Cryopreservation of bovine embryos is used to efficiently implant surrogate mothers. It has been widely accepted that high lipid content in the oocyte interrupts its survival during freeze-thaw cycles. Serum component in the culture medium is thought to increase the embryo`s lipid contents. Conversely, L-carnitine stimulates lipid metabolism by transporting long chain fatty acids into the mitochondria. Objective of this study was to analyze the effect of L-carnitine supplementation in IVM medium and defined IVC medium on the development, lipid contents and the cryosurvival of bovine IVF embryos. 0.0, 1.5, 3.0 and 6.0 mM L-carnitine was supplemented in IVM medium, respectively (IVM-LC 0.0, LC 1.5, LC 3.0 and LC 6.0). Development rate from the 2cell to the morula stages was higher in IVM-LC 3.0 groups than those of IVM-LC 6.0 (p<0.05). But there were no significant differences among the other groups in the blastocyst rates and lipid content results. When 0.0, 1.5, 3.0 and 6.0 mM L-carnitine were supplemented in IVC medium (IVC-LC 0.0, LC 1.5, LC 3.0 and LC 6.0), development competence was not significantly different between those embryos. Lipid contents of embryos treated L-carnitine (IVC-LC 1.5, 3.0 and 6.0) were significantly lower than embryos of non-treated group. L-carnitine was supplemented 0.0, 1.5, 3.0, 6.0 mM during IVM and 3.0 mM during IVC (LC 0.0 - 3.0, LC 1.5 – 3.0, LC 3.0 – 3.0, LC 6.0 – 3.0) and cryosurvival of blastocysts confirmed after freezing-thawing. There were no significant differences on development, but LC 3.0 – 3.0 was significantly lower lipid contents than other groups. And LC 3.0 – 3.0 had better survival rates and hatched rates of blastocysts than LC 0.0 – 0.0. In conclusion, supplementation of L-carnitine in defined IVC medium decreases lipid contents. And L-carnitine supplementation improves cryosurvival and developmental ability of bovine IVF embryos.

This paper is a study on data augmentation for small dataset by using deep learning. In case of training a deep learning model for recognition and classification of non-mainstream objects, there is a limit to obtaining a large amount of training data. Therefore, this paper proposes a data augmentation method using perspective transform and image synthesis. In addition, it is necessary to save the object area for all training data to detect the object area. Thus, we devised a way to augment the data and save object regions at the same time. To verify the performance of the augmented data using the proposed method, an experiment was conducted to compare classification accuracy with the augmented data by the traditional method, and transfer learning was used in model learning. As experimental results, the model trained using the proposed method showed higher accuracy than the model trained using the traditional method.