• Communications for Statistical Applications and Methods
• /
• 제15권4호
• /
• pp.543-549
• /
• 2008

Inspired by using a robust loss function in the support vector machine regression to control training error and the idea of robust template matching with M-estimator, Chen (2004) applies M-estimator techniques to gaussian radial basis functions and form a new class of robust kernels for the support vector machines. We are specially interested in the shape of the Huber's M-estimator in this context and propose a way to find the shape parameter of the Huber's M-estimating function. For simplicity, only the two-class classification problem is considered.

• Journal of Plant Biology
• /
• 제26권3호
• /
• pp.151-160
• /
• 1983

Structuer, ontogeny, classification and taxonomic significance of trichomes have been studied in 39 genera and 125 species of the selected families in Malvales. They were studied on both vegetative and floral organs. There are nine types of eglandular and eight of glandular trichomes. The trichomes were classified on the basis of their form, structure and contents. All of them originated from a single papillate hair initial. According to the trichome data, the Malvales was comfirmed as a natural order with 5 homogenous families: Malvaceae, Bombacaceae, Sterculiaceae, Tiliaceae, and Elaeocarpaceae.

• Journal of applied mathematics & informatics
• /
• 제11권1_2호
• /
• pp.173-183
• /
• 2003

In this paper, we give a classification of nonoscillatory solution of a second-order neutral delay difference equation of the form △²(x/sub n/-c/sub n/x/sub n-r/)=f(n, x/sub g1(n)/, …, x/sub gm(n)/). Some existence results for each kind of nonoscillatory solutions we also established.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권1호
• /
• pp.67-72
• /
• 2013

Cloud detection and analysis from satellite images has been a topic of research in many atmospheric and environmental studies; however, it still is a challenging task for many reasons. In this paper, we propose a new method for cloud-type classification using fuzzy logic. Knowing that visible-light images of clouds contain thickness related information, while infrared images haves height-related information, we propose a two-layered fuzzy logic based on the input source to provide us with a relatively clear-cut threshold in classification. Traditional noise-removal methods that use reflection/release characteristics of infrared images often produce false positive cloud areas, such as fog thereby it negatively affecting the classification accuracy. In this study, we used the color information from source images to extract the region of interest while avoiding false positives. The structure of fuzzy inference was also changed, because we utilized three types of source images: visible-light, infrared, and near-infrared images. When a cloud appears in both the visible-light image and the infrared image, the fuzzy membership function has a different form. Therefore we designed two sets of fuzzy inference rules and related classification rules. In our experiment, the proposed method was verified to be efficient and more accurate than the previous fuzzy logic attempt that used infrared image features.

• 한국멀티미디어학회논문지
• /
• 제19권12호
• /
• pp.1943-1950
• /
• 2016

Recently, gender classification has attracted a great deal of attention in the field of video surveillance system. It can be useful in many applications such as detecting crimes for women and business intelligence. In this paper, we proposed a method which can detect pedestrians from CCTV video and classify the gender of the detected objects. So far, many algorithms have been proposed to classify people according the their gender. This paper presents a gender classification using convolutional neural network. The detection phase is performed by AdaBoost algorithm based on Haar-like features and LBP features. Classifier and detector is trained with data-sets generated form CCTV images. The experimental results of the proposed method is male matching rate of 89.9% and the results shows 90.7% of female videos. As results of simulations, it is shown that the proposed gender classification is better than conventional classification algorithm.

• 대한공간정보학회지
• /
• 제15권3호
• /
• pp.33-39
• /
• 2007

하이퍼스펙트럴 영상자료는 객체에 대한 많은 정보를 함유하고 있어 객체의 보다 정확한 분류가 가능하다. 본 논문에서는 하이퍼스펙트럴 영상분류를 위하여 SMI(Spectral Mutual Information)이라는 새로운 스펙트럼 유사도 측정기법을 제안하였다. 본 방법은 정보이론 분야에서 대두된 상호정보량의 개념을 차용하여 고안되었으며 스펙트럼간의 통계적 의존성을 측정할 수 있다. SMI는 영상의 각 화소스펙트럼을 확률변수로 간주하고 두 스펙트럼간의 유사 상호정보량을 통하여 유사도를 측정함으로써 영상을 분류한다. 제안된 기법의 효율성을 평가하기 위해 기존에 개발된 SAM, SSV 분류기법을 이용하여 동일지역에 대해 분류를 수행하고 분류 정확도를 비교 평가하였다. 실험결과 제안한 SMI 기법은 하이퍼스펙트럴 영상분류에 유용하게 적용될 수 있으리라 판단된다.

• International Journal of Computer Science & Network Security
• /
• 제23권8호
• /
• pp.49-62
• /
• 2023

There has been a rapid increase in the creation and alteration of new malware samples which is a huge financial risk for many organizations. There is a huge demand for improvement in classification and detection mechanisms available today, as some of the old strategies like classification using mac learning algorithms were proved to be useful but cannot perform well in the scalable auto feature extraction scenario. To overcome this there must be a mechanism to automatically analyze malware based on the automatic feature extraction process. For this purpose, the dynamic analysis of real malware executable files has been done to extract useful features like API call sequence and opcode sequence. The use of different hashing techniques has been analyzed to further generate images and convert them into image representable form which will allow us to use more advanced classification approaches to classify huge amounts of images using deep learning approaches. The use of deep learning algorithms like convolutional neural networks enables the classification of malware by converting it into images. These images when fed into the CNN after being converted into the grayscale image will perform comparatively well in case of dynamic changes in malware code as image samples will be changed by few pixels when classified based on a greyscale image. In this work, we used VGG-16 architecture of CNN for experimentation.

• 대한치과교정학회지
• /
• 제44권5호
• /
• pp.254-262
• /
• 2014

Objective: The purpose of this study was to evaluate the relation between idiopathic scoliosis and facial deformity in the horizontal, vertical, and anteroposterior planes. Methods: A total of 123 female patients aged 14 years or older, who visited the Spine Clinic at the Department of Orthopedics, Korea University Guro Hospital for treatment of idiopathic scoliosis, were enrolled. Whole-spine anteroposterior and lateral radiographs were taken with the patient in a naturally erect position, and frontal and lateral cephalograms were taken in an erect position with the Frankfort horizontal line parallel to the floor. Scoliosis was classified according to the Cobb angle and Lenke classification of six curve types. Cephalometric tracing in all cases was carried out with V-Ceph 5.5 by the same orthodontist. The Kruskal-Wallis test was performed to determine whether any relation existed between each group of the idiopathic scoliosis classification and the cephalometric measurements of frontal and lateral cephalograms. Results: The measurements did not reveal any significant association between the Cobb angle and cephalometric measurements and between the curve type based on the Lenke classification and cephalometric measurements. Conclusions: Based on the results of this study, no apparent relation was observed between the severity of scoliosis and facial form variations in idiopathic scoliosis patients.

• 사상체질의학회지
• /
• 제21권1호
• /
• pp.79-84
• /
• 2009

1. Objectives This study was proposed to use the test-retest method to verify the independence and agreement between the questions (Short Form Sasang Classification Questionnaire for American ; SF_SSCQ-A). 2. Methods The questionnaire was administered to 50 American and they were asked to complete the questionnaire again two weeks after the first administration. The final subjects are 42 except of 5 dropouts and 3 insufficient respondents. A reliability analysis for each individual question was conducted using the test-retest method to verify the independence and agreement between the questions. To verify independence, a Chi-square test with crosstabs analysis and p-values was used. The agreement verification was conducted by using the Cohen kappa coefficient. In addition, the constitutional variable was defined as the constitutional attribute of each question, and Pearson's correlation coefficient was confirmed after testing the scale. 3. Results and Conclusions The test-retest method showed that Pearson's correlation coefficients for the results of the two tests ranged from 0.66 to 0.87. The Chi-square test results indicated that there are 7 independent item. Among the other 114 questions, the agreement test revealed that 88 questions (70.5%) showed above common agreement.

• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2008년도 정기학술발표대회 논문집
• /
• pp.794-799
• /
• 2008

건설 가설재 성능검정제도의 전환기에 들어서 주요 가설재들의 성능검정을 평가하고 선진국의 관련 체계와 비교하여, 안전인증제를 통해 새로운 건설공사용 가설재들의 인증제도를 제안하고자 한다. 현재의 성능검정제도는 1992년에 시작되어 2003년에 재 개정되면서, 3년마다 재 검정을 받도록 하고 있다. 그러나 제조능력을 향상시키지 못하고 업체 간 가격경쟁의 심화로 인해 대부분 같은 형태, 기능의 제품만을 양산하고 있는 실정이다. 기존 성능검정제도에서 안전인증제로의 전환은 보다 체계적인 심사방법 및 품질관리 시스템을 포함하고 있으며, 건설 환경 변화에 대응할 수 있는 다양한 요구사항에 맞춘 규격을 제시할 수 있도록 하고 있다. 안전인증제를 통한 건설공사의 가설재는 의무인증대상과 임의인증대상으로 나누어지며, 종전보다 제품의 품질과 관리 시스템을 향상시켜줄 수 있을 것으로 기대된다.