Development of Environmental Quality Predictor Using Feedforward Artificial Neural Network (Fann) In Matlab Graphical User Interface (Gui)

Rahim, Nazira Anisa (2015) Development of Environmental Quality Predictor Using Feedforward Artificial Neural Network (Fann) In Matlab Graphical User Interface (Gui). ["eprint_fieldopt_thesis_type_phd" not defined] thesis, Universiti Sains Malaysia.

[img]
Preview
PDF - Submitted Version
Download (253kB) | Preview

Abstract

Usaha pemuliharaan alam sekitar sentiasa berhadapan dengan kerumitan kerana ia melibatkan sejumlah besar pembolehubah. Walau bagaimanapun, dalam proses pembangunan model, pemilihan masukan yang betul untuk hasil ramalan yang berkaitan adalah penting. Tambahan pula, secara tradisinya laporan kualiti alam sekitar cenderung untuk lebih teknikal, menyampaikan data pemantauan alam sekitar yang tidak lengkap dan tidak mudah difahami. Oleh kerana data alam sekitar adalah berlebihan, kaedah pemilihan data input telah diperkenalkan; Analisis Koresponden Berkanun (CCA) dan Analisis Korelasi Berkanun (CCorA). Pendekatan-pendekatan ini boleh digunakan sebagai alat untuk memilih ciri dan bergabung dengan jaringan neural tiruan suapan hadapan (FANN) untuk membangunkan antara muka bergrafik (GUI) bagi peramal untuk para pengguna. Cadangan antara muka bergrafik untuk ramalan alam sekitar akan memberikan petunjuk tahap pencemaran air dan udara dan kualitinya, dengan terma-terma yang biasa digunakan oleh masyarakat. Untuk mencapai objektif tersebut, kajian ini telah dibahagikan kepada tiga fasa utama; penentuan pemilihan ciri masukan, pembangunan model FANN, dan akhir sekali, pembangunan GUI untuk pemantauan di luar talian. Terdapat dua kajian kes yang digunakan dalam kajian ini berdasarkan kepada data kualiti air sungai dan udara. Pengaplikasian CCA dan CCorA untuk menentukan masukan untuk ramalan telah berjaya dengan 7 (SS, NO3, K, NH3-NL, TS, Zn and Tur) dan 3 (kelembapan, suhu dan kelajuan angin) masukan pembolehubah telah dipilih untuk kajian kes 1 dan 2. Keputusan menunjukkan bahawa rangkaian ramalan yang dibangunkan untuk sistem ramalan kualiti alam sekitar telah dilaksanakan dengan baik bagi masukan data yang sedikit. Secara umumnya, system ramalan yang dibangunkan berdasarkan FANN dengan kombinasi CCA dan CCorA telah menunjukkan prestasi yang baik dan membantu dalam memudahkan system ramalan alam sekitar ini. Model berbilang masukan – keluaran input-output tunggal telah berjaya digunakan untuk meramal indeks kualiti air (WQI) dan indeks pencemaran udara (API) dan berjaya dibangunkan dengan nilai regresi 0.90 dan 0.91 bagi kedua-dua rangkaian untuk data masukan yang belum pernah digunakan. __________________________________________________________________________________________________________________________________ The environmental conservation efforts always deal with the complexity problem as it involves a large number of variables. However, in the process development of the model, the correct input selection for the corresponding output prediction is so important. Furthermore, traditional reports on the environmental quality tend to be too technical, presenting monitoring data without providing a complete and easy to understand facts of the environmental quality. Due to the redundancy of the environmental datas, input data selection methods were introduced; Canonical Correspondence Analysis (CCA) and Canonical Correlation Analysis (CCorA). These approaches could be applied as a feature selection tools and combined with Feedforward Artificial Neural Networks (FANN) to develop the graphical prediction interface for the end users. The proposed graphical userinterface for environmental prediction, will give an indication of the water and air pollution degree and their qualities, with the terms that are familiar within the community. To achieve those objectives, this research was divided into three main phases; determination of input feature selection, FANN model development and finally, GUI development for offline monitoring. Two case studies were used in this research which was based on river water and air quality data. The application of CCA and CCorA to determine the input for the prediction was successfully applied with 7 (SS, NO3, K, NH3-NL, TS, Zn and Tur) and 3 (humidity, temperature and wind speed) input variables were selected for Case Study 1 and 2, respectively. The results show that the developed prediction networks for the environmental quality prediction system has been executed well for less of input data. The developed prediction system based on FANN with the combination of CCA and CCorA generally has generally performed well and helped in simplifying the environmental prediction system. The final multi-input single output (MISO) models that have been used to predict the water quality index (WQI) and air pollution index (API) were successfully developed with the regression values of 0.90 and 0.91 for both of the networks for the unseen validation data input.

Item Type: Thesis (["eprint_fieldopt_thesis_type_phd" not defined])
Additional Information: Full text is available at http://irplus.eng.usm.my:8080/ir_plus/institutionalPublicationPublicView.action?institutionalItemId=2206
Subjects: T Technology
T Technology > TK Electrical Engineering. Electronics. Nuclear Engineering > TK7800-8360 Electronics
Divisions: Kampus Kejuruteraan (Engineering Campus) > Pusat Pengajian Kejuruteraaan Elektrik & Elektronik (School of Electrical & Electronic Engineering) > Thesis
Depositing User: Mr Mohd Jasnizam Mohd Salleh
Date Deposited: 26 Jun 2018 04:53
Last Modified: 26 Jun 2018 04:53
URI: http://eprints.usm.my/id/eprint/40814

Actions (login required)

View Item View Item
Share