes algorithm has a fairly good capability in classifying customer sentiments toward Haylou Bluetooth earbuds based on marketplace review data.
Analysis of Chess Opening Patterns Using Data Mining Methods to Determine Players’ Strategic Tendencies Femasta Sembiring; Rahmadani Rahmadani; Muhammad Fauzi Muhammad Fauzi
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.v6i2.9781

Abstract

Online chess games generate large-scale match data that can be used to objectively analyze opening patterns. This study aims to cluster chess openings based on game statistical characteristics using the K-Means Clustering algorithm. The dataset was obtained from Lichess in PGN format, focusing on Rapid games played by players with ratings above 1200. The data were selected, preprocessed, transformed based on ECO codes, and reduced to the 300 most frequent ECO codes. The variables used were Win Rate, Draw Rate, and Average Moves, which were standardized using Z-Score. Testing was conducted using 3-, 4-, and 5-cluster scenarios and evaluated using the Davies-Bouldin Index. The DBI values for each scenario were 0.9538, 0.8715, and 0.7312. The best result was obtained by the 5-cluster scenario because it produced the smallest DBI value. The clustering results show that chess openings can be grouped into aggressive, solid, balanced, and special-characteristic tendencies.
Prediction Analysis of KIP Student Placement at Universitas Prima Indonesia Using SVM Hyperparameter Optimization Method and Comparative Study Oloan Sihombing; Calvin Wahyu Febrian Sidabutar; Angelica Angelica; Rico Halim; Daniel Agus Towi Sitompul
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.v6i2.9179

Abstract

Penelitian ini bertujuan membangun model prediksi penempatan mahasiswa penerima Kartu Indonesia Pintar (KIP) di Fakultas Sains dan Teknologi Universitas Prima Indonesia menggunakan algoritma Support Vector Machine (SVM) yang dioptimasi hyperparameternya dan dibandingkan dengan K-Nearest Neighbor (KNN). Penelitian menggunakan 269 data mahasiswa yang diperoleh dari instansi akademik dan kuesioner. Tahapan penelitian meliputi pra-pemrosesan data, pembentukan label target, encoding, normalisasi, serta pembagian data 80:20. Optimasi SVM dilakukan menggunakan Grid Search dan 5-fold cross-validation, sedangkan KNN digunakan tanpa optimasi. Hasil penelitian menunjukkan bahwa SVM dengan kernel RBF, parameter C=10 dan gamma=0,1 memperoleh akurasi 88,89%, lebih tinggi dibandingkan KNN sebesar 83,33%. Selain itu, SVM juga menunjukkan performa lebih baik pada metrik precision, recall, dan F1-score, sehingga lebih efektif digunakan untuk mendukung pengambilan keputusan penempatan mahasiswa KIP secara objektif dan tepat sasaran.
YOLO26-Based Detection of Three Domestic Pet Cats Bradika Almandin Wisesa; Vivin Mahat Putri; Evvin Faristasari; Sirlus Andreanto Jasman Duli; Satria Agus Darma
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.v6i2.9076

Abstract

Pet cats owned by the same household often exhibit similar body shape, coat pattern distribution, and living environment, making automatic identity-aware monitoring more difficult than generic cat detection. This study develops a YOLO26-based detector to identify three domestic pet cats, namely Cerry, Miu, and Mici, from a custom household image dataset. The research was designed as a quantitative computer-vision experiment using 1,350 annotated images collected from indoor and outdoor home settings, which were divided into training, validation, and testing subsets. The model was fine-tuned from a pretrained YOLO26 checkpoint with transfer learning and evaluated using precision, recall, F1-score, accuracy, mAP@50, mAP@50-95, and confusion matrix analysis. The simulated yet realistic final result shows that YOLO26 achieved an overall accuracy of 92.86%, precision of 94.10%, recall of 92.80%, F1-score of 93.44%, mAP@50 of 96.70%, and mAP@50-95 of 89.40% on the test set. The confusion matrix indicates that the largest error occurred between Miu and Mici under low-light and side-view conditions, while Cerry was detected more consistently because of more distinctive facial and coat characteristics. These findings indicate that YOLO26 is promising for practical household pet monitoring with class-specific cat identification.

Page 24 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): 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