• 약학회지
• /
• 제49권1호
• /
• pp.74-79
• /
• 2005

Metabonomic analysis has been recognized as a powerful approach for characterizing metabolic changes in biofluids due to toxicity, disease process or environmental influences. To investigate the possibility of relating metabolic changes with $^{1}H-NMR$ spectra, urine samples from Sprague-Dawley rats treated with various dietary restrictions or toxic substances (nicotine) were analysed using $^{1}H-NMR$ spectroscopy and pattern recognition techniques. Dietary restrictions-given to male rats were normal diet and high fat diet and fasting. The nicotine urine samples were collected from SD rats administered with nicotine (25 mg/kg) at the various time intervals. $^{1}H-NMR$ spectra of all urine samples were acquired at 400 MHz on a VARIAN spectrometer. To establish the presence of any intrinsic class-related patterns or clusters in each NMR data, methods of PCA (principal component analysis) and soft independent modeling of class analogy (SIMCA) analysis were used, and the results from these analyses were compared to each other. In all cases of dietary conditions and nicotine treatment, SIMCA analysis gave better results for the discrimination of NMR spectra of urine samples than PCA.

• 비교문화연구
• /
• 제39권
• /
• pp.83-95
• /
• 2015

Every country has a dark history in the process of transition to a modern state. Many countries have until the 21st century, especially in East Asia, colonialism, has experienced conflict influenced, racial discrimination, the trauma of such massacre. Such a dark history in many countries are also still in progress. Dark History of China, which maintains the proletarian dictatorship is the 'Cultural Revolution(Wenhua da Geming)'. 'Cultural Revolution' is neither the outer aspect of the ideological struggle, but in fact it was not even class struggle ideology and class struggle. Put an end to the feudal intellectuals in China in the course of the tragedy stood and lead to build a new China suffered the humiliation of being betrayed from state power. Chinese writers after the 'Cultural Revolution' ended, was created in the process of creation reflects the tragedy of the 'Cultural Revolution' in the country(national memory) is suffering from the pain and suffering the same growth process as it saw this novel growth experienced in the personal growth process. "Road leaving at 18 years" of WiHua has ruled out the pain of growing national attention wholly to personal growth and pain. Such "Road leaving at 18 years" in the sense suggests the possibility of a typical growth story in China Contemporary Literature.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권11호
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• 대한원격탐사학회지
• /
• 제23권4호
• /
• pp.257-272
• /
• 2007

이 논문에서는 촬영 시기 및 촬영 모드(주파수, 편파, 입사각)에 있어서 여러 가지 조건을 가지는 다양한 SAR 자료로부터 특징을 추출하여 토지 피복 항목과의 상호 연관성을 분석하였다. 현재까지 가용한 인공위성 SAR 영상의 촬영 조건을 고려하여 다음의 두 가지 경우로 구분하여 특징을 추출하였다. 첫째, 단일 모드로 다중 시기에 얻어진 SAR 자료로부터 긴밀도, 시간적 변이도, 주성분 변환에 의한 특징들을 추출하였다. C-밴드인 ERS-1/2, ENVISAT SAR, Radarsat-1 자료와 L-밴드인 JERS-1 SAR 자료를 대상으로 이러한 특징들을 각각 추출하였으며, 일반적인 토지 피복 항목과의 연관성 분석을 통해 다중 센서의 특성 차이를 비교 분석하였다. 여러 특징들 중에서 Tandem 긴밀도는 대체적으로 토지 피복 항목간 구별력이 가장 좋게 나타났다. C-밴드 SAR 자료의 장기간 긴밀도에서는 도심 지역의 구분이 용이하였으며, 시간적 변이도에서는 모든 센서 자료에서 논 지역이 가장 높은 값을 나타내었다. 또한 시계열 후방 산란 계수와 긴밀도의 주성분 변환에 기반한 특징들에서는 토지 피복과 관련된 부가 정보 추출이 가능하였다. 둘째, 다중모드(편파, 입사각)로 비슷한 시기에 얻어진 SAR 자료로부터 편파비와 다중 채널 변이도를 주요 특징으로 추출하여 토지 피복 항목별로 비교하였다. 그 결과, VH/VV 편파비로부터 산림과 밭 항목의 구분력이 향상되는 것으로 나타났다. 이 연구의 분석 결과는 향후 다양한 모드의 시계열적 SAR 자료 및 지상 산란계 실험을 통한 다양한 사례 연구 결과와 결합된다면, SAR 자료를 이용한 토지 피복 분류의 정확도 향상을 위한 기초 정보로 활용될 수 있을 것으로 기대된다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제28권9호
• /
• pp.681-687
• /
• 2001

다수의 인식기를 결합하여 베이지안 결정 이론 하에서 클래스 분별력을 높이려면, 훈련 데이터 샘플로부터 얻은 클래스 변수와 결정 변수들로 구성된 조건부 엔트로피에 의해서 한정되는 베이스 에러율의 상위 경계를 최소화해야 한다. Wang과 Wong은 베이스 에러율의 상위 경계를 최소화하기 위하여 클래스 변수와 다수의 특징 패턴 변수들로 구성된 고차 확률 분포를 트리 의존관계로 근사하는 1차 근사 방법을 제안하였다. 본 논문에서는 이러한 베이스 에러율의 상위 경계 최소화에 기반한 기존의 1차 트리 의존관계 근사 방법을 확장하여 고차 의존관계까지 고려할 수 있는 확장된 곱 고차 근사 방법을 제안한다. 제안된 근사 방법을 CENPARMI의 무제약 필기 숫자를 인식하는 다수의 숫자 인식기 결합 방법에 적용하여 인식 실험을 하였으며, 이 방법에 의해서 보다 높은 인식율을 얻게 되었다.

• 한국콘텐츠학회논문지
• /
• 제10권12호
• /
• pp.84-90
• /
• 2010

Viola와 Jones가 사용한 Haar-like 특징 기반 약분류기의 분별력을 개선하기 위하여, 2차 판별식에 기반한 판정 경계(decision boundary) 결정 방법을 제안한다. Viola와 Jones가 부스팅된 약분류기 앙상블을 사용해서 강분류기를 만들 때 사용한 단일 판정 경계 기반 약분류기는 특징 공간을 지나치게 단순하게 해석한 산물이어서 대부분의 경우 최적이 아니며, 객체 클래스와 배경 클래스 간을 효율적으로 분별하기에 흔히 너무 약하다. 이 논문에서 제안하는 2차 판별식 분석에 기반한 방법은 객체 클래스와 배경 클래스 사이에 다중 판정 경계를 사용하는 약분류기를 만들어준다. 1000개의 positive 샘플과 3000개의 negative 샘플을 훈련에 사용하고, 500개의 positive와 500개의 negative를 테스트에 사용한 차량 검출 실험을 통해서, 기존의 단일 문턱치 기반 약분류기 방식에 비해, 제안 기법이 더 적은 수의 분류기를 사용하면서도 더 우수한 분류 성능을 제공하는 것을 확인하였다.

• International Journal of Control, Automation, and Systems
• /
• 제6권6호
• /
• pp.828-835
• /
• 2008

We present a novel method for eye location by means of a two-level classifier scheme. Locating the eye by machine-inspection of an image or video is an important problem for Computer Vision and is of particular value to applications in biomedical imaging. Our method aims to overcome the significant challenge of an eye-location that is able to maintain high accuracy by disregarding highly variable changes in the environment. A first level of computational analysis processes this image context. This is followed by object detection by means of a two-class discrimination classifier(second algorithmic level).We have tested our eye location system using FERET and BioID database. We compare the performance of two-level classifier with that of non-level classifier, and found it's better performance.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2001년도 The Pacific Aisan Confrence On Intelligent Systems 2001
• /
• pp.336-342
• /
• 2001

One of the most important problems on rule induction methods is that they cannot extract rules, which plausibly represent experts decision processes. On one hand, rule induction methods induce probabilistic rules, the description length of which is too short, compared with the experts rules. On the other hand, construction of Bayesian networks generates too lengthy rules. In this paper, the characteristics of experts rules are closely examined and a new approach to extract plausible rules is introduced, which consists of the following three procedures. First, the characterization of decision attributes (given classes) is extracted from databases and the classes are classified into several groups with respect to the characterization. Then, two kinds of sub-rules, characterization rules for each group and discrimination rules for each class in the group are induced. Finally, those two parts are integrated into one rule for each decision attribute. The proposed method was evaluated on a medical database, the experimental results of which show that induced rules correctly represent experts decision processes.

• 음성과학
• /
• 제8권2호
• /
• pp.61-71
• /
• 2001

Speech material, which is collected from ARS(Automatic Response System), was analyzed and classified into disease and non-disease state. The material include 11 different kinds of diseases. Along with ARS speech, DAT(Digital Audio Tape) speech is collected in parallel to give the bench mark. To analyze speech material, analysis tools, which is developed local laboratory, are used to provide an improved and robust performance to the obtained parameters. To classify speech into disease and non-disease class, multi-layered neural network was used. Three different combinations of 3, 6, 12 parameters are tested to obtain the proper network size and to find the best performance. From the experiment, the classification rate of 92.5% was obtained.

• Communications for Statistical Applications and Methods
• /
• 제31권4호
• /
• pp.365-375
• /
• 2024

Diverse methods to evaluate the prediction model of a time to event have been proposed in the context of right censored data where all subjects are subject to be susceptible. A time-dependent AUC (area under curve) measures the predictive ability of a marker based on case group and control one which are varying over time. When a substantial portion of subjects are event-free, a population consists of a susceptible group and a cured one. An uncertain curability of censored subjects makes it difficult to define both case group and control one. In this paper, our goal is to propose a time-dependent AUC for a cure rate model when a censoring distribution is related with covariates. A class of inverse probability of censoring weighted (IPCW) AUC estimators is proposed to adjust the possible sampling bias. We evaluate the finite sample performance of the suggested methods with diverse simulation schemes and the application to the melanoma dataset is presented to compare with other methods.