• 한국방재안전학회논문집
• /
• 제8권1호
• /
• pp.21-27
• /
• 2015

전세계적으로 기상이변이 빈번하게 발생하면서 기후변화가 수문환경에 미치는 영향에 대한 연구가 활발히 진행되고 있다. 기후변화 연구에는 대체로 이산화탄소 배출 시나리오에 근거한 GCM 모의 결과가 사용되며, GCM 자료를 바탕으로 미래의 수문량 변화를 예측하는 방법으로 진행된다. 기후변화가 강우에 미치는 영향과 관련해서는 기후변화가 총강우량에 미치는 영향에 대한 연구가 주를 이뤄왔으나 극한강우량에 미치는 영향에 대한 연구는 미흡한 실정이다. 또한 상세화 된 강우 자료가 월단위 또는 일 단위이기 때문에 극한홍수량 산정에 필요한 시단위 극한강우량 추정에는 한계가 있다. 본 연구에서는 기후변화가 극한강우량에 미치는 영향을 분석하기 위해 A2 시나리오에 근거한 ECHO-G GCM 모델의 모의 결과를 상세화 시켜 얻은 한강 유역내의 9개 강우 관측 지점의 일강우 자료를 바탕으로 강우의 scale invariance 특성에 근거한 시단위 확률강우량을 추정하였고, NSRPM(Neymann-Scott Rectangular Pulse Model)을 적용하여 시단위 확률강우량을 추정하였다. 이러한 방법으로 추정된 9개 지점의 확률강우량과 한강유역종합치수계획(국토해양부, 2008)에서 산정한 확률강우량을 비교하여 미래의 확률강우량 변화를 분석하였다. 분석된 한강 유역 내 강우 관측 지점의 확률강우량 변화 추이는 지점에 따라, 미래기간에 따라 상이하게 나타났으나 대체로 scaling에 의한 결과가 관측값에 근거한 확률강우량보다 대체로 큰 값을 보였고, NSRPM에 의한 결과는 미래 기간에 따라 관측값보다 크거나 작은 값을 보였다.

• The Journal of the Acoustical Society of Korea
• /
• 제27권3E호
• /
• pp.77-83
• /
• 2008

In the process of the sonar image textures produced, the orientation and scale factors are very significant. However, most of the related methods ignore the directional information and scale invariance or just pay attention to one of them. To overcome this problem, we apply Gabor wavelet to extract the features of sonar images, which combine the advantages of both the Gabor filter and traditional wavelet function. The mother wavelet is designed with constrained parameters and the optimal parameters will be selected at each orientation, with the help of bandwidth parameters based on the Fisher criterion. The Gabor wavelet can have the properties of both multi-scale and multi-orientation. Based on our experiment, this method is more appropriate than traditional wavelet or single Gabor filter as it provides the better discrimination of the textures and improves the recognition rate effectively. Meanwhile, comparing with other fusion methods, it can reduce the complexity and improve the calculation efficiency.

• Journal of the Korean Data and Information Science Society
• /
• 제14권3호
• /
• pp.653-660
• /
• 2003

In this paper, we prove that the transformed sample Lorenz curve, normalized sample Lorenz curve, and the test statistics for testing of normality based on the normalized sample Lorenz curve and the modified Lorenz curve which were introduced by Kang and Cho (2001a, 2002) are location and scale invariant statistics.

• Communications for Statistical Applications and Methods
• /
• 제2권2호
• /
• pp.52-62
• /
• 1995

Consider an estimation problem under squared error loss in a family of non-regular densities with both terminals of the support being decreasing functions of an unknown parameter. Using Karlin's(1958) technique, sufficient conditions are given for generalized Bayes estimators to be admissible for estimating an arbitrarily positive, monotone parametric function and then treat some examples which illustrate our results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권4호
• /
• pp.2094-2112
• /
• 2019

Focusing on the issue that the conventional Kernel Correlation Filter (KCF) algorithm has poor performance in handling scale change and obscured objects, this paper proposes an anti-occlusion and scale adaptive tracking algorithm in the basis of KCF. The average Peak-to Correlation Energy and the peak value of correlation filtering response are used as the confidence indexes to determine whether the target is obscured. In the case of non-occlusion, we modify the searching scheme of the KCF. Instead of searching for a target with a fixed sample size, we search for the target area with multiple scales and then resize it into the sample size to compare with the learnt model. The scale factor with the maximum filter response is the best target scaling and is updated as the optimal scale for the following tracking. Once occlusion is detected, the model updating and scale updating are stopped. Experiments have been conducted on the OTB benchmark video sequences for compassion with other state-of-the-art tracking methods. The results demonstrate the proposed method can effectively improve the tracking success rate and the accuracy in the cases of scale change and occlusion, and meanwhile ensure a real-time performance.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권1호
• /
• pp.35-43
• /
• 2015

Over the past couple of years, tremendous progress has been made in applying deep learning (DL) techniques to computer vision. Especially, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance on standard recognition datasets and tasks such as ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). Among them, GoogLeNet network which is a radically redesigned DCNN based on the Hebbian principle and scale invariance set the new state of the art for classification and detection in the ILSVRC 2014. Since there exist various deep learning techniques, this review paper is focusing on techniques directly related to DCNNs, especially those needed to understand the architecture and techniques employed in GoogLeNet network.

• 대한전자공학회논문지
• /
• 제24권5호
• /
• pp.905-913
• /
• 1987

This paper presents a speaker dependent isolated digit recognition algorithm using the Mellin transform. Since the Mellin transform converts a scale information into a phase information, attempts have been made to utilize this scale invariance property of the Mellin transform in order to alleviate a time-normalization procedure required for a speech recognition. It has been found that good results can be obtained by taking the Mellin transform to the features such as a ZCR, log energy, normalized autocorrelation coefficients, first predictor coefficient and normalized prediction error. We employed a difference function for evaluating a similarity between two patterns. When the proposed algorithm was tested on Korean digit words, a recognition rate of 83.3% was obtained. The recognition accuracy is not compatible with the other technique such as LPC distance however, it is believed that the Mellin transform can effectively perform the time-normalization processing for the speech recognition.

• 한국정보처리학회논문지
• /
• 제3권4호
• /
• pp.883-898
• /
• 1996

본 논문에서는 패턴인식 시스템의 성능 향상을 목적으로 원영상의 데이타량을 압 축하고 난 뒤 형상을 인식하는 개선된 방법을 제안한다. 제안한 방법에서는 수리형태 론적 연산을 사용하여 원영상을 미리 스켈리턴변환하여 데이터 량을 줄이고, 변환된 영상에서 이동 및 크기의 정규화와 회전불변의 과정을 수행하여 패턴을 정합하였다. 크기의 정규화는 형상인식에 필요한 픽셀의 수를 최소로 하여 정합을 하기 위하여 스켈리턴의 픽셀들에 가중치를 부여하고 이를 이용하여 크기를 조정하였다. 따라서 원영상에서 수행하는 이러한 과정들을 스켈리턴 영상에서 수행하게 함으로써 데이터 량이 크게 줄어들게 되어 기억장소의 용량이 최소화되고 연산의 량도 줄어들어 계산의 속도를 고속화 할 수 있게 하였다. 실험을 통하여 인식에 필요한 최적의 크기 인수를 조사하였고, 제안한 방법이 실제의 인식 시스템 구현시 유용하게 사용할 수 있음을 확인할 수 있었다.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제50권4호
• /
• pp.489-505
• /
• 2011

This study is an analysis on the focus of textbooks regarding the statistical chapters of "measures of representative(central tendency) and of the spread". Applying the summary-concept criteria of Juhyeon Nam(2007), 4 kinds of aspect of the chapter; (1) definition and its teleological validity of the measures of representative, (2) definition and practical value of the measures of spread (3) distributional form on the measures of representative and of spread (4) location and scale preservation or invariance of the measures of representative and of spread were observed. On the measures of representative, some definitions were insufficient to check the teleological validity of the measure. Most definitions of the measure of spread were based on the practical view points but no preparation for the future statistical inferences were found even by implication. Some books mention about the measures of representative and of spread for distributions, but we could not find any comments on the correspondence between the sample mean and the expectation of a distribution or population mean. However it is stimulant that some books check the validity of corresponding measures with the location and scale preservation or invariant property, that were not found in the previous curriculum.

• 한국산업융합학회 논문집
• /
• 제24권6_1호
• /
• pp.693-698
• /
• 2021

As technology advances, there is increasing need for research in different fields where this technology is applied. On of the most researched topic in computer vision is Human activity recognition (HAR), which has widely been implemented in various fields which include healthcare, video surveillance and education. We therefore present in this paper a human activity recognition system based on scale and rotation while employing the Kinect depth sensors to obtain the human skeleton joints. In contrast to previous approaches that use joint angles, in this paper we propose that each limb has an angle with the X, Y, Z axes which we employ as feature vectors. The use of the joint angles makes our system scale invariant. We further calculate the body relative direction in the egocentric coordinates in order to provide the rotation invariance. For the system parameters, we employ 8 limbs with their corresponding angles each having the X, Y, Z axes from the coordinate system as feature vectors. The extracted features are finally trained and tested with the Long short term memory (LSTM) Network which gives us an average accuracy of 98.3%.