• Proceedings of the Korean Institute of Landscape Architecture Conference
• /
• 2007.10b
• /
• pp.72-77
• /
• 2007

Civic participation in managing the work of a park is a natural experience, and urban culture has a role in forming and communicating ideas. However, when it comes to managing a copse, there is no clear scenic image. In this study, my intention was to determine a desirable scene involving a copse and suggest a target image for managing work from a scenic perspective. I selected 12 photographs and listed 10 pairs of adjectives that were judged to reflect the effect produced by the copse scene using the repertory grid development technique. In addition, I performed a scenic evaluation using the semantic differential(SD) method with each pair of adjectives. Factor analysis was performed based on questionnaire survey results, such that the scenic structure of the copse had a clear definition. In addition, the physical characteristics of the photographs were analyzed using Adobe Photoshop 6.0 and the correlations between the results of the questionnaire survey were understood using multiple regression analysis. A desirable scenic image of the copse became clear through this process and I was able to suggest various options of scenic images. Taking the aspects of urban culture into consideration, park improvement projects(including their planning stages) should be implemented by involving residents, which will lead to further development of park planning and maintenance theories and projects giving due consideration to residents' opinions.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.1-16
• /
• 2022

Despite recent breakthroughs in deep learning and computer vision fields, the pixel-wise identification of tiny objects in high-resolution images with complex disturbances remains challenging. This study proposes a modified U-net for tiny crack segmentation in real-world steel-box-girder bridges. The modified U-net adopts the common U-net framework and a novel Self-Attention-Self-Adaption (SASA) neuron as the fundamental computing element. The Self-Attention module applies softmax and gate operations to obtain the attention vector. It enables the neuron to focus on the most significant receptive fields when processing large-scale feature maps. The Self-Adaption module consists of a multiplayer perceptron subnet and achieves deeper feature extraction inside a single neuron. For data augmentation, a grid-based crack random elastic deformation (CRED) algorithm is designed to enrich the diversities and irregular shapes of distributed cracks. Grid-based uniform control nodes are first set on both input images and binary labels, random offsets are then employed on these control nodes, and bilinear interpolation is performed for the rest pixels. The proposed SASA neuron and CRED algorithm are simultaneously deployed to train the modified U-net. 200 raw images with a high resolution of 4928 × 3264 are collected, 160 for training and the rest 40 for the test. 512 × 512 patches are generated from the original images by a sliding window with an overlap of 256 as inputs. Results show that the average IoU between the recognized and ground-truth cracks reaches 0.409, which is 29.8% higher than the regular U-net. A five-fold cross-validation study is performed to verify that the proposed method is robust to different training and test images. Ablation experiments further demonstrate the effectiveness of the proposed SASA neuron and CRED algorithm. Promotions of the average IoU individually utilizing the SASA and CRED module add up to the final promotion of the full model, indicating that the SASA and CRED modules contribute to the different stages of model and data in the training process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2768-2787
• /
• 2023

As an important research direction of the application of computer science in the medical field, the automatic generation technology of radiology report has attracted wide attention in the academic community. Because the proportion of normal regions in radiology images is much larger than that of abnormal regions, words describing diseases are often masked by other words, resulting in significant feature loss during the calculation process, which affects the quality of generated reports. In addition, the huge difference between visual features and semantic features causes traditional multi-modal fusion method to fail to generate long narrative structures consisting of multiple sentences, which are required for medical reports. To address these challenges, we propose a multi-feature optimization Transformer (MFOT) for generating radiology reports. In detail, a multi-dimensional mapping attention (MDMA) module is designed to encode the visual grid features from different dimensions to reduce the loss of primary features in the encoding process; a feature pre-fusion (FP) module is constructed to enhance the interaction ability between multi-modal features, so as to generate a reasonably structured radiology report; a detail enhanced attention (DEA) module is proposed to enhance the extraction and utilization of key features and reduce the loss of key features. In conclusion, we evaluate the performance of our proposed model against prevailing mainstream models by utilizing widely-recognized radiology report datasets, namely IU X-Ray and MIMIC-CXR. The experimental outcomes demonstrate that our model achieves SOTA performance on both datasets, compared with the base model, the average improvement of six key indicators is 19.9% and 18.0% respectively. These findings substantiate the efficacy of our model in the domain of automated radiology report generation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.29 no.3
• /
• pp.51-65
• /
• 2024

Accurate electrical load forecasting is important to the effective operation of power systems in smart grids. With the recent development in machine learning, artificial intelligence-based models for predicting power demand are being actively researched. However, since existing models get input variables as numerical features, the accuracy of the forecasting model may decrease because they do not reflect the semantic relationship between these features. In this paper, we propose a scheme for short-term load forecasting by using features extracted through the large language models for input data. We firstly convert input variables into a sentence-like prompt format. Then, we use the large language model with frozen weights to derive the embedding vectors that represent the features of the prompt. These vectors are used to train the forecasting model. Experimental results show that the proposed scheme outperformed models based on numerical data, and by visualizing the attention weights in the large language models on the prompts, we identified the information that significantly influences predictions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.582-583
• /
• 2021

As the production of new and renewable energy such as solar and wind power has diversified, microgrid systems that can simultaneously produce and consume have been introduced. . In general, a decrease in electricity prices through solar power is expected in summer, so producer protection is required. In this paper, we propose a transparent and safe gift power transaction system between users using blockchain in a microgrid environment. A futures is simply a contract in which the buyer is obligated to buy electricity or the seller is obliged to sell electricity at a fixed price and a predetermined futures price. This system proposes a futures trading algorithm that searches for futures prices and concludes power transactions with automated operations without user intervention by using a smart contract, a reliable executable code within the blockchain network. If a power producer thinks that the price during the peak production period (Hajj) is likely to decrease during production planning, it sells futures first in the futures market and buys back futures during the peak production period (Haj) to make a profit in the spot market. losses can be compensated. In addition, if there is a risk that the price of electricity will rise when a sales contract is concluded, a broker can compensate for a loss in the spot market by first buying futures in the futures market and liquidating futures when the sales contract is fulfilled.