• Asian Journal of Innovation and Policy
• /
• v.10 no.1
• /
• pp.68-89
• /
• 2021

The expansion of irrigated agricultural production can be appropriate for the southeast region in the U.S. as a climate change adaptation strategy. This study investigated the effect of supplemental development of irrigated agriculture on the regional economy by applying the supply side Georgia multiregional input-output (MRIO) model. For the analysis, 100% conversion of non-irrigated cultivable acreage into irrigated acreage for cotton, peanuts, corn, and soybeans in 42 counties of southwest Georgia is assumed. With this assumption, the difference in total net returns of production between the non-irrigation and irrigation method is calculated as input data of the Georgia MRIO model. Based on the information of a 95% confidence interval for each crop's average price, the lower and upper bounds of estimated results are also presented. The total impact of cotton production was $60 million with the range of $35 million to $85 million: The total impact of peanuts, soybeans, corn was $10.2 million (the range of $3.28 million to $23.7 million), $6.6 million (the range of $3.1 million to $10.2 million), $1.2 million (the range of -$6 million to $8.5 million), respectively.

• Progress in Medical Physics
• /
• v.32 no.4
• /
• pp.172-178
• /
• 2021

Purpose: This study aimed to develop a deep learning architecture combining two task models to generate synthetic computed tomography (sCT) images from low-tesla magnetic resonance (MR) images to improve metallic marker visibility. Methods: Twenty-three patients with cervical cancer treated with intracavitary radiotherapy (ICR) were retrospectively enrolled, and images were acquired using both a computed tomography (CT) scanner and a low-tesla MR machine. The CT images were aligned to the corresponding MR images using a deformable registration, and the metallic dummy source markers were delineated using threshold-based segmentation followed by manual modification. The deformed CT (dCT), MR, and segmentation mask pairs were used for training and testing. The sCT generation model has a cascaded three-dimensional (3D) U-Net-based architecture that converts MR images to CT images and segments the metallic marker. The performance of the model was evaluated with intensity-based comparison metrics. Results: The proposed model with segmentation loss outperformed the 3D U-Net in terms of errors between the sCT and dCT. The structural similarity score difference was not significant. Conclusions: Our study shows the two-task-based deep learning models for generating the sCT images using low-tesla MR images for 3D ICR. This approach will be useful to the MR-only workflow in high-dose-rate brachytherapy.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.3
• /
• pp.840-860
• /
• 2023

Aiming at the serious occlusion and slow tracking speed in pedestrian target tracking and recognition in complex scenes, a target tracking method based on improved YOLO v5 combined with Deep SORT is proposed. By merging the attention mechanism ECA-Net with the Neck part of the YOLO v5 network, using the CIoU loss function and the method of CIoU non-maximum value suppression, connecting the Deep SORT model using Shuffle Net V2 as the appearance feature extraction network to achieve lightweight and fast speed tracking and the purpose of improving tracking under occlusion. A large number of experiments show that the improved YOLO v5 increases the average precision by 1.3% compared with other algorithms. The improved tracking model, MOTA reaches 54.3% on the MOT17 pedestrian tracking data, and the tracking accuracy is 3.7% higher than the related algorithms and The model presented in this paper improves the FPS by nearly 5 on the fps indicator.

• Asia-Pacific Journal of Business
• /
• v.13 no.4
• /
• pp.135-149
• /
• 2022

Purpose - The primary objective of this article is to investigate the impact of U.S. monetary policy on institutional / individual / foreign investor reactions in the Korean stock market. Design/methodology/approach - This study employs a high frequency event study methodology to identify U.S. monetary policy shocks and quantify the impact of identified shocks on investor reactions. The dependent variable in the regression model is net stock purchase, while the explanatory variables are U.S. monetary policy shocks. The model is estimated for the period 2000-2019, including 156 FOMC meetings. Findings - Foreign investors immediately sell stocks in response to contractionary U.S. monetary shocks. They do not, however, react to anticipated changes in monetary policy rates, confirming the rationality of foreign investors. Individual investors demonstrate the opposite response, indicating that a non-trivial proportion of individual investors are irrational. Research implications or Originality - This study adds to the current literature on the effect of U.S. monetary policy on the Korean stock market. This study demonstrates a heterogeneous response to U.S. monetary policy shocks, validating the rational investment behavior of foreign investors, while individual investors exhibit a certain degree of irrationality. Methodologically, this study adds to the literature by quantifying the impact of U.S. monetary policy employing a sharper identification method allowing a simple and consistent estimation.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.168-177
• /
• 2020

Seabed multiple reflections (seabed multiples) are the main cause of misinterpretations of primary reflections in both shot gathers and stack sections. Accordingly, seabed multiples need to be suppressed throughout data processing. Conventional model-driven methods, such as prediction-error deconvolution, Radon filtering, and data-driven methods, such as the surface-related multiple elimination technique, have been used to attenuate multiple reflections. However, the vast majority of processing workflows require time-consuming steps when testing and selecting the processing parameters in addition to computational power and skilled data-processing techniques. To attenuate seabed multiples in seismic reflection data, input gathers with seabed multiples and label gathers without seabed multiples were generated via numerical modeling using the Marmousi2 velocity structure. The training data consisted of normal-moveout-corrected common midpoint gathers fed into a U-Net neural network. The well-trained model was found to effectively attenuate the seabed multiples according to the image similarity between the prediction result and the target data, and demonstrated good applicability to field data.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.544-551
• /
• 2023

Speech enhancement used to improve the perceptual quality and intelligibility of noise speech has been studied as a method using a complex-valued spectrum that can improve both magnitude and phase in a method using a magnitude spectrum. In this paper, a study was conducted on how to apply attention mechanism to complex-valued spectrum-based speech enhancement systems to further improve the intelligibility and quality of noise speech. The attention is performed based on additive attention and allows the attention weight to be calculated in consideration of the complex-valued spectrum. In addition, the global average pooling was used to consider the importance of the feature map. Complex-valued spectrum-based speech enhancement was performed based on the Deep Complex U-Net (DCUNET) model, and additive attention was conducted based on the proposed method in the Attention U-Net model. The results of the experiments on noise speech in a living room environment showed that the proposed method is improved performance over the baseline model according to evaluation metrics such as Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short Time Object Intelligence (STOI), and consistently improved performance across various background noise environments and low Signal-to-Noise Ratio (SNR) conditions. Through this, the proposed speech enhancement system demonstrated its effectiveness in improving the intelligibility and quality of noisy speech.

• Nuclear Engineering and Technology
• /
• v.50 no.5
• /
• pp.794-800
• /
• 2018

The proliferation resistance (PR) of Th/U and Th/Pu fuels used in CANada Deuterium Uranium for the deep geological repository was assessed by combining the multiattribute utility analysis proposed by Chirayath et al., 2015 with the transport model of radionuclides in the repository and comparing with that of the used natural U fuel case. It was found that there was no significant advantage for Th/U and Th/Pu fuels from the viewpoint of the PR in the repository. It was also found that the PR values for used nuclear fuels in the repository of Th/U, Th/Pu, and natural U was comparable with those for enrichment and reprocessing facilities in the pressurized water reactor (PWR) nuclear fuel cycle. On the other hand, the PR values considering the transport of radionuclides in the repository were found to be slightly smaller than those without their transport after the used nuclear fuels started dissolving after 1,000 years.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1778-1797
• /
• 2021

Document image binarization is an important pre-processing step in document analysis and archiving. The state-of-the-art models for document image binarization are variants of encoder-decoder architectures, such as FCN (fully convolutional network) and U-Net. Despite their success, they still suffer from three limitations: (1) reduced feature map resolution due to consecutive strided pooling or convolutions, (2) multiple scales of target objects, and (3) reduced localization accuracy due to the built-in invariance of deep convolutional neural networks (DCNNs). To overcome these three challenges, we propose an improved semantic segmentation model, referred to as DP-LinkNet, which adopts the D-LinkNet architecture as its backbone, with the proposed hybrid dilated convolution (HDC) and spatial pyramid pooling (SPP) modules between the encoder and the decoder. Extensive experiments are conducted on recent document image binarization competition (DIBCO) and handwritten document image binarization competition (H-DIBCO) benchmark datasets. Results show that our proposed DP-LinkNet outperforms other state-of-the-art techniques by a large margin. Our implementation and the pre-trained models are available at https://github.com/beargolden/DP-LinkNet.

• Nuclear Engineering and Technology
• /
• v.53 no.2
• /
• pp.611-617
• /
• 2021

The mechanical properties of α-Na₃(U_0.84(2),Na_0.16(2))O₄ have been researched using the first-principles calculations combined with the quasi-harmonic Debye model. The obtained lattice parameters agree well with the published experimental data. The results of elastic constants indicate that α-Na₃(U_0.84(2),Na_0.16(2))O₄ is mechanically stable. The polycrystalline moduli are predicted. The results show that the α-Na₃(U_0.84(2),Na_0.16(2))O₄ exhibits brittleness and possesses obvious elastic anisotropy. The hardness shows that it can be considered a "soft material". Furthermore, the Debye temperature θ_D and the minimum thermal conductivity k_min are also discussed, respectively. Finally, the thermal expansion coefficient α, isobaric heat capacity C_P and isochoric heat capacity C_V are evaluated through the quasi-harmonic Debye model.

• Journal of the Korean Geotechnical Society
• /
• v.40 no.3
• /
• pp.33-39
• /
• 2024

Inspecting cracks to determine a structure's condition is crucial for accurate safety diagnosis. However, visual crack inspection methods can be subjective and are dependent on field conditions, thereby resulting in low reliability. To address this issue, this study automates the detection of concrete cracks in image data using ResNet, FPN, and the Mask R-CNN components as the backbone, neck, and head of a convolutional neural network. The performance of the proposed model is analyzed using the intersection over the union (IoU). The experimental dataset contained 1,203 images divided into training (70%), validation (20%), and testing (10%) sets. The model achieved an IoU value of 95.83% for testing, and there were no cases where the crack was not detected. These findings demonstrate that the proposed model realized highly accurate detection of concrete cracks in image data.