• 한국멀티미디어학회논문지
• /
• 제3권2호
• /
• pp.201-208
• /
• 2000

이 논문에서는 시계열 예측을 위하여 퍼지 엔트로피에 의한 입력공간의 분할과 퍼지 제어규칙을 자동으로 생성하는 방법을 제안하고, Mackey-Glass 데이터 Set을 이용한 시계열 예측 문제에 적용하여 그 성능을 검증한다. 이 방법은 샤논 함수와 퍼지 엔트로피 함수를 이용하여 입력공간을 분할하고, 분할된 부 공간에 대해 이력 데이터와 부합할 수 있는 각각의 규칙에 등급을 정하여 불필요한 제어규칙을 제거하여 최적의 규칙베이스를 구성하도록 한다. 적용되는 퍼지 신경망의 기본적인 구조는 퍼지 제어기의 규칙베이스와 추론의 과정을 신경회로망을 이용하여 구현하며 퍼지 제어규칙의 매개변수들은 최대 급경사 강하법에 의해 적응되어진다. 제안되는 알고리즘을 매개변수의 수를 줄이기 위하여 제어 규칙의 결론부의 출력값은 신경망의 가중치로 구성하여 퍼지 신경망의 복잡도를 줄임으로서 추론형과 기술형 접근법을 혼합한 형태의 학습 알고리즘이다.

• 한국수소및신에너지학회논문집
• /
• 제22권6호
• /
• pp.852-858
• /
• 2011

This paper is aiming to estimate the mutual influence of the stack cooling performances with the operation modes of the thermal management system for the hydrogen fuel cell vehicles. The heat capacity of the thermal management system was measured by varying the operating modes such as stack cooling heat exchanger only (Mode 1), stack cooling and electric devices cooling heat exchangers (Mode 2), and stack cooling and electric devices cooling heat exchangers with an operation of the condenser (Mode 3).As the results, Performance of the thermal management system (TMS) at Mode 3 decreased up to 34.0%, compared with the result of the Mode 1. In addition, in order to optimize the performance of TMS, the entropy change of stack cooling heat exchanger using irreversibility analysis technique was analyzed with the relationship between entropy generation and entering air velocity of the thermal management system.

• 디지털융복합연구
• /
• 제11권11호
• /
• pp.343-349
• /
• 2013

러프집합에서는 동치류와 근사공간의 개념을 이용하여 데이터 마이닝 분야에서 중복되는 정보로부터 특징점을 효율적으로 추출하여 최적화된 제어규칙을 유도할 수 있다. 이러한 추출과정에서 가장 중요하게 고려되어져야 할 부분은 많은 속성에 대한 감축이다. 본 논문에서는 속성간의 관계에서 러프엔트로피를 이용하여 가장 신뢰도가 우수한 속성을 구할 수 있는 정보이론적인 척도를 제시한다. 제안된 방법은 러프엔트로피를 기반으로 불필요한 속성을 제거함으로써 유용한 리덕트를 생성하고 이들에 대한 코어를 형성한다. 결과적으로 원시정보의 내용은 변하지 않으면서 지식감축을 통하여 간소화된 제어규칙을 구축할 수 있음을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권8호
• /
• pp.3946-3965
• /
• 2018

Network anomaly detection in Software Defined Networking, especially the detection of DDoS attack, has been given great attention in recent years. It is convenient to build the Traffic Matrix from a global view in SDN. However, the monitoring and management of high-volume feature-rich traffic in large networks brings significant challenges. In this paper, we propose a moving window Principal Components Analysis based anomaly detection and mitigation approach to map data onto a low-dimensional subspace and keep monitoring the network state in real-time. Once the anomaly is detected, the controller will install the defense flow table rules onto the corresponding data plane switches to mitigate the attack. Furthermore, we evaluate our approach with experiments. The Receiver Operating Characteristic curves show that our approach performs well in both detection probability and false alarm probability compared with the entropy-based approach. In addition, the mitigation effect is impressive that our approach can prevent most of the attacking traffic. At last, we evaluate the overhead of the system, including the detection delay and utilization of CPU, which is not excessive. Our anomaly detection approach is lightweight and effective.

• 한국가스학회지
• /
• 제16권3호
• /
• pp.1-7
• /
• 2012

고압으로 수송되는 천연가스를 수요처에 공급하는 정압기지에서는 강제로 감압하여 보내준다. 이 때, 버려지는 압력에너지를 회수하는 방법으로 터보팽창기를 이용한 전력생산이 가능하며, 터보팽창기는 정압과 전력생산의 두 가지 기능을 동시에 수행하게 된다. 터보팽창기에서 생산되는 전력의 양은 유동전후의 엔탈피 차이며, 경제성에 영향을 미치는 주요인자로는 설비비, 전력생산량, 예열량, 전력가격, 가스가격의 5가지이다. 입구와 출구의 압력과 온도 조건이 고정되므로, 전력생산량은 결국 유량에 좌우된다. 따라서, 천연가스 수요의 계절별 수급변화 패턴에 따른 터보팽창기 적정용량을 결정하는 것이 경제성확보의 핵심기술이다. 유동량변화가 심한 경우의 전력생산량 산정법의 algorithm을 제시하였으며 이를 사용한 case study를 수행하였다.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2000년도 춘계 학술대회 및 국제 감성공학 심포지움 논문집 Proceeding of the 2000 Spring Conference of KOSES and International Sensibility Ergonomics Symposium
• /
• pp.253-257
• /
• 2000

the objective of this study is to design and evaluate a methodology for diagnosing the appendicitis in a fuzzy neural network that integrates the partition of input space by fuzzy entropy and the generation of fuzzy control rules and learning algorithm. In particular the diagnosis of appendicitis depends on the rule of thumb of the experts such that it associates with the region, the characteristics, the degree of the ache and the potential symptoms. In this scheme the basic idea is to realize the fuzzy rle base and the process of reasoning by neural network and to make the corresponding parameters of the fuzzy control rules be adapted by back propagation learning rule. To eliminate the number of the parameters of the rules, the output of the consequences of the control rules is expressed by the network's connection weights. As a result we obtain a method for reducing the system's complexities. Through computer simulations the effectiveness of the proposed strategy is verified for the diagnosis of appendicitis.

• International Journal of Air-Conditioning and Refrigeration
• /
• 제7권
• /
• pp.22-32
• /
• 1999

A multi-type heat pump controls the mass flow rate of the working fluid to cope with variable heat loads when it is under dynamic load condition. This paper describes the exergy analysis associated with the unsteady response of a heat pump. First, a basic heat pump cycle is examined at a steady state to show the general trends of exergy variations in each process of the cycle. Entropy generation issue for the heat exchangers is discussed to optimize the heat pump cycle. Secondly, the performance of the inverter-driven heat pump is compared to that of the conventional one when the heat load is variable. Thirdly, the exergy destruction rate of the heat pump with On/Off operation is calculated by simulating the thermodynamic states of the working fluid in the condenser and the evaporator. The inefficiency of On/Off operation during the transient period is quantitatively described by the exergy analysis.

• 설비공학논문집
• /
• 제10권2호
• /
• pp.155-164
• /
• 1998

A multi-type heat pump controls the mass flow rate of the working fluid to cope with variable heat loads when it is under dynamic load condition. This paper describes the exergy analysis associated with the dynamic response of heat pump. First, a basic heat pump cycle is examined at steady state to show the general trends of exergy changes in each process of the cycle. Entropy generation issue in the exchangers is discussed to optimize the heat pump cycle. Second, the performance of the inverter-driven heat pump is compared to that of the conventional one when the heat load is variable. Third, the exergy destruction rate associated with the ON/OFF operations of the heat pump is calculated by simulating the thermodynamic states of the condenser and the evaporator. The inefficiency of the ON/OFF operation during the transient period is quantitatively revealed by the exergy analysis.

• 설비공학논문집
• /
• 제11권4호
• /
• pp.464-471
• /
• 1999

This paper describes a design of the helium-recondensing system utilizing cascade Roebuck refrigerators. Superconducting generator or motor has the superconducting field winding in its rotor that should be continuously cooled by cryogen. Since liquid helium transfer from the stationary system to the rotor is problematic, cumbersome, and inefficient, the novel concept of a rotating helium-recondensing system is contrived. The vaporized cold helium inside the rotor is isothermally compressed by centrifugal force and expanded sequentially in cascade refrigerators until the helium is recondensed at 4.2K. There is no helium coupling between the rotor and the stationary liquid helium storage. Thermodynamic analysis of the cascade refrigeration system is performed to determine the key design parameters. The loss mechanisms are also explained to identify entropy generation that degrades the performance of the system.

• 대한기계학회논문집
• /
• 제8권6호
• /
• pp.564-568
• /
• 1984

본 연구에서는 실제 동력 발생장치에 사용되는 사이클은 장치의 크기를 고려 한 파라미터의 선정이 필요하며, 여기서는 열전달에 의한 비가역성을 고려할 때의 열 기관 사이클을 출력에 중점을 두어 해석하고자 한다. 그리고 비가역성에 의한 엔트 로피 생성량과 출력과의 관계도 살펴볼 것이다.