Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event

Author

Aji, Alham F. ; Putra, I. Putu Edy Suardiyana ; Mursanto, Petrus ; Yazid, Setiadi

Author_Institution

Fac. of Comput. Sci., Univ. Indonesia, Depok, Indonesia

fYear

2014

fDate

March 31 2014-April 3 2014

Firstpage

72

Lastpage

77

Abstract

The possibility of using smart phone accelerometer to detect earthquake is investigated in this research. Experiments are designed to learn the pattern of an earthquake signal recorded from smart phone´s accelerometer. The signal is processed using N-gram modeling as feature extractor for machine learning. For the classifier, this study use Naïve Bayes, Multi-Layer Perceptron (MLP), and Random Forest. Our result shows that the best classification accuracy is achieved by Random Forest method. Its accuracy reached 93.15%. It can be concluded that smart phones can be used as an earthquake detector.

Keywords

earthquakes; feature extraction; geophysical signal processing; learning (artificial intelligence); multilayer perceptrons; signal classification; smart phones; MLP; N-gram modeling; classification accuracy; earthquake detection; earthquake event identification; earthquake signal pattern; feature extractor; machine learning; machine learning approach; multilayer perceptron; naive Bayes; random forest; signal processing; smart phone accelerometer; Accelerometers; Accuracy; Data models; Earthquakes; Feature extraction; Fractals; Smart phones; earthquake; machine learning; n-gram; signal processing;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems Conference (SysCon), 2014 8th Annual IEEE

Conference_Location

Ottawa, ON

Print_ISBN

978-1-4799-2087-7

Type

conf

DOI

10.1109/SysCon.2014.6819238

Filename

6819238