• Korean Journal of Remote Sensing
• /
• v.25 no.2
• /
• pp.145-154
• /
• 2009

High spatial resolution satellite image classification has a limitation when only using the spectral information due to the complex spatial arrangement of features and spectral heterogeneity within each class. Therefore, the extraction of the spatial information is one of the most important steps in high resolution satellite image classification. This study proposes a new spatial feature extraction method, named SSI(Shape-Size Index). SSI uses a simple region-growing based image segmentation and allocates spatial property value in each segment. The extracted feature is integrated with spectral bands to improve overall classification accuracy. The classification is achieved by applying a SVM(Support Vector Machines) classifier. In order to evaluate the proposed feature extraction method, KOMPSAT-2 and QuickBird-2 data are used for experiments. It is demonstrated that proposed SSI algorithm leads to a notable increase in classification accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.16 no.1
• /
• pp.75-84
• /
• 1998

To achieve more accurate information from satellite image data, a research on a technique for mixed pixel ex-traction has been produced. The mixed pixels with only two land covers have been experimented. By analyzing canonical vector in canonical correlation classification, the mixed pixels have been classified. The ratio of the two canonical weighted values-the elements of canonical vector have been used as a threshold to discriminate mixed pixels. In case of the classification for the mixed pixels of bridge and water class in TM data before or after the 1st of September, the threshold for the optimal classification of the mixed pixels is 4.0. That is, if the ratio of the two canonical weighted values is less than 4.0, the pixel is a mixed pixel. Also, using the distribution of canonical weighted values, the constitution percentages of land covers within one mixed pixel can be approximately deducted. The accuracy of mixed pixel extraction for experimental area is 90％ and quite acceptable. Conclusively, a technique for mixed pixel extraction by canonical vector analysis is effective.

• Journal of the Korea Society of Computer and Information
• /
• v.12 no.1 s.45
• /
• pp.51-56
• /
• 2007

Feature functions were used for the classification of music. The spectral roll-off, variance, average peak level, and class were chosen to make up a feature function vector. Among these, it is the spectral roll-off function that has a low-frequency to high-frequency ratio. To find the optimal roll-off point, the roll-off points from 0.05 to 0.95 were swept. The classification success rate was monitored as the roll-off point was being changed. The data that were used for the experiments were taken from the sounds made by a modern violin and a baroque one. Their shapes and sounds are similar, but they differ slightly in sound texture. As such, the data obtained from the sounds of these two kinds of violin can be useful in finding an adequate roll-off point. The optimal roll-off point, as determined through the experiment, was 0.85. At this point, the classification success rate was 85%, which was the highest.

• The KIPS Transactions:PartB
• /
• v.16B no.4
• /
• pp.281-288
• /
• 2009

This paper proposes a novel algorithm for the efficient classification and annotation of medical images, especially X-ray images. Since X-ray images have a bright foreground against a dark background, we need to extract the different visual descriptors compare with general nature images. In this paper, a Color Structure Descriptor (CSD) based on Harris Corner Detector is only extracted from salient points, and an Edge Histogram Descriptor (EHD) used for a textual feature of image. These two feature vectors are then applied to a multi-class Support Vector Machine (SVM), respectively, to classify images into one of 20 categories. Finally, an image has the Annotation Code Array based on the pre-defined hierarchical relations of categories and priority code order, which is given the several optimal keywords by the Annotation Code Array. Our experiments show that our annotation results have better annotation performance when compared to other method.

• Journal of Korean Neurosurgical Society
• /
• v.39 no.1
• /
• pp.16-19
• /
• 2006

Objective : The purpose of this study is to evaluate the effect of the corpus callosotomy and to elucidate possible prognostic factors. Methods : The cases of 39 patients who underwent corpus callosotomy were reviewed retrospectively. Clinical outcomes were analyzed using Engel's classification, with consideration of various presurgical conditions and the extent of the callosal resection during follow-up more than one year. Results : Satisfactory outcome [Engel's class I, II] was obtained in 20 patients [51%] of 39 patients. In 36 cases with drop attack seizures, the class I, II outcomes were 22 patients [61%]. When the patients were grouped according to the extent of callosal resection, the class I, II outcomes were 50% of the patients with anterior 1/2 or 2/3, 50% of those with anterior 4/5 callosotomy, and 57% of those with total callosotomy, respectively. The mean follow-up period was 34 months [24 to 58 months]. Conclusion : Although it is not statistically significant, the patients who had underwent total callosotomy show better outcomes than those with partial callosotomy. Corpus callosotomy is efficacious in controlling medically intractable epilepsy in appropriately selected patients.

• Journal of KIISE:Information Networking
• /
• v.31 no.6
• /
• pp.556-565
• /
• 2004

A Sandbox has been widely used to prevent damages caused by running of unknown malicious codes. It prevents damages by containing running environment of a program. There is a trade-off in using sandbox, between configurability and ease-of-use. MAPbox, an instance system of sandbox, had employed sandbox classification technique to satisfy both configurability and ease-of-use [1]. However, the configurability of MAPbox can be improved further. In this paper, we introduce a technique to attach dynamic class facility to MAPbox and implement MAPbox-advanced one. Newly generated class in our system has an access control with proper privileges. We show an example for improvements which denote our system have increased the configurability of MAPbox. It was determined as abnormal by MAPbox although is not. Our system could determine it as normal. We also show our techniques to overcome obstacles to implement the system.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.29 no.2
• /
• pp.128-137
• /
• 2018

In this paper, we propose a novel class separability measure for radar signals. To reduce the sensitivity of the relative aspect angle between a target and radar, to evaluate the discriminatory power of radar signals, the proposed method first calculates the correlation coefficients between two radar cross sections (RCSs) or linearly shifts one-dimensional (1D) radar signals (i.e., high-resolution range profiles (HRRPs)), or rotates two 2D radar signals (i.e., inverse synthetic aperture radar (ISAR) images). Then, it uses the maximum correlation coefficient when two radar signals are best aligned. Next, the proposed method obtains new correlation-based discriminant matrices (CDM) using maximum correlation coefficients. Finally, the cumulative distribution function (CDF) in the CDM and the value corresponding to the specific probability in the CDF are obtained, and this value represents the discriminatory power of the radar signal. Experimental results show that the proposed method can accurately measure the target separability.

• Journal of Biomedical Engineering Research
• /
• v.32 no.2
• /
• pp.134-143
• /
• 2011

The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values, but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during l0-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.

• Journal of Chest Surgery
• /
• v.29 no.11
• /
• pp.1202-1206
• /
• 1996

Ebstein's anomaly is an unusual and a rare congenital cardiac malformation but characteristic abnormality of the development of the tricuspid valve, right atrium and ventricle. The characteristic findings are a displaced tricuspid valve with a septal leaflet spiralling into the right ventricle. The surgical correction is variable and are left unsolved problem in surgical treatment of anomaly. Between January 1988 ＆ December 1995, we experienced 11 cases of Ebstein's anomaly and associated cardiac anomalies are ASD, PFO, ASD with VSD. The typically displaced tricuspid valve leaflet was found in all cases. In the NYHA functional classification, three were in class II, seven were in class III, and one was in class IV. Nine patients were operated by tricuspid annuloplasty ＆ plication with Danielson's method and two patients were done by tricuspid valve replacement with plication, and in all cases associated anomaly was corrected. Postoperatively, five patients suffered from complication - low cardiac output syndrome, arrhythmia and wound infection. There was no operative mortality and the postoperative courses were relatively good conditions with more improvement of symptoms.

• Journal of the Korea Society of Computer and Information
• /
• v.18 no.11
• /
• pp.159-165
• /
• 2013

This paper proposes a O(E) polynomial-time algorithm that has been devised to simultaneously solve edge-coloring problem and graph classification problem both of which remain NP-complete. The proposed algorithm selects an edge connecting maximum and minimum degree vertices so as to determine the number of edge coloring ${\chi}^{\prime}(G)$. Determined ${\chi}^{\prime}(G)$ is in turn either ${\Delta}(G)$ or ${\Delta}(G)+1$. Eventually, the result could be classified as class 1 if ${\chi}^{\prime}(G)={\Delta}(G)$ and as category 2 if ${\chi}^{\prime}(G)={\Delta}(G)+1$. This paper also proves Vizing's planar graph conjecture, which states that 'all simple, planar graphs with maximum degree six or seven are of class one, closing the remaining possible case', which has known to be NP-complete.