Claim Missing Document
Check
Articles

Found 4 Documents
Search

Penerapan Convolutional Neural Network (CNN) untuk Klasifikasi Kualitas Beras sebagai Strategi Peningkatan Keamanan Pangan di Indonesia Ade Bastian; Priyadi, Deni; Zaliluddin, Dadan; Mardiana, Ardi; Wahid, Abrar; Rifki, Muhamamad; Fahmi Aziz, Muhamamad
TEMATIK Vol. 12 No. 1 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Juni 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i1.2332

Abstract

Food fraud has emerged as a significant global issue, threatening public health, economic stability, and consumer trust across the food supply chain. In the context of rice—a staple consumed by more than half of the world’s population—the proliferation of counterfeit products poses a critical risk. This study aims to develop a deep learning-based classification model using Convolutional Neural Networks (CNN) to accurately distinguish between medium-grade, premium, and counterfeit rice. The research involved the systematic collection of 100 grain images per rice category, followed by preprocessing, data augmentation, and model training using an optimized CNN architecture for image-based classification. The dataset was split into training, validation, and testing subsets with a 60:20:20 ratio. The model was trained over 12 epochs, achieving a training accuracy of 95%. Evaluation using the test set yielded identical accuracy, with the confusion matrix confirming perfect classification across categories. External validation further demonstrated the model’s robustness and generalizability. The findings highlight CNN’s potential as an effective tool for enhancing food safety monitoring systems and combating rice fraud. This AI-driven approach contributes to agricultural quality control and emphasizes the role of machine learning in promoting food security and authenticity assurance. However, CNN models face limitations, including susceptibility to overfitting when trained on insufficiently diverse data and high computational demands during training. These challenges underscore the need for diversified datasets and the exploration of alternative architectures offering comparable performance with greater computational efficiency.
The Evolution of Image Captioning Models: Trends, Techniques, and Future Challenges Bastian, Ade; Wahid, Abrar; Hafsari, Zacky; Mardiana, Ardi
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol. 10, No. 4, November 2025
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/kinetik.v10i4.2305

Abstract

This study provides a comprehensive systematic literature review (SLR) of the evolution of image captioning models from 2017 to 2025, with a particular emphasis on the impending problems, methodological enhancements, and significant architectural developments. The evaluation is guided by the increasing demand for precise and contextually aware image descriptions, and it adheres to the PRISMA methodology. It selects 36 relevant papers from reputable scientific databases. The results indicate a significant transition from traditional CNN-RNN models to Transformer-based architectures, which leads to enhanced semantic coherence and contextual comprehension. Current methodologies, such as prompt engineering and GAN-based augmentation, have further facilitated generalization and diversity, while multimodal fusion solutions, which incorporate attention mechanisms and knowledge integration, have improved caption quality. Additionally, significant areas of concern include data bias, equity in model assessment, and support for low-resource languages. The study underscores the fact that modern vision-language models, such as Flamingo, GIT, and LLaVA, offer robust domain generalization through cross-modal learning and joint embedding. Furthermore, the efficacy of computing in restricted environments is improved by the development of pretraining procedures and lightweight models. This study contributes by identifying future prospects, analyzing technical trade-offs, and delineating research trends, particularly in sectors such as healthcare, construction, and inclusive AI. According to the results, in order to optimize their efficacy in real-world applications, future picture captioning models must prioritize resource efficiency, impartiality, and multilingual capabilities.
IMPLEMENTASI ALGORITMA KNN UNTUK DETEKSI GENDER DAN USIA BERBASIS PENGENALAN WAJAH Al-Hafiz, Kyana Rakayakzy; Wahid, Abrar; Ain, Ahmad Nur
SEMINAR TEKNOLOGI MAJALENGKA (STIMA) Vol 8 (2024): STIMA 8.0 : Menuju Kesinambungan : Inovasi dan Adaptasi Teknologi untuk Pembangunan Be
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31949/stima.v8i0.1154

Abstract

In the modern era, face recognition is one of the important technologies used in various security and data analysis applications. This paper aims to use Python to implement the K-Nearest Neighbors (KNN) algorithm to detect gender and age through face recognition. The main problem faced is the accuracy in classifying gender and estimating age from various facial images with lighting, pose, and expression. This study uses various steps to collect facial data, use image processing techniques to extract features, and use the KNN algorithm for classification. The results show that applying KNN can detect gender and age from faces with sufficient accuracy, although there are some problems with extreme lighting and pose conditions. These findings indicate that the KNN algorithm can be used in facial recognition applications to detect gender and age. By fixing parameters and improving data quality, further improvements can be achieved.
ANALISIS ANTARMUKA SISTEM INFORMASI AKADEMIK (SIAKAD) UNIVERSITAS MAJALENGKA MENGGUNAKAN METODE EVALUASI HEURISTIK Nida, Milhatun; Wahid, Abrar; Aros , Desfi Silvia; Winata , Satria
SEMINAR TEKNOLOGI MAJALENGKA (STIMA) Vol 9 (2025): Seminar Teknologi Majalengka (STIMA) 9.0 Tahun 2025
Publisher : Universitas Majalengka

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study evaluates the Academic Information System (SIAKAD) interface at Universitas Majalengka using the Heuristic Evaluation method to identify usability issues. The evaluation focuses on two main scenarios, namely the login process and access to the Study Result Card (KHS). The evaluation was conducted by three independent evaluators based on Jakob Nielsen's ten heuristic principles Nielsen. The findings show that there are four usability issues, with three issues categorized as high priority (major) and one issue as low priority (minor). The main issues were found on the login page in the form of uninformative error messages and password text that was not visible to users. Additionally, inconsistencies were found in the navigation access to KHS, which is still integrated with the Course Registration History page. These findings indicate the need for clear error messages, a redesign of the information architecture, and the addition of modern support features to enhance the user experience. This research opens up opportunities for further testing using methods that involve direct users to comprehensively validate the findings. The recommended improvements are expected to increase the effectiveness, efficiency, and user satisfaction in the overall use of the SIAKAD at the University of Majalengka.