• Communications for Statistical Applications and Methods
• /
• 제27권6호
• /
• pp.589-602
• /
• 2020

The development of smart grids has enabled the easy collection of a large amount of power data. There are some common patterns that make it useful to cluster power consumption patterns when analyzing s power big data. In this paper, clustering analysis is based on distance functions for time series and clustering algorithms to discover patterns for power consumption data. In clustering, we use 10 distance measures to find the clusters that consider the characteristics of time series data. A simulation study is done to compare the distance measures for clustering. Cluster validity measures are also calculated and compared such as error rate, similarity index, Dunn index and silhouette values. Real power consumption data are used for clustering, with five distance measures whose performances are better than others in the simulation.

• 한국지능시스템학회논문지
• /
• 제19권4호
• /
• pp.556-561
• /
• 2009

In this paper, we propose new method to calculate the distance between intuitionistic fuzzy sets(IFSs) based on the three dimensional representation of IFSs and analyze the relations of similarity measure and distance measure of IFSs. Finally, we apply the proposed measures to pattern recognitions.

• Smart Structures and Systems
• /
• 제6권9호
• /
• pp.991-1005
• /
• 2010

The key to detecting damage to civil engineering structures is to find an effective damage indicator. The damage indicator should promptly reveal the location of the damage and accurately identify the state of the structure. We propose to use the distance measures of low-order AR models as a novel damage indicator. The AR model has been applied to parameterize dynamical responses, typically the acceleration response. The premise of this approach is that the distance between the models, fitting the dynamical responses from damaged and undamaged structures, may be correlated with the information about the damage, including its location and severity. Distance measures have been widely used in speech recognition. However, they have rarely been applied to civil engineering structures. This research attempts to improve on the distance measures that have been studied so far. The effect of varying the data length, number of parameters, and other factors was carefully studied.

• Korean Journal of Acupuncture
• /
• 제33권1호
• /
• pp.18-32
• /
• 2016

Objectives : This study aims to analyze the co-occurrence of pathological symptoms and corresponding acupoints as documented by the comprehensive acupuncture and moxibustion records in the classical texts of Far East traditional medicine as an aid to a more efficient understanding of the tacit treatment principles of ancient physicians. Methods : The Classic of Nourishing Life with Acupuncture and Moxibustion(Zhenjiu Zisheng Jing; hereinafter ZZJ) was selected as the primary reference book for the analysis. The pathology-acupoint co-occurrence analysis was performed by applying 4 values of vector space measures(weighted Euclidean distance, Euclidean distance, $Cram\acute{e}r^{\prime}s$ V and Canberra distance), which measure the distance between the observed and expected co-occurrence counts, and 3 values of probabilistic measures(association strength, Fisher's exact test and Jaccard similarity), which measure the probability of observed co-occurrences. Results : The treatment records contained in ZZJ were preprocessed, which yielded 4162 pathology-acupoint sets. Co-occurrence was performed applying 7 different analysis variables, followed by a prediction simulation. The prediction simulation results revealed the Weighted Euclidean distance had the highest prediction rate with 24.32%, followed by Canberra distance(23.14%) and association strength(21.29%). Conclusions : The weighted Euclidean distance among the vector space measures and the association strength among the probabilistic measures were verified to be the most efficient analysis methods in analyzing the correlation between acupoints and pathologies found in the classical medical texts.

• 전자공학회논문지S
• /
• 제34S권11호
• /
• pp.93-101
• /
• 1997

A Hausdorff distance (HD) is one of commonly used measures for object matching. It calculates the distance between two point sets of edges in two-dimensional binary images without establishing correspondences. This paper proposes three object matching algorithm using robust HD measures based on M-estimation, least trimmed square (LTS), and .alpha.-trimmed mean methods, which are more efficient than the conventional HD measures. By computer simulation with synthetic and real images, the matching performance of the conventional HD smeasures and proposed' robust ones is compared.

• 한국산학기술학회논문지
• /
• 제6권3호
• /
• pp.249-254
• /
• 2005

본 논문은 얼굴인식에서 사용되고 있는 PCA/LDA 방식의 유사도 측정 방식에 따른 인식 성능을 비교 분석하였다. 총 14가지의 거리 척도를 ORL 얼굴 데이터베이스에 적용하였으며, PCA와 PCA/LDA로 나누어 성능 비교를 하였다. PCA의 경우에는 맨하튼 거리, Weighted SSE 거리의 인식률이 좋지만, PCA/LDA인 경우에는 Angle-based 거리, Modified SSE거리에 대한 인식률이 좋음이 확인되었다. 또한 PCA보다 PCA/LDA의 경우 유사도 비교 차원의 수를 줄이면서 높은 인식률을 유지할 수 있어, PCA/LDA와 Angle-based 거리 척도를 적용하여 얼굴인식을 할 경우 계산의 경제성과 인식률에서 높은 경쟁력을 갖출 수 있다.

• Journal of the Korean Statistical Society
• /
• 제27권1호
• /
• pp.113-132
• /
• 1998

In this paper, we consider a minimum distance (M.D.) estimation based on kernels for U-statistics. We use Cramer-von Mises type distance function which measures the discrepancy between U-empirical distribution function(d.f.) and modeled d.f. of kernel. In the distance function, we allow various integrating measures, which can be finite, $\sigma$-finite or discrete. Then we derive the asymptotic normality and study the qualitative robustness of M. D. estimates.

• 한국지능시스템학회논문지
• /
• 제14권1호
• /
• pp.57-62
• /
• 2004

본 논문에서는 연결 성분간의 공간적 간격에 기반하여 수표 영상 내의 필기체 문장 금액에서 단어를 효율적으로 추출하기 위한 방법을 제안한다. 인접한 연결 성분간의 거리측정을 위한 기존의 방식들은 과대추정 또는 과소추정 문제로 인한 단어 분리 오류를 초래할 수 있으나 본 논문에서는 이러한 문제를 줄이기 위해 각 측정 방식들을 수정 보완하였다. 또한 본 논문에서는 서로 다른 형태의 세 가지 거리 측정법들을 효과적으로 결합하여 각 개별 측정법이 가지는 단점을 상호 보완하고 전체 단어 추출 성능을 좀더 향상시킬 수 있는 4-클래스 군집화에 기반한 결합 방법을 새로이 제안하였다. 분장 금액에 대한 단어 추출 실험 결과로부터 수정된 각 거리 측정법이 대응되는 기존의 측정법에 비해 2-3% 정도 향상된 단어 분리율을 보임을 확인하였다. 또한 제안된 4-클래스 군집화에 기반한 결합 방식은 각 측정 방식에서 개별적으로 발생하는 에러뿐만 아니라 두 개의 방식에서 동시에 나타나는 에러도 효율적으로 감소시킴으로서 전체 단어 분리 성능을 향상 시킬수 있었다.

• 한국음향학회지
• /
• 제11권2호
• /
• pp.73-84
• /
• 1992

본 논문에서는 잡음 환경에서 음성 인식 시스템의 성능을 개선할 수 있는 잡음제거 방식과 거리 측정 방법을 연구하고 백색 및 유색 잡음 환경에서 거리 측정 방법에 따른 음성 인식 시스템의 성능을 평가하였다. 잡음 제거 방법으로는 음성 인식 시스템의 전처리 과정으로서 사용될 수 있는 스펙트럼 차감법, 자기 상관 차감법, 적응 잡음 제거, 적응 빔 형성기가 있으며 거리 측정 방법으로는 Log Likelihood Ration($d_{LLR}$), 켑스트럼에 의한 거리 측정 ($d_{CEP}$), 가중 켑스트럼 거리 측정 ($d_{WCEP}$), 스펙트럼 기울기에 의한 거리 측정 ($d_{RPS}$), 켑스트럼 투영 거리 측정방법 ($d_{CP},\;d_{BCP},\;d_{WCP},\;d_{BWCP}$)들이 있다. 백색 및 자동차 잡음 환경에서의 화자 종속 단독음 인식 실험 결과, 켑스트럼 계수의 높은 차수에 큰 가중을 두는 거리 측정 방법인 $d_{RPS},\;d_{WCEP}$가 잡음에 강한 특성을 나타내었으며, 잡음이 존재할 때는 pre-emphasis를 하지 않은 경우가 높은 인식율을 얻을 수 있었다.

• International Journal of Contents
• /
• 제1권2호
• /
• pp.1-4
• /
• 2005

In this paper, we compare 5 weighted distance measures between feature vectors with respect to the recognition performance of the principal component analysis(PCA)-based face recognition method, and propose modified weighted distance. The proposed method was modification of z, the weighted vector. The simulation was performed using the ORL face database, showed the best result for some weighted distances such as weighted manhattan, weighted angle-based, weighted modified manhattan, and weighted modified SSE. We also showed that using some various values of z(weighted values) we can achieve better recognition results that using the existing weighted value.