• Journal of Internet Computing and Services
• /
• v.20 no.3
• /
• pp.33-41
• /
• 2019

In this paper, we propose a method to learn the redesigned class with background and object for semantic segmentation of indoor scene image. Semantic image segmentation is a technique that divides meaningful parts of an image, such as walls and beds, into pixels. Previous work of semantic image segmentation has proposed methods of learning various object classes of images through neural networks, and it has been pointed out that there is insufficient accuracy compared to long learning time. However, in the problem of separating objects and backgrounds, there is no need to learn various object classes. So we concentrate on separating objects and backgrounds, and propose method to learn after class simplification. The accuracy of the proposed learning method is about 5 ~ 12% higher than the existing methods. In addition, the learning time is reduced by about 14 ~ 60 minutes when the class is configured differently In the same environment, and it shows that it is possible to efficiently learn about the problem of separating the object and the background.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.1
• /
• pp.449-459
• /
• 2014

The proposed 2+1 view integrated metamodel defined formerly with a graphical class model can not be guaranteed the syntactic clarity and accuracy precisely for the metamodel due to the informal specification. This paper specifies the syntactic semantics formally for the 2+1 view integrated metamodel using Z and Object-Z and checks the accuracy of the metamodel with Z/Eves tool. The formal specification is expressed in Z and Object-Z schema separately for syntax and statics semantics of the 2+1 view integrated metamodel, which applying the converting rule between class model and Z/Object-Z. The accuracy of the Z specification for the metamodel is verified using Z/Eves tool, which can check the syntax, type, and domain of the Z specification. The transformation specification and checking of the 2+1 view integrated metamodel can help establish more accurate the syntactic semantics of its construct and check the accuracy of the metamodel.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.10
• /
• pp.2567-2574
• /
• 1998

Many software engineering tools and techniques rely on fraphic representations of software, such as control flow graphs, program dependene graphs, or system dependence graphs. Existing graphic representations for object-oriented programs are compkicated, reduplicated. We thus propose a new graphic representation for object-oriented programs. Object-oriented Program Dependency Graph (OPDG). An OPDG consists of class dependence graph, class hierarchy graph and procedure dependence graph. Other features of OPDG are (1) the representation is compact; (2) the representation is easy to extend for the incremental development of a program; and (3) the repreesentation can be extended to provide dynamic information.

• The Journal of Society for e-Business Studies
• /
• v.7 no.1
• /
• pp.153-166
• /
• 2002

Nowadays an information exchange on Bn such as B2B electronic commerce is spreading. Therefore the systematic and stable management mechanism for storing the exchanged information is needed. For this goal there are many research activities for connection between XML application and relational database. But because XML data have hierarchical structures and relational database can store only flat-structured data, we need to store XML data in object-relational database that support hierarchical structure. Accordingly the modeling methodology for storing XML data in object-relational database is needed. In order to build good quality application systems, modeling is an important first step. In 1997, the OMG adopted the UML as its standard modeling language. Since industry has warmly embraced UML its popularity should become more important in the future. So a design methodology based on UML is need to develop efficiently XML applications. In this paper, we propose a unified design methodology for In applications based on object-relational database using In. To this goal, first we introduce a XML modeling methodology to design W3C XML schema using UML and second we propose data modeling methodology for object-relational database schema to store efficiently XML data in object-relational databases.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 1992.10a
• /
• pp.105-111
• /
• 1992

A computer program for matrix structural analysis by object-oriented programming technique using $C^{++}$ language has been developed. Object, class, method and inheritance which are used in object-oriented programming are illustrated using a graphical representation. The matrix operations and the structural analysis by matrix displacement method were satisfactorily performed by the proposed program. Numerical tests demonstrate that this proposed program can be widely used for the matrix structural analysis for personal computers.s.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1036-1046
• /
• 2005

Cohesion refers to the degree of the relatedness of the members in a class and it is widely accepted that the higher the cohesion of a module is, the easier the module to understand and maintain. Recently, several cohesion measures have been proposed to measure the cohesiveness of classes in an object-oriented program. In this paper, we propose an approach to improving the existing cohesion measures by considering the impact of write dependencies between class members. We have developed a cohesion measurement tool for supporting our approach and describe a case study performed with a C++ class library.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.8
• /
• pp.1117-1123
• /
• 2021

Object recognition is to identify the location and class of a specific object by analyzing the given image when a specific image is input. One of the fields in which object recognition technology is actively applied in recent years is autonomous vehicles, and this paper describes the trend of image-based object recognition artificial intelligence technology in autonomous vehicles. The image-based object detection algorithm has recently been narrowed down to two methods (a single-step detection method and a two-step detection method), and we will analyze and organize them around this. The advantages and disadvantages of the two detection methods are analyzed and presented, and the YOLO/SSD algorithm belonging to the single-step detection method and the R-CNN/Faster R-CNN algorithm belonging to the two-step detection method are analyzed and described. This will allow the algorithms suitable for each object recognition application required for autonomous driving to be selectively selected and R&D.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.7
• /
• pp.4290-4300
• /
• 2014

The previous HL7 interface should be developed as a separate package or conversion module for each version to process HL7 messages from different versions. This study designed and developed an HL7 parser compatible among different versions based on the requirements of compatibility defined in HL7 V2.5. According to the structure of the parser, the inheritance concept in object-oriented programming was adopted so that the class object of the HL7 message from the lower version could be inherited to the class object of the upper version. Therefore, every version's HL7 messages could be processed using only the upper class' object regardless of the version. To evaluate the compatibility of the developed parser, 700 data sets about inpatients with rheumatoid arthritis were used. The 700 cases underwent the compatibility test successfully. In the near future, further research on the Inter-compatibility HL7 parser is planned.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1899-1911
• /
• 2018

In this work, we propose a concurrency control scheme in object-oriented database (OODB). Since an OODB provides complex modeling power than the conventional relational databases, a concurrency control technique in OODB is also rather complicated and has influence on the overall performance. Thus, it is very important to develop a concurrency control technique with less overhead. The proposed scheme deals with class hierarchy that is a key concept in OODBs. The proposed scheme is developed on implicit locking scheme. Also, the proposed scheme is designed using data access frequency in order to reduce locking overhead than implicit locking. It means that, if access frequency information is not available, the proposed scheme works just like the existing implicit locking, In our work, the correctness of the proposed scheme is proved. The performance is analyzed depending on access types. Also, it is proved that our scheme performs works much better than the implicit locking does.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.32 no.1
• /
• pp.62-69
• /
• 2008

A post-processing program based on the OOP(Object-Oriented Programming) concept has been developed for flow visualization of the flow analysis code(PowerCFD) using unstructured cell-centered method. User-friendly GUI(GTaphic User Interface) has been built on the base of MFC(Microsoft Foundation Class). The program is organized as modules by classes including those based on VTK(Visualization ToolKit)-library, and these classes are made to function through inheritance and cooperation which is an important and valuable OOP concept. The major functions of this post-processor program are introduced and demonstrated, which include mesh plot, contour plot, vector plot, surface plots, cut plot, clip plot, xy-plot and streamline plot as well as view manipulation (translation, rotation, scaling etc).