Rancang Bangun Frontend Website Dan Fitur Klasifikasi Kekeruhan Air Untuk Memantau Kualitas Air Dari Data Drone

Azizah, Nur (2025) Rancang Bangun Frontend Website Dan Fitur Klasifikasi Kekeruhan Air Untuk Memantau Kualitas Air Dari Data Drone. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5025211252-Undergraduate_Thesis.pdf Restricted to Repository staff only Download (10MB) | Request a copy

Abstract

Pemantauan kualitas air di berbagai kawasan perlindungan perairan seringkali terhambat oleh terbatasnya sumber daya dan cakupan geografis yang sangat luas. Penelitian Tugas Akhir ini membahas tentang desain dan pengembangan aplikasi frontend berbasis web untuk sistem pemantauan kualitas air dengan data drone, yaitu DroneMEQ (Drones for Marine Environmental Quality), yang mengimplementasikan fitur klasifikasi kekeruhan air. Dalam sistem ini, drone dilengkapi dengan kamera RGB yang menangkap gambar permukaan air, kemudian mengirimkan gambar tersebut ke server melalui koneksi nirkabel. Gambar ini diproses menggunakan model deep learning YOLOv9 untuk mengklasifikasi kekeruhan air. Model YOLOv9 tanpa pra-progres augmentasi dipilih sebagai model final setelah evaluasi menggunakan metrik precision, recall, F1-score, dan mAP serta membandingkan performa model YOLOv8, YOLOv9, DETR, Faster R-CNN ResNet50, dan Faster R-CNN ResNet101. Evaluasi software dilakukan menggunakan SonarQube untuk analisis kode dan ESLint untuk linting serta styling kode. Pengujian fungsional dilakukan pada semua modul dan menunjukkan hasil 100% berhasil. Frontend sistem monitoring kualitas air dari data drone dan fitur klasifikasi kekeruhan air ini telah berhasil dikembangkan dan dapat digunakan untuk memantau kualitas air.
==================================================================================================================================
Water quality monitoring in various marine protected areas is often hampered by limited resources and very wide geographical coverage. This Final Project research discusses the design and development of a web-based frontend application for a water quality monitoring system with drone data, namely DroneMEQ (Drones for Marine Environmental Quality), which implements the water turbidity classification feature. In this system, the drone is equipped with an RGB camera that captures images of the water surface, then sends the images to the server via a wireless connection. These images are processed using the YOLOv9 deep learning model to classify water turbidity. The YOLOv9 model without augmentation pre-progression was selected as the final model after evaluation using precision, recall, F1-score, and mAP metrics and comparing the performance of the YOLOv8, YOLOv9, DETR, Faster R-CNN ResNet50, and Faster R-CNN ResNet101 models. Software evaluation was carried out using SonarQube for code analysis and ESLint for code linting and styling. Functional testing was carried out on all modules and showed 100% successful results. The frontend of the water quality monitoring system from drone data and the water turbidity classification feature has been successfully developed and can be used to monitor water quality.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Deep Learning, DETR, DroneMEQ, Faster R-CNN ResNet50, Faster R-CNN ResNet101, Klasifikasi Kekeruhan Air, Machine Learning, Pemantauan Kualitas Air Berbasis Drone, Pengembangan Web Frontend, Yolov8, YOLOv9 ============================================================================================================================================ Deep Learning, DETR, DroneMEQ, Faster R-CNN ResNet50, Faster R-CNN ResNet101, Machine Learning, Drone Based Water Quality Monitoring, Frontend Web Development, Water Turbidity Classification, YOLOv8, YOLOv9
Subjects:	T Technology > T Technology (General) > T58.6 Management information systems
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Nur Azizah
Date Deposited:	28 Jul 2025 07:55
Last Modified:	28 Jul 2025 07:55
URI:	http://repository.its.ac.id/id/eprint/122200

Actions (login required)

View Item