• Journal of the Korean Statistical Society
• /
• 제33권1호
• /
• pp.59-78
• /
• 2004

A regression function in generalized linear model may have a discontinuity/change point at unknown location. In order to estimate the location of the discontinuity point and its jump size, the strategy is to use a nonparametric approach based on one-sided kernel weighted local-likelihood functions. Weak convergences of the proposed estimators are established. The finite-sample performances of the proposed estimators with practical aspects are illustrated by simulated examples.

• Communications for Statistical Applications and Methods
• /
• 제24권3호
• /
• pp.271-290
• /
• 2017

We study a bivariate response regression model with arbitrary marginal distributions and joint distributions using Frank and Clayton's families of copulas. The proposed model is used for fitting dependent bivariate data with explanatory variables using the log-odd log-logistic Weibull distribution. We consider likelihood inferential procedures based on constrained parameters. For different parameter settings and sample sizes, various simulation studies are performed and compared to the performance of the bivariate odd-log-logistic-Weibull regression model. Sensitivity analysis methods (such as local and total influence) are investigated under three perturbation schemes. The methodology is illustrated in a study to assess changes on schoolchildren's oral health-related quality of life (OHRQoL) in a follow-up exam after three years and to evaluate the impact of caries incidence on the OHRQoL of adolescents.

• The International Journal of Costume Culture
• /
• 제13권2호
• /
• pp.130-140
• /
• 2010

This research was carried out by setting hypotheses on recognition of the global image of the research subject, a domestic cosmetic brand and consequent quality of the brand, reputation of the brand, purchasing decision, influence of images of expanded countries and their correlations to investigate what effect the global images of local brands practically have on domestic consumers' purchasing decision. The analysis results show that overseas expansion of the research subject brand has positive influence on the brand possessing global images. However, it can be seen that the quality of the brand has much larger influence on the reputation of the brand than the images of global brand. In addition, the images of the expanded countries have influence on purchasing decisions but the global images based on the expanded countries did not have much influence on purchasing decisions. Therefore, it can be seen that global images based on high levels of brand reputation and quality are requirements of a most competitive brand than images of the expanded countries in forecasting likelihood of purchase.

• 자원ㆍ환경경제연구
• /
• 제9권4호
• /
• pp.727-746
• /
• 2000

This paper investigates the social attitudes toward compensation of local communities hosting noxious facilities. Using a contingent valuation survey, we find that respondents are more distrustful of government institutes and waste disposal firms than non-governmental organizations. Siting procedures for waste disposal facilities are thought to be unfair 10 general. We also find that social distrust influences the likelihood of voting yes in a referendum to compensate the hosting communities of waste disposal facilities. Individuals who are distrustful of government institutes and waste disposal firms exhibit positive attitudes for the compensation of hosting communities. The higher the level of compensation offered, the less likely to vote yes for compensation.

• 제어로봇시스템학회논문지
• /
• 제10권8호
• /
• pp.742-747
• /
• 2004

Outdoors we can easily acquire our accurate location by GPS. However, the GPS signal can't be acquired indoors because of its weak signal power level. Adequate positioning method is demanded for many indoor positioning applications. At present, wireless local area network (WLAN) is widely installed in various areas such as airport, campus, and park. This paper proposes a positioning algorithm using WLAN signal strength to provide the position of the WLAN user indoors. There are two methods for WLAN based positioning, the signal propagation method uses signal strength model over space and the empirical method uses RF power propagation database. The proposed method uses the probability distribution of the power propagation and the maximum likelihood estimation (MLE) algorithm based on power strength DB. Test results show that the proposed method can provide reasonably accurate position information.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제55권9호
• /
• pp.414-419
• /
• 2006

This paper presents a design of a multi-sensor data fusion filter for a Flight Test System. The multi-sensor data consist of positional information of the target from radars and a telemetry system. The data fusion filter has a structure of a federated Kalman filter and is based on the Singer dynamic target model. It consists of dedicated local filter for each sensor, generally operating in parallel, plus a master fusion filter. A fault detection and correction algorithms are included in the local filter for treating bad measurements and sensor faults. The data fusion is carried out in the fusion filter by using maximum likelihood estimation algorithm. The performance of the designed fusion filter is verified by using both simulation data and real data.

• Journal of Information Processing Systems
• /
• 제11권4호
• /
• pp.643-654
• /
• 2015

Face recognition under controlled settings, such as limited viewpoint and illumination change, can achieve good performance nowadays. However, real world application for face recognition is still challenging. In this paper, we propose using the combination of Affine Scale Invariant Feature Transform (SIFT) and Probabilistic Similarity for face recognition under a large viewpoint change. Affine SIFT is an extension of SIFT algorithm to detect affine invariant local descriptors. Affine SIFT generates a series of different viewpoints using affine transformation. In this way, it allows for a viewpoint difference between the gallery face and probe face. However, the human face is not planar as it contains significant 3D depth. Affine SIFT does not work well for significant change in pose. To complement this, we combined it with probabilistic similarity, which gets the log likelihood between the probe and gallery face based on sum of squared difference (SSD) distribution in an offline learning process. Our experiment results show that our framework achieves impressive better recognition accuracy than other algorithms compared on the FERET database.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• pp.709-711
• /
• 2003

The purpose of this study is to detect the damaged red pine trees by pine wilt disease using high resolution satellite image of IKONOS Geo. IKONOS images are segmented with eCognition image processing software. A segment based maximum likelihood classification was performed to delineate the pine stand. The pine stands are regarded as a potential damage area. In order to develop a methodology to detect the location of damaged trees from the high resolution satellite image, black and white aerial photographs were used as a simulated image. The developed method based on filtering technique. A local maximum filter was adapted to detect the location of individual tree. This report presents a part of the first year results of an ongoing project.

• 국제지역연구
• /
• 제20권1호
• /
• pp.209-234
• /
• 2016

This study examines the effects of exporter agglomeration on purely local firms' decision to undertake internationalization and the resultant performance enhancement from internationalization using propensity score matching and difference-in-differences approach. We find that the likelihood of starting to export is higher when purely local firms are located in a region with a higher level of exporter agglomeration, as positive externalities allow them to overcome insufficient internal resources and reduce the large initial foreign market entry costs. We also find that newly exporting firms are more likely to experience greater performance enhancement from exporting when they are locate in a region with a lower level of exporter agglomeration.

• 응용통계연구
• /
• 제31권1호
• /
• pp.109-122
• /
• 2018

임계값을 기준으로 그 보다 작은 값은 로그정규분포(lognormal distribution; LN)를, 큰 값은 일반화파레토분포(generalized Pareto distribution; GPD)를 따르는 합성 분포를 LN-GPD 합성분포라 한다. Scollnik (2007)은 LN-GPD 합성분포가 로그정규분포와 GPD를 합성 시킴으로써 자료의 손실 없이 꼬리가 두꺼운 분포에서 좋은 적합력을 가진다고 밝혔다. 본 논문에서는 시간에 따라 변하는 LN-GPD 평균모형을 다루었으며 방법론으로는 국소 다항최대우도법을 기반으로 추정하는 방법에 대해서 연구하였다. 시간에 따라 변하는 분포를 추정함으로써 자료에 대한 훨씬 자세한 이해가 가능하며 이는 곧 상담원 배치나 자원배분과 같은 운영관리에 큰 도움을 줄 수 있다. 본 연구는 GPD 분포만을 고려한 Beirlant와 Goegebeur (2004)를 확장하여 절삭한 로그정규분포를 추가하여 자료의 손실 없이 자료의 특징을 살펴볼 수 있다는데도 의의가 있다. 모의실험을 통해 제안한 방법론의 적절함을 살펴 보았고 실증 자료 분석으로 이스라엘 은행의 콜센터 서비스 시간에 대해 분석하여 상담원 배치와 관련된 흥미로운 결과를 찾을 수 있었다.