• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.4
• /
• pp.2124-2148
• /
• 2017

Accurate facial expression recognition (FER) requires reliable signal filtering and the effective feature extraction. Considering these requirements, this paper presents a novel approach for FER which is robust to noise. The main contributions of this work are: First, to preserve texture details in facial expression images and remove image noise, we improved the anisotropic diffusion filter by adjusting the diffusion coefficient according to two factors, namely, the gray value difference between the object and the background and the gradient magnitude of object. The improved filter can effectively distinguish facial muscle deformation and facial noise in face images. Second, to further improve robustness, we propose a new feature descriptor based on a combination of the Histogram of Oriented Gradients with the Canny operator (Canny-HOG) which can represent the precise deformation of eyes, eyebrows and lips for FER. Third, Canny-HOG's block and cell sizes are adjusted to reduce feature dimensionality and make the classifier less prone to overfitting. Our method was tested on images from the JAFFE and CK databases. Experimental results in L-O-Sam-O and L-O-Sub-O modes demonstrated the effectiveness of the proposed method. Meanwhile, the recognition rate of this method is not significantly affected in the presence of Gaussian noise and salt-and-pepper noise conditions.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.5 no.6
• /
• pp.602-612
• /
• 2010

In this paper, we propose an object-oriented modeling technique using UML(Unified Modeling Language) for accessibility of user and efficiency of facilities under Web-based integrated manufacturing management system application. For this, we first collect user requirements and related technology of integrated manufacturing system, and then design proposed system considering business flow and various essential design part(class, component, package, use case, and etc) to reduce system risk as well as communicate peacefully between developers in system redevelopments. Additionally, we develop database of manufacturing master code, check management, repair management and error management for proposed systems. Finally, we design and implement our three main modules; manufacturing check module, manufacturing repair module, manufacturing error module under Web-based environments with JSP language.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3B
• /
• pp.314-324
• /
• 2004

Recently, high-speed internet subscribers have grown continuously, and reached up to 10 millions. But existing network management that is responsible only for user access is confronted with many difficulties, since user access network(xDSL, Cable, B-WILL, and so on) has diversified and value added wired/wireless contents service has developed. In this paper propose the Agent based Inter Networking platform as object-oriented hierarchical system that can provide various service such as access QoS(Quality of Service), customized application service and security service according to user on demand. This system has divided into two parts(user agent and agent management system ＆ local and central management systems). Management system periodically receive status information such as bandwidth, download speed, delay, current service, and so on, and process them, then build a policy based on processed information. According to personal user profile that is generated by this policy, the customized service can be provided for users. And This system adopt the object-oriented modeling in case that system migration and integration, and implement a system that is robust and stable for security through hierarchical server system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.6 no.2
• /
• pp.173-186
• /
• 2000

Real-time embedded systems should accommodate many kinds of hardware platforms and resource management policies that vary depending on their operating environments and purposes. It is not an easy job to adapt a multitasking kernel to new system services and hardware platforms, as the kernel must strictly satisfy constraints on its size and performance. This paper describes the design and implementation of an object-oriented multitasking framework that can be reused for implementing microprocessor-based real-time embedded multitasking kernels, In this kernel framework, those parts that can vary depending on hardware platforms and system resource management policies are separated into the hot spots and encapsulated by abstract classes. Our framework thus can be effectively used to implement microprocessor-based real-time embedded kernels that demand high portability and adaptability.

• The KIPS Transactions:PartD
• /
• v.13D no.2 s.105
• /
• pp.241-250
• /
• 2006

Software maintenance is an important and very expensive activity in software life cycle. To estimate the maintainability cost of software, many software metrics have been proposed. This paper presents the result of an experimental study to explore the relationship between maintainability and some software metrics. LCOM, RFC, DAC, and LOC are employed as metrics and time really spent for maintenance activity has been collected. In the experimental study, we have found that for some systems, the existing metrics may not be an indicator to maintenance effort, which is not consistent with our general knowledge on the relationship between them. Specifically speaking, we recognized that there should be more empirical study on the relationship between metrics and maintainability of softwares which have been developed using recent technologies such as software architecture and design pattern.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.19 no.1
• /
• pp.71-77
• /
• 2013

Smart work has been gaining more popularity recently. Smart work means that employees perform their works anytime and anywhere as utilizing the information and communication technology. It can be divided into four categories; the mobile office, the home office, the work-at-center and the tele-cooperation. Among them, the mobile office based on tablet personal computers(PCs) or smart phones, employees can exchange information with tablet PCs or smart phones via mobile radio communication networks and portable terminals. Smart devices such as tablet PCs and smart phones help to access intranet system for requests, approvals, information search whenever employees need. This mobile office system for real-time HSE managing can contribute to improve the productivity and work efficiency in a shipyard. In this study, the main goal is to design the specialized mobile application for the HSE management system on the shipbuilding industry. The mobile application including 10 functions is designed based on ooCBD(object-oriented Component Based Development) methodology.

• Proceedings of the Korean Institute Of Construction Engineering and Management
• /
• 2008.11a
• /
• pp.645-648
• /
• 2008

Due to the rapid increase super high-rise buildings and multi-complex spaces, the space of a staged a very complex and variety of situations occur in the space of the building. The management is still based on limited information obtained by the administrator depends on the decision is made. However, the ability of human beings during a limited time, analysis limited information, and there is a limit to take the appropriate action and situation. To overcome these limitations high information technology that can be fused to take advantage of ubiquitous system is to offer. The aim of this study is on object-oriented 3D data and collected information about the status of the 3D data extraction, to exchange data between systems, the use of object-oriented 3D data, and I studied common space information of a multi-use facilities extracted from 3D CAD information to send to the GIS system.

• Journal of KIISE:Databases
• /
• v.29 no.2
• /
• pp.89-98
• /
• 2002

As XML has become an emerging standard for information exchange on the World Wide Web it has gained attention in database communities to extract information from XML seen as a database model. Recently, many researchers have addressed the problem of storing XML data and processing XML queries using traditional database engines. Here, most of them have used relational database systems. In this paper, we show that OODBSs can be another solution. Our technique generates an OODB schema from DTDs and processes XML queries, Especially, we show that the semi-structural part of XML data can be represented by the 'inheritance' and that this can be used to improve query processing.

• Journal of Information Processing Systems
• /
• v.14 no.3
• /
• pp.751-770
• /
• 2018

Web applications are indispensable in the software industry and continuously evolve either meeting a newer criteria and/or including new functionalities. However, despite assuring quality via testing, what hinders a straightforward development is the presence of defects. Several factors contribute to defects and are often minimized at high expense in terms of man-hours. Thus, detection of fault proneness in early phases of software development is important. Therefore, a fault prediction model for identifying fault-prone classes in a web application is highly desired. In this work, we compare 14 machine learning techniques to analyse the relationship between object oriented metrics and fault prediction in web applications. The study is carried out using various releases of Apache Click and Apache Rave datasets. En-route to the predictive analysis, the input basis set for each release is first optimized using filter based correlation feature selection (CFS) method. It is found that the LCOM3, WMC, NPM and DAM metrics are the most significant predictors. The statistical analysis of these metrics also finds good conformity with the CFS evaluation and affirms the role of these metrics in the defect prediction of web applications. The overall predictive ability of different fault prediction models is first ranked using Friedman technique and then statistically compared using Nemenyi post-hoc analysis. The results not only upholds the predictive capability of machine learning models for faulty classes using web applications, but also finds that ensemble algorithms are most appropriate for defect prediction in Apache datasets. Further, we also derive a consensus between the metrics selected by the CFS technique and the statistical analysis of the datasets.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.9
• /
• pp.97-104
• /
• 2021

Since 1993, Successfully localized naval combat System has made steady development on various domestic and foreign ships. On the other hand, Engineering Control System(ECS) is dependent on foreign companies. Therefore, there is a lot of interest and research in the localization of ECS in the navy defense industry. As one of various studies, a preliminary study of domestic ECS software that can be commonly applied to naval ships is in progress. This paper propose Ecs Obts Scalable Platform(EOSPA) as the standard architecture of ECS On-Board Training System(OBTS) software by applying object-oriented programming and standardization. And this introduces EOSPA's structure, function, and features of each component. Furthermore, high reusability and maintainability are expected in the development of ECS OBTS software applying EOSPA in various naval ships.