A deep learning approach for analyzing the composition of chemometric data
This work addresses data analysis challenges for chemometric researchers, but it appears incremental as it builds on existing autoencoder and regression methods.
The authors tackled the curse of dimensionality in chemometric data analysis by proposing a deep learning technique using an L2 regularized sparse autoencoder with Pareto optimization for node selection and Gaussian process regression, achieving considerable improvement in Normalized Mean Square Error on orange juice and wine datasets compared to three state-of-the-art methods.
We propose novel deep learning based chemometric data analysis technique. We trained L2 regularized sparse autoencoder end-to-end for reducing the size of the feature vector to handle the classic problem of the curse of dimensionality in chemometric data analysis. We introduce a novel technique of automatic selection of nodes inside the hidden layer of an autoencoder through Pareto optimization. Moreover, Gaussian process regressor is applied on the reduced size feature vector for the regression. We evaluated our technique on orange juice and wine dataset and results are compared against 3 state-of-the-art methods. Quantitative results are shown on Normalized Mean Square Error (NMSE) and the results show considerable improvement in the state-of-the-art.