• 대기
• /
• 제15권3호
• /
• pp.155-165
• /
• 2005

The characteristics of six precipitation systems occurred around Cheongju in 2002 are analyzed after the convective/stratiform radar echo classification using radar reflectivity from the Meteorological Research Institute"s X-band Doppler weather radar. The Biggerstaff and Listemaa (2000) algorithm is applied for the classification and reveals a physical characteristics of the convective and stratiform rain diagnosed from the three-dimensional structure of the radar reflectivity. The area satisfying the vertical profile of radar reflectivity is well classified, while the area near the radar site and the topography-shielded area show a mis-classification. The seasonal characteristics of the precipitation system are also analyzed using the contoured frequency by altitude diagrams (CFADs). The heights of maximum reflectivity are 4 km and 5.5 km in spring and summer, respectively, and the vertical gradient of radar reflectivity from 1.5 km to the melting layer in spring is larger than in summer.

• 한국콘텐츠학회:학술대회논문집
• /
• 한국콘텐츠학회 2004년도 추계 종합학술대회 논문집
• /
• pp.389-394
• /
• 2004

본 논문에서는 디자인 패턴을 분류하기 위해 패턴구조의 특성을 가지고 분류하였다. 그리고 클러스터링에 의한 분류는 패싯 분류에 의한 방법보다 높은 정확도를 보여주었다. 따라서 자동화된 분류방법인 클러스터링 알고리즘을 사용하여 디자인 패턴을 분류하는 것이 효과적이라 할 수 있다. 디자인 패턴의 분류는 검색 시 유사한 패턴들이 같은 카테고리에 저장이 되므로 유사패턴을 비교하여 사용할 수 있으며, 패턴 클러스터링에 의해 분류되고, 패턴의 링크정보를 이용하여 저장하므로 저장소를 효율적으로 관리할 수 있다.

• 한국정밀공학회지
• /
• 제32권5호
• /
• pp.463-470
• /
• 2015

Solar cell is typical representative of renewable green energy. Silicon wafer contributes about 66 percent to its cost structure. In its manufacturing, micro-cracks are often occurred due to manufacturing process such as wire sawing, grinding and cleaning. Their detection and classification are important to process feedback information. In this paper, a classification method of micro-cracks is proposed, based on the fusion of principal component analysis(PCA) and neural network. The proposed method shows that it gives higher results than single application of two methods, in terms of shape and size classification of micro-cracks.

• International journal of advanced smart convergence
• /
• 제5권3호
• /
• pp.8-15
• /
• 2016

In recent years, one of deep learning models called Deep Belief Network (DBN) which formed by stacking restricted Boltzman machine in a greedy fashion has beed widely used for classification and recognition. With an ability to extracting features of high-level abstraction and deal with higher dimensional data structure, this model has ouperformed outstanding result on image and speech recognition. In this research, we assess the applicability of deep learning in dna classification level. Since the training phase of DBN is costly expensive, specially if deals with DNA sequence with thousand of variables, we introduce a new encoding method, using decimal-binary vector to represent the sequence as input to the model, thereafter compare with one-hot-vector encoding in two datasets. We evaluated our proposed model with different contrastive algorithms which achieved significant improvement for the training speed with comparable classification result. This result has shown a potential of using decimal-binary vector on DBN for DNA sequence to solve other sequence problem in bioinformatics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1858-1872
• /
• 2023

With the advance of radar technologies, the availability of synthetic aperture radar (SAR) images increases. To improve application of SAR images, a management system for SAR images is proposed in this paper. The system provides trainable land cover classification module and display of SAR images on the map. Users of the system can create their own classifier with their data, and obtain the classified results of newly captured SAR images by applying the classifier to the images. The classifier is based on convolutional neural network structure. Since there are differences among SAR images depending on capturing method and devices, a fixed classifier cannot cover all types of SAR land cover classification problems. Thus, it is adopted to create each user's classifier. In our experiments, it is shown that the module works well with two different SAR datasets. With this system, SAR data and land cover classification results are managed and easily displayed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• pp.1704-1720
• /
• 2020

Recognizing food from photographs presents many applications for machine learning, computer vision and dietetics, etc. Recent progress of deep learning techniques accelerates the recognition of food in a great scale. We build a hierarchical structure composed of deep CNN to recognize and classify food from photographs. We build a dataset for Korean food of 18 classes, which are further categorized in 4 major classes. Our hierarchical recognizer classifies foods into four major classes in the first step. Each food in the major classes is further classified into the exact class in the second step. We employ DenseNet structure for the baseline of our recognizer. The hierarchical structure provides higher accuracy and F1 score than those from the single-structured recognizer.

• 제어로봇시스템학회논문지
• /
• 제4권4호
• /
• pp.499-505
• /
• 1998

In developing an automated surface inspect algorithm, we have designed a hierarchical classifier using neural network. The defects which exist on the surface of cold mill strip have a scattering or singular distribution. We have considered three major problems, that is preprocessing, feature extraction and defect classification. In preprocessing, Top-hit transform, adaptive thresholding, thinning and noise rejection are used Especially, Top-hit transform using local minimax operation diminishes the effect of bad lighting. In feature extraction, geometric, moment, co-occurrence matrix, and histogram ratio features are calculated. The histogram ratio feature is taken from the gray-level image. For defect classification, we suggest a hierarchical structure of which nodes are multilayer neural network classifiers. The proposed algorithm reduced error rate by comparing to one-stage structure.

• Bulletin of the Korean Chemical Society
• /
• 제30권11호
• /
• pp.2717-2722
• /
• 2009

The use of the classification and regression tree (CART) methodology was studied in a quantitative structure-activity relationship (QSAR) context on a data set consisting of the binding affinities of 39 imidazobenzodiazepines for the α1 benzodiazepine receptor. The 3-D structures of these compounds were optimized using HyperChem software with semiempirical AM1 optimization method. After optimization a set of 1481 zero-to three-dimentional descriptors was calculated for each molecule in the data set. The response (dependent variable) in the tree model consisted of the binding affinities of drugs. Three descriptors (two topological and one 3D-Morse descriptors) were applied in the final tree structure to describe the binding affinities. The mean relative error percent for the data set is 3.20%, compared with a previous model with mean relative error percent of 6.63%. To evaluate the predictive power of CART cross validation method was also performed.

• 대한수학회논문집
• /
• 제33권1호
• /
• pp.325-335
• /
• 2018

We prove every oriented compact cyclic 3-orbifold has a contact structure. There is another proof in the web by Daniel Herr in his uploaded thesis which depends on open book decompositions, ours is independent of that. We define overtwisted contact structures, tight contact structures and Lutz twist on oriented compact cyclic 3-orbifolds. We show that every contact structure in an oriented compact cyclic 3-orbifold contactified by our method is homotopic to an overtwisted structure with the overtwisted disc intersecting the singular locus of the orbifolds. In course of proving the above results we prove a classification result for compact oriented cyclic-3 orbifolds which has not been seen by us in literature before.

• 한국기계기술학회지
• /
• 제20권6호
• /
• pp.776-782
• /
• 2018

After CNN basic structure was introduced by LeCun in 1989, there has not been a major structure change except for more deep network until recently. The deep network enhances the expression power due to improve the abstraction ability of the network, and can learn complex problems by increasing non linearity. However, the learning of a deep network means that it has vanishing gradient or longer learning time. In this study, we proposes a CNN structure with MLP layer. The proposed CNNs are superior to the general CNN in their classification performance. It is confirmed that classification accuracy is high due to include MLP layer which improves non linearity by experiment. In order to increase the performance without making a deep network, it is confirmed that the performance is improved by increasing the non linearity of the network.