Search

Your search keyword '"Wonhyuk Choi"' showing total 4 results
Start Over Author "Wonhyuk Choi" Publication Year Range Last 3 years
4 results on '"Wonhyuk Choi"'

1. Investigation of Compressive Strength Characteristics of Hardfill Material and Seismic Stability of Hardfill Dams

Author

Soogeun Kim, Wonhyuk Choi, Yunhee Kim, Jaewoo Shin, and Bumjoo Kim

Subjects
hardfill, dam, aggregates, particle size distribution, strength, seismic stability, Technology, Engineering (General). Civil engineering (General), TA1-2040, Biology (General), QH301-705.5, Physics, QC1-999, Chemistry, QD1-999
Abstract

A hardfill dam can reduce the natural damage caused by the development of quarries and recycle submerged resources. However, the particle size distribution of the aggregate can result in large variations in the mix design, resulting in a wide range of strengths in the hardfill dam body. Therefore, quality control during construction is crucial, and the stability of the dam body after construction should be thoroughly examined in advance. This study investigated the strength characteristics of hardfill dam materials according to the particle size and mixing ratio through indoor uniaxial compressive strength tests using large specimens and uniaxial compressive strength tests for field compaction and collected cores. Furthermore, the stability of hardfill dams with three types of slopes during earthquakes was evaluated through a finite element analysis. The distributions of stress in the hardfill dam body and the strength required to stabilize the dam body were investigated. Except for a 1:0.6 inclined hardfill dam body to which artificial seismic waves were applied, the overall strength range calculated from the indoor specimens and field compaction cores exceeded the required hardfill strength, thereby ensuring stability in the event of an earthquake.

Published
2023
Full Text
View/download PDF

4. Effective Pre-Training Method and Its Compositional Intelligence for Image Captioning

Author

Yong Suk Choi and Wonhyuk Choi

Subjects
Electric Power Supplies, Intelligence, Electrical and Electronic Engineering, Biochemistry, Instrumentation, Atomic and Molecular Physics, and Optics, Analytical Chemistry, compositional intelligence, image captioning, feature mapping layer, pre-training method, transfer learning, transformer
Abstract

With the increase in the performance of deep learning models, the model parameter has increased exponentially. An increase in model parameters leads to an increase in computation and training time, i.e., an increase in training cost. To reduce the training cost, we propose Compositional Intelligence (CI). This is a reuse method that combines pre-trained models for different tasks. Since the CI uses a well-trained model, good performance and small training cost can be expected in the target task. We applied the CI to the Image Captioning task. Compared to using a trained feature extractor, the caption generator is usually trained from scratch. On the other hand, we pre-trained the Transformer model as a caption generator and applied CI, i.e., we used a pre-trained feature extractor and a pre-trained caption generator. To compare the training cost of the From Scratch model and the CI model, early stopping was applied during fine-tuning of the image captioning task. On the MS-COCO dataset, the vanilla image captioning model reduced training cost by 13.8% and improved performance by up to 3.2%, and the Object Relation Transformer model reduced training cost by 21.3%.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results