• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.9
• /
• pp.652-661
• /
• 2020

Recently, the Korean government developed the RE3020 (renewable energy) policy to overcome environmental problems, such as fine dust, climate change, and large-scale PV systems interconnected with a distribution system. When a large-scale PV system is interconnected in the distribution system, however, a malfunction can occur, and the protection devices may not be operated because of the dividing effect depending on the magnitude and direction of fault current as well as connection types and location of the PV system. Therefore, this paper proposes a search algorithm for the malfunction pattern of protection devices based on various scenarios, when large-scale PV systems are operated and interconnected in a distribution system. This paper presents a malfunction mechanism of protection devices according to the installation locations of recloser (R/C). Furthermore, the modeling of a distribution system with large-scale PV systems was performed using Off-DAS S/W, and the malfunction patterns of protection devices were analyzed based on a range of scenarios. From the simulation results with the proposed model and algorithm for searching for protection devices, it was confirmed that they are useful and effective in identifying a malfunction phenomenon depending on the installation location of the R/C and connection type of PV system.

• Journal of the Korean Data and Information Science Society
• /
• v.27 no.3
• /
• pp.629-638
• /
• 2016

Among data mining techniques, the association rule is one of the most used in the real fields because it clearly displays the relationship between two or more items in large databases by quantifying the relationship between the items. There are three primary quality measures for association rule; support, confidence, and lift. We evaluate association rules using these measures. The approach taken in the previous literatures as to estimation of association rule number has been one of a determination function method or a regression modeling approach. In this paper, we proposed a few of non-linear regression equations useful in estimating the number of rules and also evaluated the estimated association rules using the quality measures. Furthermore we assessed their usefulness as compared to conventional regression models using the values of regression coefficients, F statistics, adjusted coefficients of determination and variation inflation factor.

• Journal of Digital Contents Society
• /
• v.19 no.1
• /
• pp.51-58
• /
• 2018

As the amount of users and data of NS explosively increased, research based on SNS Big data became active. In social mining, Latent Dirichlet Allocation(LDA), which is a typical topic model technique, is used to identify the similarity of each text from non-classified large-volume SNS text big data and to extract trends therefrom. However, LDA has the limitation that it is difficult to deduce a high-level topic due to the semantic sparsity of non-frequent word occurrence in the short sentence data. The BTM study improved the limitations of this LDA through a combination of two words. However, BTM also has a limitation that it is impossible to calculate the weight considering the relation with each subject because it is influenced more by the high frequency word among the combined words. In this paper, we propose a technique to improve the accuracy of existing BTM by reflecting semantic relation between words.

• Phonetics and Speech Sciences
• /
• v.15 no.1
• /
• pp.25-34
• /
• 2023

This study examined the utility of the acoustic features of vowels as cues for the place of articulation of Korean nasal consonants. In the acoustic analysis, spectral and temporal parameters were measured at the 25%, 50%, and 75% time points in the vowels neighboring nasal consonants in samples extracted from a spontaneous Korean speech corpus. Using these measurements, linear discriminant analyses were performed and classification accuracies for the nasal place of articulation were estimated. The analyses were applied separately for vowels following and preceding a nasal consonant to compare the effects of progressive and regressive coarticulation in terms of place of articulation. The classification accuracies ranged between approximately 50% and 60%, implying that acoustic measurements of vowel intervals alone are not sufficient to predict or classify the place of articulation of adjacent nasal consonants. However, given that these results were obtained for measurements at the temporal midpoint of vowels, where they are expected to be the least influenced by coarticulation, the present results also suggest the potential of utilizing acoustic measurements of vowels to improve the recognition accuracy of nasal place. Moreover, the classification accuracy for nasal place was higher for vowels preceding the nasal sounds, suggesting the possibility of higher anticipatory coarticulation reflecting the nasal place.

• Science of Emotion and Sensibility
• /
• v.13 no.1
• /
• pp.47-60
• /
• 2010

Most of the researches about classification usually have used kNN(k-Nearest Neighbor), SVM(Support Vector Machine), which are known as learn-based model, and Bayesian classifier, NNA(Neural Network Algorithm), which are known as statistics-based methods. However, there are some limitations of space and time when classifying so many web pages in recent internet. Moreover, most studies of classification are using uni-gram feature representation which is not good to represent real meaning of words. In case of Korean web page classification, there are some problems because of korean words property that the words have multiple meanings(polysemy). For these reasons, LSA(Latent Semantic Analysis) is proposed to classify well in these environment(large data set and words' polysemy). LSA uses SVD(Singular Value Decomposition) which decomposes the original term-document matrix to three different matrices and reduces their dimension. From this SVD's work, it is possible to create new low-level semantic space for representing vectors, which can make classification efficient and analyze latent meaning of words or document(or web pages). Although LSA is good at classification, it has some drawbacks in classification. As SVD reduces dimensions of matrix and creates new semantic space, it doesn't consider which dimensions discriminate vectors well but it does consider which dimensions represent vectors well. It is a reason why LSA doesn't improve performance of classification as expectation. In this paper, we propose new LSA which selects optimal dimensions to discriminate and represent vectors well as minimizing drawbacks and improving performance. This method that we propose shows better and more stable performance than other LSAs' in low-dimension space. In addition, we derive more improvement in classification as creating and selecting features by reducing stopwords and weighting specific values to them statistically.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.101-125
• /
• 2022

Recently, with the development of computing technology and the improvement of the cloud environment, deep learning technology has developed, and attempts to apply deep learning to various fields are increasing. A typical example is anomaly detection, which is a technique for identifying values or patterns that deviate from normal data. Among the representative types of anomaly detection, it is very difficult to detect a contextual anomaly that requires understanding of the overall situation. In general, detection of anomalies in image data is performed using a pre-trained model trained on large data. However, since this pre-trained model was created by focusing on object classification of images, there is a limit to be applied to anomaly detection that needs to understand complex situations created by various objects. Therefore, in this study, we newly propose a two-step pre-trained model for detecting abnormal situation. Our methodology performs additional learning from image captioning to understand not only mere objects but also the complicated situation created by them. Specifically, the proposed methodology transfers knowledge of the pre-trained model that has learned object classification with ImageNet data to the image captioning model, and uses the caption that describes the situation represented by the image. Afterwards, the weight obtained by learning the situational characteristics through images and captions is extracted and fine-tuning is performed to generate an anomaly detection model. To evaluate the performance of the proposed methodology, an anomaly detection experiment was performed on 400 situational images and the experimental results showed that the proposed methodology was superior in terms of anomaly detection accuracy and F1-score compared to the existing traditional pre-trained model.

• Journal of the Institute of Convergence Signal Processing
• /
• v.4 no.2
• /
• pp.40-45
• /
• 2003

This is the study on recognition units and segmentation of phonemes. In the case of making large vocabulary speech recognition system, it is better to use the segment than the syllable or the word as the recognition unit. In this paper, we study on the proper recognition units and segmentation of phonemes for Korean speech recognition. For experiments, we use the speech toolkit of OGI in U.S.A. The result shows that the recognition rate of the case in which the diphthong is established as a single unit is superior to that of the case in which the diphthong is established as two units, i.e. a glide plus a vowel. And recognizer using manually-aligned training data is a little superior to that using automatically-aligned training data. Also, the recognition rate of the case in which the bipbone is used as the recognition unit is better than that of the case in which the mono-Phoneme is used.

• The Journal of Society for e-Business Studies
• /
• v.20 no.4
• /
• pp.61-76
• /
• 2015

In general, we have utilized the hierarchical concept tree as a crucial data structure for indexing huge amount of textual data. This paper proposes a generality rank-based method that can automatically develop hierarchical concept structures with the Wikipedia data. The goal of the method is to regard each of Wikipedia articles as a concept and to generate hierarchical relationships among concepts. In order to estimate the generality of concepts, we have devised a special ranking function that mainly uses the number of hyperlinks among Wikipedia articles. The ranking function is effectively used for computing the probabilistic subsumption among concepts, which allows to generate relatively more stable hierarchical structures. Eventually, a set of concept pairs with hierarchical relationship is visualized as a DAG (directed acyclic graph). Through the empirical analysis using the concept hierarchy of Open Directory Project, we proved that the proposed method outperforms a representative baseline method and it can automatically extract concept hierarchies with high accuracy.

• Journal of Engineering Education Research
• /
• v.9 no.4
• /
• pp.71-82
• /
• 2006

To accomplish the educational objectives of a department, a system for CQI(Continuous Quality Improvement) is necessary. Improving the educational system by survey analysis is one of the most important factors for accomplishing the educational objectives. In general, survey analysis is carried out by using statistical distribution on an attribute or correlation analysis between two attributes. However, these analysis schemes have a limitation that they cannot find relations among various attributes. In this paper, an in-depth survey analysis method applying data mining techniques is presented. Data mining is a technique for extracting interesting knowledges from a large set of data. Survey from undergraduate students in the School of Computing of Soongsil University is analyzed in this paper by using a data mining tool, called Clementine. Results of Clementine analysis show the relationship between 'grade', and other attributes hierarchically, and provide useful information that can be applied in student consulting and program improvement.

• The Korean Journal of Applied Statistics
• /
• v.14 no.1
• /
• pp.91-101
• /
• 2001

It has been shown that the multiple trees predictors are more accurate in reducing test set error than a single tree predictor. There are two ways of generating multiple trees. One is to generate modified training sets by resampling the original training set, and then construct trees. It is known that arcing algorithm is efficient. The other is to perturb randomly the working split at each node from a list of best splits, which is expected to generate reasonably good trees for the original training set. We propose a new combined multiple regression trees predictor which uses the latter multiple regression tree predictor as a predictor based on a modified training set at each stage of arcing. The efficiency of those prediction methods are compared by applying to high throughput screening of chemical compounds for biological effects.