• 한국지능시스템학회논문지
• /
• 제10권3호
• /
• pp.203-210
• /
• 2000

본 논문에서는 패턴분류문제를 해결하기 위한 새로운 무감독학습 신경망 및 경쟁학습 알고리즘을 제한한다. 제아하는 신경망은 입력 데이터의 군집을 분류하기 위한 거리측도로서 군집들 상호간의 상대유사도(relative similarity)를 기반으로 하고 있다. 이러한 까닭에 제안하는 신경망과 알고리즘을 상대유사 신경망 (relative similarity network; RSN)및 학습 알고리즘이라 이름한다. 상대유사도를 정의하고 가중벡터 학습 규칙을 구성함으로써, RSN의 구조를 설계하고 학습알고리즘을 구현하기 의한 의사코드를 기술한다. 일반적인 패턴분류에 RSN을 적용한 결과, 초기 학습률이 없음에도 불구하고 기존이 경쟁학습 신경망인 WTAdlsk SOM고 동등한 성능을 나타내었다. 반면 기존 경쟁학습 신경망의 분류성능이 저하되었던 군집이 경걔가 불분명한 패턴, 그리고 군집이 밀집도와 군집의 크기가 다른 패턴들에 대한 실험에서는 기존의 경쟁학습망보다 효과적인 분류결과를 나타내었다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제10권3호
• /
• pp.218-223
• /
• 2010

Discussion and analysis about relative mutual information has been carried out through fuzzy entropy and similarity measure. Fuzzy relative mutual information measure (FRIM) plays an important part as a measure of information shared between two fuzzy pattern vectors. This FRIM is analyzed and explained through similarity measure between two fuzzy sets. Furthermore, comparison between two measures is also carried out.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권1호
• /
• pp.76-81
• /
• 1999

The degree of relative similarity between 2D patterns is obtained using Open-Ball Scheme. Open-Ball Scheme employs a method of transforming the geometrical information on 3D objects or 2D patterns into the features to measure the relative similarity for object(patten) recognition, with invariance on scale, rotation, and translation. The feature of an object is used to obtain the relative similarity and mapped into [0, 1] the interval of real line. For decades, Moment-Invariant Method has been used as one of the excellent methods for pattern classification and object recognition. Open-Ball Scheme uses the geometrical structure of patterns while Moment Invariant Method uses the statistical characteristics. Open-Ball Scheme is compared to Moment Invariant Method with respect to the way that it interprets two-dimensional patten classification, especially the paradigms are compared by the degree of closeness to human's intuitive understanding. Finally the effectiveness of the proposed Open-Ball Scheme is illustrated through simulations.

• 한국지능시스템학회논문지
• /
• 제7권2호
• /
• pp.66-69
• /
• 1997

본 논문에서는 퍼지 유사 척도가 제시된다. 제시된 퍼지 유사 척도는 유사도를 결정하기 위해서 유크라디안 거리와 함께 데이터와 클러스터 대표값들 사이의 상대적 거리를 고려한다. 클러스터의 경계선은 경쟁이 심한 곳에서는 축소되며 경쟁이 심하지 않은 곳에서는 확장된다. 본 논문의 결과는 상대적 거리를 유사 척도로 사용하는 가능성을 보인다.

• 경영과학
• /
• 제28권1호
• /
• pp.61-74
• /
• 2011

Not only the preference data but also the similarity data can be used for developing effective marketing strategies. Hahn et al.[10] proposes a methodology of representing a brand(focal brand)'s competitors in a single map called the Preference-Similarity Map, according to their relative preference to and similarity with the focal brand. They also proposes a way to derive the relative preference and similarity values from the survey collecting the choice data from differing choice sets. This study identifies the limitations of the preference and similarity measures proposed by Hahn et al.[10] and shows how these measures can be revised. This study also proposes how to implement the revised measures and analyze brands' positioning strategies. Based on the results of the previous studies on the effect of inter brand similarity on brand evaluations, this study assumes that it is important to analyze how much a specific brand is preferred to its close competitors when evaluating the effectiveness of the brand's positioning in the market. This study applies the proposed measures to the data used in Hahn et al.[10] and also show how the proposed measures are related to the parameters of the choice model proposed by Batsell and Polking[1].

• 대한전기학회논문지:시스템및제어부문D
• /
• 제50권7호
• /
• pp.350-353
• /
• 2001

In general, the Least Square Error method is used for signal classification to measure distance in the $l^2$ metric or the $L^2$ metric space. A defect of the Least Square Error method is that it does not classify properly some waveforms, which is due to the property of the Least Square Error method: the global analysis. This paper proposes a new linear operator, the Integra-Normalizer, that removes the problem. The Integra-Normalizer possesses excellent property that measures the degree of relative similarity between signals by expanding the functional space with removing the restriction on the functional space inherited by the Least Square Error method. The Integra-Normalizer shows superiority to the Least Square Error method in measuring the relative similarity among one dimensional waveforms.

• 제어로봇시스템학회논문지
• /
• 제5권5호
• /
• pp.550-557
• /
• 1999

This paper describes a road-following controller using the proposed neural network for autonomous vehicle. Road-following with visual sensor like camera requires intelligent control algorithm because analysis of relation from road image to steering control is complex. The proposed neural network, relative similarity modular network(RSMN), is composed of some learning networks and a partitioniing network. The partitioning network divides input space into multiple sections by similarity of input data. Because divided section has simlar input patterns, RSMN can learn nonlinear relation such as road-following with visual control easily. Visual control uses two criteria on road image from camera; one is position of vanishing point of road, the other is slope of vanishing line of road. The controller using neural network has input of two criteria and output of steering angle. To confirm performance of the proposed neural network controller, a software is developed to simulate vehicle dynamics, camera image generation, visual control, and road-following. Also, prototype autonomous electric vehicle is developed, and usefulness of the controller is verified by physical driving test.

• 한국멀티미디어학회논문지
• /
• 제21권7호
• /
• pp.772-778
• /
• 2018

We have previously proposed a preliminary cut-off indoor positioning scheme considering the reference point with the same signal similarity. This scheme estimates the position using the relative rank of the peak of received signal strength from the beacons around user. However, this scheme has a weak point with lower accuracy when there are more than one nearest reference points having the same signal similarity. In order to tackle this, we propose a weighted preliminary cut-off indoor positioning scheme. Firstly, if the above problem occurs, the similarity to the peak of signal strength is considered as well as the relative rank. Next, weights are assigned to the nearest reference points using the similarity to the peak of the received signal strength. Finally, the user's position is estimated by applying the weights. As a result, the weighted preliminary cut-off scheme improves the positioning accuracy by about 7.9% compared to the previous scheme.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.825-828
• /
• 1991

This paper addresses estimation of the relative shift vector from aerial image sequences. We perform similarity function tests and decide the most appropriate similarity function for the visual navigation system using aerial images. Finally, we propose the maximum variance reference line selection method for reducing the estimation error of the shift vector.

• 대한인간공학회지
• /
• 제21권3호
• /
• pp.47-58
• /
• 2002

The similarity of shape of shape of interface between human cognitive map and real product is the important factor to determine the human performance. Nevertheless, the degree of similarity between these has not been defined quantitatively in recent studies. Therefore, in this study, the cognitive map and the mental workload were measured by SMM(Sketch Map Method) and RNASA-TLX(Revision of NASA-Task Load Index). And the numerical expression of the accuracy point was suggested for the quantitative calculation of relative positional similarity between cognitive map and real product. In the experiment, nine subjects were participated and two kinds of vehicles were used. Mental workload was mental workload was measured immediately after the road test. The result of analysis on the relationship between accuracy and mental workload shows that the negative correlation exists on each vehicle, and the lower score of mental workloads id measured on the vehicle that has the higher score of accuracy between two vehicles.