The data processed through PCA feature selection and then applied to the 1D-CNN achieved a classification accuracy of 91.3% at 48 h, with an increasing trend at 60, 72, and 84 h, achieving accuracies of 92.6, 92.6, and 94.7%, respectively.
← all excerpts
A CNN model for early detection of pepper Phytophthora blight using multispectral imaging, integrating spectral and textural information.
1
—
—