TY - JOUR
ID - 72081
TI - Seismic Data Forecasting: A Sequence Prediction or a Sequence Recognition Task
JO - International Journal of Engineering
JA - IJE
LA - en
SN - 1025-2495
AU - mahdinejad noori, mohammad mahdi
AU - bali, aref
AD - Civil & Environmental Engineering, International Institute of Earthquake Engineering
AD - Civil & Environmental Engineering, International
Y1 - 2013
PY - 2013
VL - 26
IS - 2
SP - 137
EP - 142
KW - KEY WORDS Earthquake prediction
KW - multivariate adaptive regression splines (MARS model)
KW - sequence learning
KW - sequence recognition
KW - time series analysis.
DO -
N2 - In this paper, we have tried to predict earthquake events in a cluster of seismic data on pacific ring of fire, using multivariate adaptive regression splines (MARS). The model is employed as either a predictor for a sequence prediction task, or a binary classifier for a sequence recognition problem, which could alternatively help to predict an event. Here, we explain that sequence prediction/recognition, as two aspects of sequence learning, are not the same in general. We show that while both these approaches are plausible for earthquake prediction, the forecasting results indicate that MARS as a binary classifier outperforms the predictor MARS. The results clearly show how it is important to challenge a single earthquake forecasting problem from an appropriate point of view.
UR - http://www.ije.ir/article_72081.html
L1 - http://www.ije.ir/article_72081_29049229a43d5b9a208610ce1e9f5bd5.pdf
ER -