• 대한전기학회논문지:전력기술부문A
• /
• 제54권8호
• /
• pp.418-428
• /
• 2005

In this paper, a new probabilistic generation modeling method which can address the characteristics of changed electricity industry is proposed. The major contribution of this paper can be captured in the development of a probabilistic generation modeling considering generator maintenance outage and in the classification of market demand into multiple demand clusters for the applications to electricity markets. Conventional forced outage rates of generators are conceptually combined with maintenance outage of generators and, consequently, effective outage rates of generators are newly defined in order to properly address the probabilistic characteristic of generation in electricity markets. Then, original market demands are classified into several distinct demand clusters, which are defined by the effective outage rates of generators and by the inherent characteristic of the original demand. We have found that generators have different effective outage rates values at each classified demand cluster, depending on the market situation. From this, therefore, it can be seen that electricity markets can also be classified into several groups which show similar patterns and that the fundamental characteristics of power systems can be more efficiently analyzed in electricity markets perspectives, for this classification can be widely applicable to other technical problems in power systems such as generation scheduling, power flow analysis, price forecasts, and so on.

• 지능정보연구
• /
• 제7권2호
• /
• pp.83-93
• /
• 2001

기업부실예측은 과거로부터 많은 연구가 이루어진 분야로, 주로 통계기법에 의한 분류예측문제로 다루어져 왔다. 최근에는 인공신경망, 의사결정나무 등 비선형성을 반영할 수 있는 인공지능 기법을 적용한 연구가 많이 수행되고 있다. 본 연구에서는 최적화에 주로 활용하는 인공지능 기법인 유전자 알고리즘을 규칙추출을 통한 기업부실예측 모형의 개발에 적용하고, 활용가능성을 검증하였다.

• 한국통신학회논문지
• /
• 제29권7C호
• /
• pp.931-936
• /
• 2004

GPDF(Gaussian Probability Density Function)을 효율적으로 군집화할 수 있는 GBFCM(DM)(Gradient Based Fuzzy c_means with Divergence Measure) 알고리즘이 본 논문에서 제안되었다. 제안된 GBFCM(DM)은 데이터 사이의 거리 척도로 발산거리(Divergence measure)를 적용한 새로운 형태의 FCM으로, 기존의 GBFCM에 기반을 두는 알고리즘이다. 본 논문에서는 MPEG VBR 비디오 데이터를 GPDF형태의 다차원 데이터로 변형시켜 모델링 하고, 모델링 한 MPEG VBR 비디오 데이터를 영화 또는 스포츠 형태로 분류하는데 응용되었다. 본 논문의 실험에서 기존의 FCM, GBFCM과 새롭게 제안된 GBFCM(DM)을 사용하여 모델링 및 분류결과를 상호 비교하였다. 비교결과 GBFCM(DM)이 오분류율의 기준에서 기존의 다른 알고리즘들에 비해 약 5∼l5%의 향상된 성능을 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 제36회 하계학술대회 논문집 A
• /
• pp.804-806
• /
• 2005

In this paper, a new probabilistic generation modeling method which can address the characteristics of changed electricity industry is proposed. The major contribution of this paper can be captured in the development of a probabilistic generation modeling considering generator maintenance outage and in the classification of market demand into multiple demand clusters for the applications to electricity markets. Conventional forced outage rates of generators are conceptually combined with maintenance outage of generators and, consequently, effective outage rates of generators are new iy defined in order to properly address the probabilistic characteristic of generation in electricity markets. Then, original market demands are classified into several distinct demand clusters, which are defined by the effective outage rates of generators and by the inherent characteristic of the original demand. We have found that generators have different effective outage rates values at each classified demand cluster, depending on the market situation. From this, therefore, it can be seen that electricity markets can also be classified into several groups which show similar patterns and that the fundamental characteristics of power systems can be more efficiently analyzed in electricity markets perspectives, for this classification can be widely applicable to other technical problems in power systems such as generation scheduling, power flow analysis, price forecasts, and so on.

• 한국멀티미디어학회논문지
• /
• 제18권12호
• /
• pp.1519-1527
• /
• 2015

TFT-LCD automatic defect inspection system for detecting defects in place of the visual tester does pre-processing, candidate defect pixel detection, and recognition and classification through a blob analysis. An over-detection result of defects acts as an undue burden of blob analysis for recognition and classification. In this paper, we propose defect detection method based on the histogram distribution modeling of TFT-LCD image to minimize over-detection of candidate defective pixels. Primary defect candidate pixels are detected estimating the skewness of the luminance distribution histogram of the background pixels. Based on the detected defect pixels, the defective pixels other than noise pixels are detected using the distribution histogram model of the local area. Experimental results confirm that the proposed method shows an excellent defect detection result on the image containing the various types of defects and the reduction of the degree of over-detection as well.

• 지구물리와물리탐사
• /
• 제2권4호
• /
• pp.202-208
• /
• 1999

Chirp sonar 시스템을 이용하여 획득한 광역주파수 음향반사자료의 감쇠특성을 나타내는 음향학적 분류변수를 고안하였다. 분류변수는 퇴적물 물성에 따른 분산효과에 의한 감쇠특성을 나타내며, 음향반사신호의 푸리에 변환을 이용한 unwrapped 위상의 미분치로부터 구하였다. 그리고 각기 다른 퇴적상을 나타내는 지점에서 획득된 음향반사신호의 지질음향모델링을 통하여 퇴적물 물성에 따른 감쇠특성을 평가하였다. 그 결과, 분류변수는 입자크기와 성분에 따른 퇴적물 형태와 해저면 굳기에 따라 값의 차이를 보였으며, 이는 음향자료로부터 직접 해저면을 분류하는데 효과적으로 사용할 수 있다.

• 한국BIM학회 논문집
• /
• 제9권4호
• /
• pp.31-40
• /
• 2019

With Building Information Modeling(BIM) becoming the de facto standard for data sharing in the AEC industry, additional needs have increased to ensure the data integrity of BIM models themselves. Although the Industry Foundation Classes provide an open and neutral data format, its generalized schema leaves it open to data loss and misclassifications This research applied deep learning to automatically classify BIM elements and thus check the integrity of BIM-to-IFC mappings. Multi-view CNN(MVCC) and PointNet, which are two deep learning models customized to learn and classify in 3 dimensional non-euclidean spaces, were used. The analysis was restricted to classifying subtypes of architectural walls. MVCNN resulted in the highest performance, with ACC and F1 score of 0.95 and 0.94. MVCNN unitizes images from multiple perspectives of an element, and was thus able to learn the nuanced differences of wall subtypes. PointNet, on the other hand, lost many of the detailed features as it uses a sample of the point clouds and perceived only the 'skeleton' of the given walls.

• 전자공학회논문지
• /
• 제52권1호
• /
• pp.61-68
• /
• 2015

최근에 위,변조 영상의 처리이력 복구를 위한 포렌식 툴로서 미디언 필터링 (MF: Median Filtering) 검출기가 크게 고려되고 있다. 미디언 필터링의 분류를 위한 미디언 검출기는 적은 양의 특징 셋과 높은 검출율을 갖도록 설계되어야 한다. 본 논문은 변조된 영상의 미디언 필터링 검출을 위한 새로운 방법을 제안한다. BMP를 미디언 윈도우 사이즈에 의하여 여러 미디언 필터링 영상으로 변환하고, 윈도우 사이즈에 따른 차분포 값을 계산하여 그 값으로 미디언 필터링 윈도우 사이즈와 같은 특징 셋을 만든다. 미디언 필터링 검출기에서, 특징 셋은 잠재성장 모델링 (LFM: Latent Growth Modeling)을 사용하는 모델 특성으로 변환된다. 실험에서, 테스트 영상은 TP (True Positive)와 FN (False Negative) 두 분류로 판별된다. 제안된 알고리즘은 분류 효율성이 TP와 FN의 혼동에서 최소거리 평균이 0.119로서 훌륭한 성능임이 확인 되었다.

• 전기학회논문지
• /
• 제56권7호
• /
• pp.1224-1230
• /
• 2007

In this paper, we study the classification of defects at steam generator tube in nuclear power plant using eddy current testing (ECT). We consider 4 defect patterns of SG tube: I-In type, I-Out type, V-In type, and V-Out type. Through numerical analysis program based on finite element modeling, 400 ECT signals are generated by varying width and depth of each defect type. In order to improve the classification performance, we propose new feature extraction technique. After extracting new features from the generated ECT signals, multi-layer perceptron is used to classify the defect patterns. Through the computer simulation study, it is shown that the proposed method achieves 100% classification success rate while the previous method yields 91% success rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권11호
• /
• pp.4016-4027
• /
• 2014

Understanding network latency is important for providing consistent and acceptable levels of services in network-based applications. However, due to the difficulty of estimating applications' network demands and the difficulty of network latency modeling the management of network resources has often been ignored. We expect that, since network latency repeats cycles of congested states, a systematic classification method for network status would be helpful to simplify issues in network resource managements. This paper presents a simple empirical method to classify network status with a real operational network. By observing oscillating behavior of end-to-end latency we determine networks' status in run time. Five typical network statuses are defined based on a long-term stability and a short-term burstiness. By investigating prediction accuracies of several simple numerical models we show the effectiveness of the network status classification. Experimental results show that around 80% reduction in prediction errors depending on network status.