• Proceedings of the Korean Society of Tribologists and Lubrication Engineers Conference
• /
• 2000.06a
• /
• pp.54-61
• /
• 2000

A method and results of classification of 4 types metallic wear debris were presented by using their color features. The color image of wear debris was used (or the initial data, and the color properties of the debris were specified by HSI color model. Particle was characterized by a set of statistical features derived from the distribution of HSI color model components. The initial feature set was optimized by a principal component analysis, and multidimensional scaling procedure was used for the definition of classification plane. It was found that five features, which include mean values of H and S, median S, skewness of distribution of S and I, allow to distinguish copper based alloys, red and dark iron oxides and steel particles. In this work, a method of probabilistic decision-making of class label assignment was proposed, which was based on the analysis of debris-coordinates distribution in the classification plane. The obtained results demonstrated a good availability for the automated wear particle analysis.

• Proceedings of the KIEE Conference
• /
• 1998.07c
• /
• pp.1114-1117
• /
• 1998

Recent applications of neural networks to power system fault diagnosis have provided positive results and have shown advantages in process speed over conventional approaches. This paper describes the application of neural network to fault detection and classification in distribution lines using the fundamental component, 2-5th harmonics index, even and odd harmonics index, and zero phase current. The Electromagnetic Transients Program (EMTP) is used to obtain fault patterns for the training and testing of neural networks. The proposed fault detection and classification method in distribution lines is obtained by analysing the difference among normal, HIF, ground fault, short circuit fault condition.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.7
• /
• pp.1193-1205
• /
• 1994

This paper presents a fuzzy system that adaptively classifies subimages to four classes according to image activity distribution. In adaptive transform image coding, subimage classification improves the compression performance by assigning different bit maps to different classes. A conventional classification method sorts subimages by their AC energy and divides them to classes with equal number of subimages. The fuzzy system provides more flexible classification to natural images with various distribution of image details than does the conventional method. Clustering of training data in the input-output product space generated the fuzzy rules for subimage classification. The fuzzy system of small number of fuzzy rules successfully classified subimages to improve the compression performance of the transform image coding without sorting of AC energies.

• Journal of Biomedical Engineering Research
• /
• v.29 no.6
• /
• pp.466-476
• /
• 2008

The more people use ambulatory electrocardiogram(ECG) for arrhythmia detection, the more researchers report the automatic classification algorithms. Most of the previous studies don't consider the un-balanced data distribution. Even in patients, there are much more normal beats than abnormal beats among the data from 24 hours. To solve this problem, the hierarchical classification using 21 features was adopted for arrhythmia abnormal beat detection. The features include R-R intervals and data to describe the morphology of the wave. To validate the algorithm, 44 non-pacemaker recordings from physionet were used. The hierarchical classification model with 2 stages on domain knowledge was constructed. Using our suggested method, we could improve the performance in abnormal beat classification from the conventional multi-class classification method. In conclusion, the domain knowledge based hierarchical classification is useful to the ECG beat classification with unbalanced data distribution.

• Communications for Statistical Applications and Methods
• /
• v.12 no.1
• /
• pp.125-137
• /
• 2005

Many discriminant analysis models for binary data have been used in real applications, but none of the classification models dominates in all varying circumstances(Asparoukhov & Krzanowski(2001)). Lee and Hwang (2003) proposed a new classification model by using multinomial distribution with the maximum entropy estimation method. The model showed some promising results in case of small number of variables, but its performance was not satisfactory for large number of variables. This paper explores to use the iterative cross entropy minimization estimation method in replace of the maximum entropy estimation. Simulation experiments show that this method can compete with other well known existing classification models.

• IEIE Transactions on Smart Processing and Computing
• /
• v.4 no.4
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• Smart Media Journal
• /
• v.9 no.3
• /
• pp.80-89
• /
• 2020

Out - of - distribution (OOD) samples are frequently encountered when deploying a classification model in plenty of real-world machine learning-based applications. Those samples are normally sampling far away from the training distribution, but many classifiers still assign them high reliability to belong to one of the training categories. In this study, we address the problem of removing OOD examples by estimating marginal density estimation using variational autoencoder (VAE). We also investigate other proper methods, such as temperature scaling, Gaussian discrimination analysis, and label smoothing. We use Chonnam National University (CNU) weeds dataset as the in - distribution dataset and CIFAR-10, CalTeach as the OOD datasets. Quantitative results show that the proposed framework can reject the OOD test samples with a suitable threshold.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.3 no.4
• /
• pp.73-86
• /
• 2000

This study focused on extracting an efficient method in the fruit cropping distribution mapping with various classification methods using multi-temporal satellite images and Geographic Information Systems(GIS). For this study, multi-temporal Landsat TM images, in observation data and existing fruit cropping area statistics were used to compare and analyze the properties of fruit cropping and seasonal distribution per classification method. As a result, this study concludes that Maximum Likelihood Method with earlier autumn satellite image was most efficient for the fruit cropping mapping using Landsat TM image. In addition, it was clarified that cropping area per administrative boundary was prepared and distribution pattern was identified efficiently using GIS spatial analysis.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.3
• /
• pp.1-9
• /
• 2021

This research examines deep learning based image recognition models for beef sirloin classification. The sirloin of beef can be classified as the upper sirloin, the lower sirloin, and the ribeye, whereas during the distribution process they are often simply unified into the sirloin region. In this work, for detailed classification of beef sirloin regions we develop a model that can learn image information in a reasonable computation time using the MobileNet algorithm. In addition, to increase the accuracy of the model we introduce data augmentation methods as well, which amplifies the image data collected during the distribution process. This data augmentation enables to consider a larger size of training data set by which the accuracy of the model can be significantly improved. The data generated during the data proliferation process was tested using the MobileNet algorithm, where the test data set was obtained from the distribution processes in the real-world practice. Through the computational experiences we confirm that the accuracy of the suggested model is up to 83%. We expect that the classification model of this study can contribute to providing a more accurate and detailed information exchange between suppliers and consumers during the distribution process of beef sirloin.

• Korean Journal of Remote Sensing
• /
• v.18 no.2
• /
• pp.71-79
• /
• 2002

This research presents particulate distribution map of tidal flats of Hampyung bay using reflectance which extracted from satellite data and field survey data during same periods. The spectrum of particulate composition obtained from Landsat TM data was analysed and 7 scenes of satellite image were classified with ISODATA and K-MEANS methods. The results of unsupervised classification were estimated with in-situ data. The classification accuracy of ISODATA and K-MAMS methods were 84.3% and 85.7%. For validation of classified results of multi-temporal satellite images, TM image of May 1999(reference data), which was classified with field survey data was compared with classified results of multi-temporary satellite data.