IEEE Sensors Journal · 2022 · 42 citations · 41 references
AgricultureFood ScienceFood AnalysisFood EngineeringFood SafetyFood AutomationFood Safety AnalysisSpectroscopic Food AnalysisConsumer SafetyDiscrete Fourier TransformElectronic NosesFood Adulteration AnalysisFood Contaminant DetectionFood Quality MonitoringFood Safety DetectionInstrumental Freshness Assessment
A low‑cost handheld e‑nose using MQ gas sensors and sinusoidally varying heater voltages can assess food composition and quality in the field, offering commercial benefits and enhancing consumer safety. The device exposed samples for five two‑minute cycles, extracted harmonic amplitudes via DFT, and fed these features into discriminant analysis and random‑forest classifiers to identify the foodstuff. The classifiers achieved classification accuracies exceeding 95 %.
A low-cost handheld e-nose unit for assessing composition and quality of food in the field or for automatic discrimination of different foodstuffs would have significant commercial advantages and provide a positive impact on consumer safety and confidence. Whilst many studies have focused on the freshness of specific foodstuffs, the preliminary results presented in this report indicate that a low-cost (circa 30 euro) e-nose, based on MQ series gas sensors, using sinusoidally varying heater voltages, can successfully differentiate between samples of unspoiled lamb, hake, salmon, beef, pork and chicken, even using default, non-optimized control parameters, which could be applied in food adulteration and fraudulent labelling detection or in smart appliances to automatically select cooking parameters. Samples were exposed to the e-nose for five cycles of two minutes each and, by subjecting the response waveforms to Discrete Fourier Transform (DFT) analysis, harmonic component amplitudes were extracted. These data items were then fed into two different Machine Learning supervised classification methods (discriminant analysis and random forest) to determine which foodstuff was present. The relevance of the different DFT harmonic components and MQ sensors in the foodstuffs classification was quantified. Classification accuracies in excess of 95% were demonstrated.
41
Correlation and variable importance in random forests
Baptiste Gregorutti, Bertrand Michel, Philippe Pierre · Statistics and Computing · 2016 · 1.1K citations · Full text
Computing, Ecology, Data Mining +9
Meat spoilage during distribution
George‐John E. Nychas, Panos Skandamis, Chrysoula C. Tassou et al. · Meat Science · 2007 · 978 citations