Techniques Based on Metaheuristics Combined with an Adaptive Neurofuzzy System and Seismic Sensors for the Prediction of Earthquakes

This research looked into the viability of using metaheuristic algorithms in conjunction with an adaptive neurofuzzy system to predict seismicity and earthquakes. Different have been combined artificial intelligence (AI) algorithm. Subjected is a promising factor. The new sensors many advantages over older, more impressive-looking ones, including (a) generally linear relationship between measured values real ground motion (described above), (b) ability measure three orthogonal components movement single unit, (c) sensitivity very broad range frequencies, (d) high dynamic range, which allows for detection both small fairly large tremors. To accept acquired results as hybrid model inference particle swarm optimization (PSO), genetic algorithm (GA), extreme machine learning (ELM) (ANFIS-PSO-GA-ELM) implemented. According dataset, all approaches produce excellent realistic predictions seismic loads; however, method ANFIS-PSO produces better results. All strategies demonstrated level predictability. Finally, this urges researchers investigate performance triple MT variety methodologies, rather than existing double algorithms.