Klasifikasi Sedimen Dasar Perairan Darat Berbasis Artificial Neural Network (Ann) Menggunakan Data Backscatter Multispektral Mbes Dan Angular Response Curve (Arc)

Hadicahyo, Ogi (2023) Klasifikasi Sedimen Dasar Perairan Darat Berbasis Artificial Neural Network (Ann) Menggunakan Data Backscatter Multispektral Mbes Dan Angular Response Curve (Arc). Other thesis, Institut Teknologi Sepuluh November.

Text 03311940000092-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 September 2025. Download (10MB) | Request a copy

Abstract

Penelitian ini menyelidiki klasifikasi distribusi dan jenis sedimen di perairan pedalaman menggunakan model Artificial Neural Network (ANN) berdasarkan data echosounder multibeam. Multibeam Echosounder Technology (MBES) adalah instrumen akustik yang memancarkan pulsa suara berkecepatan tinggi untuk memetakan dasar badan air. Dengan menganalisis fenomena hamburan balik, yang mengukur intensitas akustik yang dipantulkan dari dasar air, informasi berharga tentang karakteristik sedimen dapat diperoleh. Metode Angular Response Curve (ARC), yang dikembangkan oleh Fonseca dan Calder, digunakan untuk menganalisis hubungan antara intensitas hamburan balik dan sudut refleksi. Model ANN dalam penelitian ini dilatih dan diuji menggunakan nilai intensitas dan kurva respons sudut yang diperoleh dari multibeam echosounder serta sampel sedimen yang diperoleh melalui proses pengambilan secara langsung sebanyak 16 sampel.. Arsitektur model ANN terdiri dari lapisan input, tiga lapisan tersembunyi, dan lapisan output. Fungsi aktivasi sigmoid digunakan dalam lapisan output, sedangkan fungsi aktivasi ReLU diterapkan pada lapisan input dan tersembunyi. Evaluasi kinerja menunjukkan bahwa model ANN yang menggunakan data yang tidak dikoreksi mencapai akurasi yang luar biasa, dengan akurasi 100% diperoleh pada tahap pelatihan dan pengujian. Model ini menunjukkan nilai kerugian pelatihan 0,059443 dan nilai kerugian pengujian 0,110030, menunjukkan efektivitasnya dalam menangkap pola dan mengurangi kesalahan. Memvisualisasikan distribusi sedimen di Waduk Selorejo mengungkapkan keberadaan jenis sedimen Pasir Tanah Liat dan Lumpur Berpasir yang relatif seimbang. Namun, perbedaan mencolok muncul antara data yang dikoreksi dan tidak dikoreksi, yang dapat dikaitkan dengan perubahan yang dilakukan selama proses koreksi data. Model ANN berkinerja terbaik mencapai akurasi pengujian 0,75, menunjukkan bahwa ia tidak memprediksi data yang diberikan dengan sempurna. Penting untuk mengetahui potensi kesalahan prediksi saat menggunakan data yang dikoreksi
===================================================================================================================================
This study investigates the classification of sediment distribution and types in inland waters using Artificial Neural Network (ANN) models based on multibeam echosounder data. Multibeam Echosounder Technology (MBES) is an acoustic instrument that emits high-speed sound pulses to map the bottom of water bodies. By analyzing the backscatter phenomenon, which measures the acoustic intensity reflected from the water bottom, valuable information about sediment characteristics can be obtained. The Angular Response Curve (ARC) method, developed by Fonseca and Calder, is employed to analyze the relationship between backscatter intensity and the angle of reflection. The ANN models in this study are trained and tested using intensity values and angular response curves obtained from multibeam echosounders. The ANN model architecture consists of an input layer, three hidden layers, and an output layer. The sigmoid activation function is utilized in the output layer, while the ReLU activation function is applied to the input and hidden layers. Performance evaluation demonstrates that the ANN model using uncorrected data achieves remarkable accuracy, with 100% accuracy obtained in both the training and testing stages. The model exhibits a training loss value of 0.059443 and a testing loss value of 0.110030, indicating its effectiveness in capturing patterns and reducing errors. Visualizing the sediment distribution in Waduk Selorejo reveals a relatively balanced presence of Pasir Tanah Liat and Lumpur Berpasir sediment types. However, noticeable differences arise between the corrected and uncorrected data, which can be attributed to the alterations made during the data correction process. The best-performing ANN model achieves a testing accuracy of 0.75, indicating that it does not perfectly predict the given data. It is important to acknowledge the potential for prediction errors when using corrected data

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Multibeam Echosounder (MBES), Klasifikasi Sedimen, Angular Response Curve (ARC), Artificial Neural Network (ANN); Multibeam Echosounder (MBES), Sediment Classification, Angular Response Curve (ARC), Artificial Neural Network (ANN)
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science) Q Science > QE Geology > QE571 Sedimentation and deposition. Sediment transport. Erosion.
Divisions:	Faculty of Civil, Planning, and Geo Engineering (CIVPLAN) > Geomatics Engineering > 29202-(S1) Undergraduate Thesis
Depositing User:	Ogi Hadicahyo
Date Deposited:	31 Aug 2023 03:54
Last Modified:	31 Aug 2023 03:54
URI:	http://repository.its.ac.id/id/eprint/101971

Actions (login required)

View Item