In safety-critical applications, microcontrollers must satisfy strict quality constraints and performances in terms of Fmax, that is, the maximum operating frequency. It has been demonstrated that data extracted from on-chip speed monitors can model the Fmax of integrated circuits by means of machine learning models, and that those models are suitable for the performance screening process. However, while acquiring data from these monitors is quite an accurate process, the labelling is time-consuming, costly, and may be subject to different measurements errors, impairing the final quality. This paper presents a methodology to cope with anomalous and noisy data in the context of the multi-label regression problem of microcontroller performance screening. We used outlier detection based on Inter Quartile Range (IQR) and Z-score and imputation techniques to detect errors in the labels and to avoid to drop incomplete samples, building higher-quality training set for our models, optimizing the devices characterization phase. Experiments showed that the proposed methodology increases the performance of existing models, making them more robust. These techniques permitted us to use a significantly smaller number of samples (about one third of the devices available for characterization), thus making the costly data acquisition process more efficient.

Microcontroller Performance Screening: Optimizing the Characterization in the Presence of Anomalous and Noisy Data / Bellarmino, Nicolo'; Cantoro, Riccardo; Huch, Martin; Kilian, Tobias; Schlichtmann, Ulf; Squillero, Giovanni. - (2022). (Intervento presentato al convegno IEEE International Symposium on On-Line Testing and Robust System 2022 tenutosi a Torino nel 12-14 September 2022) [10.1109/IOLTS56730.2022.9897769].

Microcontroller Performance Screening: Optimizing the Characterization in the Presence of Anomalous and Noisy Data

Bellarmino,Nicolo';Cantoro,Riccardo;Squillero,Giovanni
2022

Abstract

In safety-critical applications, microcontrollers must satisfy strict quality constraints and performances in terms of Fmax, that is, the maximum operating frequency. It has been demonstrated that data extracted from on-chip speed monitors can model the Fmax of integrated circuits by means of machine learning models, and that those models are suitable for the performance screening process. However, while acquiring data from these monitors is quite an accurate process, the labelling is time-consuming, costly, and may be subject to different measurements errors, impairing the final quality. This paper presents a methodology to cope with anomalous and noisy data in the context of the multi-label regression problem of microcontroller performance screening. We used outlier detection based on Inter Quartile Range (IQR) and Z-score and imputation techniques to detect errors in the labels and to avoid to drop incomplete samples, building higher-quality training set for our models, optimizing the devices characterization phase. Experiments showed that the proposed methodology increases the performance of existing models, making them more robust. These techniques permitted us to use a significantly smaller number of samples (about one third of the devices available for characterization), thus making the costly data acquisition process more efficient.
2022
978-1-6654-7355-2
File in questo prodotto:
File Dimensione Formato  
Microcontroller_Performance_Screening_Optimizing_the_Characterization_in_the_Presence_of_Anomalous_and_Noisy_Data.pdf

non disponibili

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Non Pubblico - Accesso privato/ristretto
Dimensione 767.29 kB
Formato Adobe PDF
767.29 kB Adobe PDF   Visualizza/Apri   Richiedi una copia
2022_IOLTS_Outlier_Detection_.pdf

accesso aperto

Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: PUBBLICO - Tutti i diritti riservati
Dimensione 712.48 kB
Formato Adobe PDF
712.48 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/11583/2971082