Optimal Synthesis of Fault-Tolerant IDK Cascades for Real-Time Classification

Sanjoy Baruah; Iain John Bate; Alan Burns; Robert Ian Davis

doi:10.1109/RTAS61025.2024.00011

Optimal Synthesis of Fault-Tolerant IDK Cascades for Real-Time Classification

Sanjoy Baruah, Iain John Bate, Alan Burns, Robert Ian Davis

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

An IDK classifier is a computational element that classifies an input provided to it into one of a set of predefined categories provided that it can achieve the necessary confidence level to do so; otherwise, it outputs “I Don’t Know” (IDK). The concept of IDK classifier cascades has emerged as a strategy for striking a balance between the requirements of rapid response and precise classification in machine perception. Effective algorithms for constructing IDK classifier cascades have recently been developed. Here we extend these prior approaches by incorporating fault-tolerance: enabling classification that is concurrently rapid and accurate even in the event of some of the IDK classifiers exhibiting faulty behavior.

Original language	English
Title of host publication	IEEE 30th Real-Time and Embedded Technology and Applications Symposium (RTAS)
Publisher	IEEE
Pages	29-41
DOIs	https://doi.org/10.1109/RTAS61025.2024.00011
Publication status	Published - 26 Jun 2024

Keywords

IDK cascades
Real-Time
fault tolerance

Access to Document

10.1109/RTAS61025.2024.00011

Optimal Synthesis of Fault-Tolerant IDK Cascades for Real-Time Classification
This is an author-produced version of the published paper. Uploaded in accordance with the University’s Research Publications and Open Access policy.
Accepted author manuscript, 476 KBLicence: CC BY

Cite this

@inproceedings{653ce9a793d8498c9d27ffa8f7ccb054,

title = "Optimal Synthesis of Fault-Tolerant IDK Cascades for Real-Time Classification",

abstract = "An IDK classifier is a computational element that classifies an input provided to it into one of a set of predefined categories provided that it can achieve the necessary confidence level to do so; otherwise, it outputs “I Don{\textquoteright}t Know” (IDK). The concept of IDK classifier cascades has emerged as a strategy for striking a balance between the requirements of rapid response and precise classification in machine perception. Effective algorithms for constructing IDK classifier cascades have recently been developed. Here we extend these prior approaches by incorporating fault-tolerance: enabling classification that is concurrently rapid and accurate even in the event of some of the IDK classifiers exhibiting faulty behavior.",

keywords = "IDK cascades, Real-Time, fault tolerance",

author = "Sanjoy Baruah and Bate, {Iain John} and Alan Burns and Davis, {Robert Ian}",

year = "2024",

month = jun,

day = "26",

doi = "10.1109/RTAS61025.2024.00011",

language = "English",

pages = "29--41",

booktitle = "IEEE 30th Real-Time and Embedded Technology and Applications Symposium (RTAS)",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Optimal Synthesis of Fault-Tolerant IDK Cascades for Real-Time Classification

AU - Baruah, Sanjoy

AU - Bate, Iain John

AU - Burns, Alan

AU - Davis, Robert Ian

PY - 2024/6/26

Y1 - 2024/6/26

N2 - An IDK classifier is a computational element that classifies an input provided to it into one of a set of predefined categories provided that it can achieve the necessary confidence level to do so; otherwise, it outputs “I Don’t Know” (IDK). The concept of IDK classifier cascades has emerged as a strategy for striking a balance between the requirements of rapid response and precise classification in machine perception. Effective algorithms for constructing IDK classifier cascades have recently been developed. Here we extend these prior approaches by incorporating fault-tolerance: enabling classification that is concurrently rapid and accurate even in the event of some of the IDK classifiers exhibiting faulty behavior.

AB - An IDK classifier is a computational element that classifies an input provided to it into one of a set of predefined categories provided that it can achieve the necessary confidence level to do so; otherwise, it outputs “I Don’t Know” (IDK). The concept of IDK classifier cascades has emerged as a strategy for striking a balance between the requirements of rapid response and precise classification in machine perception. Effective algorithms for constructing IDK classifier cascades have recently been developed. Here we extend these prior approaches by incorporating fault-tolerance: enabling classification that is concurrently rapid and accurate even in the event of some of the IDK classifiers exhibiting faulty behavior.

KW - IDK cascades

KW - Real-Time

KW - fault tolerance

UR - https://www-users.york.ac.uk/~rd17/

U2 - 10.1109/RTAS61025.2024.00011

DO - 10.1109/RTAS61025.2024.00011

M3 - Conference contribution

SP - 29

EP - 41

BT - IEEE 30th Real-Time and Embedded Technology and Applications Symposium (RTAS)

PB - IEEE

ER -

Optimal Synthesis of Fault-Tolerant IDK Cascades for Real-Time Classification

Abstract

Keywords

Access to Document

Other files and links

Cite this