• Journal of Institute of Control, Robotics and Systems
• /
• 제10권12호
• /
• pp.1295-1304
• /
• 2004

In this paper, the Bayesian recurrent neural network is proposed to predict time series data. A neural network predictor requests proper learning strategy to adjust the network weights, and one needs to prepare for non-linear and non-stationary evolution of network weights. The Bayesian neural network in this paper estimates not the single set of weights but the probability distributions of weights. In other words, the weights vector is set as a state vector of state space method, and its probability distributions are estimated in accordance with the particle filtering process. This approach makes it possible to obtain more exact estimation of the weights. In the aspect of network architecture, it is known that the recurrent feedback structure is superior to the feedforward structure for the problem of time series prediction. Therefore, the recurrent neural network with Bayesian inference, what we call Bayesian recurrent neural network (BRNN), is expected to show higher performance than the normal neural network. To verify the proposed method, the time series data are numerically generated and various kinds of neural network predictor are applied on it in order to be compared. As a result, feedback structure and Bayesian learning are better than feedforward structure and backpropagation learning, respectively. Consequently, it is verified that the Bayesian reccurent neural network shows better a prediction result than the common Bayesian neural network.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• 제39권3호
• /
• pp.156-169
• /
• 2016

The objective of this study is to investigate patent trends of Daegu city which tries to introduce environment friendly energy and to develop new technology or new industry sprung from technology convergence on smart decentralized energy technology and other technologies. After applying network analysis to corresponding groups of technology or industry convergence, strategy for future energy convergence industry is provided. Patent data applied in Daegu city area are used to obtain research goal. The technology which contains several IPC codes (IPC Co-occurrence) is considered as a convergence technology. Path finder network analysis is used for visualizing and grouping by using IPC codes. The analysis results categorized 13 groups in energy convergence industry and reclassified them into 3 cluster groups (Smart Energy Product Production Technology Group, Smart Energy Convergence Supply Technology Group, Smart Energy Indirect Application Technology Group) considering the technical characteristics and policy direction. Also, energy industry has evolved rapidly by technological convergence with other industries. Especially, it has been converged with IT industry, and there is a trend that energy industry will be converged with service industry and manufacturing industry such as textile, automobile parts, mechanics, and logistics by employing infrastructure as well as network. Based on the research results on core patent technology, convergence technology and inter-industry analysis, the direction of core technology research and development as well as evolution on decentralized energy industry is identified. By using research design and methodology in this study, the trend of convergence technology is investigated based on objective data (patent data). Above all, we can easily confirm the core technology in the local industry by analyzing the industrial competitiveness in the macro level. Based on this, we can identify convergence industry and technology by performing the technological convergence analysis in the micro level.

• Journal of Cadastre & Land InformatiX
• /
• 제44권1호
• /
• pp.1-15
• /
• 2014

This paper, at first, intends to develop a conceptual model of spatial information eco-system based on the related literature reviews. The basic requirements in constructing the model are also specified. Next, the functional roles and interrelationships among the actors constituting the eco-system are analyzed to investigate the major reasons of inefficient and unsmooth flows of value-added process of Korean spatial information industry. Especially, the Korea Cadastral Survery Corp.(KCSC), which has dual organizational characteristics of public and private entity, is analyzed to be positioned as the most dominant actors in the eco-system. However, the KCSC needs to be changed and challenged to re-establish the missions and institutional roles for upcoming network societies. Here, we proposed 4 future-oriented development strategies and action plans to promote the Korean spatial information industry and to activate the eco-system.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제7권4호
• /
• pp.65-73
• /
• 1997

This paper proposes a new method of the structure pruning of dynamic recurrent neural networks (DRNN) using evolutionary computations. In general, evolutionary computations are population-based search methods, therefore it is very useful when several different properties of neural networks need to be optimized. In order to prune the structure of the DRNN in this paper, we used the evolutionary programming that searches the structure and weight of the DRNN and evolution strategies which train the weight of neuron and pruned the net structure. An addition or elimination of the hidden-layer's node of the DRNN is decided by mutation probability. Its strategy is as follows, the node which has mhnimum sum of input weights is eliminated and a node is added by predesignated probability function. In this case, the weight is connected to the other nodes according to the probability in all cases which can in- 11:ract to the other nodes. The proposed pruning scheme is exemplified on the stabilization and position control of the inverted-pendulum system and visual servoing of a robot manipulator and the effc: ctiveness of the proposed method is demonstrated by numerical simulations.

• Transactions of the KSME C: Technology and Education
• /
• 제4권2호
• /
• pp.111-116
• /
• 2016

Consumer's value based content and business platform are more important than the existing supplier based market. Convergence civilization paradigm is being accelerated with expanded combination of information & communication technology and others. In this study, it was classified into four groups with respect to the level and viewpoints of innovation in products and services, which were already supplied on the market by industry convergence activity. Barriers that are obstacles to the development of a new converged industry through strategic approaches were identified by surveying the current industrial status. In detail, they were summarized with respect to three aspects, such as, target, infrastructure and main agent of individual sector. Finally, it presents an alternative to overcome the obstacles and develop a new growth engines for the future industrial evolution.

• CRM연구
• /
• 제1권1호
• /
• pp.87-108
• /
• 2006

This study presents how the sharing of values and philosophies in Customer Relationship Management (CRM) links the customer with the enterprise, thereby enhancing its performance. Using channel integration, customer experience management, and partner relationship management, this i-focus case suggests a number of improvements for local corporations that have adopted CRM, but have not succeeded in enterprise-wide integration. Successful execution of CRM strategy is found to require the sharing of values and philosophies not only within the organization, but also with its customers. Furthermore, the study concludes that CRM is an ongoing process which requires continuous evolution through reflection of past activities and dynamic adjustment of objectives in order to reach customer cenricity.

• Composites Research
• /
• 제12권4호
• /
• pp.42-54
• /
• 1999

FMLC(Fiber-Metal Laminate Composites) is a new structural material combining thin metal laminate with adhesive fiber prepreg, it nearly include all the advantage of metallic materials, for example: good plasticity, impact resistance, processibility, light weight and excellent fatigue properties. This research studied the optimum design of the FMLC subject to various loading conditions using genetic algorithm. The finite element method based on the shear deformation theory was used for the analysis of FMLC. Tasi-Hill failure criterion and Miser yield criterion were taken as fitness functions of the fiber prepreg and the metal laminate, respectively. The design variables were fiber orientation angles. In genetic algorithm, the tournament selection and the uniform crossover method were used. The elitist model was also used to be effective evolution strategy and the creeping random search method was adopted in order to approach a solution with high accuracy. Optimization results were given for various loading conditions and compared with CFRP(Carbon Fiber Reinforced Plastic). The results show that the FMLC is more excellent than the CFRP in point and uniform loading conditions and it is more stable to unexpected loading because the deviation of failure index is smaller than that of CFRP.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제18권2호
• /
• pp.177-184
• /
• 2017

Understanding trends and drivers of technology diffusion is imperative to forecast new technology adoption and understand the process of technological innovation. Our research utilizes a quantitative trend analysis considering both technological and economic indicators for trends and drivers of technology diffusion for 32nm, 22nm, and 14nm logic semiconductor technology. In terms of technological performance, the technology diffusion curve showed an S-curve pattern during the stages of maturity and decline, and the diffusion curve showed evidence supporting the learning curve. The diffusion curve showed the life cycle duration of 2 years, and the rate of technological performance and obsolescence are observed quantitatively between generations. Architectural innovation is affected by technological drivers more significantly than economic drivers. This research has implications as empirical research on the trends and drivers of technology diffusion in the high-tech semiconductor industry, and is meaningful in forecasting new technology adoption or build technology strategy.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 한국경영과학회 2008년도 추계학술대회 및 정기총회
• /
• pp.24-36
• /
• 2008

Architecture-based competition has become a very important issue in many industries. As companies seek lower cost, fast development, and more customizability at the same time, modular architecture of products and processes seem to be an inevitable choice. Existing literature, however, has only focused on the basic contents of architecture-based competition. Different competitive environments and technological competencies of incumbent companies influence the evolutionary dynamics of dominant architecture of industries. In this paper we suggest a new theoretical framework to deal with the complex co-adaptation process of architecture-based competition. We first explore the emerging modular architecture in Chinese commercial vehicle industry, and then compare it with the architecture strategies of Korean companies. Based on the explorative case study, we propose new hypotheses relating the market demand, technological competencies of major players and dominant architecture in an indus-try.

• Journal of the Korean Society for information Management
• /
• 제33권2호
• /
• pp.227-256
• /
• 2016

This study was carried out for the university library to find out a strategy to stand tall as an institution to lead the university, by reflecting the university environment having with drastic environmental changes and reflecting the evolution of information technology. As a result, first, university librarians responded that big issues related to the university library is the University Library Promotion Act, University Library evaluation and assessment indicators, the value of university libraries at the university, and changing spatial composition and functions of the university library. Second, university librarians responded that changes of the university environment, government policy on universities, various national projects, and various university reform policy significantly affect to the university library. Third, about what you think would be helpful to the crisis in their universities as changing role of the library, they responded that they can contribute in terms of improving students' information and technology literacy, improving students' reading skills, improving research capacity, and improve students' learning ability. Fourth, they responded that services that users demand the highest in the university library will be expansion of e-books and information resource.