Vegetables can be distinguished according to differences in color, shape, and texture. The deep learning convolutional neural network (CNN) method is a technique that can be used to classify types of vegetables for various applications in agriculture. This study proposes a vegetable classification technique that uses the CNN AlexNet model and applies compressive sensing (CS) to reduce computing time and save storage space. In CS, discrete cosine transform (DCT) is applied for the sparsing process, Gaussian distribution for sampling, and orthogonal matching pursuit (OMP) for reconstruction. Simulation results on 600 images for four types of vegetables showed a maximum test accuracy of 98% for the AlexNet method, while the combined block-based CS using the AlexNet method produced a maximum accuracy of 96.66% with a compression ratio of 2×. Our results indicated that AlexNet CNN architecture and block-based CS in AlexNet can classify vegetable images better than previous methods.
Density functional theory method at the B3LYP/6-31G level was used to determine the structure of 12mer single-strand guanine oligomers. The length and width of the optimized structure are 38.7 and 18.2 Å, respectively, and the observed high-resolution transmission electron microscopy image of the 12mer single-strand guanine sample shows similar oligomer dimensions with the calculated ones. Both HOMO and LUMO are significantly delocalized, and the calculated HOMO-LUMO gap is 3.31 eV. A total of 96 muonium trapping sites at C2, C4, C5, C6, C8, N3, N7, and O6 were investigated. All 12 C8 sites have lower energy than the other 84 sites and are clustered in the energy-muon hyperfine coupling constant scatter plot. The calculated muon hyperfine coupling constant at C8 sites range from 384.6 to 481.1 MHz, and the corresponding estimated ALC-μSR resonance for |ΔM| = 1 range from 1.419 to 1.775 T.