Search

Aflatoxins are of great concern for food safety and security due to their impact on human health and the agriculture economy in developing countries. This study aimed to evaluate the potential use of a field portable metal oxide sensors based electronic nose to detect aflatoxin contamination in Kenyan maize varieties that were artificially and naturally infected with Aspergillus flavus. Mutual information was used to select features from the electronic nose sensor signals for classification of the samples. The effectiveness of selected features to discriminate between the different classes of samples was evaluated by support vector machines and k -nearest neighbour with leave-one-out cross-validation. External validation was also conducted by analysing samples naturally contaminated with A. flavus using the classification model generated with samples that had been artificially inoculated with the aflatoxigenic A. flavus. Cross-validated classification accuracies ranged from 72% to 88% for maize samples artificially inoculated with A. flavus and 61–86% for samples naturally infected with A. flavus. Classification accuracies achieved with external validation for maize samples naturally contaminated with aflatoxins ranged from 58% to 78% and were relatively consistent with accuracies obtained from internal validation. Results suggest that the electronic nose could be a promising cost-effective screening method to detect aflatoxin contamination in maize. • Electronic nose evaluated for detection of aflatoxin contamination in maize. • Mutual information applied for selection of features for classification samples. • Cross-validated classification accuracy of 61–88% achieved. • Accuracies achieved with internal and external validation relatively consistent. • Proof of concept on electronic nose for detection of aflatoxin contamination. [ABSTRACT FROM AUTHOR]

The electronic nose offers potential as a rapid and cost effective field portable diagnostic device that would allow for quick screening of produce for aflatoxin contamination at the market entry level. This study aimed to compare the performance of three electronic nose sensor technologies: metal oxide semiconductor sensors (Fox 3000), conducting polymer sensors (Cyranose 320) and doped metal oxide semiconductor sensors with thermocycling (DiagNose), for the detection of volatiles associated with maize contaminated with aflatoxins. Australian maize (variety DK703w) samples were artificially inoculated with aflatoxigenic and non-aflatoxigenic Aspergillus flavus isolates and 2 % v/v Tween 20 as a control. Mutual information was used to select features from the electronic nose sensor signals for classification of the samples. The effectiveness, of selected features to discriminate between the different classes of samples was evaluated by support vector machines and k -nearest neighbour with leave-one-out cross-validation. Cross-validated classification accuracy for the different sample classes ranged from 81 % to 94 % for DiagNose, 76 to 79 % for Fox 3000 and 68 to 75 % for Cyranose. The results suggest that an electronic nose equipped with doped metal oxide semiconductor sensors and thermocycling is more effective for detection of aflatoxin contamination of maize. • Electronic nose sensor technologies evaluated for detection of aflatoxin. • Maize artificially infected with Aspergillus flavus used for evaluation. • Mutual information used for selection of features for classification of samples. • Accuracy of 68–94% achieved for the different technologies. • Metal oxide semiconductor sensors more effective than conducting polymer sensors. [ABSTRACT FROM AUTHOR]