Earticle

초록

영어

This study aimed to investigate the performance and factors affecting species classification of CNN architecture using whole-part and earlywood-part dataset of cross-sections in six Korean Quercus species. The accuracy of species classification for each condition using the datasets, data augmentation, and optimizers (SGD, Adam, and RMSProp) based on a CNN architecture with 3–4 convolutional layers was analyzed. The model trained with an augmented dataset yielded significantly superior results in classification accuracy compared to the model learned with a non-augmented dataset. The augmented dataset was the only factor affecting classification accuracy in the final five epochs, whereas four factors in the whole epochs, such as the Adam and SGD optimizer, and the earlywood-part and the whole-part dataset, affected species classification. The arrangement of earlywood vessels, broad ray, and axial parenchyma was identified as major influential factors for CNN species classification through Grad-CAM analysis. The augmented whole-part dataset with the Adam optimizer condition achieved the highest classification accuracy of 85.7% in the final five epochs of the test phase.

키워드

저자

• Jong-Ho Kim [ The Institute of Forest Science, Kangwon National University, Chuncheon 24341, Korea ]
• Alvin Muhammad Savero [ National Research and Innovation Agency, Jakarta 10340, Indonesia ]
• Byantara Darsan Purusatama [ National Research and Innovation Agency, Jakarta 10340, Indonesia ]
• Denni Prasetia [ Department of Forest Biomaterials Engineering, Kangwon National University, Chuncheon 24341, Korea ]
• Nam-Hun Kim [ Department of Forest Biomaterials Engineering, Kangwon National University, Chuncheon 24341, Korea ] Corresponding Author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  강원대학교 산림과학연구소 학술대회

• 간기

  부정기

• 수록기간

  2017~2024

• 십진분류

  KDC 526 DDC 634