Budiarti, Rizqi Putri Nourma (2016) Klasifikasi Air Sungai Berbasis Kombinasi Teknologi IOT-BIG Data Menggunakan SVM. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
2214205202 – Master Thesis.pdf - Published Version Download (2MB) | Preview |
Abstract
Betapa pentingnya peranan air bagi kehidupan makhluk hidup, tidak hanya bagi manusia bahkan makhluk hidup lainnya membutuhkan air sebagai salah satu unsur pendukung keberlangsungan kehidupan pada tiap makhluk hidup. Untuk menjaga keberlangsungan sumber daya air khususnya air sungai diperlukan sistem monitoring yang mampu mengambil parameter kualitas air dengan menggunakan sensor. Telah banyak tersedia perangkat sensor kualitas air, namun masih belum ada sistem monitoring yang mampu melakukan klasifikasi kualitas air tersebut secara interaktif dan akurat.
Untuk mengatasi permasalahan tersebut, pada penelitian ini akan di buat sistem perangkat Internet of Things yang terdiri dari sensor kualitas air YSI 600R, sistem benam Raspberry Pi 3 dan perangkat komunikasi 4G. Selain itu telah dibuat juga sistem Big Data yang dilengkapi dengan fitur machine learning yang dapat melakukan klasifikasi kualitas air. Proses monitoring dilakukan pada area intake PDAM Karang Pilang dengan klasifikasi menggunakan metode Support Vector Machine. Hasil dari sistem ini dapat mengklasifikasi kualitas air sungai tersebut secara interaktif dan akurat.
Hasil penelitian ini menunjukkan bahwa dengan metode Support Vector Machine menghasilkan performance nilai akurasi total untuk SVM dengan kernel Linear adalah 0.9138 dan SVM dengan kernel RBF adalah 0.8372.Pengujian hasil validasi telah dilakukan berdasarkan grafik ROC dengan nilai area Under ROC menunjukan 0.93. Dengan begitu dapat dikatakan bahwa unjuk kerja berdasarkan nilai Area Under ROC “Excellent”.
==================================================================================================================
How important to role of water for the survival of living beings, not only for human but also the other living beings need water as one of the element that supporting the continuity of life in every living creature. In order to maintain the necessary of water resources such as river, recently the need of monitoring system that able to take the parameter of water quality using sensors really important. Nowadays, has been widely the available of water quality sensor devices, but there isn’t monitoring system that able to perform the classification of water quality in interactive and accurate.
To overcome these problems, in this thesis we built a Prototype the Internet of Things system consisting of YSI water quality sensors 600R, embedded systems Raspberry Pi 3 and 4G communication device. Additionally, we built also Big-Data system that equipped with machine learning algorithm that can perform water quality classification with Support Vector Machine method. This system monitor every activities on PDAM Karang Pilang and applying classification. The result of this sistem is able to perform the classification of river water quality in interactive and accurate.
The result are, we were able to do classification by using Support Vector Machine with accuracy level 0.9138 by using Linear kernel and 0.8372 by using RBF kernel. From ROC result, we achieved AUC value until 0.93. Its mean we achieved excelent result.
| Item Type: | Thesis (Masters) |
|---|---|
| Uncontrolled Keywords: | Klasifikasi Air Sungai, Internet of Things, Big Data, Support Vector Machine. |
| Subjects: | T Technology > T Technology (General) T Technology > T Technology (General) > T58.62 Decision support systems T Technology > TD Environmental technology. Sanitary engineering > TD646 Sewage--Purification |
| Divisions: | Faculty of Industrial Technology > Electrical Engineering > 20101-(S2) Master Thesis |
| Depositing User: | - Rizqi Putri Nourma Budiarti |
| Date Deposited: | 31 Mar 2017 04:07 |
| Last Modified: | 26 Dec 2018 06:57 |
| URI: | http://repository.its.ac.id/id/eprint/2624 |
Actions (login required)
 |
View Item |