This work focuses on a machine learning based detection of ionospheric scintillation events affecting Global Navigation Satellite System (GNSS) signals. We here extend the recent detection results based on Decision Trees, designing a semi-supervised detection system based on the DeepInfomax approach recently proposed. The paper shows that it is possible to achieve good classification accuracy while reducing the amount of time that human experts must spend manually labelling the datasets for the training of supervised algorithms. The proposed method is scalable and reduces the required percentage of annotated samples to achieve a given performance, making it a viable candidate for a realistic deployment of scintillation detection in software defined GNSS receivers

Semi-Supervised GNSS scintillations detection based on DeepInfomax / Franzese, Giulio; Linty, Nicola; Dovis, Fabio. - In: APPLIED SCIENCES. - ISSN 2076-3417. - ELETTRONICO. - 10:1(2020), p. 381. [10.3390/app10010381]

Semi-Supervised GNSS scintillations detection based on DeepInfomax

Franzese, Giulio;Linty, Nicola;Dovis, Fabio
2020

Abstract

This work focuses on a machine learning based detection of ionospheric scintillation events affecting Global Navigation Satellite System (GNSS) signals. We here extend the recent detection results based on Decision Trees, designing a semi-supervised detection system based on the DeepInfomax approach recently proposed. The paper shows that it is possible to achieve good classification accuracy while reducing the amount of time that human experts must spend manually labelling the datasets for the training of supervised algorithms. The proposed method is scalable and reduces the required percentage of annotated samples to achieve a given performance, making it a viable candidate for a realistic deployment of scintillation detection in software defined GNSS receivers
File in questo prodotto:
File Dimensione Formato  
applsci-10-00381 (2).pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 299.2 kB
Formato Adobe PDF
299.2 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

Caricamento pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2777700