• 한국컴퓨터산업교육학회:학술대회논문집
• /
• 2003.11a
• /
• pp.95-98
• /
• 2003

Power semiconductors are being currently used as a application of intelligent power inverters to a refrigerator, a washing machine and a vacuum cleaner as well as core parts of industrial system. The rating of semiconductor devices is an important factor in decision on the field of application and the forward blocking voltage is one of factors in decision of the rating. The Power MOS device has a merit of high input impedance, short switching time, and stability in temperature as well known. Power MOS devices are mainly used as switches in the field of power electronics, especially the on-state resistance and breakdown voltage are regarded as the most important parameters. Power MOS devices that enable a small size, a light weight, high-integration and relatively high voltage are required these days. In this paper, we proposed the new lateral power MOS which has forward blocking voltage of 250V and contains trench electrodes and verified manufactural possibility by using TSUPREM-4 that is process simulator.

• Journal of Korea Multimedia Society
• /
• v.6 no.5
• /
• pp.937-944
• /
• 2003

The most important problems in the multi-agent system are to accomplish a gnat through the efficient coordination of several agents and to prevent collision with other agents. In this paper, we propose a new control strategy for succeeding the goal of a prey pursuit problem efficiently Our control method uses reinforcement learning to control the multi-agent system and consider the distance as well as the space relationship among the agents in the state space of the prey pursuit problem.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.235-236
• /
• 2017

최근 제4차 산업혁명 시대가 도래함에 따라 지능정보기술은 대규모 데이터에 대한 자가학습(Machine Learning)을 통해 알고리즘 성능을 지속적으로 강화함으로써 데이터와 지식이 산업의 주요 경쟁 원천으로 부상시키고 있다. 지능정보기술은 산업전반에 구조적 대변혁을 촉발할 것으로 전망됨에 따라 전세계적으로 지능정보기술을 선제적으로 확보, 도입 및 확산하여 국가경쟁력을 제고해나가려 하고 있다. 따라서 지능정보기술을 확보하기 위한 R&D 전략수립이 무엇보다 중요해졌다. 본 조사 연구에서는 IoT, Cloud, Bigdata, Mobile, AI 등 지능정보기술 분야의 기술경쟁력 수준을 파악하기 위해 전문가 정성적 기술수준평가와 함께 특허, 논문 등 데이터기반의 기술수준평가에 대한 것이다.

• Journal of Mechanical Science and Technology
• /
• v.19 no.5
• /
• pp.1131-1137
• /
• 2005

Methods for measuring surface roughness based on light reflectivity have advantages over methods based on light interference or diffraction, especially in in-situ, on-the-machine and in-process applications. However, measurement inconsistencies caused by changes in the specimen are still a drawback for field applications. In this study, we propose a new feedback-based algorithm to enhance the consistency against changes in the specimen. The algorithm is deduced from simulations based on light reflectance theory with typical modeled surfaces. The proposed method is similar to a digital controller and regulates the power of reflected light. Experiments varying heights and materials, verified the improvements in robustness of the method against measurement disturbances caused by specimen changes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.12
• /
• pp.4489-4501
• /
• 2014

We propose a novel lane detection method based on classification in image sequences. Both structural and statistical features of the extracted bright shape are applied to the neural network for finding correct lane marks. The features used in this paper are shown to have strong discriminating power to locate correct traffic lanes. The traffic lanes detected in the current frame is also used to estimate the traffic lane if the lane detection fails in the next frame. The proposed method is fast enough to apply for real-time systems; the average processing time is less than 2msec. Also the scheme of the local illumination compensation allows robust lane detection at nighttime. Therefore, this method can be widely used in intelligence transportation systems such as driver assistance, lane change assistance, lane departure warning and autonomous vehicles.

• Proceedings of the KSR Conference
• /
• 2008.06a
• /
• pp.948-951
• /
• 2008

Ubiquitous sensor network (USN) based on ZigBee communication protocol has been used in various application fields, such as home-network, intelligent building and machine, logistics, environmental monitoring, military field, security field and etc. The ZigBee is targeted at radio-frequency application that require a low data rate, long battery life and secure network. Especially, the USN system can be applied efficiently to building-indoor where the complex geometry is adopted. In this study, all 90 points of railway cabin indoor were monitored for temperature and humidity using USN technology. All sensors were pre/post-calibrated and the temperature/humidity change were analyzed in a railway cabin in real-time. The results would be useful to develop the cabin heating, ventilating and air conditing (HVAC) system to meet all passengers' thermal comfort regardless of their seat position.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2004.11a
• /
• pp.179-188
• /
• 2004

Bankruptcy prediction is an important and widely studied topic since it can have significant impact on bank lending decisions and profitability. Recently, support vector machine (SVM) has been applied to the problem of bankruptcy prediction. The SVM-based method has been compared with other methods such as neural network, logistic regression and has shown good results. Genetic algorithm (GA) has been increasingly applied in conjunction with other AI techniques such as neural network, CBR. However, few studies have dealt with integration of GA and SVM, though there is a great potential for useful applications in this area. This study proposes the methods for improving SVM performance in two aspects: feature subset selection and parameter optimization. GA is used to optimize both feature subset and parameters of SVM simultaneously for bankruptcy prediction.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.61 no.4
• /
• pp.228-233
• /
• 2012

In power system, substation facilities have become too complex and larger according to an extended power system. Also, customers require the high quality of electrical power system. However, some facilities become old and often break down unexpectedly. The unexpected failure may cause a break in power system and loss of profits. Therefore it is important to prevent abrupt faults by monitoring the condition of power systems. Among the various power facilities, power transformers play an important role in the transmission and distribution systems. In this research, we develop intelligent diagnosis technique for monitoring of power transformer by FCM(Fuzzy c-means) and ELM(Extreme Learning Machine). The proposed technique make it possible to diagnosis the faults occurred in transformer. To demonstrate the validity of proposed method, various experiments are performed and their results are presented.

• Proceedings of the KIPE Conference
• /
• 2005.07a
• /
• pp.152-155
• /
• 2005

본 논문에서는 CCD 카메라의 시각정보 이미지를 이용한 Machine Vision System을 개발하여 산업용 로봇에 적용하고 이를 통해 이동물체에 대한각종 조작 및 자동화 작업을 수행하는 지능형 산업용 로봇을 위한 실시간 비전 트래킹 시스템을 연구하였다. 비전 트래킹 시스템에서 물체의 위치 계산에 대한 정밀도와 함께 빠른 처리속도를 요구하므로 로봇제어기와는 별개의 Embadded 시스템으로 비전 제어기를 구성하고 로봇제어기와의 Serial 통신을 통하여 트래킹 시스템을 구현하였다.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.51 no.4
• /
• pp.211-218
• /
• 2002

We propose a intelligent controller for FACTS device to stabilize a power system. In order to identify the nonlinear characteristics of the power system and to estimate a control signal, an artificial neural network is utilized. Parameter and location of Unified Power Flow Controller(UPFC) on power system operating conditions are discussed. A UPFC is composed of an excitation transformer, a boosting, two three-phase GTO based voltage source converters, and a dc link capacitor. The proposed controller is applied to UPFC to verified the effectiveness of the proposed control system. The results show that the proposed nonlinear FACTS controller is able to enhance the transient stability of a three machine and nine bus system.