• The Transactions of the Korea Information Processing Society
• /
• v.4 no.6
• /
• pp.1541-1549
• /
• 1997

Many classification algorithms require that training examples contain only discrete values. In order to use these algorithms when some attributes have continuous numeric values, the numeric attributes must be converted into discrete ones. This paper describes a new way of discretizing numeric values using information theory. Our method is context-sensitive in the sense that it takes into account the value of the target attribute. The amount of information each interval gives to the target attribute is measured using Hellinger divergence, and the interval boundaries are decided so that each interval contains as equal amount of information as possible. In order to compare our discretization method with some current discretization methods, several popular classification data sets are selected for experiment. We use back propagation algorithm and ID3 as classification tools to compare the accuracy of our discretization method with that of other methods.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.2
• /
• pp.49.1-49.1
• /
• 2016

Asteroid taxonomy dates back to the mid-1970's and is based mostly on broadband photometric and spectroscopic observations in the visible wavelength. Different taxonomic classes have long been characterized by spectral slope shortward of 0.75 microns and the absorption band in 1 micron, the principal components. In this way, taxonomic classes are grouped and divided into four broad complexes; silicates (S), carbonaceous (C), featureless (X), Vestoids (V), and the end-members that do not fit well within the S, C, X and V complexes. The past decade witnessed an explosion of data due to the advent of large-scale asteroid surveys such as SDSS. The classification scheme has recently been expanded with the analysis of the SDSS 4th Moving Object Catalog (MOC 4) data. However, the boundaries of each complex and subclass are rather ambiguously defined by hand. Furthermore, there are only few studies on asteroid taxonomy using Johnson-Cousins filters, and those were conducted on a small number of objects, with significant uncertainties. In this paper, we present our preliminary results for a new taxonomic classification of asteroids using SMASS, Bus and DeMeo (2014) and the SDSS MOC 4 datasets. This classification scheme is simply represented by a triplet of photometric colors, either in SDSS or in Johnson-Cousins photometric systems.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.29-32
• /
• 2008

In this paper, we propose one unsupervised classification technique using the degree of polarization (DoP) and the co-polarized phase-difference (CPD) statistics, instead of the entropy and alpha. It is shown that the DoP is closely related to the entropy, and the CPD to the alpha. The DoP explains the feature how much the effect of multiple reflections is contained. Hence, the DoP could be used as an important factor for classifying classes. The CPD can also be computed from the measured Mueller matrix elements. For the smooth surface scattering, the CPD is about $0^{\circ}$, and for dihedral-type scattering, the CPD is about $180^{\circ}$. A DoP-CPD diagram with appropriate boundaries between six different classes is developed based on the SAR image. The classification results are compared with the existing Entropy-alpha diagram as well as the IPL-AirSAR polarimetric data. The technique may have capability to classify an SAR image into six major classes; a bare surface, a village, a crown-layer short vegetation canopy, a trunk-layer short vegetation canopy, a crown-layer forest, and a trunk-dominated forest. Based on the DoP and CPD analysis, a simple three-component decomposition technique was also proposed.

• Korean Journal of Remote Sensing
• /
• v.32 no.5
• /
• pp.471-482
• /
• 2016

This paper presents an extraction method for water body which uses block-based image partitioning and extension of water body boundaries to improve the performance of supervised classification for water body extraction. The Mahalanobis distance image is created by computing the spectral information of Normalized Difference Water Index (NDWI) and Near Infrared (NIR) band images over a training site within the water body in order to extract an initial water body area. To reduce the effect of noise contained in the Mahalanobis distance image, we apply mean curvature diffusion to the image, which controls diffusion coefficients based on connectivity strength between adjacent pixels and then extract the initial water body area. After partitioning the extracted water body image into the non-overlapping blocks of same size, we update the water body area using the information of water body belonging to water body boundaries. The update is performed repeatedly under the condition that the statistical distance between water body area belonging to water body boundaries and the training site is not greater than a threshold value. The accuracy assessment of the proposed algorithm was tested using KOMPSAT-2 images for the various block sizes between $11{\times}11$ and $19{\times}19$. The overall accuracy and Kappa coefficient of the algorithm varied from 99.47% to 99.53% and from 95.07% to 95.80%, respectively.

• Proceedings of the IEEK Conference
• /
• 2000.06c
• /
• pp.177-180
• /
• 2000

Recently, a feature extraction method based on decision boundary has been proposed for neural networks. The method is based on the fact that all the features necessary to achieve the same classification accuracy as in the original space can be obtained from the vectors normal to decision boundaries. However, the normal vector was estimated numerically. resulting in inaccurate estimation and a long computational time. In this paper. we propose a new method to calculate the normal vector analytically. Experiments show that the proposed method provides a better performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.718-723
• /
• 1993

In this paper, we propose a neural network with fuzzy preprocessor not only for improving the classification accuracy but also for being able to classify objects whose attribute values do not have clear boundaries. The fuzzy input signal representation scheme is included as a preprocessing module. It transforms imprecise input in linguistic form and precisely stated numerical input into multidimensional numerical values. The transformed input is processed in the postprocessing module. The experimental results indicate the superiority of the backpropagation network with fuzzy preprocessor in comparison to the conventional backpropagation network.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• The Research Journal of the Costume Culture
• /
• v.21 no.6
• /
• pp.961-966
• /
• 2013

Being one of the most important textile and apparel producers for years, Turkey began to become active in terms of retailing. Although retailing industry is in its growing phase, the social and economic influences caused the customers' tastes and demands to be more distinctive and segmented in parallel with the advancement of the retail industry. Therefore, the retail industry began to develop in more fragmented way where clear boundaries between different types of retailers were established. In this study, the apparel retail market is overviewed and analyzed within the context for determination of the current situation and future prospective. To this aim, the textile and apparel companies that are active in Turkey were classified into groups based on the type of distribution channels they used. Then, the performances of the groups were established using the secondary type of resources. Finally, the findings were summarized, by showing the similarities and differences between different channels.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.2
• /
• pp.187-196
• /
• 2006

A new GA-based methodology using information granules is suggested for the construction of fuzzy classifiers. The proposed scheme consists of three steps: selection of information granules, construction of the associated fuzzy sets, and tuning of the fuzzy rules. First, the genetic algorithm (GA) is applied to the development of the adequate information granules. The fuzzy sets are then constructed from the analysis of the developed information granules. An interpretable fuzzy classifier is designed by using the constructed fuzzy sets. Finally, the GA is utilized for tuning of the fuzzy rules, which can enhance the classification performance on the misclassified data (e.g., data with the strange pattern or on the boundaries of the classes). To show the effectiveness of the proposed method, an example, the classification of the Iris data, is provided.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.2098-2106
• /
• 2014

In the area of clustering, there are numerous approaches to construct clusters in the input space. For regression problem, when forming clusters being a part of the overall model, the relationships between the input space and the output space are essential and have to be taken into consideration. Conditional Fuzzy C-Means (c-FCM) clustering offers an opportunity to analyze the structure in the input space with the mechanism of supervision implied by the distribution of data present in the output space. However, like other clustering methods, c-FCM focuses on the distribution of the data. In this paper, we introduce a new method, which by making use of the ambiguity index focuses on the boundaries of the clusters whose determination is essential to the quality of the ensuing classification procedures. The introduced design is illustrated with the aid of numeric examples that provide a detailed insight into the performance of the fuzzy classifiers and quantify several essentials design aspects.