IDENTIFICATION OF EARTHQUAKES USING WAVELET TRANSFORM AND CLUSTERING METHODOLOGIES

An earthquake is the shaking and vibration at the surface of the Earth, caused by energy being released along a fault plane, at the edge of a tectonic plate or by volcanic activity in the earth crust. They are one of the most powerful natural forces on earth and regularly affect people, animals, aquatic life and so on around the world. The size of an earthquake is referred to as its magnitude on a scale ranges from 1 – 10. Magnitudes as low as 1 are measured in mines due to rock bursts and the maximum magnitude possible is less than 10. Determining earthquake magnitudes quickly is of great utility in disaster prevention. Many researchers have put forward their utmost effort for the prediction of earthquake. Detection of earthquake was done earlier based on W-MLP and MLP, Wavelet-Aggregated Signal and Synchronous Peaked Fluctuations model, detection using the P wave of the earthquake, prediction based on radon emissions, EEW algorithm, M8 algorithm, prediction using extraction of instantaneous frequency from underground water, but neither of them could provide an effective and efficient result prediction. In the present research work, Sym wavelet transform is used over the seismic signals (the seismic signals are obtained from USGS (United States Geological Survey), SSA (Seismological Society of America), SCEDC (Sothern California Earthquake Data Center), and JMA (Japan Metrological Agency)) of earthquake and are processed through MATLAB and WEKA tool in order to generate the magnitude and the prediction accuracy, recall and precision performance measures. The obtained results are taken up as datasets and are tested using classification algorithms such as J48, Random Forest, REP tree, LMT, Naïve Bayes and Back propagation model of neural networks to evaluate the accuracy, precision and recall performance measures