• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.21 no.4
• /
• pp.489-502
• /
• 2023

This article presents the crucial role played by the French underground research laboratory (URL) in initiating the deep geological repository project Cigéo. In January 2023, Andra finalized the license application for the initial construction of Cigéo. Depending on Government's decision, the construction of Cigéo may be authorized around 2027. Cigéo is the result of a National program, launched in 1991, aiming to safely manage high-level and intermediate level long-lived radioactive wastes. This National program is based on four principles: 1) excellent science and technical knowledge, 2) safety and security as primary goals for waste management, 3) high requirements for environment protection, 4) transparent and open-public exchanges preceding the democratic decisions and orientations by the Parliament. The research and development (R&D) activities carried out in the URL supported the design and the safety demonstration of the Cigéo project. Moreover, running the URL has provided an opportunity to gain practical experience with regard to the security of underground operations, assessment of environmental impacts, and involvement of the public in the preparation of decisions. The practices implemented have helped gradually build confidence in the Cigéo project.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.786-799
• /
• 2021

Road damage detection is important for road maintenance. With the development of deep learning, more and more road damage detection methods have been proposed, such as Fast R-CNN, Faster R-CNN, Mask R-CNN and RetinaNet. However, because shallow and deep layers cannot be extracted at the same time, the existing methods do not perform well in detecting objects with fewer samples. In addition, these methods cannot obtain a highly accurate detecting bounding box. This paper presents a Multi-level Feature Pyramids method based on M2det. Because the feature layer has multi-scale and multi-level architecture, the feature layer containing more information and obvious features can be extracted. Moreover, an attention mechanism is used to improve the accuracy of local boundary boxes in the dataset. Experimental results show that the proposed method is better than the current state-of-the-art methods.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3730-3744
• /
• 2020

This study proposes a deep learning-based evolutionary recommendation model for heterogeneous big data integration, for which collaborative filtering and a neural-network algorithm are employed. The proposed model is used to apply an individual's importance or sensory level to formulate a recommendation using the decision-making feedback. The evolutionary recommendation model is based on the Deep Neural Network (DNN), which is useful for analyzing and evaluating the feedback data among various neural-network algorithms, and the DNN is combined with collaborative filtering. The designed model is used to extract health information from data collected by the Korea National Health and Nutrition Examination Survey, and the collaborative filtering-based recommendation model was compared with the deep learning-based evolutionary recommendation model to evaluate its performance. The RMSE is used to evaluate the performance of the proposed model. According to the comparative analysis, the accuracy of the deep learning-based evolutionary recommendation model is superior to that of the collaborative filtering-based recommendation model.

• Electronics and Telecommunications Trends
• /
• v.33 no.4
• /
• pp.43-53
• /
• 2018

As face recognition (FR) has been well studied over the past decades, FR technology has been applied to many real-world applications such as surveillance and biometric systems. However, in the real-world scenarios, FR performances have been known to be significantly degraded owing to variations in face images, such as the pose, illumination, and low-resolution. Recently, visual intelligence technology has been rapidly growing owing to advances in deep learning, which has also improved the FR performance. Furthermore, the FR performance based on deep learning has been reported to surpass the performance level of human perception. In this article, we discuss deep-learning based high-performance FR technologies in terms of representative deep-learning based FR architectures and recent FR algorithms robust to face image variations (i.e., pose-robust FR, illumination-robust FR, and video FR). In addition, we investigate big face image datasets widely adopted for performance evaluations of the most recent deep-learning based FR algorithms.

• ETRI Journal
• /
• v.38 no.6
• /
• pp.1207-1217
• /
• 2016

The general method of machine learning has encountered disadvantages in terms of the significant amount of time and effort required for feature extraction and engineering in natural language processing. However, in recent years, these disadvantages have been solved using deep learning. In this paper, we propose a mention pair (MP) model using deep learning, and a system that combines both rule-based and deep learning-based systems using a guided MP as a coreference resolution, which is an information extraction technique. Our experiment results confirm that the proposed deep-learning based coreference resolution system achieves a better level of performance than rule- and statistics-based systems applied separately

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.14 no.2
• /
• pp.179-188
• /
• 2016

Spent fuels from nuclear power plants, as well as high-level radioactive waste from the recycling of spent fuels, should be safely isolated from human environment for an extremely long time. Recently, meaningful studies on the development of deep borehole radioactive waste disposal system in 3-5 km depth have been carried out in USA and some countries in Europe, due to great advance in deep borehole drilling technology. In this paper, domestic deep geoenvironmental characteristics are preliminarily investigated to analyze the applicability of deep borehole disposal technology in Korea. To do this, state-of-the art technologies in USA and some countries in Europe are reviewed, and geological and geothermal data from the deep boreholes for geothermal usage are analyzed. Based on the results on the crystalline rock depth, the geothermal gradient and the spent fuel types generated in Korea, a preliminary deep borehole concept including disposal canister and sealing system, is suggested.

• Journal of Nuclear Fuel Cycle and Waste Technology(JNFCWT)
• /
• v.17 no.3
• /
• pp.355-362
• /
• 2019

This technical note introduces a newly-proposed concept of deep horizontal drillhole disposal of spent nuclear fuel, and considers how it can be applied in the Korean environment. This disposal concept, in which high-level radioactive waste is disposed in deep horizontal drillholes installed with directional drilling technique, is expected to have great advantages over the existing deep mined repository concept in economics and safety. Since this concept is still at the idea level, however, it is necessary for worldwide expert groups to demonstrate its safety and performance. In addition, the development of guidelines by the regulatory body should be supported. The Korean circumstances, which include a narrow territory and a high population density, as well as the amount of spent nuclear fuel, make the NIMBY (Not In My Back Yard) phenomenon very strong and the siting conditions difficult. Under these conditions, if the disposal section of deep horizontal drillhole concept can be located at the continental shelf, with a stable environment, rather than in a coastal land area, it is expected to alleviate the psychological anxiety of the local community and stakeholders. Moreover, even when constructing a centralized deep mined repository in the future, it is necessary to consider locating the repository in the continental shelf.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Korean Journal of Radiology
• /
• v.21 no.7
• /
• pp.891-899
• /
• 2020

Objective: To assess the diagnostic performance of a deep learning-based algorithm for automated detection of acute and chronic rib fractures on whole-body trauma CT. Materials and Methods: We retrospectively identified all whole-body trauma CT scans referred from the emergency department of our hospital from January to December 2018 (n = 511). Scans were categorized as positive (n = 159) or negative (n = 352) for rib fractures according to the clinically approved written CT reports, which served as the index test. The bone kernel series (1.5-mm slice thickness) served as an input for a detection prototype algorithm trained to detect both acute and chronic rib fractures based on a deep convolutional neural network. It had previously been trained on an independent sample from eight other institutions (n = 11455). Results: All CTs except one were successfully processed (510/511). The algorithm achieved a sensitivity of 87.4% and specificity of 91.5% on a per-examination level [per CT scan: rib fracture(s): yes/no]. There were 0.16 false-positives per examination (= 81/510). On a per-finding level, there were 587 true-positive findings (sensitivity: 65.7%) and 307 false-negatives. Furthermore, 97 true rib fractures were detected that were not mentioned in the written CT reports. A major factor associated with correct detection was displacement. Conclusion: We found good performance of a deep learning-based prototype algorithm detecting rib fractures on trauma CT on a per-examination level at a low rate of false-positives per case. A potential area for clinical application is its use as a screening tool to avoid false-negative radiology reports.

• Journal of the Korean Society of Industry Convergence
• /
• v.8 no.3
• /
• pp.161-168
• /
• 2005

This study is analysis for adjacent structures and ground movement by deep excavation work. Underground Inclinometer has shown that deformation of increment is minor within to allowable limit. According to the measurements result of slope and crack for adjacent structures, a detached house showed bigger than hospital structure to deformation of increment. Variation of underground water level didn't effect so much to ground and adjacent structures movement because underground water flows in rock and didn't give the water press to propped walls. Measurement data of strut variation is within tolerance limit. Because excavation site's wall was strengthened suitably. This study will contribute in establishment of measurement standard and information-oriented construction during deep excavation in multi-layered ground including rock masses.