Flood Image Classification using Convolutional Neural Networks
Flood disaster is a natural disaster that leads to loss of lives, properties damage, devastating effects on the economy and environment; therefore, there should be effective predictive measures to curb this problem. Between the years 2002- 2023, flood has caused death of over 200,000 people globall...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
College of Engineering of Afe Babalola University, Ado-Ekiti (ABUAD), Ekiti State, Nigeria
2023-10-01
|
| Series: | ABUAD Journal of Engineering Research and Development |
| Subjects: | |
| Online Access: | https://journals.abuad.edu.ng/index.php/ajerd/article/view/143 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850033105073602560 |
|---|---|
| author | Olusogo Julius Adetunji Ibrahim Adepoju Adeyanju Adebimpe Omolayo Esan Adedayo Aladejobi Sobowale Sobowale |
| author_facet | Olusogo Julius Adetunji Ibrahim Adepoju Adeyanju Adebimpe Omolayo Esan Adedayo Aladejobi Sobowale Sobowale |
| author_sort | Olusogo Julius Adetunji |
| collection | DOAJ |
| description |
Flood disaster is a natural disaster that leads to loss of lives, properties damage, devastating effects on the economy and environment; therefore, there should be effective predictive measures to curb this problem. Between the years 2002- 2023, flood has caused death of over 200,000 people globally and occurred majorly in resource poor countries and communities. Different machine learning approaches have been developed for the prediction of floods. This study develops a novel model using convolutional neural networks (CNN) for the prediction of floods. Important parameters such as standard deviation and variance were incorporated in the parameters tuned CNN model that performed flood images feature extraction and classification for better predictive performance. The enhanced model was assessed with accuracy and loss measurement and compared with the existing model. The model leverage on the unique features of region of Interest aligns to resolve the issues of misalignments caused by the use of region of Interest pooling engaged in the traditional Faster-RCNN. The techniques and the developed system were implemented using a Python-based integrated development environment called “Anaconda Navigator” on Intel Core i5 with 8G Ram hardware of Window 10 operating system. The developed model achieved optimal accuracy at 200 epochs with 99.80% and corresponding loss of 0.0890. The results confirmed that predictive performance of a model can be improved by incorporating standard deviation and variance on model, coupled with its parameters tunning approach before classification.
|
| format | Article |
| id | doaj-art-3bdb7cfb4aa04042871b22a475607e82 |
| institution | DOAJ |
| issn | 2756-6811 2645-2685 |
| language | English |
| publishDate | 2023-10-01 |
| publisher | College of Engineering of Afe Babalola University, Ado-Ekiti (ABUAD), Ekiti State, Nigeria |
| record_format | Article |
| series | ABUAD Journal of Engineering Research and Development |
| spelling | doaj-art-3bdb7cfb4aa04042871b22a475607e822025-08-20T02:58:19ZengCollege of Engineering of Afe Babalola University, Ado-Ekiti (ABUAD), Ekiti State, NigeriaABUAD Journal of Engineering Research and Development2756-68112645-26852023-10-016210.53982/ajerd.2023.0602.11-j119Flood Image Classification using Convolutional Neural NetworksOlusogo Julius Adetunji0Ibrahim Adepoju Adeyanju1Adebimpe Omolayo Esan2Adedayo Aladejobi Sobowale Sobowale3Department of Computer Engineering, Bells University of Technology, Ota, Ogun State, NigeriaDepartment of Computer Engineering, Federal University, Oye- Ekiti, Ekiti State, NigeriaDepartment of Computer Engineering, Federal University, Oye- Ekiti, Ekiti State, NigeriaDepartment of Computer Engineering, Federal University, Oye- Ekiti, Ekiti State, Nigeria Flood disaster is a natural disaster that leads to loss of lives, properties damage, devastating effects on the economy and environment; therefore, there should be effective predictive measures to curb this problem. Between the years 2002- 2023, flood has caused death of over 200,000 people globally and occurred majorly in resource poor countries and communities. Different machine learning approaches have been developed for the prediction of floods. This study develops a novel model using convolutional neural networks (CNN) for the prediction of floods. Important parameters such as standard deviation and variance were incorporated in the parameters tuned CNN model that performed flood images feature extraction and classification for better predictive performance. The enhanced model was assessed with accuracy and loss measurement and compared with the existing model. The model leverage on the unique features of region of Interest aligns to resolve the issues of misalignments caused by the use of region of Interest pooling engaged in the traditional Faster-RCNN. The techniques and the developed system were implemented using a Python-based integrated development environment called “Anaconda Navigator” on Intel Core i5 with 8G Ram hardware of Window 10 operating system. The developed model achieved optimal accuracy at 200 epochs with 99.80% and corresponding loss of 0.0890. The results confirmed that predictive performance of a model can be improved by incorporating standard deviation and variance on model, coupled with its parameters tunning approach before classification. https://journals.abuad.edu.ng/index.php/ajerd/article/view/143Convolutional neural networksFloodMachine learningPredictionNatural disasters |
| spellingShingle | Olusogo Julius Adetunji Ibrahim Adepoju Adeyanju Adebimpe Omolayo Esan Adedayo Aladejobi Sobowale Sobowale Flood Image Classification using Convolutional Neural Networks ABUAD Journal of Engineering Research and Development Convolutional neural networks Flood Machine learning Prediction Natural disasters |
| title | Flood Image Classification using Convolutional Neural Networks |
| title_full | Flood Image Classification using Convolutional Neural Networks |
| title_fullStr | Flood Image Classification using Convolutional Neural Networks |
| title_full_unstemmed | Flood Image Classification using Convolutional Neural Networks |
| title_short | Flood Image Classification using Convolutional Neural Networks |
| title_sort | flood image classification using convolutional neural networks |
| topic | Convolutional neural networks Flood Machine learning Prediction Natural disasters |
| url | https://journals.abuad.edu.ng/index.php/ajerd/article/view/143 |
| work_keys_str_mv | AT olusogojuliusadetunji floodimageclassificationusingconvolutionalneuralnetworks AT ibrahimadepojuadeyanju floodimageclassificationusingconvolutionalneuralnetworks AT adebimpeomolayoesan floodimageclassificationusingconvolutionalneuralnetworks AT adedayoaladejobisobowalesobowale floodimageclassificationusingconvolutionalneuralnetworks |