• IEMEK Journal of Embedded Systems and Applications
• /
• v.11 no.3
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• Journal of KIISE
• /
• v.42 no.12
• /
• pp.1590-1599
• /
• 2015

As a variety of personal medical devices appear, it is possible to acquire a large number of diverse medical contexts from the devices. There have been efforts to analyze the medical contexts via software applications. In this paper, we propose a generic model of medical analytics schemes that are used by medical experts, identify inference methods for realizing each medical analytics scheme, and present guidelines for applying the inference methods to the medical analytics schemes. Additionally, we develop a PoC inference system and analyze real medical contexts to diagnose relevant diseases so that we can validate the feasibility and effectiveness of the proposed medical analytics schemes and guidelines of applying inference methods.

• Journal of Korea Multimedia Society
• /
• v.12 no.12
• /
• pp.1787-1795
• /
• 2009

This paper describes an automation of architectural design processes and the direction between this automation and robotic system in building construction using the concept of the object-oriented design in architecture. The research starts from the premise that many computer-aided design systems are mostly aimed at serving as drawing tools which are used only after a design formal solution has already been established by the architect. If the computer is well applied to the architectural design process, many positive things such as standardization of design detail, increasing productivity and collaboration, minimizing construction costs etc. can be done. To support an early design solution in the computer-based environment, the proposed automation was developed and tested in a real building project, using the object-oriented design concept such as product model. This design automation gives various design alternatives from the early design phase to the final stage of design details, according to musical harmony. This paper shows how architectural design process can be automated and how the data of the applied architectural design can be integrated into product model environment, in relation to robotic system in building construction.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.231-237
• /
• 2015

However XML languages can logically define the type of structure with their's own grammar, it is inadequate to use them as a tool for conceptual model that represents the semantics of data and the relationships between the data in the real world. In this paper, we propose conceptual modeling techniques, called CMXML, for modeling the XML schema at the conceptual level. For this purpose, we define the model formally, and provide a way to represent the model in a graphical and text form. We also propose an mapping methodology providing transformation from CMXML to XML schema to show the feasibility of the proposed model.

• The Journal of Industrial Distribution & Business
• /
• v.9 no.10
• /
• pp.63-72
• /
• 2018

Purpose - This thesis is to develop a management plan and checklist by analyzing the prevention of accidents in advance by presenting the management plan for the major causes of railway accidents. Research design, data and methodology - In recent 5 years, we have analyzed the cases of railway accident, presented the management plan for the accident, and made a practical safety checklist focusing on the main measures according to the management plan. Results - The analysis of the cases of near-railway accidents suggests more concrete and practical safety management measures because the similar accidents are continuously occurring due to formal safety management. Conclusions - It is more valuable to apply to the adjacent construction of the railway line by creating a detailed checklist based on cases rather than the existing checklist. This study is written only as a human factor. For future real - time safety management, it is necessary to study more precisely cause analysis and safety equipment as a big data - based safety control system for more systematic safety management.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.6
• /
• pp.33-44
• /
• 2005

This study lets you know how semantic network programs called mind tools have an effect on students' learning achievements and learning motives regarded students' cognitive levels. It helps improve the education in the real situation of the classroom. It shows that the class applied by mind tools regarded transitional students' cognitive levels and motive strategies increases students' biologies-learning achievements because it improves students' concentration and confidence efficiently connected with new knowledge by using visual effects. Also, it shows that transitional students' semantic network learning is superior to students' in formal operation stage and it is effective in forming learning contents in the structural organization with students' knowledge.

• Journal of KIISE:Software and Applications
• /
• v.26 no.10
• /
• pp.1167-1167
• /
• 1999

Although spatial databases support an efficient spatial management on objects in the real world, they have a characteristic that process only spatial information valid at current time, So in case of change in the spatial domain, it is very hard to support an efficient historical management for time-varying spatial information because they delete an old value and then replace with new value that is valid at current time. To solve these problems, there are rapidly increasing of interest for spatiotemporal databases, which serve historical functions for spatial information as well as spatial management functions for an object. However most of them presented in an abstract time-varying spatial phenomenon, but have not presented a concrete policy in spatiotemporal databases. In this paper, we propose a spatiotemporal data model that supports bitemporal time concepts in three dimensional architecture. In the proposed model, not only data types and their operation for object of spatiotemporal databases have been classified, but also mathematical expressions using formal semantics for them have been given. Then, the data structures and their operations based on relational database model as well as object-oriented database model are presented.

• Knowledge Management Research
• /
• v.13 no.1
• /
• pp.13-24
• /
• 2012

Unlike the traditional belief that knowledge flows along the formal reporting procedures, recent social network research has reported the importance of informal social networks which may play a critical role as the real knowledge conduits. In fact, as a complementary approach of utilizing knowledge management systems (KMSs), many firms have focused on managing informal knowledge flow through which to acquire and transfer valuable knowledge in a fast and effective way. In a case of global companies that have newly developed foreign branches or subsidiaries, due to cultural or institutional differences and lack of understanding of knowledge management and its benefits, they often have difficulties in activating knowledge sharing in local branches. In these situations, diagnosing organizational knowledge flow through SNA can be a first step to solve the problems. Therefore, in this paper, I report on the result of case study on a foreign branch of "A" global company by identifying organizational knowledge paths. Based on the results of the diagnosis, some implications and insights for building knowledge management (KM) strategy specified for a newly developed foreign branch will also be discussed.

• Journal of the Society of Naval Architects of Korea
• /
• v.41 no.3
• /
• pp.41-48
• /
• 2004

Ship is being operated under a highly dynamic environments and many factors are related with ship's collision and those factors are interacting. So, the analysis on ship's collision causes are very important to prepare countermeasures which will ensure the safe navigation. This study analysed the ship's collision data over the past 10 years(1991-2000), which is compiled by Korea Marine Accidents Inquiry Agency. The analysis confirmed that ‘ship's collision' is occurred most frequently and the cause is closely related with human factor. The main purpose of this study is to propose risk control measures of ship's collision. For this, the structure of human factor is analysed by the questionnaire methodology. Marine experts were surveyed based on major elements that were extracted from the human factor affecting to ship's collision. FSM has been widely adopted in modeling a dynamic system which is composed of human factors. Then, the structure analysis on the causes of ship's collision are performed using FSM. This structure model could be used in understanding and verifying the procedure of real ship's collision. Furthermore it could be used as the model to prevent ship's collision and reduce marine accidents.

• Korean Institute of Interior Design Journal
• /
• no.20
• /
• pp.114-120
• /
• 1999

The study on architecture can be started with the aesthetic attitude which cognizes it as the art of the space. Architectural space as the subject of the aesthetical study, however, has been ignored such a long period though it should be centered of the whole architectural theory. Even it has not been dealt with independently but just only as a part of aesthetic or artistic field. Also it is true that academic approach to the architectural space as per the aesthetic cognition has not been done so satisfactorily. This study, therefore, aims at prescribing compositional scope from aesthetic cognition of architecture understanding the rational function, mechanic structure, and artistic beauty by man's subject standard of judgement as per the space, the special sphere of architecture. For the absolves, the architectural space in this study is not approached as the spatial art with the meaning of being included the arts general, but with the meaning of intrinsic peculiarity of architecture, based both in practicality of scientific concept and arts of the aesthetic notiov. In order words, the essence of architecture can be prescribed as the architectural realities as the functional, formal and symbolical space not simply the spatial art, and its real but aesthetic meaning can be cognized aesthetically.