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

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

doi:10.1109/SysCon.2014.6819238

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

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

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

8 Citations (Scopus)

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.

Original language	English
Title of host publication	8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings
Publisher	IEEE Computer Society
Pages	72-77
Number of pages	6
ISBN (Print)	9781479920877
DOIs	https://doi.org/10.1109/SysCon.2014.6819238
Publication status	Published - 2014
Event	8th Annual IEEE International Systems Conference, SysCon 2014 - Ottawa, ON, Canada Duration: 31 Mar 2014 → 3 Apr 2014

Publication series

Name	8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings

Conference

Conference	8th Annual IEEE International Systems Conference, SysCon 2014
Country/Territory	Canada
City	Ottawa, ON
Period	31/03/14 → 3/04/14

Keywords

earthquake
machine learning
n-gram
signal processing

Access to Document

10.1109/SysCon.2014.6819238

Cite this

Fikri Aji, A., Putra, I. P. E. S., Mursanto, P., & Yazid, S. (2014). Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event. In 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings (pp. 72-77). Article 6819238 (8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings). IEEE Computer Society. https://doi.org/10.1109/SysCon.2014.6819238

Fikri Aji, Alham ; Putra, I. Putu Edy Suardiyana ; Mursanto, Petrus et al. / Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event. 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings. IEEE Computer Society, 2014. pp. 72-77 (8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings).

@inproceedings{ca8a43233be1427ea8705b46dea7d37a,

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

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 Na{\"i}ve 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 = "earthquake, machine learning, n-gram, signal processing",

author = "{Fikri Aji}, Alham and Putra, {I. Putu Edy Suardiyana} and Petrus Mursanto and Setiadi Yazid",

year = "2014",

doi = "10.1109/SysCon.2014.6819238",

language = "English",

isbn = "9781479920877",

series = "8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings",

publisher = "IEEE Computer Society",

pages = "72--77",

booktitle = "8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings",

address = "United States",

note = "8th Annual IEEE International Systems Conference, SysCon 2014 ; Conference date: 31-03-2014 Through 03-04-2014",

}

Fikri Aji, A, Putra, IPES, Mursanto, P & Yazid, S 2014, Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event. in 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings., 6819238, 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings, IEEE Computer Society, pp. 72-77, 8th Annual IEEE International Systems Conference, SysCon 2014, Ottawa, ON, Canada, 31/03/14. https://doi.org/10.1109/SysCon.2014.6819238

Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event. / Fikri Aji, Alham; Putra, I. Putu Edy Suardiyana; Mursanto, Petrus et al.
8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings. IEEE Computer Society, 2014. p. 72-77 6819238 (8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event

AU - Fikri Aji, Alham

AU - Putra, I. Putu Edy Suardiyana

AU - Mursanto, Petrus

AU - Yazid, Setiadi

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

KW - earthquake

KW - machine learning

KW - n-gram

KW - signal processing

UR - http://www.scopus.com/inward/record.url?scp=84902491314&partnerID=8YFLogxK

U2 - 10.1109/SysCon.2014.6819238

DO - 10.1109/SysCon.2014.6819238

M3 - Conference contribution

AN - SCOPUS:84902491314

SN - 9781479920877

T3 - 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings

SP - 72

EP - 77

BT - 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings

PB - IEEE Computer Society

T2 - 8th Annual IEEE International Systems Conference, SysCon 2014

Y2 - 31 March 2014 through 3 April 2014

ER -

Fikri Aji A, Putra IPES, Mursanto P , Yazid S. Can smartphones be used to detect an earthquake? Using a machine learning approach to identify an earthquake event. In 8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings. IEEE Computer Society. 2014. p. 72-77. 6819238. (8th Annual IEEE International Systems Conference, SysCon 2014 - Proceedings). doi: 10.1109/SysCon.2014.6819238

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

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this