Flood Prediction and warning system using SVM and ELM models
M Madhuram1, Anuj Kakar2, Anushri Sharma3, Saurav Chaudhuri4
1M Madhuram, Department of Computer Science, Sri Ramaswamy Memorial Institute of Science and Technology(SRM), Ramapuram, Chennai, India.
2Anuj Kakar, Pursuing Bachelors of Technology, Computer Science and Engineering, Sri Ramaswamy Memorial Institute of Science and Technology(SRM), Ramapuram, Chennai, Inidia.
3Anushri Sharma, Pursuing Bachelors of Technology, Computer Science and Engineering, Sri Ramaswamy Memorial Institute of Science and Technology(SRM), Ramapuram, Chennai, India.
4Saurav Chaudhuri, Pursuing Bachelors of Technology, Computer Science and Engineering, Sri Ramaswamy Memorial Institute of Science and Technology(SRM), Ramapuram, Chennai, India.
Manuscript received on November 12, 2019. | Revised Manuscript received on November 25, 2019. | Manuscript published on 30 November, 2019. | PP: 5366-5369 | Volume-8 Issue-4, November 2019. | Retrieval Number: D7573118419/2019©BEIESP | DOI: 10.35940/ijrte.D7573.118419
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Seeing the rising amount of flood calamities worldwide flood management system are recently in limelight and are receiving the much needed attention. However the technologies used in determining and predicting the occurrence of a flood is somewhat inaccurate. Taking into consideration the number of lives at stake this project is aimed at introducing newer and possibly, more effective methods and techniques than its previously used flood prediction models. The proposed system seeks to implement machine learning by gathering the previously existing data along with a periodic live feed update so as to predict the chances of flood occurrence and so as to implement the necessary counteractive measures that can be deployed so as to evade such a mishap. The area taken into consideration for testing this new system is based on Chennai; capital of Tamil Nadu which spans over an area of 426 km2.The study illustrates how a hybrid model is generated by taking all the data and using the Support Vector Machine (SVM) model and Extreme Learning Machine (ELM) model on it. The experimental results show that the integrated algorithm performs much better than other benchmarks. Moreover, testing the algorithm with live data makes it even more efficient and precise compared to other algorithms and proposed systems helping us to counteract real time fiascos. The main application of this system is to enable the user to warn and evacuate a mass population in case of a mishap.
Keywords: SVM, ELM, Image, Classification, Flood Forecasting, Machine Learning.
Scope of the Article: Machine Learning.