An E-nose and Convolution Neural Network based Recognition Method for Processed Products of Crataegi Fructus

Area of Science:

• Food Science
• Analytical Chemistry
• Machine Learning

Background:

• Manual identification of Fructus Crataegi processed products is inefficient and unreliable.
• Accurate identification is crucial for quality control and authenticity.

Purpose of the Study:

• To develop an efficient and reliable method for identifying Fructus Crataegi processed products.
• To leverage electronic nose technology and convolutional neural networks for odor-based classification.

Main Methods:

• Utilized an electronic nose to capture odor profiles of Fructus Crataegi processed products.
• Applied convolutional neural network (CNN) layers (LCP1, LCP2, LFC) for feature extraction.
• Trained a recognition model using optimized parameters (filters, biases, matrices) for classification.

Main Results:

• The proposed method achieved high accuracy in identifying Fructus Crataegi processed products.
• The CNN-based approach demonstrated competitive performance compared to other machine learning methods.

Conclusions:

• The developed electronic nose and CNN method is effective for identifying Fructus Crataegi processed products.
• This approach offers a reliable alternative to traditional manual identification methods.