Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal Jurnal Sisfokom (Sistem Informasi dan Komputer) MIND (Multimedia Artificial Intelligent Networking Database) Journal
Malinda, Threa
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Implementation of an IoT-based Threshold Method for a Food Hazardous Substance Detection Tool Malinda, Threa; Salamah, Irma; Anugraha, Nurhajar
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 14 No. 3 (2025): JULY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v14i3.2397

Abstract

Food safety is a critical issue that has a direct impact on public health. Illegal addition of hazardous substances such as rhodamine B, melachite green, methanyl yellow, formalin, borax, and sodium hypochlorite are still commonly found in food products sold in the market. This research project aims to develop a tool for detecting hazardous substances in Internet of Things (IoT) based foods using a threshold method that refers to BPOM regulations. The threshold method refers to BPOM regulations. This system integrates two sensors: The TCS3200 sensor is used for RGB color analysis, and the HCHO sensor detects volatile compounds detecting volatile compounds. Test results show that this tool achieves 96.67% accuracy in identifying hazardous substances without producing false positives. The novelty of this research lies in combining both sensors into one system with real-time notification via Telegram. This research is novel because it combines both sensors into one system with real-time notifications via Telegram. It combines both sensors into a single system with real-time notifications via Telegram and ThingSpeak.
Identifikasi CNN dalam Deteksi Penyakit Daun Jagung Berbasis Pengenalan Gambar ARYANTI, ARYANTI; APRILIANI, DEFINA; PUTRI, WULAN ZAHRA; RAMADHANI, DWI; MALINDA, THREA; ANDREANSYAH, DIMAS
MIND (Multimedia Artificial Intelligent Networking Database) Journal Vol 10, No 2 (2025): MIND Journal
Publisher : Institut Teknologi Nasional Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26760/mindjournal.v10i2.195-205

Abstract

AbstrakProduktivitas jagung sangat terancam oleh penyakit daun seperti common rust, gray leaf spot, dan leaf blight. Identifikasi penyakit yang lambat dan tidak akurat menjadi masalah utama yang mendesak. Oleh karena itu, penelitian ini bertujuan mengembangkan mekanisme identifikasi otomatis penyakit daun jagung menggunakan algoritma Convolutional Neural Network (CNN) berbasis citra digital, mendukung upaya pertanian presisi. Penelitian menggunakan 4.188 citra daun (sehat, leaf blight, rust, dan gray leaf spot) yang diproses melalui preprocessing seperti normalisasi dan augmentasi. Hasil pengujian menunjukkan efektivitas tinggi, di mana model CNN mencapai akurasi klasifikasi 95% dengan waktu inferensi cepat, hanya 0,48 detik per gambar. Kontribusi utama penelitian ini adalah penyediaan model CNN yang sangat akurat dan efisien, berpotensi besar menjadi dasar sistem diagnostik lapangan untuk membantu petani meningkatkan kualitas dan hasil produksi jagung.Kata kunci: CNN, Deteksi Penyakit, Jagung, Pengenalan Citra, Deep Learning AbstractCorn productivity is severely threatened by leaf diseases such as common rust, gray leaf spot, and leaf blight. Slow and inaccurate disease identification is a pressing issue. Therefore, this study aims to develop an automatic corn leaf disease identification mechanism using a digital image-based Convolutional Neural Network (CNN) algorithm, supporting precision agriculture efforts. The study used 4,188 leaf images (healthy, leaf blight, rust, and gray leaf spot) that were processed through preprocessing such as normalization and augmentation. The test results demonstrated high effectiveness, where the CNN model achieved 95% classification accuracy with a fast inference time of only 0.48 seconds per image. The main contribution of this study is the provision of a highly accurate and efficient CNN model, with great potential to become the basis of a field diagnostic system to help farmers improve corn quality and yield.Keywords: CNN, Disease Detection, Corn, Image Recognition, Deep Learning
Co-Authors ANDREANSYAH, DIMAS APRILIANI, DEFINA Aryanti Aryanti DWI RAMADHANI Irma Salamah Nurhajar Anugraha PUTRI, WULAN ZAHRA