• The Journal of the Korea Contents Association
• /
• v.19 no.4
• /
• pp.609-620
• /
• 2019

The purpose of this study is to examine the co-offending implementation process of robbery and burglary crime. To this end, interview data for research projects conducted by the Korea Institute of Criminology in 2013(Advancing Knowledge About Co-Offending - Burglary and Robbery in Korea) were used as secondary data. Using secondary data, we attempted a grounded theory approach. Based on the procedure presented by Strauss&Corbin (1990), the open coding stage was derived from 51 concepts, 22 subcategories and 8 upper categories. According to an analysis tool called "coding paradigm," the causal condition is the cause of the robbery and burglary crime. Contextual conditions are the formation of co-offending relationship and the reason for selecting co-offending. The central phenomenon is the co-offending implementation of robbery and burglary crime. Interventing conditions are conflict between co-offenders and occurrence of arrest factor. The action/interaction strategy is arrested all co-offenders. The consequence consisted of ending the co-offending relationship. Finally, the selective coding stage selected 'the development of conflict between formation and end of co-offending relationship' as the core category, and newly established the co-offending relationship of robbery and burglary crime through the process of 'formation-implementation-conflict-arrest-end'.

• Smart Media Journal
• /
• v.11 no.9
• /
• pp.9-20
• /
• 2022

Deep reinforcement learning(RL) is an end-to-end data-driven control method that is widely used in the autonomous driving domain. However, conventional RL approaches have difficulties in applying it to autonomous driving tasks due to problems such as inefficiency, instability, and uncertainty. These issues play an important role in the autonomous driving domain. Although recent studies have attempted to solve these problems, they are computationally expensive and rely on special assumptions. In this paper, we propose a new algorithm MCDT that considers inefficiency, instability, and uncertainty by introducing a method called uncertainty sequence modeling to autonomous driving domain. The sequence modeling method, which views reinforcement learning as a decision making generation problem to obtain high rewards, avoids the disadvantages of exiting studies and guarantees efficiency, stability and also considers safety by integrating uncertainty estimation techniques. The proposed method was tested in the OpenAI Gym CarRacing environment, and the experimental results show that the MCDT algorithm provides efficient, stable and safe performance compared to the existing reinforcement learning method.

• 한국방재학회:학술대회논문집
• /
• 2008.02a
• /
• pp.279-282
• /
• 2008

The vertical forces in rail fasteners at areas of bridge transitions near the embankment and on the pier will occur due to different deformations of adjoining bridges caused by the trainloads. The up-lifting forces is not large problem in the blast track because the elasticity of blast and rail pad buffs up-lifting effect. But, it is likely to be difficult to ensure the serviceability of the railway and the safety of the fastener in the end in that concrete slab track consist of rail, fastener, and track in a single body, delivering directly the up-lifting force to the fastener if the deck is bended because of the end rotation of the overhang due to the vertical load. When the up-lifting force exceeds the clamp force of the fastener clip, the rail pad is out of fastener, which makes decrease the serviceability of the railway, such as noise and vibration. Furthermore, it is possible to reduce the safety of the track as the longitudinal resistance. This study is focused on guideline suggestion to decrease up-lifting force in the fastener adjacent to the civil joint of slab track of bridge throughout the parametric analysis between the vertical spring stiffness of the fastener as the material approach, the space of fastener adjacent to bridge transition, the rigidity of the girder as the geometrical approach and up-lifting force under the train load.

• Knowledge Management Research
• /
• v.1 no.1
• /
• pp.65-80
• /
• 2000

The main purpose of this study is to answer a question that how a company can be a learning organization producing useful knowledge by applying neuro-cybernetics approach. This approach borrows its working principles from the human body systems. The current study urges that the principles can be applied to build a learning organization. System 1 to 5, the core parts of neuro-cybernetics, are explained. And it is explored that how these systems can be designed for a company to be a learning organization. Limitations of the current study are discussed at the end of the paper.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.7B
• /
• pp.697-710
• /
• 2004

Differentiated services (DiffServ) model has been prevailed as a scalable approach to provide quality of service in the Internet. However, there are difficulties in providing the guaranteed service in terms of end-to-end systems since differentiated services network considers quality of service of aggregated traffic due to the scalability and many researches have been mainly focused on per hop behavior or a single domain behavior. Furthermore quality of service may be time varying according to the network conditions. In this paper, we study dynamic class mapping mechanism to guarantee the end-to-end quality of service for multimedia traffics with the minimum network cost over differentiated services network. The proposed algorithm consists of an effective implementation of relative differentiated service model, quality of service advertising mechanism and dynamic class mapping mechanism. Finally, the experimental results are provided to show the performance of the proposed algorithm.

• Proceedings of the Korean Vacuum Society Conference
• /
• 2012.02a
• /
• pp.436-437
• /
• 2012

Double patterning technology (DPT) has been suggested as a promising candidates of the next generation lithography technology in FLASH and DRAM manufacturing in sub-40nm technology node. DPT enables to overcome the physical limitation of optical lithography, and it is expected to be continued as long as e-beam lithography takes place in manufacturing. Several different processes for DPT are currently available in practice, and they are litho-litho-etch (LLE), litho-etch-litho-etch (LELE), litho-freeze-litho-etch (LFLE), and self-aligned double patterning (SADP) [1]. The self-aligned approach is regarded as more suitable for mass production, but it requires precise control of sidewall space etch profile for the exact definition of hard mask layer. In this paper, we propose etch end point detection (EPD) in spacer etching to precisely control sidewall profile in SADP. Conventional etch EPD notify the end point after or on-set of a layer being etched is removed, but the EPD in spacer etch should land-off exactly after surface removal while the spacer is still remained. Precise control of real-time in-situ EPD may help to control the size of spacer to realize desired pattern geometry. To demonstrate the capability of spacer-etch EPD, we fabricated metal line structure on silicon dioxide layer and spacer deposition layer with silicon nitride. While blanket etch of the spacer layer takes place in inductively coupled plasma-reactive ion etching (ICP-RIE), in-situ monitoring of plasma chemistry is performed using optical emission spectroscopy (OES), and the acquired data is stored in a local computer. Through offline analysis of the acquired OES data with respect to etch gas and by-product chemistry, a representative EPD time traces signal is derived. We found that the SE-EPD is useful for precise control of spacer etching in DPT, and we are continuously developing real-time SE-EPD methodology employing cumulative sum (CUSUM) control chart [2].

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.51-62
• /
• 2021

Plant disease is one of the issues that can create losses in the production and economy of the agricultural sector. Early detection of this disease for finding solutions and treatments is still a challenge in the sustainable agriculture field. Currently, image processing techniques and machine learning methods have been applied to detect plant diseases successfully. However, the effectiveness of these methods still needs to be improved, especially in multiclass plant diseases classification. In this paper, a convolutional neural network with a batch normalization-based deep learning approach for classifying plant diseases is used to develop an automatic diagnostic assistance system for leaf diseases. The significance of using deep learning technology is to make the system be end-to-end, automatic, accurate, less expensive, and more convenient to detect plant diseases from their leaves. For evaluating the proposed model, an experiment is conducted on a public dataset contains 20654 images with 15 plant diseases. The experimental validation results on 20% of the dataset showed that the model is able to classify the 15 plant diseases labels with 96.4% testing accuracy and 0.168 testing loss. These results confirmed the applicability and effectiveness of the proposed model for the plant disease detection task.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.346-353
• /
• 2023

In this paper, we propose an innovative approach that leverages deep learning to find optimal reference points for achieving precise tooth segmentation in three-dimensional tooth point cloud data. A dataset consisting of 350 aligned maxillary and mandibular cloud data was used as input, and both end coordinates of individual teeth were used as correct answers. A two-dimensional image was created by projecting the rendered point cloud data along the Z-axis, where an image of individual teeth was created using an object detection algorithm. The proposed algorithm is designed by adding various modules to the Unet model that allow effective learning of a narrow range, and detects both end points of the tooth using the generated tooth image. In the evaluation using DSC, Euclid distance, and MAE as indicators, we achieved superior performance compared to other Unet-based models. In future research, we will develop an algorithm to find the reference point of the point cloud by back-projecting the reference point detected in the image in three dimensions, and based on this, we will develop an algorithm to divide the teeth individually in the point cloud through image processing techniques.

• Structural Engineering and Mechanics
• /
• v.66 no.5
• /
• pp.557-568
• /
• 2018

An investigation is made in the present work on the post-buckling and geometrically nonlinear behaviors of moderately thick perfect and imperfect rectangular plates made-up of functionally graded materials. Spectral collocation approach based on Legendre basis functions is developed to analyze the functionally graded plates while they are subjected to end-shortening strain. The material properties in this study are varied through the thickness according to the simple power law distribution. The fundamental equations for moderately thick rectangular plates are derived using first order shear deformation plate theory and taking into account both geometric nonlinearity and initial geometric imperfections. In the current study, the domain of interest is discretized with Legendre-Gauss-Lobatto nodes. The equilibrium equations will be obtained by discretizing the Von-Karman's equilibrium equations and also boundary conditions with finite Legendre basis functions that are substituted into the displacement fields. Due to effect of geometric nonlinearity, the final set of equilibrium equations is nonlinear and therefore the quadratic extrapolation technique is used to solve them. Since the number of equations in this approach will always be more than the number of unknown coefficients, the least squares technique will be used. Finally, the effects of boundary conditions, initial geometric imperfection and material properties are investigated and discussed to demonstrate the validity and capability of proposed method.