Claim Missing Document
Check
Articles

Found 34 Documents
Search

Enhanced RegNetY-400MF for Fruit Fly Species Classification: Fine-Tuning Strategies and Data Balancing for Improved Accuracy Rahman, Sayuti; Indrawati, Asmah; Zen, Muhammad; Zealtiel, Billiam; Tanjung, Shabila Shaharani
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 9 No 6 (2025): December 2025
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v9i6.6973

Abstract

Fruit fly infestations pose a significant threat to agricultural productivity, especially in chili plantations, which can cause substantial yield losses. Accurate and rapid species classification is crucial for implementing targeted pest control strategies. This study developed a computationally efficient fruit fly species classification model using a deep learning approach that focused on improving accuracy with fine tuning and class balancing strategies. The dataset consists of 1049 images across 4 fruit fly species, captured in a natural plantation environment and available at www.inaturalist.org. The model evaluated several lightweight Convolutional Neural Network (CNN) architectures, including MobileNetV3-Small, RegNetY-400MF, and SqueezeNet among others, with RegNetY-400MF emerging as the best performing model, achieving a validation accuracy of 96.10% and a macro F1 score of 95.70%. The models tested in this study included several lightweight Convolutional Neural Network (CNN) architectures, including MobileNetV3-Small, RegNetY-400MF, and SqueezeNet, among others. RegNetY-400MF proved to be the best performing model, achieving a validation accuracy of 96.10% and a macro F1 score of 95.70%. Compared to other state-of-the-art models, RegNetY-400MF demonstrated higher accuracy while maintaining a lower number of parameters (8.3 million) and reduced computational complexity (0.41 GFLOPs). This makes the model highly suitable for real-time applications in resource-constrained agricultural environments. The model offers a practical solution for fruit fly species detection, enabling early and accurate identification of pest infestations in chili plantations, thereby reducing the risk of crop failure. By providing an efficient and scalable pest control tool, the model supports precision pest management, improves yield stability, and contributes to sustainable agriculture.
INTEGRASI MAQASHID SYARIAH DAN SGDS DALAM MODEL PEMBIAYAAN MIKRO SYARIAH KONTEMPORER fatkhullah, imam; zen, muhammad
JSE: Jurnal Sharia Economica Vol. 5 No. 1 (2026): Januari
Publisher : LPPM STAI Muhammadiyah Probolinggo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46773/jse.v5i1.2912

Abstract

This study aims to analyze the relevance of maqasid al-shariah in microfinance through a comparative dialogue between classical fiqh and the practices of contemporary Islamic Microfinance Institutions (IMFIs). Using a qualitative descriptive-comparative approach based on library research, the study examines classical sources such as al-Ghazali, al-Syatibi, and Ibn ‘Ashur, alongside modern literature on Islamic microfinance. The findings reveal that classical fiqh emphasizes normative protection of the five essential dimensions of maqasid through simple contracts such as qardh, mudharabah, and musyarakah. In contrast, contemporary IMFIs apply maqasid in a more practical manner, focusing on financial inclusion, economic empowerment, and sustainable development. The study also identifies challenges in consistent implementation due to limited resources and market competition, yet highlights opportunities through innovative Islamic financial instruments and the legitimacy of DSN-MUI fatwas. Thus, maqasid al-shariah can be viewed as a dynamic framework that balances shariah compliance with socio-economic welfare, positioning IMFIs as agents of just, inclusive, and sustainable transformation.
Perancangan Antarmuka Website Labusel Creative sebagai Media Informasi Daerah Menggunakan Metode UCD Rezki, Ahmad; Zen, Muhammad; Hafni
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.827

Abstract

Kabupaten Labuhanbatu Selatan memiliki peluang besar di bidang ekonomi kreatif dan UMKM, tetapi sistem informasi digital yang mendukung masih kurang terintegrasi. Penelitian ini bertujuan membuat website "Labusel Creative" sebagai pusat informasi yang menyatu, dengan menggunakan metode User Centered Design (UCD) agar pengguna merasa nyaman dan mudah dalam mengakses informasi. Selain itu, fitur Internet of Things (IoT) yang menggunakan mikrokontroler ESP32 diintegrasikan untuk mengawasi suhu di studio kreatif secara langsung. Hasil penelitian berhasil menciptakan antarmuka yang mudah digunakan oleh masyarakat umum, serta memberikan platform informasi lokal yang efektif untuk meningkatkan penjualan produk daerah di dunia maya.
IoT-Based Smart Home System for LPG Leak Detection and Mitigation in Households Integrated with Blynk Riding, Redistia; Muttaqin, Muhammad; Zen, Muhammad
Jurnal Komputer Teknologi Informasi Sistem Informasi (JUKTISI) Vol. 4 No. 3 (2026): Februari 2026
Publisher : LKP KARYA PRIMA KURSUS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62712/juktisi.v4i3.846

Abstract

Liquefied Petroleum Gas (LPG) is widely used as the primary energy source in Indonesian households; however, gas leakage poses a serious risk that may lead to fires and explosions if not detected at an early stage. This study aims to design and implement a smart home system based on the Internet of Things (IoT) for the detection and mitigation of LPG gas leaks in households integrated with the Blynk application. The research employed an experimental method by designing and testing a system using an ESP32 microcontroller, an MQ-2 gas sensor, a buzzer, LED indicators, and the Blynk application for remote monitoring and notifications. System testing was conducted in a real household environment with variations in the distance between the gas source and the sensor to evaluate sensor sensitivity, system response time, and IoT connectivity stability. The experimental results indicate that the system can effectively detect LPG gas leaks at an optimal distance of 5–15 cm, with an alarm response time of less than 2 seconds and an average Blynk notification delay of 2–3 seconds. In addition, the system demonstrated stable performance during continuous operation. Based on these results, the proposed system is considered effective, easy to implement, and has strong potential to enhance household safety against LPG gas leakage risks in Indonesia.