Preliminary vertical TEC prediction using neural network: Input data selection and preparation

Rohaida Mat Akir, Mardina Abdullah, Kalaivani Chell, Alina Marie Hasbi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Total electron content (TEC) is a fundamental and most prevailing ionospheric parameter that leads to Global Positioning System (GPS) error source such as delays, poor signal or lost data. Neural Network (NN) based approaches has proven track record in ionospheric process modeling. In this work, a data preparation method was developed to perform neural network based on VTEC forecast over two stations in Malaysia. GPS Ionospheric Scintillation & TEC Monitor (GISTM) at UKM and LGKW became a part of the feasibility study for the development of data sets as inputs to the NN based TEC prediction model. The study period was selected based on the availability of data, which is from January 2011 to December 2012. The factors that influence VTEC performance are identified and processed accordingly, to be used as input parameter for the VTEC prediction NN model development. The selected parameters are seasonal variation, diurnal variation, and sunspot number which have similar conduct with VTEC for the selected 24 months.

Original languageEnglish
Title of host publicationInternational Conference on Space Science and Communication, IconSpace
PublisherIEEE Computer Society
Pages283-287
Number of pages5
Volume2015-September
ISBN (Print)9781479919406
DOIs
Publication statusPublished - 29 Sep 2015
Event4th International Conference on Space Science and Communication, IconSpace 2015 - Langkawi, Malaysia
Duration: 10 Aug 201512 Aug 2015

Other

Other4th International Conference on Space Science and Communication, IconSpace 2015
CountryMalaysia
CityLangkawi
Period10/8/1512/8/15

Fingerprint

neural network
Neural networks
Electrons
Global positioning system
data preparation
seasonal variation
Scintillation
development model
Malaysia
Availability
performance

Keywords

  • GPS
  • ionosphere
  • neural network
  • sunspot number
  • total electron content

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Aerospace Engineering
  • Electrical and Electronic Engineering
  • Communication

Cite this

Akir, R. M., Abdullah, M., Chell, K., & Hasbi, A. M. (2015). Preliminary vertical TEC prediction using neural network: Input data selection and preparation. In International Conference on Space Science and Communication, IconSpace (Vol. 2015-September, pp. 283-287). [7283767] IEEE Computer Society. https://doi.org/10.1109/IconSpace.2015.7283767

Preliminary vertical TEC prediction using neural network : Input data selection and preparation. / Akir, Rohaida Mat; Abdullah, Mardina; Chell, Kalaivani; Hasbi, Alina Marie.

International Conference on Space Science and Communication, IconSpace. Vol. 2015-September IEEE Computer Society, 2015. p. 283-287 7283767.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Akir, RM, Abdullah, M, Chell, K & Hasbi, AM 2015, Preliminary vertical TEC prediction using neural network: Input data selection and preparation. in International Conference on Space Science and Communication, IconSpace. vol. 2015-September, 7283767, IEEE Computer Society, pp. 283-287, 4th International Conference on Space Science and Communication, IconSpace 2015, Langkawi, Malaysia, 10/8/15. https://doi.org/10.1109/IconSpace.2015.7283767
Akir RM, Abdullah M, Chell K, Hasbi AM. Preliminary vertical TEC prediction using neural network: Input data selection and preparation. In International Conference on Space Science and Communication, IconSpace. Vol. 2015-September. IEEE Computer Society. 2015. p. 283-287. 7283767 https://doi.org/10.1109/IconSpace.2015.7283767
Akir, Rohaida Mat ; Abdullah, Mardina ; Chell, Kalaivani ; Hasbi, Alina Marie. / Preliminary vertical TEC prediction using neural network : Input data selection and preparation. International Conference on Space Science and Communication, IconSpace. Vol. 2015-September IEEE Computer Society, 2015. pp. 283-287
@inproceedings{3c1be07dc10a424db9a61b039d833a2e,
title = "Preliminary vertical TEC prediction using neural network: Input data selection and preparation",
abstract = "Total electron content (TEC) is a fundamental and most prevailing ionospheric parameter that leads to Global Positioning System (GPS) error source such as delays, poor signal or lost data. Neural Network (NN) based approaches has proven track record in ionospheric process modeling. In this work, a data preparation method was developed to perform neural network based on VTEC forecast over two stations in Malaysia. GPS Ionospheric Scintillation & TEC Monitor (GISTM) at UKM and LGKW became a part of the feasibility study for the development of data sets as inputs to the NN based TEC prediction model. The study period was selected based on the availability of data, which is from January 2011 to December 2012. The factors that influence VTEC performance are identified and processed accordingly, to be used as input parameter for the VTEC prediction NN model development. The selected parameters are seasonal variation, diurnal variation, and sunspot number which have similar conduct with VTEC for the selected 24 months.",
keywords = "GPS, ionosphere, neural network, sunspot number, total electron content",
author = "Akir, {Rohaida Mat} and Mardina Abdullah and Kalaivani Chell and Hasbi, {Alina Marie}",
year = "2015",
month = "9",
day = "29",
doi = "10.1109/IconSpace.2015.7283767",
language = "English",
isbn = "9781479919406",
volume = "2015-September",
pages = "283--287",
booktitle = "International Conference on Space Science and Communication, IconSpace",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Preliminary vertical TEC prediction using neural network

T2 - Input data selection and preparation

AU - Akir, Rohaida Mat

AU - Abdullah, Mardina

AU - Chell, Kalaivani

AU - Hasbi, Alina Marie

PY - 2015/9/29

Y1 - 2015/9/29

N2 - Total electron content (TEC) is a fundamental and most prevailing ionospheric parameter that leads to Global Positioning System (GPS) error source such as delays, poor signal or lost data. Neural Network (NN) based approaches has proven track record in ionospheric process modeling. In this work, a data preparation method was developed to perform neural network based on VTEC forecast over two stations in Malaysia. GPS Ionospheric Scintillation & TEC Monitor (GISTM) at UKM and LGKW became a part of the feasibility study for the development of data sets as inputs to the NN based TEC prediction model. The study period was selected based on the availability of data, which is from January 2011 to December 2012. The factors that influence VTEC performance are identified and processed accordingly, to be used as input parameter for the VTEC prediction NN model development. The selected parameters are seasonal variation, diurnal variation, and sunspot number which have similar conduct with VTEC for the selected 24 months.

AB - Total electron content (TEC) is a fundamental and most prevailing ionospheric parameter that leads to Global Positioning System (GPS) error source such as delays, poor signal or lost data. Neural Network (NN) based approaches has proven track record in ionospheric process modeling. In this work, a data preparation method was developed to perform neural network based on VTEC forecast over two stations in Malaysia. GPS Ionospheric Scintillation & TEC Monitor (GISTM) at UKM and LGKW became a part of the feasibility study for the development of data sets as inputs to the NN based TEC prediction model. The study period was selected based on the availability of data, which is from January 2011 to December 2012. The factors that influence VTEC performance are identified and processed accordingly, to be used as input parameter for the VTEC prediction NN model development. The selected parameters are seasonal variation, diurnal variation, and sunspot number which have similar conduct with VTEC for the selected 24 months.

KW - GPS

KW - ionosphere

KW - neural network

KW - sunspot number

KW - total electron content

UR - http://www.scopus.com/inward/record.url?scp=84962514774&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962514774&partnerID=8YFLogxK

U2 - 10.1109/IconSpace.2015.7283767

DO - 10.1109/IconSpace.2015.7283767

M3 - Conference contribution

AN - SCOPUS:84962514774

SN - 9781479919406

VL - 2015-September

SP - 283

EP - 287

BT - International Conference on Space Science and Communication, IconSpace

PB - IEEE Computer Society

ER -