• Proceedings of the KIEE Conference
• /
• 2001.07a
• /
• pp.318-322
• /
• 2001

본 논문은 뉴로-퍼지 모델의 구조 학습을 이용한 단기 전력 수요 예측시스템에서 예측치별로 신뢰도를 계산하는 체계적인 방법을 제안한다. 예측시스템의 신뢰도를 추정하는 작업은 특히 신경회로망과 같은 경험적 모델을 실제 활용하기 위해서 필수적인 연구로 인식되고 있다. 본 논문에서 제안하는 출력별 신뢰 구간 계산 방법은 지역 표현하는 뉴로-퍼지 모델의 특성을 활용하여 학습된 퍼지 규칙 각각에 대해 신뢰도를 추정하는 Local reliability measure 기법을 사용한다. 제안된 신뢰도 계산이 가능한 단기 전력 수요 예측시스템은 먼저 결정 트리를 이용하여 초기 구조를 생성하고, 이를 초기 구조 뱅크에 저장한다. 저장된 초기 구조 뱅크를 이용하여 뉴로-퍼지 모델을 학습하고, 학습된 퍼지 규칙의 신뢰도를 추정한다. 제안된 시스템의 실효성을 검증하기 위해서 한국 전력에서 수집한 1996년과 1997년의 실제 전력 수요 데이터를 이용하여 한 시간 앞의 수요를 예측하는 모의 실험을 수행하고 실험 결과를 비교 분석한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.3
• /
• pp.242-251
• /
• 2000

퍼지관계 개념을 응용한 BK-퍼지정보검색기법은 형태론에 입각하는 기존의 정보검색기법과는 달리 문서와 용어의 상대적 의미에 근거한 정보검색 기법이다. 그러나 BK-퍼지정보검색기법은 높은 시간복잡도(time complexity)의 검색 연산을 내재하고 있어 실제 대용량의 정보 검색은 사실상 불가능하다. 본 논문에서는 BK-퍼지검색정보모델의 시간복잡도를 낮추기 위해, 축소용어집합(reduced term set)을 이용한 개선된 BK-퍼지정보검색모델(A-FIRM)을 제안한다. 개선된 BK-FIRM은 시스템 처리시간과 신뢰도 간 상층점(trade-off)을 제공한다. 축소용어집합은 용어집합의 부분집합으로서 검색결과의 신뢰도와 밀접한 관계를 가진다. 동일한 크기의 축소용어집합이 주어질 때, 보다 적절한 용어들로 구성된 축소용어집합이 보다 나은 검색 신뢰도를 이끈다. 따라서 보다 적절한 축소용어집합 구성을 위한 축소용어집합 추출방법이 요구된다. 본 논문에서는 축소용어집합 추출방법을 크게 무작위 추출, 규칙에 의한 추출, 인간에 의한 직관적 추출 방법으로 구분하고 검색결과의 신뢰도 변화 형태를 분석한다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.4 no.1
• /
• pp.64-80
• /
• 1994

본 연구에서는 장기전원구성의 수립에 있어서 가정한 시나리오에서 최적해를 찾는 기존의 방법을 탈피하여 건설단가나 연료단가의 변동과 같은 경제성의 변동 및 최대부하의 예측의 불확실성에 대한 외부충격등에 견딜 수 있는 유연성을 정량적으로 고려할 수 있는 새로운 방법을 제안한다.그 수법으로 Fuzzy 동적계획법을 이용하여 각 대표년도별로 최적전원구성안을 결정하므로써 년도별 전원 구성의 추이를 쉽게 알 수 있고 비선형 멤버쉽함수도 용이하게 고려할 수 있도록 하였다. 여기서는 경제성, 신뢰성, 부하불확실성 및 유연성에 대한 멤버쉽 함수치를 각상태별로 계산하고 Bellman-Zadeh의 최대화 결전과정에 따라 처리하므로서 그 안을 결정하도록 하였다. 본 수법을 우리나라 KEPCO 계통에 적용하여 그 유용성을 검토하였다.

• Journal of the Korean Society for Railway
• /
• v.16 no.4
• /
• pp.272-277
• /
• 2013

Power quality is a term that is now extensively used in power systems applications, and in this context the voltage, current, and phase angle are discussed widely. In particular, different algorithms that are capable of detecting the voltage sag and swell information in a real time environment have been proposed and developed. Voltage sag and swell play an important role in determining the stability, quality, and operation of a power system. This paper presents ANFIS (Adaptive Network based Fuzzy Inference System) models with different membership functions to build the voltage shape with the knowledge of known system parameters, and detect voltage sag and swell accurately. The performance of each method has been compared with each other/other methods to determine the effectiveness of the different models, and the results are presented.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.05a
• /
• pp.434-436
• /
• 2004

Load forecasting is essential in the electricity market for the participants to manage the market efficiently and stably. The percentage errors of 24 hourly load forecasting for holidays is relatively large. In this paper, we propose the maximum and minimum load forecasting method for holidays using a fuzz linear regression algorithm. 24 hourly loads are forecasted from the maximum and minimum loads and the 24 hourly normalized values. The proposed algorithm is tested for 24 hourly load forecasting in 1996. The test results show the proposed algorithm improves the accuracy of the load forecasting.

• Journal of information and communication convergence engineering
• /
• v.9 no.4
• /
• pp.369-374
• /
• 2011

Generally the neural network and the Fuzzy compensative algorithms are applied to forecast the time series for power demand with the characteristics of a nonlinear dynamic system, but, relatively, they have a few prediction errors. They also make long term forecasts difficult because of sensitivity to the initial conditions. In this paper, we evaluate the chaotic characteristic of electrical power demand with qualitative and quantitative analysis methods and perform a forecast simulation of electrical power demand in regular sequence, attractor reconstruction and a time series forecast for multi dimension using Lyapunov Exponent (L.E.) quantitatively. We compare simulated results with previous methods and verify that the present method is more practical and effective than the previous methods. We also obtain the hourly predictability of time series for power demand using the L.E. and evaluate its accuracy.

• The Journal of the Korea Contents Association
• /
• v.9 no.10
• /
• pp.51-58
• /
• 2009

Reinforcement learning is a sub area of machine learning concerned with how an agent ought to take actions in an environment so as to maximize some notion of long-term reward. In the case of multi-agent, especially, which state space and action space gets very enormous in compared to single agent, so it needs to take most effective measure available select the action strategy for effective reinforcement learning. This paper proposes a multi-agent reinforcement learning model based on fuzzy inference system in order to improve learning collect speed and select an effective action in multi-agent. This paper verifies an effective action select strategy through evaluation tests based on Robocup Keepaway which is one of useful test-beds for multi-agent. Our proposed model can apply to evaluate efficiency of the various intelligent multi-agents and also can apply to strategy and tactics of robot soccer system.

• Journal of Korea Multimedia Society
• /
• v.17 no.11
• /
• pp.1363-1373
• /
• 2014

In this study, a hybrid multi-cup electric cupping system (HMECS) was proposed, based on the ancient cupping method. HMECS consisted of several cups that could be used simultaneously to treat different areas of the patient's body. Each cup was equipped with its own pump and pressure-monitoring system. Moreover, the vacuum pressure of the cups was controlled using fuzzy logic. Through automated control of the vacuum pressure, long-term relief of muscle tightness was achieved. To develop a scientific foundation for this alternative treatment, we compared the VAS(Visual Analog Scale) and ODI(Oswestry Disability Index) scores from conventional basic cupping to the VAS and ODI scores for our proposed HMECS. The improvement rate in the VAS and ODI scores using HMECS after three treatments was higher than that achieved by basic cupping. These results, combined with the convenience offered by enhanced IT capabilities, should increase the popularity of this device among an aging society, and facilitate the opportunity to further explore the potential of Oriental medical practices.

• The KIPS Transactions:PartC
• /
• v.17C no.3
• /
• pp.271-280
• /
• 2010

For the next generation mobile communication system, diverse wireless network techniques such as beyond 3G LTE, WiMAX/WiBro, and next generation WLAN etc. are proceeding to the form integrated into the All-IP core network. According to this development, Beyond 3G integrated into heterogeneous wireless access technologies must support the vertical handover and network to be used of several radio networks. However, unified management of each network is demanded since it is individually serviced. Therefore, in order to solve this problem this study is introducing the theory of Common Radio Resource Management (CRRM) based on Generic Link Layer (GLL). This study designs the structure and functions to support the vertical handover and propose the vertical handover algorithm of which policy-based and MCDM are composed between LTE and WLAN systems using GLL. Finally, simulation results are presented to show the improved performance over the data throughput, handover success rate, the system service cost and handover attempt number.

• The Journal of the Korea Contents Association
• /
• v.11 no.3
• /
• pp.271-280
• /
• 2011

Heart Rate Variability (HRV) analysis is a convenient tool to assess Myocardial Ischemia (MI). The analysis methods of HRV can be divided into time domain and frequency domain analysis. This paper uses wavelet transform as frequency domain analysis in contrast to time domain analysis in short term HRV analysis. ST-T and normal episodes are collected from the European ST-T database and the MIT-BIH Normal Sinus Rhythm database, respectively. An episode can be divided into several segments, each of which is formed by 32 successive RR intervals. Eighteen HRV features are extracted from each segment by the time and frequency domain analysis. To diagnose MI, the Neural Network with Weighted Fuzzy Membership functions (NEWFM) is used with the extracted 18 features. The results show that the average accuracy from time and frequency domain features is 75.29% and 80.93%, respectively.