• The Korean Journal of Ecology
• /
• 제10권2호
• /
• pp.91-107
• /
• 1987

This study is concerned with some methods and applications, used as a basis on information and entropy analysis of vegetation data. These methods are adopted for the evaluating the effect of sampling intensity on information, which repersnets the departure of observed variable from standard component. Classes on the data matrix are caluculated by using marginal dispersion array for rank and weighting information program. Finally the information and entropy are computed by applying seven options. On the application of vegetation studies, two models for cluster analysis and analysis of concentration are explained in detail. Cluster analysis is based on use of equivocation information and Rajski's metrics. The analysis of concentration utilizes coherence coefficience being transformed values, which has been adjusted from blocks and entropy values. The relationship btween three begetation clusters and four stands of Naejangsan data is highly significant in 79% of total variance. Cluster A relatively tends to prefer north side, and cluster C south side.

• IEIE Transactions on Smart Processing and Computing
• /
• 제5권2호
• /
• pp.85-93
• /
• 2016

The existence of correlation characteristics brings significant potential advantages to the development of efficient routing protocols in wireless sensor networks. This research proposes a new simple method of clustering sensor nodes into correlation groups in multiple-correlation areas. At first, the evaluation of joint entropy for multiple-sensed data is considered. Based on the evaluation, the definition of correlation region, based on entropy theory, is proposed. Following that, a correlation clustering scheme with less computation is developed. The results are validated with a real data set.

• 한국수자원학회논문집
• /
• 제42권7호
• /
• pp.537-546
• /
• 2009

상수관망의 유지 관리를 위한 최적 압력 계측 위치 선정은 효율적인 상수관망 운영을 위해 필수적이다. 본 연구에서는 최적 압력 계측 위치 결정에 기존 연구의 단점을 보완하기 위하여 정보이론인 엔트로피 이론을 사용하였다. 기존의 방법은 실측자료를 이용한 검 보정이 필요로 하기에 체계적인 관리가 미흡한 지역에서는 적용이 어려운 단점이 있다. 또한 대부분의 연구가 상수관망 모형의 정확도를 높이며 측정비용을 최소화하는 절점을 제안하였으며, 이는 상수관망 유지 관리를 위한 압력 계측기 위치 결정목적과는 다소 차이가 있다. 본 연구에서 제안된 방법은 특정 절점에서의 유량변화에 의한 다른 절점에서의 압력변화를 정보량인 엔트로피로 정의하여 객관적이고 정량화된 기준을 제시하였다. 절점에서 비정상상태가 발생했을 때 전체 상수관에 미치는 영향 정도를 정량화된 수치인 엔트로피로 나타내며, 또한 각 절점에서 실제적으로 변동하는 압력을 반영하고자 EPANET의 에미터(emitter) 기능을 사용하여 실제 압력변화 패턴을 파악하였다. 최적 압력계 설치 지점은 엔트로피 기준에 의해 전체 시스템으로부터 제공받는 정보량이 가장 큰 절점을 우선으로 설치해야 한다고 제시하였으며, 제안된 모형을 branch형과 loop형 관망에 각각 적용하여 최적 압력 계측 위치를 선정하고 그 결과를 분석하였다. 분석 결과 현재 실무자의 경험적 판단에 의해 계측기를 설치 운영하고 있는 국내의 상수관리 시스템을 고려할 때, 엔트로피 이론을 통해 보다 객관적인 기준으로 상수관망에서의 압력계 설치 우선순위를 운영자에게 제시할 수 있을 것이며, 상수관망에 압력계를 설치하기 위한 효율적인 의사결정 기준으로 활용이 가능할 것으로 판단된다.

• 한국지능시스템학회논문지
• /
• 제17권2호
• /
• pp.149-153
• /
• 2007

본 논문에서 우리는 Wang와 Li(1998)와 Turksen(1986)에 의해 소개된 구간치 퍼지집합을 생각하고 구간치 퍼지집합상에서 쇼케이적분에 의해 정의된 엔트로피를 조사한다. 더욱이, 이러한 엔트로피와 관련된 성질들을 토의하고 간단한 예들을 알아본다. 이 공식은 구간치 퍼지집합상의 결정이론 및 정보이론과 같은 응용 영역에서 중요한 역할을 한다.

• 한국환경과학회지
• /
• 제12권4호
• /
• pp.399-417
• /
• 2003

The seasonal variation and frequency of rainfalls of Korea peninsula in Changma period show strong local weather phenomenon because of it's topographical and geographical factors in Northeast side of Asia. Based on weather entropy(statistical parameter)-the amount of average weather information-and information ratio, we can define each area's weather representativeness, which can show us more constant form included topographical and geographical factors and seasonal variation. The data used for this study are the daily precipitation and cloudiness during the recent ten years(1990-1999) at the 73 stations in Korea. To synthesize weather Entropy, information ratio of decaying tendency and half$.$decay distance, Seoul's weather representativeness has the smallest in Summer Changma period. And Puyo has the largest value in September.

• International Journal of Contents
• /
• 제10권1호
• /
• pp.18-22
• /
• 2014

Hidden nodes have a key role in the information processing of feed-forward neural networks in which inputs are processed through a series of weighted sums and nonlinear activation functions. In order to understand the role of hidden nodes, we must analyze the effect of the nonlinear activation functions on the weighted sums to hidden nodes. In this paper, we focus on the effect of nonlinear functions in a viewpoint of information theory. Under the assumption that the nonlinear activation function can be approximated piece-wise linearly, we prove that the entropy of weighted sums to hidden nodes decreases after piece-wise linear functions. Therefore, we argue that the nonlinear activation function decreases the uncertainty among hidden nodes. Furthermore, the more the hidden nodes are saturated, the more the entropy of hidden nodes decreases. Based on this result, we can say that, after successful training of feed-forward neural networks, hidden nodes tend not to be in linear regions but to be in saturated regions of activation function with the effect of uncertainty reduction.

• 산업경영시스템학회지
• /
• 제26권2호
• /
• pp.55-61
• /
• 2003

The purpose of this paper is to propose a method for selecting the preferred alternatives of Multiple- Attribute Decision-Making(MADM) problem using the Entropy measure. A decision-maker who wants to estimate exactly the weight to be applied to her/his MADM problem is usually confronted with the embarrassing situation where, although there exist a variety of weighting methods, it is hard to find a right procedure to choose a pertinent value To remedy this uncomfortable situation, the Entropy measure commonly used in information theory, Is proposed as a tool that can be used by decision-makers to more efficiently select the preferred alternatives. As a result, the method proposed in the paper can be significant in that relatively easy to understand by decision-makers.

• Journal of information and communication convergence engineering
• /
• 제1권4호
• /
• pp.205-208
• /
• 2003

Voice activity detection is a important problem in the speech recognition and speech communication. This paper introduces new feature parameter which are reconstructed by spectral entropy of information theory for robust voice activity detection in the noise environment, then analyzes and compares it with energy method of voice activity detection and performance. In experiments, we confirmed that spectral entropy and its reconstructed parameter are superior than the energy method for robust voice activity detection in the various noise environment.

• 산업기술연구
• /
• 제3권
• /
• pp.39-46
• /
• 1983

This paper presents a quantitative measure of the degree of part commonality and redundancy in a product line based on entropy measure of information theory. The several possible methods of analysis are discussed and the use of the entropy measure is discussed. These commonality and redundancy measure can be applied to analyze the usage pattern of part across a product line and to determine which parts have the broadest usage across the firm's product lines. An analysis of the results by entropy statistics is compared with the practical part usage in a simulation of several types of part usage's distributions.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2007년도 학술발표회 논문집
• /
• pp.178-182
• /
• 2007

In this study, we evaluated current raingauge network of Soyanggang dam region applying spatial-correlation analysis and Entropy theory to recommend an optimized raingauge network. In the process of analysis, correlation distance of raingauge stations is estimated and evaluated via spatial-correlation method and entropy method. From this correlation distances, respective influencing radii of each dataset and each methods is assessed. The result of correlation and entropy analysis has estimated correlation distance of 25.546km and influence radius of 7.206km, deducing a decrease of network density from $224.53km^2$ to $122.47km^2$ which satisfy the recommended minimum densities of $250km^2$ in mountainous regions(WMO, 1994) and an increase of basin coverage from 59.3% to 86.8%. As for the elevation analysis the relative evaluation ratio increased from 0.59(current) to 0.92(optimized) resulting an obvious improvement.