• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 춘계 학술발표회
• /
• pp.791-800
• /
• 2010

This paper presents the construction status and the conceptual designs of midium and high level radioactive waste disposal facilities from all around world. For the midium radioactive waste, a shallow disposal using trench or a deep depth disposal are adopted. However, these are rather focusing on the social and cultural point of view than the technical. Meanwhile, the high level radioactive waste is basically disposed in the deep underground. The corresponding ground conditions are usually dense and composed of sedimentary and crystalline rocks mainly with low permeability. A barrier system is made of canister which consists of copper, titanium, and tin. The inner and outer side of the canister are composed of different materials respectively.

• 스마트미디어저널
• /
• 제9권3호
• /
• pp.9-17
• /
• 2020

Hippocampus is a complex brain structure embedded deep into the temporal lobe. Studies have shown that this structure gets affected by neurological and psychiatric disorders and it is a significant landmark for diagnosing neurodegenerative diseases. Hippocampus features play very significant roles in region-of-interest based analysis for disease diagnosis and prognosis. In this study, we have attempted to learn the embeddings of this important biomarker. As conventional metric learning methods for feature embedding is known to lacking in capturing semantic similarity among the data under study, we have trained deep Siamese convolutional neural network for learning metric of the hippocampus. We have exploited Gwangju Alzheimer's and Related Dementia cohort data set in our study. The input to the network was pairs of three-view patches (TVPs) of size 32 × 32 × 3. The positive samples were taken from the vicinity of a specified landmark for the hippocampus and negative samples were taken from random locations of the brain excluding hippocampi regions. We have achieved 98.72% accuracy in verifying hippocampus TVPs.

• 한국수학교육학회지시리즈D:수학교육연구
• /
• 제12권3호
• /
• pp.215-233
• /
• 2008

Deep comprehension of basic mathematical notions and concepts is a basic condition of a successful teaching. Some elements of algebraic thinking belong to the elementary school mathematics. The question "What stays the same and what changes?" link arithmetic problems with algebraic conception of variable. We have studied beliefs and comprehensions of future elementary school mathematics teachers on early algebra. Pre-service teachers from three academic pedagogical colleges deal with mathematical problems from the pre-algebra point of view, with the emphasis on changes and invariants. The idea is that the intensive use of non-formal algebra may help learners to construct a better understanding of fundamental ideas of arithmetic on the strong basis of algebraic thinking. In this article the study concerning arithmetic series is described. Considerable number of pre-service teachers moved from formulas to deep comprehension of the subject. Additionally, there are indications of ability to apply the conception of change and invariance in other mathematical and didactical contexts.

• 센서학회지
• /
• 제29권6호
• /
• pp.433-439
• /
• 2020

Recently, the need for IoT-based intelligent systems is increasing in various fields. In this study, we implemented the system that automatically measures the sugar content of fruits without damage to fruit's marketability using near-infrared radiation and machine learning. The spectrums were measured several times by passing a broadband near-infrared light through a fruit, and the average value for them was used as the input raw data of the machine-learned DNN(Deep Neural Network). Using this system, he sugar content value of fruits could be predicted within 5 s, and the prediction accuracy was about 93.86%. The proposed non-destructive sugar content measurement system can predict a relatively accurate sugar content value within a short period of time, so it is considered to have sufficient potential for practical use.

• 한국산업융합학회 논문집
• /
• 제25권4_2호
• /
• pp.573-586
• /
• 2022

Corrosion can cause dangerous and expensive damage and failures of ship hulls and equipment. Therefore, it is necessary to maintain the vessel by periodic corrosion inspections. During visual inspection, many corrosion locations are inaccessible for many reasons, especially safety's point of view. Including subjective decisions of inspectors is one of the issues of visual inspection. Automation of visual inspection is tried by many pieces of research. In this study, we propose image preprocessing methods by image patch segmentation and thresholding. YOLOv5 was used as an object detection model after the image preprocessing. Finally, it was evaluated that corrosion detection performance using the proposed method was improved in terms of mean average precision.

• 로봇학회논문지
• /
• 제12권3호
• /
• pp.313-321
• /
• 2017

One of the most frequently performed tasks in human-robot interaction (HRI), intelligent vehicles, and security systems is face related applications such as face recognition, facial expression recognition, driver state monitoring, and gaze estimation. In these applications, accurate head pose estimation is an important issue. However, conventional methods have been lacking in accuracy, robustness or processing speed in practical use. In this paper, we propose a novel method for estimating head pose with a monocular camera. The proposed algorithm is based on a deep neural network for multi-task learning using a small grayscale image. This network jointly detects multi-view faces and estimates head pose in hard environmental conditions such as illumination change and large pose change. The proposed framework quantitatively and qualitatively outperforms the state-of-the-art method with an average head pose mean error of less than $4.5^{\circ}$ in real-time.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2008년도 춘계 학술발표회 초청강연 및 논문집
• /
• pp.1216-1223
• /
• 2008

Displacement control of earth retaining wall is recognized as the most important item for insuring the stability of ground in urban deep excavation site near by major structure such as subway etc. The field monitoring system is classified by two types as manual system and automatic system. The application case of latter type of field monitoring is increased because real time measurement is possible in automatic system and that is correspondent with the recent constructional trend. Though the automatic monitoring system is more useful and advanced than manual monitoring system, accuracy of the system is not verified sufficiently. It was examined that the reliance of automatic monitoring system in this paper through the comparison of monitoring result obtained three urban excavation site in which the each type of monitoring system was executed concurrently. Result of the examination is that the two types of monitoring system is generally alike in view of monitoring result, so the engineering reliance of automatic system was confirmed in case site. This task was researched in restricted case site, it is expected more precise analysis from security of more data monitored and progressive study.

• 한국멀티미디어학회논문지
• /
• 제24권7호
• /
• pp.890-902
• /
• 2021

Although the object detection accuracy with still images has been significantly improved with the advance of deep learning techniques, the object detection problem with video data remains as a challenging problem due to the real-time requirement and accuracy drop with occlusion. In this research, we propose a method in pig detection for video monitoring environment. First, we determine a motion, from a video data obtained from a tilted-down-view camera, based on the average size of each pig at each location with the training data, and extract key frames based on the motion information. For each key frame, we then apply YOLO, which is known to have a superior trade-off between accuracy and execution speed among many deep learning-based object detectors, in order to get pig's bounding boxes. Finally, we merge the bounding boxes between consecutive key frames in order to reduce false positive and negative cases. Based on the experiment results with a video data set obtained from a pig farm, we confirmed that the pigs could be detected with an accuracy of 97% at a processing speed of 37fps.

• 한국측량학회지
• /
• 제37권2호
• /
• pp.45-53
• /
• 2019

RGB-D SLAM (Simultaneous Localization and Mapping) refers to the technology of using deep camera as a visual sensor for SLAM. In view of the disadvantages of high cost and indefinite scale in the construction of maps for laser sensors and traditional single and binocular cameras, a method for creating three-dimensional map of indoor environment with deep environment data combined with RGB-D SLAM scheme is studied. The method uses a mobile robot system equipped with a consumer-grade RGB-D sensor (Kinect) to acquire depth data, and then creates indoor three-dimensional point cloud maps in real time through key technologies such as positioning point generation, closed-loop detection, and map construction. The actual field experiment results show that the average error of the point cloud map created by the algorithm is 0.0045m, which ensures the stability of the construction using deep data and can accurately create real-time three-dimensional maps of indoor unknown environment.

• 천문학회보
• /
• 제44권1호
• /
• pp.63.2-63.2
• /
• 2019

Eight hundred thousand asteroids in the solar system have been identified so far under extensive sky surveys. Kilometer to sub-km sized asteroids, however, are still waiting for discovery, and their size and orbital distribution will provide a better understanding of the collisional and dynamical evolution of the solar system. In order to study the number of asteroids which is detectable with 1.6 m telescope and their orbital distribution, we conducted a small observation campaign as a part of Deep Ecliptic Patrol of the Southern Sky (DEEP-South) project, which is an asteroid survey in the southern hemisphere with Korea Microlensing Telescope Network (KMTNet). We observed the ecliptic plane near opposition ($2^{\circ}{\times}2^{\circ}$ field of view centering on ${\alpha}=22h40m31s$, ${\delta}=-08^{\circ}22^{\prime}58^{{\prime}{\prime}}$) in August 2018, and identified 464 moving objects by visual inspection. As a result, 266 of 464 moving objects turn out to be previously unknown asteroids, and their signal to noise ratio is below two on numerous occasions. Most of the newly detected objects are main belt asteroids (MBAs), while three Hildas, one Jupiter trojan, and two Hungarias are also identified. In this meeting, we report the differences in the orbital distributions between the previously known asteroids and newly discovered ones using statistical methods. We also talk about the observational bias of this survey and suggest future works.