Seismic Signal Classification using Multi-Layer Perceptron Neural Network

Abstract

The aim of the present study is to investigate and explore the capability of the multilayer perceptron neural network to classify seismic signals recorded by the local seismic network of Agadir (M orocco). The problem is divided into two main steps, the feature extraction step and classification step. In the former, relevant discriminant features are extracted from the seismic signal based on the time and frequency domains. These are selected based on the analysts' experience. In the latter step, a process of trial an error was carried out to find the best neural network architecture. Classification results on a data set of 343 seis mic signals have demonstrated that the accuracy of the proposed classier can achieve more than 94%.

Effective and extensible feature extraction method using genetic algorithm-based frequency-domain feature search for epileptic EEG multiclassification

“…MLP [ 37 ] is a feed-forward ANN consisting of multiple layers of nodes in a directed graph, with each layer fully connected to the next. Each node is a processing element with an activation function.…”

Proposal for a System Model for Offline Seismic Event Detection in Colombia

“…The input dataset for a feature-based technique is a set of single values that describes the original P-waves and non-P-waves in the seismic signals. Among the most commonly used machine learning feature-based algorithms applied to P-wave detection are Hidden Markov Models [56], Bayesian Networks [57], Support Vector Machines [58][59][60], Logistic Regression [53,61,62] and Artificial Neural Networks (ANN) [41,53,[63][64][65][66][67]. Conversely, the input dataset for a time-series technique is a set of signals split into P-wave signals and non-P-wave signals.…”