Data-driven models trained in an end-to-end manner can reliably detect events within optical signals. Unfortunately, event detection models poorly generalize when monitoring signals collected from devices with different acquisition procedures. We overcome this limitation by presenting a novel domain adaptation solution for event detection networks that enables inference across multiple types of devices. Rather than training a black-box detection network, we decouple event localization and classification tasks. Localization is performed by the Interval Proposal Algorithm (IPA), which leverages signal processing techniques to localize candidate events and derive context features. These events are then standardized and fed to a feature extractor to obtain morphological features. By combining domain-specific context features with domain-invariant morphological features, the classifier achieves good generalization capabilities through different domains. Our method can successfully detect events in OTDR traces achieving a mAP@0.5 of 75.33% on traces from the source domain and generalizing well (mAP@0.5 of 69.27%) on traces from the target domain, despite being trained solely from the source domain.

Event Detection in Optical Signals via Domain Adaptation / Rizzo, ANTONINO MARIA; Magri, Luca; Invernizzi, Pietro; Sozio, Enrico; Aquaro, Gabriele; Binetti, Stefano; Alippi, Cesare; Boracchi, Giacomo. - ELETTRONICO. - (2023), pp. 1435-1439. (Intervento presentato al convegno EUropean SIgnal Processing COnference (EUSIPCO) tenutosi a Helsinki (Finland) nel September 4-8, 2023) [10.23919/EUSIPCO58844.2023.10289940].

Event Detection in Optical Signals via Domain Adaptation

Antonino Maria Rizzo;Luca Magri;
2023

Abstract

Data-driven models trained in an end-to-end manner can reliably detect events within optical signals. Unfortunately, event detection models poorly generalize when monitoring signals collected from devices with different acquisition procedures. We overcome this limitation by presenting a novel domain adaptation solution for event detection networks that enables inference across multiple types of devices. Rather than training a black-box detection network, we decouple event localization and classification tasks. Localization is performed by the Interval Proposal Algorithm (IPA), which leverages signal processing techniques to localize candidate events and derive context features. These events are then standardized and fed to a feature extractor to obtain morphological features. By combining domain-specific context features with domain-invariant morphological features, the classifier achieves good generalization capabilities through different domains. Our method can successfully detect events in OTDR traces achieving a mAP@0.5 of 75.33% on traces from the source domain and generalizing well (mAP@0.5 of 69.27%) on traces from the target domain, despite being trained solely from the source domain.
2023
978-9-4645-9360-0
File in questo prodotto:
File Dimensione Formato  
rizzo_eusipco2023.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 1.3 MB
Formato Adobe PDF
1.3 MB Adobe PDF Visualizza/Apri
Event_Detection_in_Optical_Signals_via_Domain_Adaptation.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 1.32 MB
Formato Adobe PDF
1.32 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
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/11583/2982237