Sistem Monitoring Warna Air Limbah Berstandar Platinum-Cobalt Melalui Sensor Ezo-RGB dengan Integrasi Artificial Neural Network

Jolie, Salsabilla Muntarilla (2024) Sistem Monitoring Warna Air Limbah Berstandar Platinum-Cobalt Melalui Sensor Ezo-RGB dengan Integrasi Artificial Neural Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2042201120-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (12MB) | Request a copy

Abstract

Penelitian ini mengkaji integrasi jaringan saraf tiruan (artificial neural network, ANN) dalam platform Python untuk monitoring warna air berstandar platinum-cobalt (PtCo) menggunakan sensor EZO RGB. ANN diusulkan sebagai solusi potensial untuk mengatasi tantangan ini karena dapat mempelajari data sensor RGB dan mengembangkan sistem pemantauan air dengan standar Pt-Co secara otomatis dan real-time. Penelitian ini menggunakan pendekatan kuantitatif dengan desain kelompok kontrol dan eksperimen. Perangkat keras yang dikembangkan melibatkan sensor EZO-RGB, single-board computer, dan monitor. Proses pengukuran melibatkan analisis data warna RGB menggunakan ANN, dengan validasi menggunakan standar Pt-Co. Sistem yang dikembangkan memanfaatkan ANN untuk memprediksi nilai PtCo berdasarkan parameter warna air yang diukur oleh sensor. Model ANN yang dihasilkan menunjukkan performa yang sangat baik dengan Mean Squared Error (MSE) rendah dan koefisien determinasi (R²) tinggi sebesar 0,999951. Hasil pengujian menunjukkan bahwa model ANN tidak mengalami overfitting dan mampu melakukan generalisasi dengan baik pada data baru. Integrasi ANN dalam Python mempermudah pengembangan, pengujian, dan visualisasi hasil. Penelitian ini membuktikan bahwa ANN yang diimplementasikan dalam Python dapat meningkatkan akurasi dan efisiensi monitoring kualitas air, serta dapat diandalkan untuk aplikasi monitoring real-time. Saran untuk pengembangan lebih lanjut mencakup peningkatan kompleksitas model, penggunaan dataset yang lebih besar, dan implementasi dalam sistem monitoring real-time.

======================================================================================================================================
This research examines the integration of artificial neural networks (ANN) within a Python platform for monitoring water color according to platinum-cobalt (PtCo) standards using an EZO RGB sensor. ANN is proposed as a potential solution to this challenge because there will be a trained RGB sensor data and develop an automatic and real-time water monitoring system with Pt-Co standards. This study uses a quantitative approach with a control and experimental group design. The developed hardware involves an EZO-RGB sensor, a single-board computer, and a monitor. The measurement process involves analyzing RGB color data using ANN, with validation using Pt-Co standards. The developed system utilizes ANN to predict PtCo values based on water color parameters measured by the sensor. The resulting ANN model shows a quiet good performance with a low Mean Squared Error (MSE) and a high coefficient of determination (R²) of 0.999951. Testing results indicate that the ANN model does not experience overfitting and can generalize well to new data. The integration of ANN in Python facilitates development, testing, and visualization of results. This research demonstrates that ANN implemented in Python can enhance the accuracy and efficiency of water quality monitoring and is reliable for real-time monitoring applications. Recommendations for further development include increasing model complexity, using larger datasets, and implementing in real-time monitoring systems.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Monitoring water quality, watercolor, RGB sensor, artificial neural network, clean water and sanitation, Pemantauan kualitas air, warna air, sensor RGB, jaringan saraf tiruan, Clean water and sanitation
Subjects:	T Technology > TD Environmental technology. Sanitary engineering > TD433 Water treatment plants
Divisions:	Faculty of Vocational > Instrumentation Engineering
Depositing User:	Jolie Salsabilla Muntarilla
Date Deposited:	30 Jul 2024 08:45
Last Modified:	30 Jul 2024 08:45
URI:	http://repository.its.ac.id/id/eprint/110133

Actions (login required)

View Item