• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2015년도 제52차 하계학술대회논문집 23권2호
• /
• pp.250-251
• /
• 2015

본 논문에서는 자기 조직화 기능을 갖는 Kohonen의 SOM(Self organization map) 신경회로망과 주어지는 데이터에 따라 초기의 클러스터 개수를 설정하여 처리하는 수정된 K-Means 알고리즘을 결합한 Hybrid Kohonen Network 를 제안한다. 또한, 실제의 항공영상에 적용하여 고전적인 K-Means 알고리즘 및 고전적인 SOM 알고리즘보다 우수함을 보인다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 추계학술대회 논문집 학회본부
• /
• pp.447-449
• /
• 1996

This paper describes an algorithm for short term load forecasting using the Kohonen neural network. Single layer Kohonen neural network presents a lot of advantageous features for practical application. It takes less training time compared to other networks such as BP network, and moreover, its self organized feature can amend the distorted data. The originality of proposed approach is to use a Kohonen map toclassify data representing load patterns and to use directly the information stored in the weight vectors of the Kohonen map to pridict the load. Proposed method was tested with KEPCO hourly record(1993-1995) show better forecasting results compared with conventional exponential smoothing method.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2001년도 추계종합학술대회
• /
• pp.571-574
• /
• 2001

본 논문에서는 코호넨 네트워크를 이용한 효과적인 적응 코딩 방법을 제안한다. 신경망을 응용한 압축법 분석을 통해 설명되는 코딩방법은 압축률을 높이기 위해서 우선 영상을 8$\times$8 부영상으로 나누고, 나눠진 모든 부영상은 DCT로 변형한다. 이들 DCT 부블럭들은 코호넨 네트워크로 N(4) 등급으로 나누어지게 되고, 비트들은 DCT 부블럭의 변수에 따라 분류된다. 그래서 N(4)비트 할당 행렬을 얻었다. 실험 결과는 시뮬레이션으로 나타내었고, 제안한 방법이 신경네트워크에서의 AC 에너지에 의해 부영상을 분류하는 것보다 우수하다는 결론을 얻을 수 있었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 추계학술대회 논문집 학회본부 A
• /
• pp.239-241
• /
• 1999

This paper proposes a novel wavelet transform and Kohonen neural network based technique for short-time load forecasting of power systems. Firstly. Kohonen Self-organizing map(KSOM) is applied to classify the loads and then the Daubechies D2, D4 and D10 wavelet transforms are adopted in order to forecast the short-term loads. The wavelet coefficients associated with certain frequency and time localisation are adjusted using the conventional multiple regression method and then reconstructed in order to forecast the final loads through a four-scale synthesis technique. The outcome of the study clearly indicates that the proposed composite model of Kohonen neural network and wavelet transform approach can be used as an attractive and effective means for short-term load forecasting.

• 한국시뮬레이션학회논문지
• /
• 제20권4호
• /
• pp.115-125
• /
• 2011

제품의 품질 수준 제고를 위해 통계적 공정 관리(SPC : Statistical Process Control)의 다양한 관리도가 기업의 생산 공정을 관리하는데 사용된다. 관리도에 기록되는 공정 데이터는 특정 요인(Assignable Cause)에 의한 이상이 발생했을 때 그 요인에 따라 서로 다른 패턴(Pattern)으로 변화한다. 이러한 패턴을 구별하는 관리도 패턴(CCP : Control Chart Pattern) 인식(Recognition)은 공정에 대한 관리자의 빠른 의사 결정을 위해 매우 중요하다. 앞 선 연구들은 수집되는 원 데이터를 가공 하지않고 그대로 사용하였기 때문에 인식기(Recognizer)의 성능과 학습 속도가 저하되는 문제점이 있었다. 따라서 최근 데이터의 차원 축소와 인식기의 성능 향상을 위해 특질 추출법(Feature Extraction)을 적용한 특질 기반 인식기(Feature based Recognizer)에 대한 연구가 활발히 진행 중이다. 본 논문은 BDK(Bi-Directional Kohonen Network)를 사용하여 CCP의 참조 벡터(Reference Vector)를 생성하고 참조 벡터와 CCP 데이터의 거리를 기반으로 하는 특질을 추출하였다. 추출된 특질을 인공 신경망 기반 인식기의 입력 벡터로 사용하여 학습하였으며 원 데이터를 사용하여 학습하는 인공신경망 인식기와 예측 정확도 비교를 통해 제안 알고리즘의 성능을 평가하였다.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제52권5호
• /
• pp.277-282
• /
• 2003

In this paper we propose Using Higher Order Neuron on the Supervised Learning Machine of the Kohonen Feature Map. The architecture of proposed model adopts the higher order neuron in the input layer of Kohonen Feature Map as a Supervised Learning Machine. It is able to estimate boundary on input pattern space because or the higher order neuron. However, it suffers from a problem that the number of neuron weight increases because of the higher order neuron in the input layer. In this time, we solved this problem by placing the second order neuron among the higher order neuron. The feature of the higher order neuron can be mapped similar inputs on the Kohonen Feature Map. It also is the network with topological mapping. We have simulated the proposed model in respect of the recognition rate by XOR problem, discrimination of 20 alphabet patterns, Mirror Symmetry problem, and numerical letters Pattern Problem.

• International Journal of Automotive Technology
• /
• 제6권4호
• /
• pp.341-350
• /
• 2005

In this study, fault diagnosis and monitoring of serial wound pre-engaged starter motors have been carried out. Starter motors are DC motors that enable internal combustion engine (ICE) to run. In case of breakdown of a starter motor, internal combustion engine can not be worked. Starter motors have vital importance on internal combustion engines. Kohonen network based fault diagnosis system is proposed for fault diagnosis and monitoring of starter motors. A graphical user interface (GUI) software has been developed by using Visual Basic 6.0 for fault diagnosis. Six faults, seen in starter motors, have been diagnosed successfully by using the developed fault diagnosis system. GUI software makes it possible to diagnose the faults in starter motors before they occur by keeping fault records of past occurrences.

• 대한전기학회논문지:전력기술부문A
• /
• 제51권9호
• /
• pp.417-424
• /
• 2002

This paper presents an industrial peak load management system for the peak demand control. Kohonen neural network and wavelet transform based techniques are adopted for industrial peak load forecasting that will be used as input data of the peak demand control. Firstly, one year of historical load data of a steel company were sorted and clustered into several groups using Kohonen neural network and then wavelet transforms are applied with Biorthogonal 1.3 mother wavelet in order to forecast the peak load of one minute ahead. In addition, for the peak demand control, composite fuzzy model is proposed and implemented in this work. The results are compared with those of conventional model, fuzzy model and composite model, respectively. The outcome of the study clearly indicates that the composite fuzzy model approach can be used as an attractive and effective means of the peak demand control.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2000년도 하계학술대회 논문집 A
• /
• pp.301-303
• /
• 2000

This paper presents Kohonen neural network and wavelet transform analysis based technique for industrial peak load forecasting for the purpose of peak demand control. Firstly, one year of historical load data were sorted and clustered into several groups using Kohonen neural network and then wavelet transforms are adopted using the Biorthogonal mother wavelet in order to forecast the peak load of one hour ahead. The 5-level decomposition of the daily industrial load curve is implemented to consider the weather sensitive component of loads effectively. The wavelet coefficients associated with certain frequency and time localization is adjusted using the conventional multiple regression method and the components are reconstructed to predict the final loads through a six-scale synthesis technique.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권9호
• /
• pp.1103-1111
• /
• 1999

STACOM will be utilized to control substation voltage in the near future. Although STACOM shows good voltage regulation performance owing to its rapid and continuous response, it needs additional reactive power compensation device to keep control margin for emergency such as fault. ULTC transformer is one of good candidates. This paper presents a Kohonen Neural Network (KNN) based coordination control scheme of ULTC transformer and STACOM. In this paper, the objective function of the coordination control is minimization of both STACOM output and the number of switchings of ULTC transformer while maintaining substation voltage magnitude to the predefined constant value. This coordination, control is performed based on reactive load trend of the substation and KNN which offers optimal tap position in view of STACOM output minimization. The input variables of KNN are active and reactive power of the substation, current tap position, and current STACOM output. The KNN is trained by effective Iterative Condensed Nearest Neighbor (ICNN) rule. This coordination control applied to IEEE 14 bus system and shows satisfactory results.