{"id":{"repo_id":"uthm","oai_identifier":"oai:eprints.uthm.edu.my:708"},"canonical_url":"https://search.dev.ndltd.org/etd/uthm/oai:eprints.uthm.edu.my:708","repository":{"repo_id":"uthm","name":"Universiti Tun Hussein Onn Malaysia","base_url":"http://eprints.uthm.edu.my/cgi/oai2"},"display":{"title":"Peramalan jumlah kandungan elektron menggunakan kaedah suapan ke hadapan rangkaian neural di Semenanjung Malaysia","abstract":"Total Electron Content (TEC) is one of the physical quantities that can be derived from global positioning system (GPS) data and provides an indication of ionospheric variability. TEC variations have significant effects on radio communications, applications involving navigational systems, GPS surveying and space weather. In order to understand these effects, there is a need to develop forecasting techniques. Several ionospheric models have been developed to predict the ionospheric variability at different locations of the world. However, due to the scarcity of data in the equatorial region, the models do not give accurate forecasting of the ionospheric variability over Malaysia region. Therefore, this study aims to investigate the possibilities for the modeling of TEC values derived from the GPS Ionospheric Scintillation and TEC Monitor (GISTM) receiver using feed forward neural network (NN). It also aims to investigate the TEC forecasting method for radio wave propagation value during both equinox and solstices periods. Two GISTM locations at Universiti Kebangsaan Malaysia, 2�550 N, 101�460 E and National Observatory Langkawi, Kedah 6�190 N, 99�50 E are identified and used in the development of an input space and NN design for the model. GPS TEC data measurement from 2011 to 2015 was selected to perform regional TEC modelling over Peninsular Malaysia, which is ascending solar cycle on solar cycle 24. TEC values and the factors that influence its variability as dependent and independent variable respectively, the capabilities of NN for TEC modelling were investigated. For this purpose, TEC was modelled as a function of seasonal variation (day number), diurnal variation (hour) and solar activity (sunspot number). The TEC data was forecasted in the seasonal, diurnal and hourly variations. An analysis was made by comparing the TEC value from the neural network prediction with real TEC and the TEC from the recent version of the International Reference Ionosphere model (IRI-2012). The maximum value in the seasonal variation was observed in June solstices with 88% and the minimum in the September equinox, 83%. Results showed that the NN model can predict the TEC with a maximum accuracy of 86% compared with the IRI-2012 model by 58% during equinoxes and solstices periods. In conclusion, NN model has a potentially effective method with a higher performance of TEC prediction in the Malaysian region compared to the IRI-2012 model. The forecasted value is useful to radio operators in order to know the condition of the ionosphere in advance, especially during disturbed ionospheric condition. The outcome of this research offer a new model as a Peninsular Malaysia TEC forecasting.","abstract_html":"Total Electron Content (TEC) is one of the physical quantities that can be derived from global positioning system (GPS) data and provides an indication of ionospheric variability. TEC variations have significant effects on radio communications, applications involving navigational systems, GPS surveying and space weather. In order to understand these effects, there is a need to develop forecasting techniques. Several ionospheric models have been developed to predict the ionospheric variability at different locations of the world. However, due to the scarcity of data in the equatorial region, the models do not give accurate forecasting of the ionospheric variability over Malaysia region. Therefore, this study aims to investigate the possibilities for the modeling of TEC values derived from the GPS Ionospheric Scintillation and TEC Monitor (GISTM) receiver using feed forward neural network (NN). It also aims to investigate the TEC forecasting method for radio wave propagation value during both equinox and solstices periods. Two GISTM locations at Universiti Kebangsaan Malaysia, 2�550 N, 101�460 E and National Observatory Langkawi, Kedah 6�190 N, 99�50 E are identified and used in the development of an input space and NN design for the model. GPS TEC data measurement from 2011 to 2015 was selected to perform regional TEC modelling over Peninsular Malaysia, which is ascending solar cycle on solar cycle 24. TEC values and the factors that influence its variability as dependent and independent variable respectively, the capabilities of NN for TEC modelling were investigated. For this purpose, TEC was modelled as a function of seasonal variation (day number), diurnal variation (hour) and solar activity (sunspot number). The TEC data was forecasted in the seasonal, diurnal and hourly variations. An analysis was made by comparing the TEC value from the neural network prediction with real TEC and the TEC from the recent version of the International Reference Ionosphere model (IRI-2012). The maximum value in the seasonal variation was observed in June solstices with 88% and the minimum in the September equinox, 83%. Results showed that the NN model can predict the TEC with a maximum accuracy of 86% compared with the IRI-2012 model by 58% during equinoxes and solstices periods. In conclusion, NN model has a potentially effective method with a higher performance of TEC prediction in the Malaysian region compared to the IRI-2012 model. The forecasted value is useful to radio operators in order to know the condition of the ionosphere in advance, especially during disturbed ionospheric condition. The outcome of this research offer a new model as a Peninsular Malaysia TEC forecasting.","abstract_has_math":false,"creators":["Mat Akir, Rohaida"],"institution":"Universiti Kebangsaan Malaysia","degree_name":"phd","degree_level":"doctoral","degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2018,"date_issued":"2018-05","date_published":"2018-05","updated_at":"2026-07-24T05:48:03Z","subjects":["QC801-809 Geophysics. Cosmic physics"],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Mat Akir, Rohaida"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2018-05"]},{"key":"dc:date.issued","label":"Date","values":["2018-05"]},{"key":"dc:publisher.department","label":"Dc Publisher Department","values":["Fakulti Kejuruteraan dan Alam Bina"]},{"key":"dc:publisher.institution","label":"Dc Publisher Institution","values":["Universiti Kebangsaan Malaysia"]},{"key":"dc:relation.isreferencedby","label":"Dc Relation Isreferencedby","values":["http://eprints.uthm.edu.my/708/"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"dc:type.qualificationlevel","label":"Dc Type Qualificationlevel","values":["doctoral"]},{"key":"dc:type.qualificationname","label":"Dc Type Qualificationname","values":["phd"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["QC801-809 Geophysics. Cosmic physics"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://eprints.uthm.edu.my/708/1/24p%20ROHAIDA%20MAT%20AKIR.pdf"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Total Electron Content (TEC) is one of the physical quantities that can be derived from global positioning system (GPS) data and provides an indication of ionospheric variability. TEC variations have significant effects on radio communications, applications involving navigational systems, GPS surveying and space weather. In order to understand these effects, there is a need to develop forecasting techniques. Several ionospheric models have been developed to predict the ionospheric variability at different locations of the world. However, due to the scarcity of data in the equatorial region, the models do not give accurate forecasting of the ionospheric variability over Malaysia region. Therefore, this study aims to investigate the possibilities for the modeling of TEC values derived from the GPS Ionospheric Scintillation and TEC Monitor (GISTM) receiver using feed forward neural network (NN). It also aims to investigate the TEC forecasting method for radio wave propagation value during both equinox and solstices periods. Two GISTM locations at Universiti Kebangsaan Malaysia, 2�550 N, 101�460 E and National Observatory Langkawi, Kedah 6�190 N, 99�50 E are identified and used in the development of an input space and NN design for the model. GPS TEC data measurement from 2011 to 2015 was selected to perform regional TEC modelling over Peninsular Malaysia, which is ascending solar cycle on solar cycle 24. TEC values and the factors that influence its variability as dependent and independent variable respectively, the capabilities of NN for TEC modelling were investigated. For this purpose, TEC was modelled as a function of seasonal variation (day number), diurnal variation (hour) and solar activity (sunspot number). The TEC data was forecasted in the seasonal, diurnal and hourly variations. An analysis was made by comparing the TEC value from the neural network prediction with real TEC and the TEC from the recent version of the International Reference Ionosphere model (IRI-2012). The maximum value in the seasonal variation was observed in June solstices with 88% and the minimum in the September equinox, 83%. Results showed that the NN model can predict the TEC with a maximum accuracy of 86% compared with the IRI-2012 model by 58% during equinoxes and solstices periods. In conclusion, NN model has a potentially effective method with a higher performance of TEC prediction in the Malaysian region compared to the IRI-2012 model. The forecasted value is useful to radio operators in order to know the condition of the ionosphere in advance, especially during disturbed ionospheric condition. The outcome of this research offer a new model as a Peninsular Malaysia TEC forecasting."]},{"key":"dc:format","label":"Dc Format","values":["text"]},{"key":"dc:title","label":"Title","values":["Peramalan jumlah kandungan elektron menggunakan kaedah suapan ke hadapan rangkaian neural di Semenanjung Malaysia"]}]}],"canonical_facts":{"dc:creator":["Mat Akir, Rohaida"],"dc:date":["2018-05"],"dc:date.issued":["2018-05"],"dc:description.abstract":["Total Electron Content (TEC) is one of the physical quantities that can be derived from global positioning system (GPS) data and provides an indication of ionospheric variability. TEC variations have significant effects on radio communications, applications involving navigational systems, GPS surveying and space weather. In order to understand these effects, there is a need to develop forecasting techniques. Several ionospheric models have been developed to predict the ionospheric variability at different locations of the world. However, due to the scarcity of data in the equatorial region, the models do not give accurate forecasting of the ionospheric variability over Malaysia region. Therefore, this study aims to investigate the possibilities for the modeling of TEC values derived from the GPS Ionospheric Scintillation and TEC Monitor (GISTM) receiver using feed forward neural network (NN). It also aims to investigate the TEC forecasting method for radio wave propagation value during both equinox and solstices periods. Two GISTM locations at Universiti Kebangsaan Malaysia, 2�550 N, 101�460 E and National Observatory Langkawi, Kedah 6�190 N, 99�50 E are identified and used in the development of an input space and NN design for the model. GPS TEC data measurement from 2011 to 2015 was selected to perform regional TEC modelling over Peninsular Malaysia, which is ascending solar cycle on solar cycle 24. TEC values and the factors that influence its variability as dependent and independent variable respectively, the capabilities of NN for TEC modelling were investigated. For this purpose, TEC was modelled as a function of seasonal variation (day number), diurnal variation (hour) and solar activity (sunspot number). The TEC data was forecasted in the seasonal, diurnal and hourly variations. An analysis was made by comparing the TEC value from the neural network prediction with real TEC and the TEC from the recent version of the International Reference Ionosphere model (IRI-2012). The maximum value in the seasonal variation was observed in June solstices with 88% and the minimum in the September equinox, 83%. Results showed that the NN model can predict the TEC with a maximum accuracy of 86% compared with the IRI-2012 model by 58% during equinoxes and solstices periods. In conclusion, NN model has a potentially effective method with a higher performance of TEC prediction in the Malaysian region compared to the IRI-2012 model. The forecasted value is useful to radio operators in order to know the condition of the ionosphere in advance, especially during disturbed ionospheric condition. The outcome of this research offer a new model as a Peninsular Malaysia TEC forecasting."],"dc:format":["text"],"dc:identifier.uri":["http://eprints.uthm.edu.my/708/1/24p%20ROHAIDA%20MAT%20AKIR.pdf"],"dc:language":["en"],"dc:publisher.department":["Fakulti Kejuruteraan dan Alam Bina"],"dc:publisher.institution":["Universiti Kebangsaan Malaysia"],"dc:relation.isreferencedby":["http://eprints.uthm.edu.my/708/"],"dc:subject":["QC801-809 Geophysics. Cosmic physics"],"dc:title":["Peramalan jumlah kandungan elektron menggunakan kaedah suapan ke hadapan rangkaian neural di Semenanjung Malaysia"],"dc:type":["Thesis"],"dc:type.qualificationlevel":["doctoral"],"dc:type.qualificationname":["phd"]},"updated_at":"2026-07-24T05:48:03Z"}