• Proceedings of the Korea Water Resources Association Conference
• /
• 2021.06a
• /
• pp.136-136
• /
• 2021

In this study, a deep convolutional neural network (DCNN) model is proposed for short-term precipitation forecasting using weather radar-based images. The DCNN model is a combination of convolutional neural networks, autoencoder neural networks, and U-net architecture. The weather radar-based image data used here are retrieved from competition for rainfall forecasting in Korea (AI Contest for Rainfall Prediction of Hydroelectric Dam Using Public Data), organized by Dacon under the sponsorship of the Korean Water Resources Association in October 2020. This data is collected from rainy events during the rainy season (April - October) from 2010 to 2017. These images have undergone a preprocessing step to convert from weather radar data to grayscale image data before they are exploited for the competition. Accordingly, each of these gray images covers a spatial dimension of 120×120 pixels and has a corresponding temporal resolution of 10 minutes. Here, each pixel corresponds to a grid of size 4km×4km. The DCNN model is designed in this study to provide 10-minute predictive images in advance. Then, precipitation information can be obtained from these forecast images through empirical conversion formulas. Model performance is assessed by comparing the Score index, which is defined based on the ratio of MAE (mean absolute error) to CSI (critical success index) values. The competition results have demonstrated the impressive performance of the DCNN model, where the Score value is 0.530 compared to the best value from the competition of 0.500, ranking 16^th out of 463 participating teams. This study's findings exhibit the potential of applying the DCNN model to short-term rainfall prediction using weather radar-based images. As a result, this model can be applied to other areas with different spatiotemporal resolutions.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.652-654
• /
• 2021

Objectives : The purpose of this study is to investigate the effectiveness of McKenzie Exercise of cervical part Method : A case-controlled clinical trial was searched for the effect of McKenzie Exercise on the cervical part. From 2015 to June 2021, 8 studies were selected from the RISS database published in Korea. The selected studies included an experimental group with McKenzie Exercise and a control group with general physical therapy and stretching Results : McKenzie Exercise, ROM, muscle activion, pain, posture were improved. Conclusion : This study summarizes the results of applying McKenzie Exercise of cervical part. This study suggests for cervical function who wants to intervene in McKenzie Exercise of cervical part.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.30 no.5D
• /
• pp.513-522
• /
• 2010

Underground construction for traffic networks, complexes, and storage facilities has risen as an effective land use plan for dealing with emerging problems such as overcrowded urban cities and traffic jams. This paper performed an economic feasibility analysis of the development of the integrated field management system which provides field workers and managers with 3D-based location tracking and clear communication during underground construction works. To conduct the analysis, processes and problems of field management for underground construction were analyzed and deduction in accidents and field management costs and productivity improvement were estimated as expected benefits. Based on computed benefits and costs, an economic analysis was conducted using Benefit/Cost ratio(B/C), Net Present Value(NPV), and Internal Rate of Return(IRR) and then sensitivity analysis was performed to cope with the uncertainty of assumed variables.

• Journal of English Language & Literature
• /
• v.56 no.1
• /
• pp.25-45
• /
• 2010

While environmental ethics, a relatively new field of philosophy, has gained its practical power in the contemporary world, the ethics of ecological poetry has not been studied well and the relationship between poetry and ethics has also been troubled for a long time. How can it be probed, interrogated, and constructed in ecological criticism? Attempting to steer some critical focus to the topic of ethics and poetic language, this essay is to elucidate these questions within the ecological traits of Mary Oliver's poems. In the process of revisiting Oliver's poems, this essay tries to rescue the poet Oliver, one of the most gifted poets in contemporary American poetic landscape, but a long-neglected one, and questions of ethics which have been evaded for a long time in ecological criticism. Oliver's ecological imagination at once invites readers to become other in the outer world in a most spontaneous way and re-questions the fundamental distance between the self and the other in the process of becoming other. Challenging the humanistic view of nature, she opens the various layers of becoming other: from the possible state of perfect merging to the sad recognition of the impossibility of merging, from the happy moment of rebirth beyond death, to the conflicting moment of being-together. In the different cycles and levels of becoming other, Oliver's poetry completes the poetics of relation in the components of 'self-in-relation.' In those different layers of relations, the ethics of ecological poetry is newly explored rather than residing in the safe net of goodness or sympathy between the self and the other, or the stark division between the two. Oliver's witty, sensitive, sometimes sad eyes toward others, therefore, entice readers to move from the established view of nature to the extraordinary moment of encountering it, thus accomplishing the ethics of beings, not just of ecological poetry.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.6
• /
• pp.267-275
• /
• 2023

This paper presents the development of specialized software for annotating volume-of-interest on ¹⁸F-FDG PET/CT images with the goal of facilitating the studies and diagnosis of head and neck cancer (HNC). To achieve an efficient annotation process, we employed the SE-Norm-Residual Layer-based U-Net model. This model exhibited outstanding proficiency to segment cancerous regions within ¹⁸F-FDG PET/CT scans of HNC cases. Manual annotation function was also integrated, allowing researchers and clinicians to validate and refine annotations based on dataset characteristics. Workspace has a display with fusion of both PET and CT images, providing enhance user convenience through simultaneous visualization. The performance of deeplearning model was validated using a Hecktor 2021 dataset, and subsequently developed semi-automatic annotation functionalities. We began by performing image preprocessing including resampling, normalization, and co-registration, followed by an evaluation of the deep learning model performance. This model was integrated into the software, serving as an initial automatic segmentation step. Users can manually refine pre-segmented regions to correct false positives and false negatives. Annotation images are subsequently saved along with their corresponding ¹⁸F-FDG PET/CT fusion images, enabling their application across various domains. In this study, we developed a semi-automatic annotation software designed for efficiently generating annotated lesion images, with applications in HNC research and diagnosis. The findings indicated that this software surpasses conventional tools, particularly in the context of HNC-specific annotation with ¹⁸F-FDG PET/CT data. Consequently, developed software offers a robust solution for producing annotated datasets, driving advances in the studies and diagnosis of HNC.

• Journal of Biomedical Engineering Research
• /
• v.45 no.2
• /
• pp.90-94
• /
• 2024

Diagnosing wounds presents a significant challenge in clinical settings due to its complexity and the subjective assessments by clinicians. Wound deep learning algorithms quantitatively assess wounds, overcoming these challenges. However, a limitation in existing research is reliance on specific datasets. To address this limitation, we created a comprehensive dataset by combining open dataset with self-produced dataset to enhance clinical applicability. In the annotation process, machine learning based on Gradient Vector Flow (GVF) was utilized to improve objectivity and efficiency over time. Furthermore, the deep learning model was equipped U-net with residual blocks. Significant improvements were observed using the input dataset with images cropped to contain only the wound region of interest (ROI), as opposed to original sized dataset. As a result, the Dice score remarkably increased from 0.80 using the original dataset to 0.89 using the wound ROI crop dataset. This study highlights the need for diverse research using comprehensive datasets. In future study, we aim to further enhance and diversify our dataset to encompass different environments and ethnicities.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.34-41
• /
• 2024

This work presents experimental data and modelling of the release of Mo from high-burnup spent nuclear fuel (63 MWd/kgU) at two different pH values, 8.4 and 13.2 in air. The release of Mo from SF to the solution is around two orders of magnitude higher at pH = 13.2 than at pH = 8.4. The high Mo release at high pH would indicate that Mo would not be congruently released with uranium and would have an important contribution to the Instant Release Fraction, with a value of 5.3%. Parallel experiments with pure non irradiated Mo(s) and XPS determinations indicated that the faster dissolution at pH = 13.2 could be the consequence of the higher releases from metallic Mo in the fuel through a surface complexation mechanism promoted by the OH^- and the oxidation of the metal to Mo(VI) via the formation of intermediate Mo(IV) and Mo(V) species.

• International Journal of Computer Science & Network Security
• /
• v.23 no.12
• /
• pp.151-160
• /
• 2023

Breast cancer is the most dangerous and deadly form of cancer. Initial detection of breast cancer can significantly improve treatment effectiveness. The second most common cancer among Indian women in rural areas. Early detection of symptoms and signs is the most important technique to effectively treat breast cancer, as it enhances the odds of receiving an earlier, more specialist care. As a result, it has the possible to significantly improve survival odds by delaying or entirely eliminating cancer. Mammography is a high-resolution radiography technique that is an important factor in avoiding and diagnosing cancer at an early stage. Automatic segmentation of the breast part using Mammography pictures can help reduce the area available for cancer search while also saving time and effort compared to manual segmentation. Autoencoder-like convolutional and deconvolutional neural networks (CN-DCNN) were utilised in previous studies to automatically segment the breast area in Mammography pictures. We present Automatic SegmenAN, a unique end-to-end adversarial neural network for the job of medical image segmentation, in this paper. Because image segmentation necessitates extensive, pixel-level labelling, a standard GAN's discriminator's single scalar real/fake output may be inefficient in providing steady and appropriate gradient feedback to the networks. Instead of utilising a fully convolutional neural network as the segmentor, we suggested a new adversarial critic network with a multi-scale L1 loss function to force the critic and segmentor to learn both global and local attributes that collect long- and short-range spatial relations among pixels. We demonstrate that an Automatic SegmenAN perspective is more up to date and reliable for segmentation tasks than the state-of-the-art U-net segmentation technique.

• Nuclear Engineering and Technology
• /
• v.56 no.7
• /
• pp.2584-2594
• /
• 2024

A novel approach to incorporating oxide formers into ferritic ODS production has been developed using the co-precipitation technique. This method enables the tailored design of complex nano-oxides, integrated during Mechanical Alloying (MA) and precipitated during Spark Plasma Sintering (SPS) consolidation. Findings illustrate that co-precipitation effectively produces nano-powders with customised compositions, enriching Y, Ti, and Zr in the ferritic grade to condition subsequent oxide precipitation. While the addition of Y-Ti-Zr-O nano-oxides did not prevent the formation of Y-Al-O and Al-containing nano-oxides, these were refined thanks to the presence of well-dispersed Zr. Additionally, the Spark Plasma Sintering (SPS) parameters were optimised to tailor the bimodal grain size distribution of the ODS steels, aiming for favourable strength-to-ductility ratios. Comprehensive microstructural analyses were performed using SEM, EDS, EBSD, and TEM techniques, alongside mechanical assessments involving microtensile tests conducted at room temperature and small punch tests carried out at room temperature, 300 ℃, and 500 ℃. The outcomes yielded promising findings, showcasing similar or better performance with conventionally manufactured ODS steels. This reinforces the effectiveness and success of this innovative approach.

• Nuclear Engineering and Technology
• /
• v.56 no.7
• /
• pp.2842-2849
• /
• 2024

The amorphous glasses containing PbO, ZnO, MgO, and B₂O₃ have been fabricated using the melt quenching technique. The structural properties have been analysed using the Fourier-transform infrared (FTIR) and Raman spectroscopy. Derivative of Absorption Spectra Fitting (DASF) method have been used to estimate the band gap energy from the UV-Vis absorption data which decreases from 3.02 eV to 2.66 eV with increasing the concentration of the PbO.The four glass samples 0.284 and 0.826 MeV showed unique variations in terms of gamma attenuation ability. LZMB4 glass sample proved to be the mist effective in terms of shielding of gamma radiation as it requires little distance compared to LZMB3, LZMB2 and LZMB1 to attenuate. RPE revealed a raise with increase in the thickness of the material and reduces as the energy raises. TF is superior in LZMB1 compared to LZMB2, LZMB3 and LZMB4, confirming that, LZMB4 will attenuate better. The Z_Eff of the materials was seen falling as the energy increases, confirming that the linear attenuation coefficient of the glass materials decreases when the energy is increased. The results confirmed that, glass material LZMB4 is the best option especially for gamma radiation shielding applications compared to LZMB3, followed by LZMB2, then LZMB1.