• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.156-166
• /
• 2002

Decision tree induction is a kind of useful machine learning approach for extracting classification rules from a set of feature-based examples. According to the partitioning style of the feature space, decision trees are categorized into univariate decision trees and multivariate decision trees. Due to observation error, uncertainty, subjective judgment, and so on, real-world data are prone to contain some errors in their feature values. For the purpose of making decision trees robust against such errors, there have been various trials to incorporate fuzzy techniques into decision tree construction. Several researches hove been done on incorporating fuzzy techniques into univariate decision trees. However, for multivariate decision trees, few research has been done in the line of such study. This paper proposes a fuzzy decision tree induction method that builds fuzzy multivariate decision trees named fuzzy oblique decision trees, To show the effectiveness of the proposed method, it also presents some experimental results.

• STI Policy Review
• /
• v.6 no.2
• /
• pp.54-86
• /
• 2015

The study examines the U.S. Small Business Innovation Research (SBIR) program, with a focus on the recent Reauthorization, and compares, in the political context, the U.S. and East Asian countries-Japan, Korea and Taiwan-that adopted the U.S. SBIR program. For the systematic analysis and cross-country comparison, the study employs Kingdon (2003)'s framework-his political theory and Garbage Can Model-to identify political participants and processes underlying the SBIR Reauthorization and to analyze the differences in problem, policy, and politics streams between the U.S. and East Asian countries. For the cross-country comparison, specifically, the study uses various data sources such as OECD, Global Entrepreneurship Monitor, Hofstede's Cultural Dimensions, and World Value Survey. Based on the analysis outcomes, implications of U.S. practices on East Asian countries are extracted as follows. East Asian countries tend to: Have higher entrepreneurial aspiration while lower entrepreneurial activity and attitude than the U.S.; bear higher long term orientation and uncertainty avoidance while lower individualism than the U.S.; and have greater expectations of technology development and higher confidence in political parties while participating less in political action than the U.S. Drawing on the differences, the following policy recommendations are suggested. East Asian countries should: Improve entrepreneurs' access to resources (in particular, financial resource) in order to link their high entrepreneurial aspiration to actual entrepreneurial activities; cultivate failure-tolerating culture and risk-taking entrepreneurs, for instance, by providing a second chance to SBIR-participating businesses that failed to materialize their innovative ideas; and leverage their high expectations of new technology in order to take bold actions regarding their SBIR programs, and update the programs by drawing out constructive dialogues between SBIR stakeholders.

• The Journal of Korean Association of Computer Education
• /
• v.23 no.2
• /
• pp.13-20
• /
• 2020

The interest in artificial intelligence is due to an increase in influence on companies, organizations, daily lives and society. The purpose of this study is to analyze the key elements in the teaching subjects of artificial intelligence-related subjects of Korean universities based on the intelligent system area of Computer Science 2013 in terms of human resources development. According to the analysis, there are five out of nine universities that run the required courses. Based on the 12 detailed knowledge domains of intelligent systems, the compulsory subjects of universities are distributed in the field of basic search theory, basic knowledge expression and reasoning, and inference based on uncertainty. The elective courses of each university covered topics in five to eight areas of the total knowledge area of the intelligent system, with 69.9 percent of universities with the highest average ratio of areas involving the subject of teaching subjects and 46.3 percent of universities with the lowest. This study has implications for the fact that prior to entering an artificial intelligence graduate school, we were able to grasp the level of knowledge about artificial intelligence at the undergraduate level.

• Journal of Mechanical Science and Technology
• /
• v.17 no.7
• /
• pp.999-1010
• /
• 2003

Uninterrupted power supply has become indispensable during the maintenance task of active electric power lines as a result of today's highly information-oriented society and increasing demand of electric utilities. This maintenance task has the risk of electric shock and the danger of falling from high place. Therefore it is necessary to realize an autonomous robot system using electro-hydraulic manipulators because hydraulic manipulators have the advantage of electric insulation and power/mass density. Meanwhile an electro-hydraulic manipulator using hydraulic actuators has many nonlinear elements, and its parameter fluctuations are greater than those of an electrically driven manipulator. So it is relatively difficult to realize not only stable contact work but also accurate force control for the autonomous assembly tasks using hydraulic manipulators. In this paper, the robust force control of a 6-link electro-hydraulic manipulator system used in the real maintenance task of active electric lines is examined in detail. A nominal model for the system is obtained from experimental frequency responses of the system, and the deviation of the manipulator system from the nominal model is derived by a multiplicative uncertainty. Robust disturbance observers for force control are designed using this information in an H$\_$$\infty$/ framework, and implemented on the two different setups. Experimental results show that highly robust force tracking by a 6-link electro-hydraulic manipulator could be achieved even if the stiffness of environment and the shape of wall change.

• Health Policy and Management
• /
• v.18 no.1
• /
• pp.1-20
• /
• 2008

How health care providers compete and how competition among them affects their behavior are crucial questions in theory and health policy. In ordinary markets, competition improves social welfare, However in health care markets facing uncertainty and information asymmetry, competition can take the form of wasteful quality competition and result in cost increase. The purpose of this study is to examine the characteristics of hospital service markets and examine the impact of hospital competition on hospital behavior, more specifically hospital cost and the size of personnel. Based on patient discharge data of 2002 by the Ministry of Health and Welfare and Korea Institute for Health and Social Affairs, and health insurance EDI claims data of 2002, this study measures the degree of competition in the inpatient service market of hospitals, using variable radius method and Herfindahl index. The result of the study shows that the hospital service market consists of on average 3.13 government administrative units(shi, gun, or gu). Compared with hospitals, general or general specialized hospitals cover larger markets and operate in more competitive markets. Nearly 60% of patients use hospitals, which are not located in their government administrative units, meaning that market definition based on variable radius is better than the conventional method of market definition based on government administrative units. The results of multivariate analysis show that competition is not associated with high cost index of hospitals. But hospitals in more competitive markets employ larger(more intensive) input of personnel per 100 beds, implying that hospital competition in Korea can have the form of quality and cost-increasing competition.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1995.04a
• /
• pp.240-245
• /
• 1995

제어이론의 역사적 발전사를 고찰해보면 1930년대부터 1960년대까지를 고전 제어(classical control) 시대로 분류되고 이때 주로 사용되었던 용어들은 주파수역(frequency domain)에서 사용된 개념인 극점(pole), 영점(zero), Nyquist, 근궤적(root-Locus) 선도(plot)등으로 대표된다. 그 다음단계인 현대 제어(modern control) 시대 (1960년대-1980년대)때는 새로운 개념들이 도입 되었는데 시간역(time domain)에서 사용되는 상태공간(state-space) 모델, 가제어성(controllability), 가관측성(observability), Kalman 필터, LQG 제어 등이다. 1980년대부터 현재까지를 강인제어(robust control) 시대로 분류하는데 이것의 특징들은 극점이나 영점 대신 상태공간 모델을 사용하여 주파수역에서 정의되는 개념들인 H$_{\infty}$ 합성법, .$\mu$ 해석법, LQG/LTR 및 QFT, Lyapunov 등으로 대표된다. 현대제어시대때는 제어기 K는 공칭 플랜트 모델 G$_{0}$를 기준으로 설계되었으나 실제로 공칭 플랜트 모델은 실제 플랜트와 항상 같을 수가 없었다. 따라서 실제 플랜트 G는 G=G$_{0}$ + .DELTA.G로 표현되며 여기서 .DELTA.G는 플랜트 불 확실성(plant uncertainty), 즉 실제 플랜트와 공칭 플랜트의 차이를 나타낸 다. 이 플랜트 불확실성은 제어기가 실제 응용되어 사용되었을 때 제대로 작동하지 않는 주요 이유중에 하나이다. 이와 같은 상황에서 안정도 강인성 (stability robustness) 및 성능 강인성(performance rosubtness)의 보장은 상 당히 중요한 문제로 대두되었으며 주어진 플랜트 불확실성하에서 이러한 강이성들이 보장되는 제어이론들 중 H$_{\infty}$ 제어이론이 많이 연구/응용 되고 있다. 특히 공칭 플랜트 모델과 함께 사용되는 플랜트 모델과 함께 사용되는 플랜트 불확실성 모델은 직접적으로 성능 및 안정도에 영향을 미치므로 주의 깊게 선정해야 한다.

• Smart Structures and Systems
• /
• v.26 no.2
• /
• pp.227-239
• /
• 2020

Despite proven effectiveness and accuracy in laboratories, the existing damage assessment based on guided ultrasonic waves (GUWs) or acoustic emission (AE) confronts challenges when extended to real-world structural health monitoring (SHM) for railway tracks. Central to the concerns are the extremely complex signal appearance due to highly dispersive and multimodal wave features, restriction on transducer installations, and severe contaminations of ambient noise. It remains a critical yet unsolved problem along with recent attempts to implement SHM in bourgeoning high-speed railway (HSR). By leveraging authors' continued endeavours, an SHM framework, based on actively generated diffuse ultrasonic waves (DUWs) and a benchmark-free condition contrast algorithm, has been developed and deployed via an all-in-one SHM system. Miniaturized lead zirconate titanate (PZT) wafers are utilized to generate and acquire DUWs in long-range railway tracks. Fatigue cracks in the tracks show unique contact behaviours under different conditions of external loads and further disturb DUW propagation. By contrast DUW propagation traits, fatigue cracks in railway tracks can be characterised quantitatively and the holistic health status of the tracks can be evaluated in a real-time manner. Compared with GUW- or AE-based methods, the DUW-driven inspection philosophy exhibits immunity to ambient noise and measurement uncertainty, less dependence on baseline signals, use of significantly reduced number of transducers, and high robustness in atrocious engineering conditions. Conformance tests are performed on HSR tracks, in which the evolution of fatigue damage is monitored continuously and quantitatively, demonstrating effectiveness, adaptability, reliability and robustness of DUW-driven SHM towards HSR applications.

• Journal of Navigation and Port Research
• /
• v.34 no.10
• /
• pp.763-768
• /
• 2010

Today the light of mankind since the dawn of mankind and that they were living "lives" on the huge influence across space is a dynamic energy. Because of this, when all human beings with the light and you can feel more comfortable with a stable mind to the beauty and the pursuit of happiness is to have instincts. In this paper, a fuzzy control system using a combination of external environmental factors, respectively, the conversion of quantitative uncertainty information into the LED lighting is designed to express algorithms, available in indoor circadian control circuit was designed and fabricated LED. Factor in the external environment temperature, humidity, and light intensity values to the controller through the sensor to accept these values and the optimal values for lighting the fuzzy control algorithm is converted into human emotion to feel comfortable to express through the dimming control LED lighting.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.12
• /
• pp.885-893
• /
• 2006

The Bayesian network(BN) has emerged in recent years as a powerful technique for handling uncertainty iii complex domains. Parameter learning of BN to find the most proper network from given data set has been investigated to decrease the time and effort for designing BN. Off-line learning needs much time and effort to gather the enough data and since there are uncertainties in real world, it is hard to get the complete data. In this paper, we propose an online learning method of Bayesian network parameters from incomplete data. It provides higher flexibility through learning from incomplete data and higher adaptability on environments through online learning. The results of comparison with Voting EM algorithm proposed by Cohen at el. confirm that the proposed method has the same performance in complete data set and higher performance in incomplete data set, comparing with Voting EM algorithm.

• Journal of KIISE:Computer Systems and Theory
• /
• v.36 no.5
• /
• pp.360-370
• /
• 2009

Using solar power in wireless sensor networks requires a different approach to energy optimization from networks with battery-based nodes. Solar energy is an inexhaustible supply which can potentially allow a system to run forever, but there are several issues to be considered such as the uncertainty of energy supply and the constraint of rechargeable battery capacity. In this paper, we present SolarSS: a reliable storage system for solar-powered sensor networks, which provides a set of functions, in separate layers, such as sensory data collection, replication to prevent failure-induced data loss, and storage balancing to prevent depletion-induced data loss. SolarSS adapts the level of layers activated dynamically depending on solar energy availability, and provides an efficient resource allocation and data distribution scheme to minimize data loss.