Modelling the growth domain of Clostridium botulinum via kernel survival analysis

R. J. Foxall; G. C. Cawley; M. W. Peck

doi:10.1109/IJCNN.2003.1224041

Modelling the growth domain of Clostridium botulinum via kernel survival analysis

R. J. Foxall, G. C. Cawley, M. W. Peck

Research output: Contribution to conference › Paper

1 Citation (Scopus)

Abstract

Clostridium botulinum is a bacterium present in the raw ingredients of many foods. It produces a powerful neurotoxin as part of its growth process, that can prove fatal when doses as small as 30ng are consumed. It is therefore vital to be able to accurately determine the food processing and storage conditions where toxin production is possible, known as the "growth domain". This paper describes a new approach to modelling the growth domain of microbial pathogens, by constructing a regularised kernel model relating heat treatment and subsequent incubation conditions to the parameters of a statistical distribution modelling the probability of growth as a function of incubation time. We demonstrate that the use of the "kernel trick" permits the extension of methods from classical survival analysis to account for non-linear dependencies in a principled manner.

Original language	English
Pages	2958-1963
Number of pages	996
DOIs	https://doi.org/10.1109/IJCNN.2003.1224041
Publication status	Published - Jul 2003
Event	IEEE/INNS International Joint Conference on Artificial Neural Networks - Portland, United States Duration: 20 Jul 2003 → 24 Jul 2003

Conference

Conference	IEEE/INNS International Joint Conference on Artificial Neural Networks
Abbreviated title	IJCNN-2003
Country/Territory	United States
City	Portland
Period	20/07/03 → 24/07/03

Access to Document

10.1109/IJCNN.2003.1224041

Cite this

@conference{c3859fb19174463db6046682b431c93e,

title = "Modelling the growth domain of Clostridium botulinum via kernel survival analysis",

abstract = "Clostridium botulinum is a bacterium present in the raw ingredients of many foods. It produces a powerful neurotoxin as part of its growth process, that can prove fatal when doses as small as 30ng are consumed. It is therefore vital to be able to accurately determine the food processing and storage conditions where toxin production is possible, known as the {"}growth domain{"}. This paper describes a new approach to modelling the growth domain of microbial pathogens, by constructing a regularised kernel model relating heat treatment and subsequent incubation conditions to the parameters of a statistical distribution modelling the probability of growth as a function of incubation time. We demonstrate that the use of the {"}kernel trick{"} permits the extension of methods from classical survival analysis to account for non-linear dependencies in a principled manner.",

author = "Foxall, {R. J.} and Cawley, {G. C.} and Peck, {M. W.}",

year = "2003",

month = jul,

doi = "10.1109/IJCNN.2003.1224041",

language = "English",

pages = "2958--1963",

note = "IEEE/INNS International Joint Conference on Artificial Neural Networks, IJCNN-2003 ; Conference date: 20-07-2003 Through 24-07-2003",

}

TY - CONF

T1 - Modelling the growth domain of Clostridium botulinum via kernel survival analysis

AU - Foxall, R. J.

AU - Cawley, G. C.

AU - Peck, M. W.

PY - 2003/7

Y1 - 2003/7

N2 - Clostridium botulinum is a bacterium present in the raw ingredients of many foods. It produces a powerful neurotoxin as part of its growth process, that can prove fatal when doses as small as 30ng are consumed. It is therefore vital to be able to accurately determine the food processing and storage conditions where toxin production is possible, known as the "growth domain". This paper describes a new approach to modelling the growth domain of microbial pathogens, by constructing a regularised kernel model relating heat treatment and subsequent incubation conditions to the parameters of a statistical distribution modelling the probability of growth as a function of incubation time. We demonstrate that the use of the "kernel trick" permits the extension of methods from classical survival analysis to account for non-linear dependencies in a principled manner.

AB - Clostridium botulinum is a bacterium present in the raw ingredients of many foods. It produces a powerful neurotoxin as part of its growth process, that can prove fatal when doses as small as 30ng are consumed. It is therefore vital to be able to accurately determine the food processing and storage conditions where toxin production is possible, known as the "growth domain". This paper describes a new approach to modelling the growth domain of microbial pathogens, by constructing a regularised kernel model relating heat treatment and subsequent incubation conditions to the parameters of a statistical distribution modelling the probability of growth as a function of incubation time. We demonstrate that the use of the "kernel trick" permits the extension of methods from classical survival analysis to account for non-linear dependencies in a principled manner.

U2 - 10.1109/IJCNN.2003.1224041

DO - 10.1109/IJCNN.2003.1224041

M3 - Paper

SP - 2958

EP - 1963

T2 - IEEE/INNS International Joint Conference on Artificial Neural Networks

Y2 - 20 July 2003 through 24 July 2003

ER -