• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1134-1139
• /
• 2019

One of the most important applications of computer vision algorithms is the detection of threat objects in x-ray security images. However, in the practical setting, this task is complicated by two properties inherent to the dataset, namely, the problem of class imbalance and visual complexity. In our previous work, we resolved the class imbalance problem by using a GAN-based anomaly detection to balance out the bias induced by training a classification model on a non-practical dataset. In this paper, we propose a new method to alleviate the visual complexity problem by using a KNN-based automatic cropping algorithm to remove distracting and irrelevant information from the x-ray images. We use the cropped images as inputs to our current model. Empirical results show substantial improvement to our model, e.g. about 3% in the practical dataset, thus further outperforming previous approaches, which is very critical for security-based applications.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.4 no.2
• /
• pp.46-60
• /
• 2001

This study proposes the Web-based GIS system based on distributed object management and conceptualise system architecture and its methods specifications through UML(unified modeling language). By using class diagram and creating prototype based on UML and reverse engineering, our conceptual shape file model is proposed to illustrate an integrated architecture. Through system analysis and software configuration management, this study enables to not only improve pliable capabilities for problematic domains and increase abilities for analytical domains when user requirements are dynamic, but also assist effective and consistent maintenances of large software systems.

• The Transactions of the Korea Information Processing Society
• /
• v.2 no.5
• /
• pp.746-756
• /
• 1995

This paper describes the intractive visual programming environment using multi-view which shows the tools of visualization for called and the visualizations for called member-function flow in C＋＋ language. This research defines new visual symbols for class and constructs interactive visual programming environment of various views by using visual symbols. Our proposed interactive multi-view visual programming environment can represent visualization for representation of class and execution relationships between objects in the object-oriented language, which is easy to understand the structure of object-oriented program, therefore our proposed interactive visual programming environment enables easy program development, and can use of education and trainning for beginner in useful.

• The KIPS Transactions:PartD
• /
• v.11D no.2
• /
• pp.397-406
• /
• 2004

Usually, design method to use UML by Object-Oriented Modelling is used much. But, generation of Metadata that use UML is not easy by difference of expression about detailed functions that Is Involved language and this in environment that differ. In this paper that solution method use XML Metadata Interchange Format(XMI) for standardization and normalization of Pattern and Class. And, for design of Metamodel select frequency A many 4 element of use among XMI Metamodel and create Metadata. Design DB repository for created Metadata storing and add pattern and Information about each class composition and use query and did so that reusability and extension of Metadata nay be easy.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3523-3529
• /
• 1999

In this paper, we propose an improved regression testing method, which use method as the basic unit of changing. The testing method consists of three steps. We represent the relationship of classes using the notation of UML(Unified Modeling Language), find the nodes of the modified methods and affected methods by node analysis, and then select changed test cases from the original test cases. The proposed object-oriented regression testing method can reduce the number of test cases, testing time and cost through reuse of test cases.

• School Mathematics
• /
• v.16 no.3
• /
• pp.633-657
• /
• 2014

This study aims to verify the effect of the situated learning-based instruction on mathematics learning of sixth-grade elementary school students. For this purpose, this study examined the differences in mathematical learning achievement and mathematical attitude between a group participating in the situated learning-based class and a group participating in the normal instructor-led mathematics class. Moreover, this study verified the educational effect of the situated learning-based class by analyzing teacher's role in the class and students' way of participating in the class. The study results are as follows. First, the situated learning-based class positively influenced students' mathematics achievement and mathematical attitude. Second, teacher performed a role as a learning guide and facilitator. Third, other became an object to give help to or to learn from in the situated learning-based class. These situations had a positive influence on the organization of knowledge through active efforts of students for communication and problem solving which belongs to a cooperative socialization process happening in the class.

• Journal of Korea Society of Industrial Information Systems
• /
• v.16 no.5
• /
• pp.83-92
• /
• 2011

IDEF is a widely used methodology for traditional structured software development. As object-oriented softwares are widely used, an object-oriented version of IDEF, IDEF4, is developed. UML is de facto standard for object-oriented software development methods. Whereas IDEF is widely used for CALS/EC, UML is used for general object-oriented software development. Most software developers are not familiar with IDEF4 but familiar with UML. Moreover, UML has many CASE tools. So we can develop software efficiently if we convert IDEF4 model to UML model. In this paper, we transform IDEF4 models to UML models. We explain the rules and methods to convert IDEF4 model to UML model and applied the transform methods and rules to a case study.

• Journal of the Korea Society of Computer and Information
• /
• v.9 no.3
• /
• pp.1-6
• /
• 2004

there needs a new Geographic information system development Technology of the abstraction, encapsulation, modulation and hierarchy using Graphic representation of object modeling Technique. The method is based on composite object of Graphic data with the hierarchy concepts and abstraction of Graphic information in order to improve data abstraction of the graphic data file and described concept of multiple inheritance and classification that supports a wide variety of graphic class such as mesh unit, layer. segment and so on. in simple case of software development using SPICE model and object modeling techniques. this thesis suggested object representation of Graphic data which can reduce software development life cycle and the cost of software maintenance.

• Journal of Korea Spatial Information System Society
• /
• v.1 no.2 s.2
• /
• pp.127-135
• /
• 1999

Currently, many geographic information systems deal with only vector data. Therefore, handling raster data for various types of information is greatly needed. In this paper, we design and implement a raster processor which handles spatial information in a spatial object management system called Object Management system for Geospatial Application (OMEGA). We define the data structure of the raster information to be stored in the spatial object management system and implement it to a class library in order for use in making an application program. Furthermore, a query operation and related module is implemented to extract raster information. They are then imbedded in the query executer to process a query of the raster information. Simulation results are given.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.33 no.3
• /
• pp.173-179
• /
• 2015

In this paper, object-based classification of urban areas based on a combination of information from lidar and aerial images is introduced. High resolution images are frequently used in automatic classification, making use of the spectral characteristics of the features under study. However, in urban areas, pixel-based classification can be difficult since building colors differ and the shadows of buildings can obscure building segmentation. Therefore, if the boundaries of buildings can be extracted from lidar, this information could improve the accuracy of urban area classifications. In the data processing stage, lidar data and the aerial image are co-registered into the same coordinate system, and a local maxima filter is used for the building segmentation of lidar data, which are then converted into an image containing only building information. Then, multiresolution segmentation is achieved using a scale parameter, and a color and shape factor; a compactness factor and a layer weight are implemented for the classification using a class hierarchy. Results indicate that lidar can provide useful additional data when combined with high resolution images in the object-oriented hierarchical classification of urban areas.