Claim Missing Document
Check
Articles

Found 23 Documents
Search

Optimization of Gray Level Co-occurrence Matrix (GLCM) Texture Feature Parameters in Determining Rice Seed Quality Aji Setiawan; Adam Arif Budiman
EMITTER International Journal of Engineering Technology Vol 13 No 1 (2025)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v13i1.928

Abstract

Rice seed quality assessment is a critical measure in promoting agricultural productivity, as high-quality seeds directly influence crop yield and resilience. One of method for evaluating seed quality is texture analysis, which leverages the Gray Level Co-occurrence Matrix (GLCM) to extract meaningful features from seed images, providing insights into their condition and potential performance. This research aims to determine the optimal performance of GLCM parameters in identifying the texture characteristics of rice seed quality. The experiments were conducted using four angles (0°, 45°, 90°, and 135°) and three-pixel distances (1, 2, and 3), evaluating features such as homogeneity, contrast, dissimilarity, and energy. The results indicate that certain parameter configurations significantly affect the discriminative power of the extracted features, with the Support Vector Machine (SVM) classifier achieving the highest performance at a pixel distance of 1, with an accuracy of 0.73, precision of 0.79, recall of 0.73, and F1-score of 0.72. These findings demonstrate that optimizing GLCM parameter settings directly contributes to improved classification performance, highlighting the method's potential for enhancing rice seed quality assessment.
Optimizing Deep Learning: Workshop on Improving Teacher Capacity in the Application of Artificial Inteligent (AI) and Coding at SDIT Mafatih Suzuki Syofian; Andi Susilo; Yan Sofyan Andhana Saputra; Aji Setiawan; Afri Yudha
JEPTIRA Vol 4 No 1 (2026): Jurnal Pengabdian Teknologi, Ekonomi dan Humaniora
Publisher : Fakultas Teknik Universitas Darma Persada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70491/jeptira.v4i1.136

Abstract

The integration of Coding and Artificial Intelligence (AI) in elementary education faces significant challenges, particularly regarding teacher readiness and infrastructure. SDIT Mafatih teachers often perceive Computational Thinking (CT) solely as a programming activity, overlooking its core pillars: decomposition, pattern recognition, abstraction, and algorithms. This community service program aims to enhance teacher capacity at SDIT Mafatih through a structured four-stage approach: a basic CT workshop emphasizing unplugged activities, provision of basic digital infrastructure, development of an integrative curriculum guide, and progressive Scratch training. The program utilized a participatory method involving 23 participants, supported by the provision of tablets and projectors. Results indicated a significant improvement in teacher competency, with average initial knowledge scores reaching 79.9% of the maximum. The activities successfully produced integrative lesson plans and digital learning modules, demonstrating an effective model for digital transformation in resource-limited educational settings.
Digitalization of The Transaction Management and Financial Reporting System at D'jakarta Barbershop Nabillah Indah Tsuraya; Zahra Khanza Aurilia; Fajar Ilhami Indo Syaputra; Aji Setiawan; Herianto
JEPTIRA Vol 4 No 1 (2026): Jurnal Pengabdian Teknologi, Ekonomi dan Humaniora
Publisher : Fakultas Teknik Universitas Darma Persada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70491/rz2fb380

Abstract

Barbershop D'Jakarta is a hair care business that requires integrated transaction and financial management to ensure efficient business operations. This study aims to design and develop a web-based financial and operational management information system using the Laravel 11 framework with a MySQL database. The system was developed using the Waterfall method and is divided into two user roles: Owner and Admin. Key features include a home screen (START), authentication, an adaptive dashboard, account and employee management, products/services, customers, two-step transactions with JPEG payment proof upload, expenses, monthly targets, statistics along with employee rankings, and automatically numbered PDF financial reports. The interface is built with custom, responsive CSS and supports both light and dark modes. Black-box testing results show that all features function as required with a 100% success rate. This system has proven to replace manual record-keeping, improve data accuracy, and make it easier for owners to monitor business performance in real time.