• Journal of the Korean Society for information Management
• /
• v.40 no.1
• /
• pp.1-21
• /
• 2023

This study specifically reviewed the performance of the ranking schemes as an efficient feature selection method for text classification. Until now, feature ranking schemes are mostly based on document frequency, and relatively few cases have used the term frequency. Therefore, the performance of single ranking metrics using term frequency and document frequency individually was examined as a feature selection method for text classification, and then the performance of combination ranking schemes using both was reviewed. Specifically, a classification experiment was conducted in an environment using two data sets (Reuters-21578, 20NG) and five classifiers (SVM, NB, ROC, TRA, RNN), and to secure the reliability of the results, 5-Fold cross-validation and t-test were applied. As a result, as a single ranking scheme, the document frequency-based single ranking metric (chi) showed good performance overall. In addition, it was found that there was no significant difference between the highest-performance single ranking and the combination ranking schemes. Therefore, in an environment where sufficient learning documents can be secured in text classification, it is more efficient to use a single ranking metric (chi) based on document frequency as a feature selection method.

• Proceedings of the KIEE Conference
• /
• 2002.07a
• /
• pp.105-107
• /
• 2002

This paper presents a algorithm for contingency ranking using the real power ratio. The fundamemtal cause of voltage collapse is considered due to excessive power trnsfer through the line. To obtain contingency ranking, maximum real power tansferred to the load is obtained when load impedance $Z_r$ equal to line impedance $Z_s$. This algorithm is verified by simulation on a 6-bus test system.

• Proceedings of the KIEE Conference
• /
• 2002.06a
• /
• pp.146-148
• /
• 2002

This paper presents a algorithm for contingency ranking using the real power ratio, The fundamemtal cause of voltage collapse is considered due to excessive power trnsfer through the line To obtain contingency ranking, maximum real power tansferred to the load is obtained when load $impedance^{Z_r}$ equal to line $impedance^{Z_s}$, This algorithm is verified by simulation on a 6-bus test system.

• Journal of Electrical Engineering and Technology
• /
• v.4 no.4
• /
• pp.438-442
• /
• 2009

Voltage instability is a phenomenon that could occur in power systems due to stressed conditions. The result would be an occurrence of voltage collapse leading to total blackout of the system. Therefore, voltage collapse prediction is an important part of power system planning and operation, and can help ensure that voltage collapse due to voltage instability is avoided. Line outages in power systems may also cause voltage collapse, thereby implying the contingency in the system. Contingency problems caused by line outages have been identified as one of the main causes of voltage instability in power systems. This paper presents a new technique for contingency ranking based on voltage stability conditions in power systems. A new line stability index was formulated and used to identify the critical line outages and sensitive lines in the system. Line outage contingency ranking was performed on several loading conditions in order to identify the effect of an increase in loading to critical line outages. Correlation studies on the results obtained from contingency ranking and voltage stability analysis were also conducted, and it was found that line outages in weak lines would cause voltage instability conditions in a system. Subsequently, using the results from the contingency ranking, weak areas in the system can be identified. The proposed contingency ranking technique was tested on the IEEE reliability test system.

• Proceedings of the KIEE Conference
• /
• 2000.07e
• /
• pp.95-98
• /
• 2000

This paper presents a technique for contingency ranking using line capacity calculation method and outage distribution factors (LODF) which are established by generation shift distribution factors from DC load flow solutions. By using the LODF, the line flow can be calculated a ccording to the modification of base load flow if the contingency occur. To obtain contingency ranking, maximum power tansferred to the load is obtained when load impedance $Z_r$ equal to line impedance $Z_s$. The proposed algorithm has been validated in tests on a 6-bus test system.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.12 no.1
• /
• pp.20-25
• /
• 1998

This paper presents an algorithm for contingency ranking using line outage distribution factors(LODF) which are established by generation shift distribution factors(GSDF) from DC load flow solutions. By using the LODF, the line flow can be calculated according to the modification of base load flow if the contingency occur. To obtain faster contingency ranking, only the loading line more than 35[%](60[%] at 154[kV]) is included in the computation of Performance Index(PI). The proposed algorithm has been validated in tests on a 6-bus test system.system.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.760-763
• /
• 1996

This paper presents an algorithm for the contingency ranking in a power system. The method utilizes line outage distribution factors(LODF) which are established from DC load flow solutions. The LODF are formulated using changes in network power generations to simulate the outaged line from the network. To abtain better ranking. one can take a line loading of 60% over into account in the computation of PI. The proposed algorithm has been validated in tests on a 6-bus test system.

• International Journal of Contents
• /
• v.14 no.3
• /
• pp.46-52
• /
• 2018

The objective of this study was to determine the status of star chart game applications in the Google play store in Korea. The share of game genres in paid and free star charts of game applications was searched. Also, the average reviewer's rating, average number of reviews, and average age rating based on the genre of paid and free star charts of game applications, and the average price of paid applications based on genre were analyzed. Hypothesis tests for the differences in average reviewer's rating, average number of reviews, average age rating according to the genre of game applications were performed. Also, hypothesis tests for the differences in average reviewer's rating, average number of reviews, average age rating between the paid and free game applications along with the hypothesis test for the differences in price according to the genre of paid game applications were performed. Lastly, hypothesis tests for the correlation between the start chart ranking and number of reviews in association with the correlation between the start chart ranking and reviewer's rating were performed. Statistically significant differences in average reviewer's rating, average number of reviews, average age rating according to the genre of game applications, and between the paid and free game applications were verified. However, the correlation between the start chart ranking and number of reviews in association with the correlation between the start chart ranking and reviewer's rating were not statistically significant.

• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.1-11
• /
• 2002

In this paper, a test was performed to determine whether words in Anchor Text were appropriate as key words. As a result of the test. there were proper words of high weighting factor, while some others did not even appear in the text. therefore, were not appropriate as key words. In order to resolve this problem. a new method was proposed to extract key words. Using the proposed method, inappropriate key words can be removed so that new key words be set, and then, ranking becomes possible with the TFIDF value as a weighting factor of the key word. It was verified that the new method has higher accuracy compared to the previous methods.

• Proceedings of the Safety Management and Science Conference
• /
• 2012.04a
• /
• pp.579-583
• /
• 2012

The Design of Experiment (DOE) is a most practical technique when establishing an optimal condition for production technology in Six Sigma innovation project. This research proposes the assessment of properties of error terms, such as normality, equal variance, unbiasedness and independence. The properties of six nonparametric ranking techniques for checking normality assumption are discussed as well as run test which is used to identify the randomness, and to check unbiased assumption. Furthermore, Durbin-Watson (DW) statistics and ARIMA (p,d,q) process are discussed to identify the serial correlation.