Radial basis neural network for the classification of fresh edible oils using an electronic nose

Zulfiqur Ali; David James; W. T. Liam O'Hare; Frederick J Rowell; Stephanie M Scott

doi:10.1023/A:1022222402328

Radial basis neural network for the classification of fresh edible oils using an electronic nose

Zulfiqur Ali, David James, W. T. Liam O'Hare, Frederick J Rowell, Stephanie M Scott

Teesside University

Research output: Contribution to journal › Article › peer-review

Abstract

An electronic nose utilising an array of six-bulk acoustic wave polymer coated Piezoelectric Quartz (PZQ) sensors has been developed. The nose was presented with 346 samples of fresh edible oil headspace volatiles, generated at 45°C. Extra virgin olive (EVO), Non-virgin olive oil (OI) and Sunflower oil (SFO), were used over a period of 30 days. The sensor responses were then analysed producing an architecture for the Radial Basis Function Artificial Neural Network (RBF). It was found that the RBF results were excellent, giving classifications of above 99% for the vegetable oil test samples.

Original language	English
Pages (from-to)	147-154
Journal	Journal of Thermal Analysis and Calorimetry
Volume	71
Issue number	1
DOIs	https://doi.org/10.1023/A:1022222402328
Publication status	Published - Jan 2003
Event	29th International Vacuum Microbalance Techniques Conference - Teesside University, Middlesbrough, United Kingdom Duration: 5 Sept 2001 → 7 Sept 2001 Conference number: 29

Access to Document

10.1023/A:1022222402328

http://link.springer.com/10.1023/A:1022222402328

Cite this

@article{b0c3787c5d31467ba1ed2bd995087907,

title = "Radial basis neural network for the classification of fresh edible oils using an electronic nose",

abstract = "An electronic nose utilising an array of six-bulk acoustic wave polymer coated Piezoelectric Quartz (PZQ) sensors has been developed. The nose was presented with 346 samples of fresh edible oil headspace volatiles, generated at 45°C. Extra virgin olive (EVO), Non-virgin olive oil (OI) and Sunflower oil (SFO), were used over a period of 30 days. The sensor responses were then analysed producing an architecture for the Radial Basis Function Artificial Neural Network (RBF). It was found that the RBF results were excellent, giving classifications of above 99% for the vegetable oil test samples.",

author = "Zulfiqur Ali and David James and O'Hare, {W. T. Liam} and Rowell, {Frederick J} and Scott, {Stephanie M}",

year = "2003",

month = jan,

doi = "10.1023/A:1022222402328",

language = "English",

volume = "71",

pages = "147--154",

journal = "Journal of Thermal Analysis and Calorimetry",

issn = "1418-2874",

publisher = "Springer Netherlands",

number = "1",

note = "29th International Vacuum Microbalance Techniques Conference ; Conference date: 05-09-2001 Through 07-09-2001",

}

TY - JOUR

T1 - Radial basis neural network for the classification of fresh edible oils using an electronic nose

AU - Ali, Zulfiqur

AU - James, David

AU - O'Hare, W. T. Liam

AU - Rowell, Frederick J

AU - Scott, Stephanie M

N1 - Conference code: 29

PY - 2003/1

Y1 - 2003/1

N2 - An electronic nose utilising an array of six-bulk acoustic wave polymer coated Piezoelectric Quartz (PZQ) sensors has been developed. The nose was presented with 346 samples of fresh edible oil headspace volatiles, generated at 45°C. Extra virgin olive (EVO), Non-virgin olive oil (OI) and Sunflower oil (SFO), were used over a period of 30 days. The sensor responses were then analysed producing an architecture for the Radial Basis Function Artificial Neural Network (RBF). It was found that the RBF results were excellent, giving classifications of above 99% for the vegetable oil test samples.

AB - An electronic nose utilising an array of six-bulk acoustic wave polymer coated Piezoelectric Quartz (PZQ) sensors has been developed. The nose was presented with 346 samples of fresh edible oil headspace volatiles, generated at 45°C. Extra virgin olive (EVO), Non-virgin olive oil (OI) and Sunflower oil (SFO), were used over a period of 30 days. The sensor responses were then analysed producing an architecture for the Radial Basis Function Artificial Neural Network (RBF). It was found that the RBF results were excellent, giving classifications of above 99% for the vegetable oil test samples.

U2 - 10.1023/A:1022222402328

DO - 10.1023/A:1022222402328

M3 - Article

SN - 1418-2874

VL - 71

SP - 147

EP - 154

JO - Journal of Thermal Analysis and Calorimetry

JF - Journal of Thermal Analysis and Calorimetry

IS - 1

T2 - 29th International Vacuum Microbalance Techniques Conference

Y2 - 5 September 2001 through 7 September 2001

ER -

Radial basis neural network for the classification of fresh edible oils using an electronic nose

Abstract

Access to Document

Fingerprint

Cite this