A Novel Approach for Seismic Signal Magnitude Detection Using Haar Wavelet

Earth quakes are among the most damaging event caused by the earth itself. As urbanization progresses universally, earthquakes pose severe risk to lives and properties for urban areas and all the subduction zones. Short term earthquake prediction, months in advance, is an elusive goal of earth sciences, and is of great importance for fundamental science and for disaster preparedness. Till date, many of the researchers applied different techniques like prediction based on radon emissions, EEW algorithm, M8 algorithm, prediction using extraction of instantaneous frequency from underground water and so on, but neither of them could provide an effective and efficient result. In the present research seismic signals are analyzed by using Haar wavelet transform in order to evaluate the parameters such as energy, frequency, magnitude of the signal. Among all the parameters the magnitude which forms the base of analysis is used for the detection of earthquake. The minor quakes are neglected and the surface wave magnitude of the quakes that show impact on earth´s surface is calculated and found as 3.0. 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.