• Korean Journal of Heritage: History & Science
• /
• v.57 no.3
• /
• pp.24-35
• /
• 2024

Recently, research using deep learning technologies such as artificial intelligence, convolutional neural networks, etc. has been actively conducted in various fields including healthcare, manufacturing, autonomous driving, and security, and is having a significant influence on society. In line with this trend, the present study attempted to apply deep learning to the classification of archaeological artifacts, specifically ancient Korean roof-end tiles. Using 100 images of roof-end tiles from each of the Goguryeo, Baekje, and Silla dynasties, for a total of 300 base images, a dataset was formed and expanded to 1,200 images using data augmentation techniques. After building a model using transfer learning from the pre-trained EfficientNetB0 model and conducting five-fold cross-validation, an average training accuracy of 98.06% and validation accuracy of 97.08% were achieved. Furthermore, when model performance was evaluated with a test dataset of 240 images, it could classify the roof-end tile images from the three dynasties with a minimum accuracy of 91%. In particular, with a learning rate of 0.0001, the model exhibited the highest performance, with accuracy of 92.92%, precision of 92.96%, recall of 92.92%, and F1 score of 92.93%. This optimal result was obtained by preventing overfitting and underfitting issues using various learning rate settings and finding the optimal hyperparameters. The study's findings confirm the potential for applying deep learning technologies to the classification of Korean archaeological materials, which is significant. Additionally, it was confirmed that the existing ImageNet dataset and parameters could be positively applied to the analysis of archaeological data. This approach could lead to the creation of various models for future archaeological database accumulation, the use of artifacts in museums, and classification and organization of artifacts.

• Journal of Radiation Protection and Research
• /
• v.40 no.3
• /
• pp.162-167
• /
• 2015

Although the perfomance indicators of the nuclear power plants in Korea show optimal, it requires detailed analysis and discussion centered on the radiation dose. As analysis methods, analysis on the radiation dose of nuclear power plants over the past five years was assessed by comparing the relevant radiation dose of radiation workers and per capita average annual radiation dose of the world's major nuclear power stations was also analyzed. The radiation workers over the annual radiation dose limit of 50 mSv were not. The contrast ratio of the radiation exposure according to the reactor type was the normal operation of PHWR was 6.2% higher than those of the PWR. This shows the radiation work of PHWR during normal driving operation is much more than those of PWR. According to the Performance Indicators of the World Association of Nuclear Operator, the annual radiation dose per unit in 2013 showed 527 man-mSv of Korea is the best country among the major nuclear power generating states, the world average was 725 man-mSv. The annual per capita radiation dose is about 80% less than 1 mSv of the public dose limit and also the average per capita dose showed a very low level as 0.82 mSv. Workers in related organizations showed 1.07 mSv, the non-destructive inspection agency workers showed 3.87 mSv. The remarkable results were due to radiation reduced program such as development of radiation shielding and radiation protection. In conclusion, the radiation exposured dose of nuclear power plants workers in Korea showed a trend which is ideally reduced. But more are expected to be difficul and the psychological insecurity against the operation of the nuclear power plants is existed to the residents near the nuclear power plants. So the radiation dose reduction policy and radiation dose follow up study of nuclear power plants will be continously excuted.