Developing deep learning based regression approaches for determination of chemical compositions in dry black goji berries (Lycium ruthenicum Murr.) using near-infrared hyperspectral imaging.

Black goji berry (Lycium ruthenicum Murr.) has great commercial and nutritional values. Near-infrared hyperspectral imaging (NIR-HSI) was used to determine total phenolics, total flavonoids and total anthocyanins in dry black goji berries. Convolutional neural networks (CNN) were designed and developed to predict the chemical compositions. These CNN models and deep autoencoder were used as supervised and unsupervised feature extraction methods, respectively. Partial least squares (PLS) and least-squares support vector machine (LS-SVM) as modelling methods, successive projections algorithm and competitive adaptive reweighted sampling (CARS) as wavelength selection methods, and principal component analysis (PCA) and wavelet transform (WT) as feature extraction methods were studied as conventional approaches for comparison. Deep learning approaches as modelling methods and feature extraction methods obtained good and equivalent performances to the conventional methods. The results illustrated that deep learning had great potential as modelling and feature extraction methods for chemical compositions determination in NIR-HSI.