Article Per Year (5 Year)
p-Index From 2021 - 2026
0.659
P-Index
This Author published in this journals
All Journal Journal of Artificial Intelligence
Luthfi Nurul Huda
Universitas Amikom Yogyakarta

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Sentiment Analysis of Movie Reviews Using Spark on IMDB Review Dataset Luthfi Nurul Huda
Khatulistiwa SMART: Science, Methodology, Artificial intelligence, Research, and Technology Vol 1 No 1 (2024): December 2024
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/kjarti.v1i1.231

Abstract

Analisis sentimen pada ulasan film telah menjadi topik penting dalam penelitian berbasis teks, terutama untuk mendeteksi polaritas sentimen seperti positif, negatif, atau netral. Penelitian ini mengevaluasi kinerja dua algoritma, Support Vector Machine (SVM) dan Logistic Regression (LR), dalam mengklasifikasikan ulasan film dengan menggunakan dataset IMDb yang tersedia untuk umum di Kaggle. Data tersebut dibagi menjadi 80% untuk pelatihan dan 20% untuk pengujian, melalui tahapan preprocessing seperti case folding, tokenisasi, penghilangan stop words, stemming, dan ekstraksi fitur dengan menggunakan Word2Vec. Hasil evaluasi menunjukkan bahwa SVM memiliki akurasi sebesar 76%, mengungguli LR yang mencapai 69%. Keunggulan SVM terletak pada kemampuannya untuk menemukan hyperplane yang optimal dalam ruang berdimensi tinggi, yang sesuai dengan sifat data teks yang jarang dan berbentuk vektor. Sebaliknya, meskipun LR lebih sederhana dan lebih cepat untuk dilatih, model ini menunjukkan kinerja yang lebih rendah karena keterbatasannya dalam menangani hubungan non-linear. Preprocessing terbukti memberikan kontribusi yang signifikan dalam meningkatkan kualitas data input, sementara representasi Word2Vec memberikan fitur-fitur yang berarti untuk mendukung analisis sentimen. Penelitian ini menggarisbawahi pentingnya memilih algoritma yang tepat untuk analisis sentimen berbasis data besar, dengan hasil yang menunjukkan bahwa SVM lebih unggul dalam menangani data teks berskala besar. Penelitian ini berkontribusi dalam memahami efektivitas metode pembelajaran mesin dalam analisis sentimen ulasan film, sekaligus memberikan dasar untuk penelitian di masa depan yang dapat memperluas metode dan set data ke domain lain.
Web-Based E-Commerce Application Development with Real-Time Notifications via Telegram Bot Luthfi Nurul Huda
Khatulistiwa SMART: Science, Methodology, Artificial intelligence, Research, and Technology Vol 2 No 2 (2025): December 2025
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/kjarti.v2i2.334

Abstract

This research aims to develop a web-based e-commerce system equipped with real-time notifications through a Telegram bot. The background of the study originates from issues in sales transactions that are still conducted through chat messages, which often lead to delayed confirmations and irregular order recording. The system being developed is expected to simplify the transaction process, improve data organization, and enhance the efficiency of communication among system users. The research employs an Agile approach with development stages that adapt to user needs. The system is designed to support three types of users with different access rights: customers, employees, and owners. The main features implemented include product management with ready-stock and pre-order categories, order management, payment confirmation, transaction history, sales reports, and automated notifications via a Telegram bot. Testing was conducted using Black Box Testing to evaluate system functionality, along with external testing to obtain feedback from users. The test results indicate that the system operates according to its functions and provides a good level of user satisfaction. Based on these findings, it can be concluded that the system is capable of improving the effectiveness and efficiency of business processes while supporting the digitalization of small and medium enterprises, particularly in the integrated management of ready-stock and pre-order product models.
Eye Disease Classification Using VGG-19 and TensorFlow on Fundus Images Luthfi Nurul Huda; Abdelghani Dahou
Khatulistiwa SMART: Science, Methodology, Artificial intelligence, Research, and Technology Vol 3 No 1 (2026): June 2026
Publisher : CV Narasi Khatulistiwa Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.67490/kjarti.v3i1.674

Abstract

Eye disorders are health problems that can reduce visual quality and may lead to blindness if they are not detected at an early stage. The use of deep learning technology has become a promising approach to support the classification of eye diseases based on medical images. This study aims to classify eye diseases from fundus images using a Convolutional Neural Network architecture based on VGG-19 with the support of TensorFlow and Keras frameworks. The dataset used in this study was obtained from Kaggle and consists of eight classes, namely Normal, Cataract, Diabetes, Glaucoma, Hypertension, Myopia, Age Issues, and Other. The research stages include data collection, image preprocessing, dataset generation, training and testing data splitting, VGG-19 model design using transfer learning, model training, model testing, and evaluation using accuracy, precision, recall, F1-score, and confusion matrix. The testing results show that the model achieved an accuracy of 78.24% on the testing data with a loss value of 0.0983. Meanwhile, evaluation using k-fold cross validation obtained an accuracy of 91.35% with a margin of ±2.25%. The confusion matrix results indicate that Cataract and Myopia achieved the best classification performance, while the Normal class still showed a low recall value. These findings indicate that TensorFlow-based VGG-19 can be used for eye disease classification, although further development is still needed to improve the model’s generalization ability
Co-Authors Abdelghani Dahou