Lightning severity classification technique using Very Low Frequency signal feature extraction

N. S. Arshad, M. Abdullah, S. A. Samad, N. M. Hatta

Research output: Contribution to journalArticle

Abstract

High intensity lightning strike can lead to Very Low Frequency (VLF) signal reception. The lack of VLF signal feature characterisation creates the need for commercial lightning dataset subscription, so as to determine the causative lightning strike. This paper presents a signal feature analysis of VLF signal for high intensity lightning severity classification purpose. As such, the analysis was comprised of dual stages, namely feature extraction and feature classification, for two-class recognition. In the feature extraction stage, Discrete Wavelet Transform was implemented to decompose the VLF signal into four frequency bands. In each frequency band, five-signal parameter analysis was executed to yield twenty signal features. Next, the classification stage was executed to determine the best signal feature combination and the most dominant signal feature that generated the highest classification accuracy within the five classifiers. The simulation revealed that the most optimum signal feature combination was achieved via Boosted Trees classifier with classification accuracies of 70% and 50% for training and test datasets, respectively. Class prediction in the skewed test dataset appeared consistent with the test data classification accuracy. The Zero Crossing Rate between 30 and 60 kHz emerged as the most dominant signal feature due to its impact on all classifiers' best signal feature arrangement. The proposed recognition model enables the detection of high intensity lightning classes through the use of VLF signal features.

Original languageEnglish
Article number105136
JournalJournal of Atmospheric and Solar-Terrestrial Physics
Volume195
DOIs
Publication statusPublished - 15 Nov 2019

Fingerprint

very low frequencies
lightning
pattern recognition
classifiers
signal reception
roots of equations
wavelet analysis
wavelet
education
transform

Keywords

  • Feature classification
  • Feature extraction
  • Lightning
  • VLF signal

ASJC Scopus subject areas

  • Geophysics
  • Atmospheric Science
  • Space and Planetary Science

Cite this

Lightning severity classification technique using Very Low Frequency signal feature extraction. / Arshad, N. S.; Abdullah, M.; Samad, S. A.; Hatta, N. M.

In: Journal of Atmospheric and Solar-Terrestrial Physics, Vol. 195, 105136, 15.11.2019.

Research output: Contribution to journalArticle

@article{bf837951b77b436c98b94e6e68b545bb,
title = "Lightning severity classification technique using Very Low Frequency signal feature extraction",
abstract = "High intensity lightning strike can lead to Very Low Frequency (VLF) signal reception. The lack of VLF signal feature characterisation creates the need for commercial lightning dataset subscription, so as to determine the causative lightning strike. This paper presents a signal feature analysis of VLF signal for high intensity lightning severity classification purpose. As such, the analysis was comprised of dual stages, namely feature extraction and feature classification, for two-class recognition. In the feature extraction stage, Discrete Wavelet Transform was implemented to decompose the VLF signal into four frequency bands. In each frequency band, five-signal parameter analysis was executed to yield twenty signal features. Next, the classification stage was executed to determine the best signal feature combination and the most dominant signal feature that generated the highest classification accuracy within the five classifiers. The simulation revealed that the most optimum signal feature combination was achieved via Boosted Trees classifier with classification accuracies of 70{\%} and 50{\%} for training and test datasets, respectively. Class prediction in the skewed test dataset appeared consistent with the test data classification accuracy. The Zero Crossing Rate between 30 and 60 kHz emerged as the most dominant signal feature due to its impact on all classifiers' best signal feature arrangement. The proposed recognition model enables the detection of high intensity lightning classes through the use of VLF signal features.",
keywords = "Feature classification, Feature extraction, Lightning, VLF signal",
author = "Arshad, {N. S.} and M. Abdullah and Samad, {S. A.} and Hatta, {N. M.}",
year = "2019",
month = "11",
day = "15",
doi = "10.1016/j.jastp.2019.105136",
language = "English",
volume = "195",
journal = "Journal of Atmospheric and Solar-Terrestrial Physics",
issn = "1364-6826",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Lightning severity classification technique using Very Low Frequency signal feature extraction

AU - Arshad, N. S.

AU - Abdullah, M.

AU - Samad, S. A.

AU - Hatta, N. M.

PY - 2019/11/15

Y1 - 2019/11/15

N2 - High intensity lightning strike can lead to Very Low Frequency (VLF) signal reception. The lack of VLF signal feature characterisation creates the need for commercial lightning dataset subscription, so as to determine the causative lightning strike. This paper presents a signal feature analysis of VLF signal for high intensity lightning severity classification purpose. As such, the analysis was comprised of dual stages, namely feature extraction and feature classification, for two-class recognition. In the feature extraction stage, Discrete Wavelet Transform was implemented to decompose the VLF signal into four frequency bands. In each frequency band, five-signal parameter analysis was executed to yield twenty signal features. Next, the classification stage was executed to determine the best signal feature combination and the most dominant signal feature that generated the highest classification accuracy within the five classifiers. The simulation revealed that the most optimum signal feature combination was achieved via Boosted Trees classifier with classification accuracies of 70% and 50% for training and test datasets, respectively. Class prediction in the skewed test dataset appeared consistent with the test data classification accuracy. The Zero Crossing Rate between 30 and 60 kHz emerged as the most dominant signal feature due to its impact on all classifiers' best signal feature arrangement. The proposed recognition model enables the detection of high intensity lightning classes through the use of VLF signal features.

AB - High intensity lightning strike can lead to Very Low Frequency (VLF) signal reception. The lack of VLF signal feature characterisation creates the need for commercial lightning dataset subscription, so as to determine the causative lightning strike. This paper presents a signal feature analysis of VLF signal for high intensity lightning severity classification purpose. As such, the analysis was comprised of dual stages, namely feature extraction and feature classification, for two-class recognition. In the feature extraction stage, Discrete Wavelet Transform was implemented to decompose the VLF signal into four frequency bands. In each frequency band, five-signal parameter analysis was executed to yield twenty signal features. Next, the classification stage was executed to determine the best signal feature combination and the most dominant signal feature that generated the highest classification accuracy within the five classifiers. The simulation revealed that the most optimum signal feature combination was achieved via Boosted Trees classifier with classification accuracies of 70% and 50% for training and test datasets, respectively. Class prediction in the skewed test dataset appeared consistent with the test data classification accuracy. The Zero Crossing Rate between 30 and 60 kHz emerged as the most dominant signal feature due to its impact on all classifiers' best signal feature arrangement. The proposed recognition model enables the detection of high intensity lightning classes through the use of VLF signal features.

KW - Feature classification

KW - Feature extraction

KW - Lightning

KW - VLF signal

UR - http://www.scopus.com/inward/record.url?scp=85072911657&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072911657&partnerID=8YFLogxK

U2 - 10.1016/j.jastp.2019.105136

DO - 10.1016/j.jastp.2019.105136

M3 - Article

AN - SCOPUS:85072911657

VL - 195

JO - Journal of Atmospheric and Solar-Terrestrial Physics

JF - Journal of Atmospheric and Solar-Terrestrial Physics

SN - 1364-6826

M1 - 105136

ER -