Detecting complex anomalies on massive amounts of data is a crucial task in Industry 4.0, best addressed by deep learning. However, available solutions are computationally demanding, requiring cloud architectures prone to latency and bandwidth issues. This work presents Varade, a novel solution implementing a light autoregressive framework based on variational inference, which is best suited for real-time execution on the edge. The proposed approach was validated on a robotic arm, part of a pilot production line, and compared with several state-of-the-art algorithms, obtaining the best trade-off between anomaly detection accuracy, power consumption and inference frequency on two different edge platforms.

VARADE: a Variational-based AutoRegressive model for Anomaly Detection on the Edge / Mascolini, Alessio; Gaiardelli, Sebastiano; Ponzio, Francesco; Dall’Ora, Nicola; Macii, Enrico; Vinco, Sara; Di Cataldo, Santa; Fummi, Franco. - ELETTRONICO. - (2024). (Intervento presentato al convegno DAC '24: 61st ACM/IEEE Design Automation Conference tenutosi a San Francisco (USA) nel June 23-27, 2024) [10.1145/3649329.3655691].

VARADE: a Variational-based AutoRegressive model for Anomaly Detection on the Edge

Mascolini, Alessio;Ponzio, Francesco;Macii, Enrico;Vinco, Sara;Di Cataldo, Santa;Fummi, Franco
2024

Abstract

Detecting complex anomalies on massive amounts of data is a crucial task in Industry 4.0, best addressed by deep learning. However, available solutions are computationally demanding, requiring cloud architectures prone to latency and bandwidth issues. This work presents Varade, a novel solution implementing a light autoregressive framework based on variational inference, which is best suited for real-time execution on the edge. The proposed approach was validated on a robotic arm, part of a pilot production line, and compared with several state-of-the-art algorithms, obtaining the best trade-off between anomaly detection accuracy, power consumption and inference frequency on two different edge platforms.
2024
979-8-4007-0601-1
File in questo prodotto:
File Dimensione Formato  
3649329.3655691.pdf

accesso riservato

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 701.89 kB
Formato Adobe PDF
701.89 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
2409.14816v2.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Pubblico - Tutti i diritti riservati
Dimensione 864.7 kB
Formato Adobe PDF
864.7 kB Adobe PDF Visualizza/Apri
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/11583/2992269