• The Journal of the Acoustical Society of Korea
• /
• v.13 no.1
• /
• pp.5-13
• /
• 1994

This paper presents a study on Neural Networks for Phoneme Recognition and performs the Phoneme Recognition using TDNN (Time Delay Neural Network). Also, this paper proposes training algorithm for speech recognition using neural nets that is a proper to large scale TDNN. Because Phoneme Recognition is indispensable for continuous speech recognition, this paper uses TDNN to get accurate recognition result of phonemes. And this paper proposes new training algorithm that can converge TDNN to an optimal state regardless of the number of phonemes to be recognized. The recognition experiment was performed with new training algorithm for TDNN that combines backpropagation and Cauchy algorithm using stochastic approach. The results of the recognition experiment for three phoneme classes for two speakers show the recognition rates of $98.1\%$. And this paper yielded that the proposed algorithm is an efficient method for higher performance recognition and more reduced convergence time than TDNN.

• Journal of Navigation and Port Research
• /
• v.26 no.4
• /
• pp.407-417
• /
• 2002

Japanese oil companies have begun to set up a mutual support system to prepare for any large scale oil spillages due to the huge increase in size of tankers since 1973. In 1990, the Petroleum Association of Japan established the Oil Spill Response Department and has been conducting researches on management of oil spill combatting materials and the effective prevention of maritime oil disasters. Japan Coast Guard, in accordance with the regulations of the OPRC in 1995, formulated the national contingency plan and built a mutual-contact network among the related government institutions. Its Guard & Rescue Department. Disaster Prevention Section has been working for the maintenance of oil spill combatting materials and coordinating related work with private organizations. The Japanese government has been strengthening the maritime oil spillage management system since the Nakhodka wreck incident in 1997.

• The KIPS Transactions:PartD
• /
• v.13D no.6 s.109
• /
• pp.789-796
• /
• 2006

Context-aware is the core in ubiquitous environment of sensor network to support intelligent and contextual adaptation service. The new context information model is demanded to support context-aware applications. The model should not depend on a specified application and be shareable between applications in the same environment. Also, it should support various context representation and complex context-aware. In this paper, we define the context information according to context-aware process. Also we design the knowledge of domain as well as applications using ontologies and rules. The domain spatial ontology and application knowledge are represented using the spatial object model and the rules of expanded ontologies, respectively. The expression of abundant spatial ontology represents the context information about distance between objects and adjacent object as well as the location of the object. The proposed context information model which is able to exhibit various spatial context and recognizes complex spatial context through the existing GIS. This model shows that it can adapt to a large scale outdoor context-aware applications such as air pollution and prevention of disasters as well as various context-aware applications.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.9
• /
• pp.608-614
• /
• 2006

The popularization of high-speed networks and the innovation of high-performance hardware/servers have enlarged the role of large-scale, highly distributed IT infrastructure. Though many criteria on the assessment of IT infrastructure can be considered, the survivability assessment is treated as the most important one due to the essential role as an infrastructure. While assessing the survivability of some given IT infrastructures, we can not only choose the best one among them but also improve their survivability by modifying their structure and security policies. In this paper, we propose a DMKB-based assessment system on the survivability of IT infrastructures, where DMKB is a kind of database which provides the known vulnerabilities and defense mechanism for many system components.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.30 no.5
• /
• pp.15-23
• /
• 2002

For molecular dynamics requires high-performance computers or supercomputers to handle huge amount of computation, it is not until recent days that the application of molecular dynamics to materials fracture simulations draw some attention from many researchers. With the recent advent of high-performance computers, computation intensive methods become more tractable than ever. However, carrying out materials simulation on high-performance computers costs too much in general. In this study, a PC cluster consisting of multiple commodity PCs is established and computer simulations of materials with cracks are carried out on it via molecular dynamics technique. The effect of the number of nodes, speedup factors, and communication time between nodes are measured to verify the performance of the PC cluster. Upon using the PC cluster, materials fracture simulations with more than 50,000 molecules are carried out successfully.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.4
• /
• pp.127-136
• /
• 2007

With the construction of vast networks, Internet based services such as online games and Internet banking are steadily increasing. As dysfunctions of the trend, various threats from worms/viruses to hacking are proliferating and new types and variations of worms/viruses are emerging. In response to the problems, telecommunication carriers and the government we establishing systems to cope with infringement accidents and resultant damages. However, in case of nationwide emergencies like the 1.25 Accident, infringement may spread rapidly while analyzing what kind of infringement it is and that may result in enormous losses. Thus, the paper purposed to analyze the states of infringement accidents occurring at each network and coping methods and checklist, based on the results. and to propose strategies for controlling services in case of large scale infringement accidents.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.2938-2956
• /
• 2020

Objective image quality assessment (IQA) models have been developed by effective features to imitate the characteristics of human visual system (HVS). Actually, HVS is extremely sensitive to color degradation and complex texture changes. In this paper, we firstly reveal that many existing full reference image quality assessment (FR-IQA) methods can hardly measure the image quality with contrast and masking texture changes. To solve this problem, considering texture masking effect, we proposed a novel FR-IQA method, called Texture and Color Quality Index (TCQI). The proposed method considers both in the masking effect texture and color visual perceptual threshold, which adopts three kinds of features to reflect masking texture, color difference and structural information. Furthermore, random forest (RF) is used to address the drawbacks of existing pooling technologies. Compared with other traditional learning-based tools (support vector regression and neural network), RF can achieve the better prediction performance. Experiments conducted on five large-scale databases demonstrate that our approach is highly consistent with subjective perception, outperforms twelve the state-of-the-art IQA models in terms of prediction accuracy and keeps a moderate computational complexity. The cross database validation also validates our approach achieves the ability to maintain high robustness.

• Smart Structures and Systems
• /
• v.15 no.5
• /
• pp.1373-1392
• /
• 2015

Placing sensors at appropriate locations is an important task in the design of an efficient structural health monitoring (SHM) system for a large-scale civil structure. In this paper, a hybrid optimization algorithm called virus monkey algorithm (VMA) based on the virus theory of evolution is proposed to seek the optimal placement of sensors. Firstly, the dual-structure coding method is adopted instead of binary coding method to code the solution. Then, the VMA is designed to incorporate two populations, a monkey population and a virus population, enabling the horizontal propagation between the monkey and virus individuals and the vertical inheritance of monkey's position information from the previous to following position. Correspondingly, the monkey population in this paper is divided into the superior and inferior monkey populations, and the virus population is divided into the serious and slight virus populations. The serious virus is used to infect the inferior monkey to make it escape from the local optima, while the slight virus is adopted to infect the superior monkey to let it find a better result in the nearby area. This kind of novel virus infection operator enables the coevolution of monkey and virus populations. Finally, the effectiveness of the proposed VMA is demonstrated by designing the sensor network of the Canton Tower, the tallest TV Tower in China. Results show that innovations in the VMA proposed in this paper can improve the convergence of algorithm compared with the original monkey algorithm (MA).

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.3
• /
• pp.192-203
• /
• 2012

As a leading nation of ubiquitous technology, South Korea has been promoting u-City pilot projects throughout the country. According to 'Fundamental Construction Law of u-City,' u-City projects are classified into old-town and new-town types. However, most projects have focused only on the new-town type. Pushing forward large-scale land development projects, Korea Land and Housing Corporation (LH Co.) under Ministry of Land Transport and Maritime Affairs (MLTM) has gained a development profit out of the u-City infrastructure and then donated the infrastructure to a local government without making any plan for operations. In the process of u-City pilot projects, old-towns have been relatively ignored and various of unexpected problems have emerged. Building the u-City of an old-town is not easy due to many constraints such as huge initial investment, long validity and verification procedures, lack of useful services for citizens, lack of professional outsourcing methods for business promotion, high operating costs of the integrated control center, inadequate law related, insufficient institutional requirements and so on. This paper introduces a case study on u-City development for an old-town, Ansan City, as a private investment project. The case will help boost u-City projects for old-towns by solving their problems and providing an effective operational mechanism. As the first BTL (Build-Transfer-Lease) project for constructing u-City, 'Broadband Information Network Development Project' of Ansan City will provide a reference model of expanding u-City projects for other cities.

• 한국태양에너지학회:학술대회논문집
• /
• 2011.04a
• /
• pp.246-249
• /
• 2011

SolarPACES is an international cooperative network bringing together teams of national exports from around the world to focus on the development and marketing of concentrating solar power systems (also known as solar thermal power systems). It is one of a number of collaborative programs, called Implementing Agreements, managed under the umbrella of the International Energy Agency to help find solutions to worldwide energy problems. Technology development is at the core of the work of SolarPACES. Member countries work together on activities aimed at solving the wide range of technical problems associated with commercialization of concentrating solar technology, including large-scale system tests and the development of advanced technologies, components, instrumentation, and systems analysis techniques. In addition to technology development, market development and building of awareness of the potential of concentrating solar technologies are key elements of the SolarPACES program The Implementing Agreement specifies broad "Tasks," or thematic areas of work SolarPACES currently has three ongoing tasks, focusing on concentrating solar electric power systems (Task I), solar chemistry research (Task II), and solar technology and applications (Task III). An Operating Agent, nominated by the ExCo, is responsible for overseeing the work of each task Each task maintains a detailed program of work that defines all task activities, including their objectives, participants, plans, and budgets. In addition to technical reports of the activities and their participants, accomplishments and progress are summarized in the SolarPACES annual report. Many SolarPACES activities involve close cooperation among member countries (either through sharing of task activities or, occasionally, cost-sharing), although some cooperation is limited to sharing of information and results with other participants. In this paper, structure, works, and members of SolarPACES and Korean activies in the SolarPACES are introduced.