• 대한원격탐사학회지
• /
• 제35권6_3호
• /
• pp.1285-1298
• /
• 2019

가뭄은 산불을 일으킬 수 있는 요소 중 하나로, 산불의 빈도 및 피해 면적과 연관성이 있다. 특히, 우리나라는 가뭄이 주로 발생하는 건조한 봄과 가을에 산불이 많이 발생하고, 그 중 일부는 강풍을 동반하여 대형산불로 번지는 경향을 보인다. 따라서 본 연구에서는 우리나라를 대상으로 산불발생 및 면적과 가뭄 변수의 관련성을 파악하고, 우리나라에 적합한 가뭄 변수를 이용하여 산불발생위험 추정을 위한 위성기반의 가뭄지수를 개발하였다. 사용한 가뭄 변수는 다운스케일링(downscaling)한 고해상도의 토양수분, Normalized Different Water Index(NDWI), Normalized Multi-band Drought Index(NMDI), Normalized Different Drought Index(NDDI), Temperature Condition Index(TCI), Precipitation Condition Index(PCI), Vegetation Condition Index(VCI)이며, 경험적 가중 선형조합(Weighted Linear Combination) 및 One-class SVM을 통해 지수 개발을 하였다. 2013년부터 2017년 기간 동안의 변수를 이용하여 상관성 분석을 통해 대부분의 가뭄 변수가 산불 발생에 유의미한 결과를 보임을 확인했으며, 특히 토양수분과 NDWI, PCI가 우리나라 산불과 상관성을 보였다(88 % 이상 일치함). 개발된 지수를 2018년 산불 발생 건에 대해 적용한 결과, 다섯 가지의 선형조합 중에서 토양수분과 NDWI의 조합이 시 공간적으로 적합한 것으로 나타났으며, One-class SVM은 대형산불에 적합한 것으로 나타났다.

• 정보처리학회논문지B
• /
• 제17B권3호
• /
• pp.233-238
• /
• 2010

본 논문에서는 화질 저하 모델에 기반한 다중 인식기 결합을 이용하여 저화질 영상에 대한 인식 성능을 개선하기 위한 방법을 제안한다. 제안하는 방법은 화질 저하 모델을 이용해 특정 화질에 각각 특화된 복수의 인식기들을 생성한다. 인식 과정에서는 인식기들의 결과를 가중 평균에 의해 결합함으로써 최종 결과를 결정한다. 이 때, 각 인식기의 가중치는 입력 영상의 화질 추정 결과에 따라 동적으로 결정된다. 입력 영상의 화질에 특화된 인식기에는 큰 가중치를, 그렇지 않은 인식기에는 작은 가중치를 지정한다. 그 결과, 입력 영상의 화질 변이에 효과적으로 적응할 수 있다. 뿐만 아니라, 복수의 인식기를 사용하기 때문에 저화질 영상에 대하여 단일 인식 시스템보다 더욱 안정적인 성능을 나타낸다. 제안하는 다중 인식기 결합 방법은 화질을 고려하지 않은 다중 인식기 결합 방법이나, 화질을 고려한 단일 인식 방법과 비교하여 더 높은 인식률을 보였다.

• 전기학회논문지
• /
• 제63권4호
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• 한국멀티미디어학회논문지
• /
• 제23권5호
• /
• pp.625-632
• /
• 2020

In the diagnosis of lung cancer, the tumor size is measured by the longest diameter of the tumor in the entire slice of the CT. In order to accurately estimate the size of the tumor, it is better to measure the volume, but there are some limitations in calculating the volume in the clinic. In this study, we propose an algorithm to segment lung cancer by applying a custom loss function that combines focal loss and dice loss to a U-Net model that shows high performance in segmentation problems in chest CT images. The combination of values of the various parameters in custom loss function was compared to the results of the model learned. The purposed loss function showed F1 score of 88.77%, precision of 87.31%, recall of 90.30% and average precision of 0.827 at α=0.25, γ=4, β=0.7. The performance of the proposed custom loss function showed good performance in lung cancer segmentation.

• Smart Structures and Systems
• /
• 제3권2호
• /
• pp.147-172
• /
• 2007

The present paper is concerned with the design of distributed sensors and actuators. Strain type sensors and actuators are considered with their intensity continuously distributed throughout a continuous structure. The sensors measure a weighted average of the strain tensor. As a starting point for their design we introduce the concept of collocated sensors and actuators as well as the so-called natural output. Then we utilize the principle of virtual work for an auxiliary quasi-static problem to assign a mechanical interpretation to the natural output of the sensors to be designed. Therefore, we take the virtual displacements in the principle of virtual work as that part of the displacement in the original problem, which characterizes the deviation from a desired one. We introduce different kinds of distributed sensors, each of them with a mechanical interpretation other than a weighted average of the strain tensor. Additionally, we assign a mechanical interpretation to the collocated actuators as well; for that purpose we use an extended body force analogy. The sensors and actuators are applied to solve the displacement tracking problem for continuous structures; i.e., the problem of enforcing a desired displacement field. We discuss feed forward and feed back control. In the case of feed back control we show that a PD controller can stabilize the continuous system. Finally, a numerical example is presented. A desired deflection of a clamped-clamped beam is tracked by means of feed forward control, feed back control and a combination of the two.

• 전기학회논문지
• /
• 제66권4호
• /
• pp.692-700
• /
• 2017

In this paper, we propose the structural design of Interval Type-2 FCM based RBFNN. Proposed model consists of three modules such as condition, conclusion and inference parts. In the condition part, Interval Type-2 FCM clustering which is extended from FCM clustering is used. In the conclusion part, the parameter coefficients of the consequence part are estimated through LSE(Least Square Estimation) and WLSE(Weighted Least Square Estimation). In the inference part, final model outputs are acquired by fuzzy inference method from linear combination of both polynomial and activation level obtained through Interval Type-2 FCM and acquired activation level through Interval Type-2 FCM. Additionally, The several parameters for the proposed model are identified by using differential evolution. Final model outputs obtained through benchmark data are shown and also compared with other already studied models' performance. The proposed algorithm is performed by using Iris and Vehicle data for pattern classification. For the validation of regression problem modeling performance, modeling experiments are carried out by using MPG and Boston Housing data.

• 한국음향학회지
• /
• 제20권6호
• /
• pp.51-56
• /
• 2001

최근 잡음이 심한 환경에서 음성인식을 신뢰성있게 하기 위하여 입모양의 움직임과 음성을 같이 사용하는 방법이 활발히 연구되고 있다 본 논문에서도 이러한 목적으로 영상언어인식기와 음성인식기의 결과에 각각 가중치를 주어 결합하는 방법을 제안한다. 특히 가중치를 입력음성의 잡음의 정도에 따라 자동적으로 결정하는 방법을 제안한다. 가중치의 결정을 위하여 입력샘플간의 상관도와 LPC분석의 잔여 오차를 이용한다. 모의실험 결과, 이런 방식으로 결합된 인식기는 잡음이 심한 환경에서도 약 83%의 인식성능을 보이고 있다.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2003년도 추계학술대회논문집
• /
• pp.177-182
• /
• 2003

This study is directed toward determining the number and characteristics of psychologically meaningful perceptual dimensions required for assessing the sound Ouaiity with respect to vehicle interior and/or exterior noises. and toward identifying the acoustical or psychoacoustical bases underlying the perception. By nonmetric MDS and clustring analysis of sound quality data sets on our own, of critical importance are two perceptual dimensions for which subjective verdicts can be interpreted as loudness and sharpness. The perceptual dimensions based upon similarity judgments could be accounted for 48% and 24% of the variance. each of which might be a match for the acoustic parameter "A-weighted maximum pressure level"(r= .85) and for the psychoacoustic parameter "sharpness" (r= .65), respectively. On the other hand, the perceptual dimensions based upon preference ratings could explain 66% and 10% of the variance. where the acoustic parameter "A-weighted maximum pressure leve"(r= .92) might be taken to be a best predictor, but sharpness appeared to be less suitable for the description of Preference behavior. Linked to the results, the problems of quantitative modelling of subjective sound quality evaluation and also of implementing corresponding cognitive combination rule for technical and industrial applications, say having "winner-sound qualify" according to preference criteria will be shortly in discussion.

• 한국농공학회지
• /
• 제43권5호
• /
• pp.70-82
• /
• 2001

This study was conducted to derive the regional design rainfall by the regional frequency analysis based on the regionalization of the precipitation suggested by the first report of this project. Using the L-moment ratios and Kolmogorov-Smirnov test, the underlying regional probability distribution was identified to be the Generalized extreme value distribution among applied distributions. Regional and at-site parameters of the generalized extreme value distribution were estimated by the linear combination of the probability weighted moments, L-moment. The regional and at-site analysis for the design rainfall were tested by Monte Carlo simulation. Relative root-mean-square error(RRMSE), relative bias(RBIAS) and relative reduction(RR) in RRMSE were computed and compared with those resulting from at-site Monte Carlo simulation. All show that the regional analysis procedure can substantially reduce the RRMSE, RBIAS and RR in RRMSE in the prediction of design rainfall. Consequently, optimal design rainfalls following the legions and consecutive durations were derived by the regional frequency analysis.

• Industrial Engineering and Management Systems
• /
• 제9권3호
• /
• pp.262-274
• /
• 2010

This article investigates how to adaptively predict the time-varying metrology delay that could realistically occur in the semiconductor manufacturing practice. Metrology delays pose a great challenge for the existing run-to-run (R2R) controllers, driving the process output significantly away from target if not adequately predicted. First, the expected asymptotic double exponentially weighted moving average (DEWMA) control output, by using the EWMA and recursive least squares (RLS) prediction methods, is derived. It has been found that the relationships between the expected control output and target in both estimation methods are parallel, and six cases are addressed. Within the context of time-varying metrology delay, this paper presents a modified recursive least squares-linear trend (RLS-LT) controller, in combination with runs test. Simulated single input-single output (SISO) R2R processes subject to various time-varying metrology delay scenarios are used as a testbed to evaluate the proposed algorithms. The simulation results indicate that the modified RLS-LT controller can yield the process output more accurately on target with smaller mean squared error (MSE) than the original RLSLT controller that only deals with constant metrology delays.