Solar flare M-class prediction using artificial intelligence techniques

Azam Zavvari, Mohammad Tariqul Islam, Radial Anwar, Zamri Zainal Abidin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Currently, astronomical data have increased in terms of volume and complexity. To bring out the information in order to analyze and predict, the artificial intelligence techniques are required. This paper aims to apply artificial intelligence techniques to predict M-class solar flare. Artificial neural network, support vector machine and naïve bayes techniques are compared to define the best prediction performance accuracy technique. The dataset have been collected from daily data for 16 years, from 1998 to 2013. The attributes consist of solar flares data and sunspot number. The sunspots are a cooler spot on the surface of the sun, which have relation with solar flares. The Java-based machine learning WEKA is used for analysis and predicts solar flares. The best forecasted performance accuracy is achieved based on the artificial neural network method.

Original languageEnglish
Pages (from-to)63-67
Number of pages5
JournalJournal of Theoretical and Applied Information Technology
Volume74
Issue number1
Publication statusPublished - 2015

Fingerprint

Solar Flares
Artificial intelligence
Artificial Intelligence
Neural networks
Sunspots
Prediction
Predict
Sun
Support vector machines
Artificial Neural Network
Learning systems
Performance Prediction
Bayes
Java
Support Vector Machine
Machine Learning
Attribute
Class

Keywords

  • Artificial intelligence techniques
  • Naïve bayes
  • Neural network
  • Solar flare
  • Support vector machine

ASJC Scopus subject areas

  • Computer Science(all)
  • Theoretical Computer Science

Cite this

Solar flare M-class prediction using artificial intelligence techniques. / Zavvari, Azam; Islam, Mohammad Tariqul; Anwar, Radial; Abidin, Zamri Zainal.

In: Journal of Theoretical and Applied Information Technology, Vol. 74, No. 1, 2015, p. 63-67.

Research output: Contribution to journalArticle

@article{e6bf9fa8f8194d598d5c346926ca3c01,
title = "Solar flare M-class prediction using artificial intelligence techniques",
abstract = "Currently, astronomical data have increased in terms of volume and complexity. To bring out the information in order to analyze and predict, the artificial intelligence techniques are required. This paper aims to apply artificial intelligence techniques to predict M-class solar flare. Artificial neural network, support vector machine and na{\"i}ve bayes techniques are compared to define the best prediction performance accuracy technique. The dataset have been collected from daily data for 16 years, from 1998 to 2013. The attributes consist of solar flares data and sunspot number. The sunspots are a cooler spot on the surface of the sun, which have relation with solar flares. The Java-based machine learning WEKA is used for analysis and predicts solar flares. The best forecasted performance accuracy is achieved based on the artificial neural network method.",
keywords = "Artificial intelligence techniques, Na{\"i}ve bayes, Neural network, Solar flare, Support vector machine",
author = "Azam Zavvari and Islam, {Mohammad Tariqul} and Radial Anwar and Abidin, {Zamri Zainal}",
year = "2015",
language = "English",
volume = "74",
pages = "63--67",
journal = "Journal of Theoretical and Applied Information Technology",
issn = "1992-8645",
publisher = "Asian Research Publishing Network (ARPN)",
number = "1",

}

TY - JOUR

T1 - Solar flare M-class prediction using artificial intelligence techniques

AU - Zavvari, Azam

AU - Islam, Mohammad Tariqul

AU - Anwar, Radial

AU - Abidin, Zamri Zainal

PY - 2015

Y1 - 2015

N2 - Currently, astronomical data have increased in terms of volume and complexity. To bring out the information in order to analyze and predict, the artificial intelligence techniques are required. This paper aims to apply artificial intelligence techniques to predict M-class solar flare. Artificial neural network, support vector machine and naïve bayes techniques are compared to define the best prediction performance accuracy technique. The dataset have been collected from daily data for 16 years, from 1998 to 2013. The attributes consist of solar flares data and sunspot number. The sunspots are a cooler spot on the surface of the sun, which have relation with solar flares. The Java-based machine learning WEKA is used for analysis and predicts solar flares. The best forecasted performance accuracy is achieved based on the artificial neural network method.

AB - Currently, astronomical data have increased in terms of volume and complexity. To bring out the information in order to analyze and predict, the artificial intelligence techniques are required. This paper aims to apply artificial intelligence techniques to predict M-class solar flare. Artificial neural network, support vector machine and naïve bayes techniques are compared to define the best prediction performance accuracy technique. The dataset have been collected from daily data for 16 years, from 1998 to 2013. The attributes consist of solar flares data and sunspot number. The sunspots are a cooler spot on the surface of the sun, which have relation with solar flares. The Java-based machine learning WEKA is used for analysis and predicts solar flares. The best forecasted performance accuracy is achieved based on the artificial neural network method.

KW - Artificial intelligence techniques

KW - Naïve bayes

KW - Neural network

KW - Solar flare

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=84926642061&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926642061&partnerID=8YFLogxK

M3 - Article

VL - 74

SP - 63

EP - 67

JO - Journal of Theoretical and Applied Information Technology

JF - Journal of Theoretical and Applied Information Technology

SN - 1992-8645

IS - 1

ER -