Qualitative and Quantitative Detection of Food Adulteration Using a Smart E-Nose

Area of Science:

• Food Science
• Analytical Chemistry
• Sensor Technology

Background:

• Food adulteration poses significant risks to public health and consumer trust.
• Rapid and reliable detection methods are crucial for ensuring food safety.

Purpose of the Study:

• To design and develop a smart electronic nose (SE-Nose) for fast-track qualitative and quantitative detection of food adulteration.
• To validate the SE-Nose methodology using pork adulteration in beef as a case study.

Main Methods:

• The SE-Nose methodology incorporates a dataset, sample slicing window protocol, normalization, pattern recognition, and output.
• Support Vector Machine (SVM) classification and regression models were employed for qualitative and quantitative analysis.
• A 10-fold cross-validation method was used to validate the models.

Main Results:

• The SE-Nose achieved a high accuracy of 99.996% with the SVM classification model.
• An RMSE of 0.02864 was obtained with the SVM regression model for quantitative analysis.
• The recognition time for detecting pork adulteration in beef was reduced to 40 seconds, a one-third reduction.

Conclusions:

• The proposed SE-Nose methodology enables high-performance, fast-track detection of food adulteration.
• The system provides accurate qualitative and quantitative analysis, enhancing food safety measures.
• This technology offers a significant advancement in the rapid assessment of food quality and authenticity.