A Spectral Feature Based CNN Long Short-Term Memory Approach for Classification

Abstract

This paper presents a Gaussian data augmentation-assisted deep learning using a convolutional neural network (PCA18+GDA100+CNN LSTM) on the analysis of the state-of-the-art infrared backscatter imaging spectroscopy (IBIS) images. Both PCA and data augmentation methods were used to preprocess classification input and predict with a comparable degree of accuracy. Initially, PCA was used to reduce the number of features. We used 18 principal components based of the cumulative variance, which totaled 99.92%. GDA was also used to increase the number of samples. CNN-LSTM (long short-term memory) was then used to perform multiclass classification on the IBIS hyperspectral image. Experiments were conducted and results were collected from the K-fold cross-validation with K=20. They were analyzed with a confusion matrix and the average accuracy is 99%.