Seong Joon Yoo

Seong Joon Yoo


Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 December 2020 in Agriculture
Verified
Journal Article
Open access
PDF file
HYHELIN YIN
HELIN YIN
DJDong Jin
Dong Jin
YGYeonghyeon Gu
Yeonghyeon Gu
CPChang-Jin Park
Chang-Jin Park
SHSang Keun Han
Sang Keun Han
SYSeong Joon Yoo
Seong Joon Yoo
It is difficult to forecast vegetable prices because they are affected by numerous factors, such as weather and crop production, and the time-series data have strong non-linear and non-stationary characteristics. To address these issues, we propose the STL-ATTLSTM (STL-Attention-based LSTM) model, which integrates the seasonal trend decomposition using the Loess (STL) preprocessing method and attention mechanism based on long short-term memory (LSTM). The proposed STL-ATTLSTM forecasts monthly vegetable prices using various types of information, such as vegetable prices, weather information of the main production areas, and market trading volumes. The STL method decomposes time-series vegetable price data into trend, seasonality, and remainder components. It uses the remainder component by removing the trend and seasonality components. In the model training process, attention weights are assigned to all input variables; thus, the model’s prediction performance is improved by focusing on the variables that affect the prediction results. The proposed STL-ATTLSTM was applied to five crops, namely cabbage, radish, onion, hot pepper, and garlic, and its performance was compared to three benchmark models (i.e., LSTM, attention LSTM, and STL-LSTM). The performance results show that the LSTM model combined with the STL method (STL-LSTM) achieved a 12% higher prediction accuracy than the attention LSTM model that did not use the STL method and solved the prediction lag arising from high seasonality. The attention LSTM model improved the prediction accuracy by approximately 4% to 5% compared to the LSTM model. The STL-ATTLSTM model achieved the best performance, with an average root mean square error (RMSE) of 380, and an average mean absolute percentage error (MAPE) of 7%.

10 February 2022 in Agriculture
Verified
Journal Article
Open access
PDF file
YGYeonghyeon Gu
Yeonghyeon Gu
DJDong Jin
Dong Jin
HYHELIN YIN
HELIN YIN
RZRi Zheng
Ri Zheng
XPXianghua Piao
Xianghua Piao
SYSeong Joon Yoo
Seong Joon Yoo
Fluctuations in agricultural commodity prices affect the supply and demand of agricultural commodities and have a significant impact on consumers. Accurate prediction of agricultural commodity prices would facilitate the reduction of risk caused by price fluctuations. This paper proposes a model called the dual input attention long short-term memory (DIA-LSTM) for the efficient prediction of agricultural commodity prices. DIA-LSTM is trained using various variables that affect the price of agricultural commodities, such as meteorological data, and trading volume data, and can identify the feature correlation and temporal relationships of multivariate time series input data. Further, whereas conventional models predominantly focus on the static main production area (which is selected for each agricultural commodity beforehand based on statistical data), DIA-LSTM utilizes the dynamic main production area (which is selected based on the production of agricultural commodities in each region). To evaluate DIA-LSTM, it was applied to the monthly price prediction of cabbage and radish in the South Korean market. Using meteorological information for the dynamic main production area, it achieved 2.8% to 5.5% lower mean absolute percentage error (MAPE) than that of the conventional model that uses meteorological information for the static main production area. Furthermore, it achieved 1.41% to 4.26% lower MAPE than that of benchmark models. Thus, it provides a new idea for agricultural commodity price forecasting and has the potential to stabilize the supply and demand of agricultural products.

6 December 2019 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
SLSang Il Lee
Sang Il Lee
SYSeong Joon Yoo
Seong Joon Yoo

28 September 2020 in Agriculture
Verified
Journal Article
Open access
PDF file
HYHELIN YIN
HELIN YIN
YGYeonghyeon Gu
Yeonghyeon Gu
CPChang-Jin Park
Chang-Jin Park
JPJong-Han Park
Jong-Han Park
SYSeong Joon Yoo
Seong Joon Yoo
The use of conventional classification techniques to recognize diseases and pests can lead to an incorrect judgment on whether crops are diseased or not. Additionally, hot pepper diseases, such as “anthracnose” and “bacterial spot” can be erroneously judged, leading to incorrect disease recognition. To address these issues, multi-recognition methods, such as Google Cloud Vision, suggest multiple disease candidates and allow the user to make the final decision. Similarity-based image search techniques, along with multi-recognition, can also be used for this purpose. Content-based image retrieval techniques have been used in several conventional similarity-based image searches, using descriptors to extract features such as the image color and edge. In this study, we use eight pre-trained deep learning models (VGG16, VGG19, Resnet 50, etc.) to extract the deep features from images. We conducted experiments using 28,011 image data of 34 types of hot pepper diseases and pests. The search results for diseases and pests were similar to query images with deep features using the k-nearest neighbor method. In top-1 to top-5, when using the deep features based on the Resnet 50 model, we achieved recognition accuracies of approximately 88.38–93.88% for diseases and approximately 95.38–98.42% for pests. When using the deep features extracted from the VGG16 and VGG19 models, we recorded the second and third highest performances, respectively. In the top-10 results, when using the deep features extracted from the Resnet 50 model, we achieved accuracies of 85.6 and 93.62% for diseases and pests, respectively. As a result of performance comparison between the proposed method and the simple convolutional neural network (CNN) model, the proposed method recorded 8.62% higher accuracy in diseases and 14.86% higher in pests than the CNN classification model.

4 January 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YGYeonghyeon Gu
Yeonghyeon Gu
ZPZhe Gao Piao
Zhe Gao Piao
SYSeong Joon Yoo
Seong Joon Yoo
In magnetic resonance imaging (MRI) segmentation, conventional approaches utilize U-Net models with encoder–decoder structures, segmentation models using vision transformers, or models that combine a vision transformer with an encoder–decoder model structure. However, conventional models have large sizes and slow computation speed and, in vision transformer models, the computation amount sharply increases with the image size. To overcome these problems, this paper proposes a model that combines Swin transformer blocks and a lightweight U-Net type model that has an HarDNet blocks-based encoder–decoder structure. To maintain the features of the hierarchical transformer and shifted-windows approach of the Swin transformer model, the Swin transformer is used in the first skip connection layer of the encoder instead of in the encoder–decoder bottleneck. The proposed model, called STHarDNet, was evaluated by separating the anatomical tracings of lesions after stroke (ATLAS) dataset, which comprises 229 T1-weighted MRI images, into training and validation datasets. It achieved Dice, IoU, precision, and recall values of 0.5547, 0.4185, 0.6764, and 0.5286, respectively, which are better than those of the state-of-the-art models U-Net, SegNet, PSPNet, FCHarDNet, TransHarDNet, Swin Transformer, Swin UNet, X-Net, and D-UNet. Thus, STHarDNet improves the accuracy and speed of MRI image-based stroke diagnosis.

14 September 2018 in The Journal of Supercomputing
Verified
Journal Article
Closed access
PDF file
SLSang Il Lee
Sang Il Lee
SYSeong Joon Yoo
Seong Joon Yoo