• KEPCO Journal on Electric Power and Energy
• /
• 제7권1호
• /
• pp.115-123
• /
• 2021

Through machine learning-based load prediction, it is possible to prevent excessive power generation or unnecessary economic investment by estimating the appropriate amount of facility investment in consideration of the load that will increase in the future or providing basic data for policy establishment to distribute the maximum load. However, in order to secure the reliability of the developed load prediction model in the field, the performance comparison verification between the distribution line load prediction models must be preceded, but a comparative performance verification system between the distribution line load prediction models has not yet been established. As a result, it is not possible to accurately determine the performance excellence of the load prediction model because it is not possible to easily determine the likelihood between the load prediction models. In this paper, we developed a reliability verification system for load prediction models including a method of comparing and verifying the performance reliability between machine learning-based load prediction models that were not previously considered, verification process, and verification result visualization methods. Through the developed load prediction model reliability verification system, the objectivity of the load prediction model performance verification can be improved, and the field application utilization of an excellent load prediction model can be increased.

• 대한안전경영과학회지
• /
• 제10권3호
• /
• pp.81-87
• /
• 2008

The reliability prediction and evaluation for general electronic components are required to guarantee in quality and in efficiency. Although many methodologies for predicting the reliability of electronic components have been developed, their reliability might be subjective according to a particular set of circumstances, and therefore it is not easy to quantify their reliability. In this study reliability prediction of electronic components, that is the interface card, which is used in the CNC(Computerized Numerical Controller) of machine tools, was carried out using PRISM reliability prediction specification. Reliability performances such as MTBF(Mean Time Between Failure), failure rate and reliability were obtained, and the variation of failure rate for electronic components according to temperature change was predicted. The results obtained from this study are useful information to consider a counter plan for weak components before they are used.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2003년도 춘계학술대회
• /
• pp.329-337
• /
• 2003

Stock market prediction is regarded as a challenging task of financial time-series prediction. There have been many studies using artificial neural networks in this area. Recently, support vector machines (SVMs) are regarded as promising methods for the prediction of financial time-series because they me a risk function consisting the empirical ewer and a regularized term which is derived from the structural risk minimization principle. In this study, I apply SVM to predicting the Korea Composite Stock Price Index (KOSPI). In addition, this study examines the feasibility of applying SVM in financial forecasting by comparing it with back-propagation neural networks and case-based reasoning. The experimental results show that SVM provides a promising alternative to stock market prediction.

• Geomechanics and Engineering
• /
• 제18권4호
• /
• pp.373-389
• /
• 2019

It is important to study the problem of durability for tunnel structures. As a main influence on the durability of tunnel structures, carbonation-induced corrosion is studied. For the complicated environment of tunnel structures, based on the data samples from real engineering examples, the intelligent method (genetic programming) is used to construct the service life prediction model of tunnel structures. Based on the model, the prediction of service life for tunnel structures in carbonation environments is studied. Using the data samples from some tunnel engineering examples in China under carbonation environment, the proposed method is verified. In addition, the performance of the proposed prediction model is compared with that of the artificial neural network method. Finally, the effect of two main controlling parameters, the population size and sample size, on the performance of the prediction model by genetic programming is analyzed in detail.

• ETRI Journal
• /
• 제44권2호
• /
• pp.208-219
• /
• 2022

Crime amount prediction is crucial for optimizing the police patrols' arrangement in each region of a city. First, we analyzed spatiotemporal correlations of the crime data and the relationships between crime and related auxiliary data, including points-of-interest (POI), public service complaints, and demographics. Then, we proposed a crime amount prediction model based on 2D convolution and long short-term memory neural network (2DCONV-LSTM). The proposed model captures the spatiotemporal correlations in the crime data, and the crime-related auxiliary data are used to enhance the regional spatial features. Extensive experiments on real-world datasets are conducted. Results demonstrated that capturing both temporal and spatial correlations in crime data and using auxiliary data to extract regional spatial features improve the prediction performance. In the best case scenario, the proposed model reduces the prediction error by at least 17.8% and 8.2% compared with support vector regression (SVR) and LSTM, respectively. Moreover, excessive auxiliary data reduce model performance because of the presence of redundant information.

• 한국지능시스템학회논문지
• /
• 제14권5호
• /
• pp.533-538
• /
• 2004

본 논문은 뉴로-퍼지 모델의 구조 학습을 이용하여 단기 전력 수요 예측시스템을 개발하기 위한 체계적인 방법을 제안한다. 제안된 단기 수요 예측시스템은 1시간, 24시간, 168시간의 예측 리드 타임을 갖고 예측을 수행하기 위해서 요일 유형과 시간 별로 총 96개의 초기 구조를 미리 생성하고, 이를 초기 구조 뱅크에 저장한다. 예측이 수행되는 시점에 해당하는 초기구조를 선택하여 뉴로-퍼지 모델을 초기화하고, 학습하고, 예측을 수행한다. 제안된 예측시스템은 단지 2개의 입력 변수만을 이용하기 때문에 간단한 모델 구조를 가질 뿐 아니라 학습된 퍼지 규칙을 해석하는 것이 매우 용이하다는 장점을 갖는다. 제안된 방법의 실효성을 검증하기 위해 1996년과 1997년의 한극전력의 실제 전력 수요 데이터를 이용하여 1시간, 24시간, 168시간 앞의 전력 수요를 예측하는 모의 실험을 수행한다. 실험 결과 제안된 방법은 단지 2개의 입력 변수를 사용함에도 불구하고, 기존의 예측 방법과 비교하여 예측의 정확도와 신뢰도 측면에서 우수한 성능을 얻는다.

• 한국ITS학회 논문지
• /
• 제19권1호
• /
• pp.1-16
• /
• 2020

4차 산업혁명 시대가 도래함에 따라 빅데이터를 활용하는 딥러닝에 대한 관심이 높아졌으며 다양한 분야에서 딥러닝을 이용한 연구가 활발하게 진행되고 있다. 교통 분야에서도 교통빅데이터를 많이 활용하는 만큼 딥러닝을 연구에 이용한다면 많은 이점이 있을 것이다. 본 연구에서는 통행속도를 예측하기 위하여 딥러닝 기법인 LSTM을 이용한 단기 통행속도 예측 모형을 구축하였다. 예측에 활용한 데이터인 통행속도 데이터가 시계열 데이터인 것을 고려하여 시계열 예측에 적합한 LSTM 모델을 선택하였다. 통행속도를 보다 정확하게 예측하기 위하여 시간적, 공간적 영향을 모두 반영하는 모형을 구축하였으며, 모형은 1시간 이후를 예측하는 단기 예측모형이다. 분석데이터는 서울시 교통정보센터에서 수집한 5분 단위 통행속도를 활용하였고 분석구간은 교통이 혼잡한 강남대로 일부구간으로 선정하여 연구를 수행하였다.

• 한국지능시스템학회논문지
• /
• 제26권4호
• /
• pp.286-294
• /
• 2016

초기설계 단계에서 시스템의 성능을 고려한 형상의 최적화가 필요하다. 하지만, 일반적으로 공학시스템의 성능예측은 많은 계산 시간이 요구되는 작업이다. 시스템 형상의 최적화를 위해서는 다양한 설계대안에 대한 성능의 평가가 요구되므로 초기 설계과정에서 많은 어려움이 있다. 이러한 문제를 해결하기 위해, 많은 연구자들은 응답표면방법을 이용한 성능예측에 관한 다양한 연구를 시도하고 있다. 하지만, 이 방법은 비선형성이 강한 문제에서 예측오차가 비교적 크게 발생하는 단점이 있다. 따라서 본 연구의 최종목표는 초기설계과정에서 성능예측을 위한 적절한 근사모델을 제시하고, 해양시스템 성능예측문제(부유식 해상발전기 하부구조물 최적화 문제, 유조선의 선저외판 최적화 문제)에 적용하여 제시된 근사모델을 검증하는 것이다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권7호
• /
• pp.2513-2530
• /
• 2021

With the fast development of information and communication technologies, video streaming services and applications are increasing rapidly. However, the network condition is volatile. In order to provide users with better quality of service, it is necessary to develop an accurate and low-complexity model for Quality of Experience (QoE) prediction of time-varying video. Memory effects refer to the psychological influence factor of historical experience, which can be taken into account to improve the accuracy of QoE evaluation. In this paper, we design subjective experiments to explore the impact of Short-Term Memory (STM) on QoE. The experimental results show that the user's real-time QoE is influenced by the duration of previous viewing experience and the expectations generated by STM. Furthermore, we propose analytical models to determine the relationship between intrinsic video quality, expectation and real-time QoE. The proposed models have better performance for real-time QoE prediction when the video is transmitted in a fluctuate network. The models are capable of providing more accurate guidance for improving the quality of video streaming services.

• 한국지능시스템학회논문지
• /
• 제17권6호
• /
• pp.799-803
• /
• 2007

본 논문에서는 FSVM(Putty Support Vector Machine)의 퍼지소속함수를 새롭게 제안한다. SVM의 완화변수(slack-variable)에 퍼지소속함수를 결합하는 FSVM은 주어진 데이터베이스의 특성이 반영되어 안정적으로 분류성능을 향상시킬 수 있는 퍼지소속 함수를 필요로 한다. 시계열 자료의 패턴분류 성능을 비교하기 위하여 SVM, FSVM(1), 그리고 제안하는 FSVM(2) 등의 분류모델들을 비교 실험하였다. 사용한 데이터베이스는 한국금융시장의 시계열 경제지표 지수들이다.