Performance of convolutional neural network (CNN) and performance influencing factors for wood species classification of Lepidobalanus growing in Korea.

This study aimed to investigate the performance and factors affecting the species classification of convolutional neural network (CNN) architecture using whole-part and earlywood-part cross-sectional datasets of six Korean Quercus species. The accuracy of species classification for each condition was analyzed using the datasets, data augmentation, and optimizers-stochastic gradient descent (SGD), adaptive moment estimation (Adam), and root mean square propagation (RMSProp)-based on a CNN architecture with three to four convolutional layers. The model trained with the augmented dataset yielded significantly superior results in terms of classification accuracy compared to the model trained with the non-augmented dataset.

Enhanced Electrochemical Properties of LiMnPO4/C by Glucose-Assisted Polyol Synthesis.

Carbon-coated nano-sized LiMnPO4/C particles are synthesized by polyol method using low-cost glucose as the carbon source. The X-ray diffraction patterns of the synthesized samples are well indexed to the orthorhombic olivine-LiMnPO4 structure. The morphology studies using FE-SEM and HR-TEM images clearly illustrate thin layered carbon coatings on LiMnPO4 particles of sizes ranging between 50~100 nm.