Development of a novel continuous statistical modelling technique for detecting the adulteration of extra virgin olive oil with hazelnut oil by using spectroscopic data

Research output: Contribution to conferencePosterpeer-review

308 Downloads (Pure)

Abstract

The adulteration of extra virgin olive oil with other vegetable oils is a certain problem with economic and health consequences. Current official methods have been proved insufficient to detect such adulterations. One of the most concerning and undetectable adulterations with other vegetable oils is the addition of hazelnut oil. The main objective of this work was to develop a novel dimensionality reduction technique able to model oil mixtures as a part of an integrated pattern recognition solution. This final solution attempts to identify hazelnut oil adulterants in extra virgin olive oil at low percentages based on spectroscopic chemical fingerprints. The proposed Continuous Locality Preserving Projections (CLPP) technique allows the modelling of the continuous nature of the produced in house admixtures as data series instead of discrete points. This methodology has potential to be extended to other mixtures and adulterations of food products. The maintenance of the continuous structure of the data manifold lets the better visualization of this examined classification problem and facilitates a more accurate utilisation of the manifold for detecting the adulterants.
Original languageEnglish
Publication statusPublished - Dec 2014
Event43rd Annual Food Research Conference - UCD O’Brien Science Centre, Belfield, Dublin, Ireland
Duration: 10 Dec 201411 Dec 2014

Conference

Conference43rd Annual Food Research Conference
CountryIreland
CityDublin
Period10/12/201411/12/2014

Fingerprint Dive into the research topics of 'Development of a novel continuous statistical modelling technique for detecting the adulteration of extra virgin olive oil with hazelnut oil by using spectroscopic data'. Together they form a unique fingerprint.

Cite this