TD-Magic: From Pictures of Timing Diagrams To Formal Specifications

Jie He (Vortragende:r), Dejan Nickovic, Ezio Bartocci, Radu Grosu

Publikation: Beitrag in Buch oder TagungsbandVortrag mit Beitrag in TagungsbandBegutachtung


We introduce TD-Magic, the first neuro-symbolic approach for translating an image of a timing-diagram (TD) to a formal specification. We overcome the lack of labelled data for supervised learning, by first developing a synthetic data generator of labelled TDs. We then use object detection techniques to identify rising and failing edges, OCR to recognise the text, and image processing algorithms to capture synchronisation patterns. Finally, we use semantic interpretation to analyse the extracted features and generate the associated formal specification. Our experiments on industrial TDs show high translation accuracy opening the way to more sophisticated requirements-extraction algorithms from pictures.
Titel60th ACM/IEEE Design Automation Conference, DAC 2023, San Francisco, CA, USA, July 9-13, 2023
ISBN (elektronisch)979-8-3503-2348-1
PublikationsstatusVeröffentlicht - 9 Juli 2023
Veranstaltung2023 60th ACM/IEEE Design Automation Conference (DAC) - San Francisco, San Francisco, USA/Vereinigte Staaten
Dauer: 9 Juli 202313 Juli 2023


Konferenz2023 60th ACM/IEEE Design Automation Conference (DAC)
Land/GebietUSA/Vereinigte Staaten
StadtSan Francisco

Research Field

  • Dependable Systems Engineering


Untersuchen Sie die Forschungsthemen von „TD-Magic: From Pictures of Timing Diagrams To Formal Specifications“. Zusammen bilden sie einen einzigartigen Fingerprint.

Diese Publikation zitieren