Feature selection and array optimization of sensor array based on principal component analysis
A feature selection method, sensor array technology, applied to instruments, character and pattern recognition, computer components, etc., can solve problems such as poor effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0082] Example: There is an existing original sensor array comprising 10 sensors (the sensors are numbered 1 to 10 respectively), and it is necessary to identify fresh meat and spoiled meat through odor detection. To this end, a total of 600 data samples (including 300 fresh meat samples and 300 spoiled meat samples) were collected, and each data sample contained 10 sensor response curves. Four feature extraction methods including maximum value, peak area, maximum difference, and maximum slope are initially selected.
[0083] A: First evaluate the performance of various feature extraction methods, that is, use each feature extraction method to extract features separately and send them to the SVM classifier for the discrimination of fresh meat and spoiled meat. The best recognition results of each method are: the recognition rate of the maximum value method is 81%, the recognition rate of the peak area method is 75%, the recognition rate of the maximum difference method is 78%,...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


