Authors : Hasmeda Erna Che Hamid, Nurjannatul Jannah Aqilah Md Saad, Noor Afiza Mat Razali, Muslihah Wook, Mohammad Adib Khairuddin and Mohd Nazri Ismail
Abstract: Based on the National Security Council (NSC) Directive No. 20 that concern in coordinating responsible agencies and committee, the Malaysian government has established a disaster management coordination and preparedness agency. Among the natural disasters that occurred in Malaysia, floods are the most destructive. Thus, research to develop the flood forecasting model tailored to Malaysia requirements is crucially needed. Nowadays, neural network, SVM and decision tree have been used extensively as the data mining models. Support Vector Machine (SVM) is greatly popular, robust and efficient in flood modeling and prediction. SVM has been also extended as a regression tool, known as Support Vector Regression (SVR). However, the increasing volume and varying format of collecting data from remote sensing presents challenges on the efficiency of data classification for forecasting. Data that are obtained are high dimensional in nature and dimensionality reduction needs to be improved by reducing random variable in classification techniques. This research aims to propose flood disaster forecasting using data mining classification techniques by reducing random variable for efficient result in flood forecasting. This research will investigates/identify the data mining technique in disaster that being research by the researchers and proposed a conceptual model to analyze flood data. SVR will be employed to select nearby sensors and develops a linear model for a target sensor. Neural network will be used to extract patterns and detect trends that are too complex to be noticed by either humans or other computer techniques. The proposed model will be tested using data from Malaysian disaster management agencies. The result of this study shall create a new model that is expected to improve flood disaster forecasting and contribute to enhancement of early warning system and decision making during a disaster in Malaysia.
Hasmeda Erna Che Hamid, Nurjannatul Jannah Aqilah Md Saad, Noor Afiza Mat Razali, Muslihah Wook, Mohammad Adib Khairuddin and Mohd Nazri Ismail, 2020. Classification of Remote Sensor Data for Flood Disaster Forecasting using Data Mining Hybrid Techniques: A Proposed Model. Journal of Engineering and Applied Sciences, 15: 2542-2548.