• Journal of KIISE
• /
• v.43 no.8
• /
• pp.883-892
• /
• 2016

Spectrum-based fault localization (SFL) method assigns a suspicious ratio. The statement is strongly affected by a failed test case compared to a passed test case. A failed test case assigns a suspicious ratio while a passed test case reduces some parts of assigned suspicious ratio. In the absence of a failed test case, it is impossible to localize the fault. Thus, a failed test case is very important for fault localization. However, spectrum-based fault localization has difficulty in reflecting the unique characteristics of a failed test because a failed test case and a passed test case are input at the same time to calculate a suspicious ratio. This paper supplements for this limitation and suggests a test case grouping method for more accurate fault localization. In addition, this paper suggested a filtering method considering test efficiency and verified the effectiveness by applying 65 algorithms. In 90 % of whole methods, the accuracy was improved by 13% and the effectiveness was improved by 72% based on EXAM score.

• Communications of Mathematical Education
• /
• v.22 no.3
• /
• pp.349-368
• /
• 2008

The purpose of this study was to investigate the small-group instruction of mathematics in elementary schools. For this, a sample of 742 teachers of elementary schools completed the survey. As a result, about 27.8% of the teachers reported using small group instruction while they worked with one group or they assigned to other groups worked alone. Only 2% of the teachers reported using small group in which students were encouraged to participated cooperatively. This study discusses the five issues about small group instruction in elementary school. The five issues were investigated in this survey. First, major teaching method in mathematics classroom and using of small group instruction were described. Second, frequency and period of small-group instruction were reported. Third, grouping method in small-group instruction was described. And Fourth, effect grouping practices of small-group instruction were described. Fifth, the model of small group instruction and assessment in small-group instruction were reported.

• Journal of Korean Society on Water Environment
• /
• v.39 no.5
• /
• pp.377-389
• /
• 2023

Chungcheongnam-do has been measuring the flow rate and water quality of streams in the province once a month since 2011 in order to water environment policies. Based on the results, after evaluating the coefficient of variation and the tendency of the water quality trend by using the Mann-Kendall test and Sen's Slope for each stream, the streams subject to priority introduction of Total Pollution Load Management at Tributaries were selected through the Stream Grouping Method. The water quality trend analysis results for 125 streams using the Mann-Kendall test and Sen's Slope were evaluated as streams showing a tendency of deteriorating water quality Biochemical oxygen demand (BOD): 13 streams, Total Phosphorus (T-P): 16 streams). Streams with deteriorating water quality were classified into A-D groups using the Stream Grouping Method. Group A, which has a high flow rate and high water quality, is a stream that requires priority management, and was selected as a stream for introduction of Total Pollution Load Management at Tributaries. There are 7 streams that need to be introduced into the BOD category, and there are 7 streams that need to be introduced into the T-P category. In this study, based on flow and water quality monitoring data accumulated over a long period of time (2011-2022), statistical techniques are used to select watersheds in which water quality is deteriorating. Accordingly, it is expected that it will be useful in establishing a water quality improvement plan in the future.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.9 no.2
• /
• pp.217-224
• /
• 2005

A methodology of selecting an optimal model is proposed for applying a frequency-domain SI method effectively. Instead of using a reduced finite element model, a reasonably detail finite element model is established first and then the model is identified. To satisfy the identifiability criterion, a parameter grouping scheme is applied to control the number of unknowns. Among the simulated member grouping cases, an optimal model is selected as the one with the minimal statistical error. The proposed approach has been examined through simulation studies on a single span box-girder bridge.

• Asian-Australasian Journal of Animal Sciences
• /
• v.4 no.3
• /
• pp.245-250
• /
• 1991

Analysis of the characteristics and the grouping of the species of sown and weeds in artificial pastures was studied applying the principal component analysis method. Presency and coverage of six sown species and fifteen weed species which occurred in pastures of under-grazing and optimumgrazing were subject to analysis. From field survey, species were divided into three groups: the group A included five species such as Festuca arundinacea, Lolium perenne and Dactylis glomerata, etc., the group B included eleven species such as Polygonum longisetum, Agrostis alba and Rumex obtusifolius, etc., and the group C included five species such as Miscanthus sinensis, Rubus palmatus and Artemisia princeps, etc. The group A species corresponded to good pasture conditions and management. On the contrary, the group C species occurred in poor pasture conditions with inadequate management. The group B species corresponded to intermediate pasture conditions and management. Interrelated pair species co-existing and species non-co-existing were discovered. Factor loading as negative for the group A species. positive for the group C species and positive but lower than the group C species for the group B species. From these results it is concluded that the principal component analysis seems to one of the useful tools for the analysis of characteristics of species and the diagnosis of sown pasture vegetation, although further studies are required to get more general information about species characteristics.

• Journal of Institute of Control, Robotics and Systems
• /
• v.17 no.8
• /
• pp.739-746
• /
• 2011

Recently, recommender systems have been widely applied in E-commerce websites to help their customers find the items what they want. A recommender system should be able to provide users with useful information regarding their interests. The ability to immediately respond to the changes in user's preference is a valuable asset of recommender systems. This paper proposes a novel recommender system which aims to effectively adapt and respond to the immediate changes in user's preference. The proposed system combines IEC (Interactive Evolutionary Computation) with a content-based filtering method and also employs data grouping in order to improve time efficiency. Experiments show that the proposed system makes acceptable recommendations while ensuring quality and speed. From a comparative experimental study with an existing recommender system which uses the content-based filtering, it is revealed that the proposed system produces more reliable recommendations and adaptively responds to the changes in any given condition. It denotes that the proposed approach can be an alternative to resolve limitations (e.g., over-specialization and sparse problems) of the existing methods.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.889-902
• /
• 2013

Several goodness-of-fit test statistics have been proposed for a multinomial logit regression model; however, the properties of the proposed tests were not adequately studied. This paper evaluates three different goodness-of-fit tests using grouping strategies, proposed by Fagerland et al. (2008), Bull (1994), and Pigeon and Heyse (1999). In addition, Pearson (1900)'s method is also examined as a reference. Simulation studies were conducted to evaluate the four methods in terms of null distribution and power. A real data example is presented to illustrate the methods.

• Journal of the Ergonomics Society of Korea
• /
• v.35 no.6
• /
• pp.611-619
• /
• 2016

Objective:This study aims to analyze the relationships between personality factors measured by Minnesota Multiphasic Personality Inventory (MMPI) scales and the indices of safety and health in the shipbuilding industry. Background: Many researches reported that there were significant relationships between some MMPI subscales and traffic and industrial accidents. Method: This study analyzes 230 male workers in shipyard for their MMPI scores gathered during recruitment process and their safety and health indices from the performance record during their working period. ${\chi}^2-test$ and one-way ANOVA are used for finding the statistical significance for personality factors. The conventional grouping rule for MMPI scales and other grouping criteria considering the attitude of positive answer for the MMPI test during recruitment process are used for analysis. Results: The Hypomania (Ma) and Psychopathic Deviate (Pd) scales of the MMPI are the main factors related to the safety and health related indices for most grouping rules. Depression (D), Psychasthenia (Pt), Hypochondriasis (Hs), Schizophrenia (Sc), and Masculinity and Femininity (Mf) scales are also related to the safety and health indices. Conclusion and Application: The results can be used for understanding the psychological factors in human behaviors and safety and can help professional personnel take the necessary steps in improving safety on the job and also in providing the effective teaching of safe work methods.

• Journal of Wetlands Research
• /
• v.17 no.4
• /
• pp.380-390
• /
• 2015

In this study, the major 38 tributaries in Nakdong River were monitored for flow rate and water quality in order to understand the characteristics of the watershed and to find improvement plan. The flow rate and water quality for each target tributary were evaluated based on the monitoring data in 2013~2014 using a statistical package SPSS-22.0. In addition, the tributary grouping method was conducted using a $BOD_5$ concentration/flowrate and TP concentration/flowrate monitoring data. The average values of $BOD_5$, $COD_{Mn}$, TP and TOC concentrations in Gumicheon, Gyeonghocheon, Jincheoncheon, Gisegokcheon, Yonghacheon and Yonghocheon located at Nakdong Waegwan and Nakdong Goryung watershed were high and in the grade of III or IV (5~8 mg/L). The Pearson correlation coefficients of TOC with $BOD_5$, $COD_{Mn}$, and TP were greater (r=0.8, p<0.01) than those of the other water quality parameters (12 species). The tributaries with high values of water quality parameters ($BOD_5$ > 3.0 mg/L, TP > 0.1 mg/L) and flowrate (Q > $0.1m^3/sec$) were selected for improving water quality according to the stream grouping method. Five tributaries (Gumicheon, Gisegokcheon, Yonghacheon, Yeongsancheon, Mijeoncheon and Yonghocheon) were classified as Group I, which require polices and plans for water quality improvement.

• The KIPS Transactions:PartB
• /
• v.11B no.6
• /
• pp.709-716
• /
• 2004

According to the current increase of the usefulness of information by Internet Communication network, several methods are proposed in which a specific domain information nay be efficiently constructed and serviced. This paper proposes Relationship Grouping of Fuzzy Filtering Objects for Multimedia Statistic Post-office Box Construction. The proposed method exploits RelCRO( $D_{omain}$, Gi), RelSRO( $D_{omain}$, Gi) and FAS in order to group using (equation omitted)-cut. To know how well the proposed method is able to work, this paper have test against the methods with 1600 items of multimedia type information, and our system are compared with Random-Key, OGM and the proposed method. The results shows that the proposed method provides the better performance than the other methods.