• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.922-934
• /
• 2015

In this paper, The classification between precipitation echo(PRE) and non-precipitation echo(N-PRE) (including ground echo and clear echo) is carried out from weather radar data using neuro-fuzzy algorithm. In order to classify between PRE and N-PRE, Input variables are built up through characteristic analysis of radar data. First, the event classifier as the first classification step is designed to classify precipitation event and non-precipitation event using input variables of RBFNNs such as DZ, DZ of Frequency(DZ_FR), SDZ, SDZ of Frequency(SDZ_FR), VGZ, VGZ of Frequency(VGZ_FR). After the event classification, in the precipitation event including non-precipitation echo, the non-precipitation echo is completely removed by the echo classifier of the second classifier step that is built as Type-2 FCM based RBFNNs. Also, parameters of classification system are acquired for effective performance using PSO(Particle Swarm Optimization). The performance results of the proposed echo classifier are compared with CZ. In the sequel, the proposed model architectures which use event classifier as well as the echo classifier of Interval Type-2 FCM based RBFNN show the superiority of output performance when compared with the conventional echo classifier based on RBFNN.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.6
• /
• pp.646-650
• /
• 2014

In this paper, in order to avoid the deterioration of the pattern classification performance which results from the curse of dimensionality, we propose a new feature selection method. The newly proposed feature selection method is based on Fuzzy C-Means clustering algorithm which analyzes the data points to divide them into several clusters and the concept of a function with fuzzy numbers. When it comes to the concept of a function where independent variables are fuzzy numbers and a dependent variable is a label of class, a fuzzy number should be related to the only one class label. Therefore, a good feature is a independent variable of a function with fuzzy numbers. Under this assumption, we calculate the goodness of each feature to pattern classification problem. Finally, in order to evaluate the classification ability of the proposed pattern classifier, the machine learning data sets are used.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 2017.04a
• /
• pp.23-23
• /
• 2017

Recent favor on high quality food and concern on food safety have demonstrated the superiority of Hanwoo (Korean native cattle). In general, the price of cow is higher than those of steer and bull, causing cheating issues in the market. Hence, this study is to discriminate genders of Hanwoo with identification of factors which highly influence gender discrimination based on the big-size deboning data. Totally, there were 31 variables in the deboning data, and we divided into them two categories: data obtained before and after deboning. Discriminant function analysis was then applied into the data to determined the accuracy of gender discrimination in Hanwoo. The result showed that Hanwoo could be classified by gender with 99.2% of accuracy when using all 31 variables. In detail, it was possible to identify 93 of 94 bulls (98.9%), 96 of 96 cows (100%) and 74 of 75 steers (98.7%). The most significant variables was chuck, sirloin, armbone shin, plates, retail and cuts percentage, sequentially. With variables obtainable before deboning, accuracies of classification were 91.5% for bulls, 92.7% for cows, and 89.3% for steers. The most significant variables was water, cold carcass weight and back-fat thickness. The discrimination accuracy was higher with data obtainable after deboning: bulls (98.9%), cows (99.0%) and steers (98.7%). In this case, chuck, sirloin and armbone shin were the factors determined the classification ability. This study showed that Hanwoo can be classified based on deboning data with appropriate statistics, further suggesting weight of cut of beef might be the standard for gender classification.

• Journal of Energy Engineering
• /
• v.20 no.3
• /
• pp.200-208
• /
• 2011

KHNP (Korea Hydro & Nuclear Power Co.) defines and manages equipment of Nuclear Power Plants systematically with functional importance determination of each equipment for efficient maintenance and optimal preventive maintenance. But the existing functional importance determinations have some different results between the plants, systems and engineers due to gap of understanding of classification criteria because they have been done in terms of equipment level rather than function level. so that caused the repeated work. To make up for this problem improve methodology of functional importance determination using MR (Maintenance Rule) and do classification of equipment for new nuclear power plants based on function level. In addition, methodical documentation for basis of importance determination is done to help that system engineers can easily understand and use.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.225-230
• /
• 2020

Machine learning is an algorithm which learns a computer based on the data so that the computer can identify the trend of the data and predict the output of new input data. Machine learning can be classified into supervised learning, unsupervised learning, and reinforcement learning. Supervised learning is a way of learning a machine with given label of data. In other words, a method of inferring a function of the system through a pair of data and a label is used to predict a result using a function inferred about new input data. If the predicted value is continuous, regression analysis is used. If the predicted value is discrete, it is used as a classification. A result of analysis, no. 8 (5, 3.4, setosa), 27 (5, 3.4, setosa), 41 (5, 3.5, setosa), 44 (5, 3.5, setosa) and 40 (5.1, 3.4, setosa) in Table 3 were classified as the most similar Iris flower. Therefore, theoretical practical are suggested.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.3
• /
• pp.123-128
• /
• 2007

This Paper Presents new transient signal classification algorithms for underwater transient signals. In general. the ambient noise has small spectral deviation and energy variation. while a transient signal has large fluctuation. Hence to detect the transient signal, we use the spectral deviation and power variation. To classify the detected transient signal. the feature Parameters are obtained by using the Wigner-Ville distribution based eigenvalue decomposition. The correlation is then calculated between the feature vector of the detected signal and all the feature vectors of the reference templates frame-by-frame basis, and the detected transient signal is classified by the frame mapping rate among the class database.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1042-1042
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from daily monitoring of two Japanese cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from two cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA md FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference.

• Journal of Internet Computing and Services
• /
• v.8 no.3
• /
• pp.109-118
• /
• 2007

This paper proposed a method that can be simply analyzed instead of the basic general Fuzzy rule that its insufficient characters are cut out. Based on the proposed method. Rough sets are used to eliminate the incomplete attributes included in the rule and also for a classification more precise; the agreement of the membership function's output extracted the maximum attributes. Besides, the proposed method in the simulation shows that in order to verify the validity, compare the max-product result of fuzzy before and after reducing rule hosed on the rice taste data; then, we can see that both the max-product result of fuzzy before and after reducing rule are exactly the same; for a verification more objective, we compared the defuzzificated real number section.

• Speech Sciences
• /
• v.15 no.2
• /
• pp.55-65
• /
• 2008

Recently, the multi-model based speech recognizer has been used quite successfully for noisy speech recognition. For the selection of the reference HMM (hidden Markov model) which best matches the noise type and SNR (signal to noise ratio) of the input testing speech, the estimation of the SNR value using the VAD (voice activity detection) algorithm and the classification of the noise type based on the GMM (Gaussian mixture model) have been done separately in the multi-model framework. As the SNR estimation process is vulnerable to errors, we propose an efficient method which can classify simultaneously the SNR values and noise types. The KL (Kullback-Leibler) distance between the single Gaussian distributions for the noise signal during the training and testing is utilized for the classification. The recognition experiments have been done on the Aurora 2 database showing the usefulness of the model compensation method in the multi-model based speech recognizer. We could also see that further performance improvement was achievable by combining the probability density function of the MCT (multi-condition training) with that of the reference HMM compensated by the D-JA (data-driven Jacobian adaptation) in the multi-model based speech recognizer.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.69-79
• /
• 2022

In this study, a method of generating and utilizing a normal map image used to represent the characteristics of the surface of an image material to improve the classification accuracy of the original material image is proposed. First of all, (1) to generate a normal map that reflects the surface properties of a material in an image, a U-Net with attention-R2 gate as a generator was used, and a Pix2Pix-based method using the generated normal map and the similarity with the original normal map as a reconstruction loss was used. Next, (2) we propose a network that can improve the accuracy of classification of the original material image by applying the previously created normal map image to the attention gate of the classification network. For normal maps generated using Pixar Dataset, the similarity between normal maps corresponding to ground truth is evaluated. In this case, the results of reconstruction loss function applied differently according to the similarity metrics are compared. In addition, for evaluation of material image classification, it was confirmed that the proposed method based on MINC-2500 and FMD datasets and comparative experiments in previous studies could be more accurately distinguished. The method proposed in this paper is expected to be the basis for various image processing and network construction that can identify substances within an image.