Abstract Natural disaster is a foremost undesirable event resultant from natural processes of the Earth and causes loss of life or property damage. 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... Natural disaster is a foremost undesirable event resultant from natural processes of the Earth and causes loss of life or property damage. 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, of great importance for fundamental science and for disaster preparedness. Detection of earthquake was done earlier based on W-MLP and MLP, Wavelet-Aggregated Signal and Synchronous Peaked Fluctuations model, detection using the P waves 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. In the present research, seismic signals are analyzed by using Haar wavelet transform and SYM wavelet transform in order to evaluate the energy, frequency, magnitude of the signal. 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 from Haar and SYM wavelet transforms 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. Read More Read Less

Abstract For robustly handling the appearance change of target object and heavy occlusion, a novel super- pixels clique based tracking algorithm is proposed. By two stage adaptive appearance modelling method, we propose the method of learning the target-background appearance framework, which is based on super pixels principle histogram bins cluster method. The process of computing superpixels cliques confidence not only store the location information... For robustly handling the appearance change of target object and heavy occlusion, a novel super- pixels clique based tracking algorithm is proposed. By two stage adaptive appearance modelling method, we propose the method of learning the target-background appearance framework, which is based on super pixels principle histogram bins cluster method. The process of computing superpixels cliques confidence not only store the location information of the superpixels, the super- pixels cliques recent history and last history also are equally weighted. The first phase of twostage adaptive cliques construct and update algorithm is target template superpixels cliques construct stage. By calculating feature distance between superpixels and cliques center, it is to determine whether a superpixel belongs to the cliques. The second phase for detection and updating stage, through compare superpixels features surrounding region of target in training frame, with cliques, the confidence of cliques can be updated. For the target appearance model adaptive learning, a principle histogram bins clustering method be proposed to adaptive update appearance model, and the computational overhead is small. The object can be tracked under appearance changing and occlusion, by bayesian filtering method with using MAP and the adaptive appearance model. Theoretical analysis and experiments results demonstrate that our method outperforms the sate-of-the-art methods when the target under occlusion and illumination changes dramatically. Read More Read Less