• Journal of the Korean Data and Information Science Society
• /
• v.22 no.2
• /
• pp.245-253
• /
• 2011

Powers of rank transformed statistic for testing main effects and interaction effects for $2{\times}2$ factorial design in randomized complete block design are very superior to powers of parametric statistic without regard to the block size, composition method of effects and the type of population distributions such as exponential, double exponential, normal and uniform. $2{\times}2$ factorial design in RCBD increases error effects and decreases powers of parametric statistic which results in conservativeness. However powers of rank transformed statistic maintain relative preference. In general powers of rank transformed statistic show relative preference over those of parametric statistic with small block size and big effect size.

• Journal of Korea Water Resources Association
• /
• v.46 no.2
• /
• pp.99-109
• /
• 2013

Increasing complexity of the basin environments makes it difficult for single decision maker to consider all relevant aspects of problem, and thus the uncertainty of decision making grows. This study attempts to develop an approach to quantify the spatial flood vulnerability of South Korea. Fuzzy TOPSIS is used to calculate individual preference by each group and then three GDM techniques (Borda count method, Condorcet method, and Copeland method) are used to integrate the individual preference. Finally, rankings from Fuzzy TOPSIS, TOPSIS, and GDM are compared with Spearman rank correlation, Kendall rank correlation, and Emond & Mason rank correlation. As a result, the rankings of some areas are dramatically changed by the use of GDM techniques. Because GDM technique in regional vulnerability assessment may cause a significant change in priorities, the model presented in this study should be considered for objective flood vulnerability assessment.

• The Journal of the Korea Contents Association
• /
• v.18 no.11
• /
• pp.317-326
• /
• 2018

The purpose of this study is to develop an AHP model to evaluate the relative importance and priorities of multi-cultural policies under bounded Rationality. The results of the study are as follows. First, in the evaluation elements for each measurement area, the following are the stable social settlement support policy (1rank), social capability development policy of multi-cultural family second generation (2rank), socio-economic activity policy (3rank), collaborative governance policy enforcement(4rank). Second, the priority of the measurement element is as follows. social settlement service target expansion policy was proved to be the top priority project stable social settlement support policy aspect and social capacity development policies of the second generation of multi-cultural families, social support policy was most important evaluated. Active economic activity support policy was as the top priority project socio-economic activity policy, and construct cooperation system of policy practice main agents was proved to be the top priority collaborative governance policy enforcement. These results will contribute to explain the reality of multi-cultural policy.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.77-84
• /
• 2022

In this paper, we propose a novel unsupervised feature selection method. Conventional unsupervised feature selection method defines virtual label and uses a regression analysis that projects the given data to this label. However, since virtual labels are generated from data, they can be formed similarly in the space. Thus, in the conventional method, the features can be selected in only restricted space. To solve this problem, in this paper, features are selected using orthogonal projections and low-rank approximations. To solve this problem, in this paper, a virtual label is projected to orthogonal space and the given data set is also projected to this space. Through this process, effective features can be selected. In addition, projection matrix is restricted low-rank to allow more effective features to be selected in low-dimensional space. To achieve these objectives, a cost function is designed and an efficient optimization method is proposed. Experimental results for six data sets demonstrate that the proposed method outperforms existing conventional unsupervised feature selection methods in most cases.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.12
• /
• pp.547-554
• /
• 2021

Cancer patients can have different kinds of cancer driver genes, and identification of these patient-specific cancer driver genes is an important step in the development of personalized cancer treatment and drug development. Several bioinformatic methods have been proposed for this purpose, but there is room for improvement in terms of accuracy. In this paper, we propose NPD (Network based Patient-specific Driver gene identification) for identifying patient-specific cancer driver genes. NPD consists of three steps, constructing a patient-specific gene network, applying the modified PageRank algorithm to assign scores to genes, and identifying cancer driver genes through a score comparison method. We applied NPD on six cancer types of TCGA data, and found that NPD showed generally higher F1 score compared to existing patient-specific cancer driver gene identification methods.

• Korean Journal of Adult Nursing
• /
• v.18 no.4
• /
• pp.533-542
• /
• 2006

Purpose: The purposes of this study were to investigate medical records and to develop care records for management of patients with chest pain in the emergency department. Method: Retrospective review of the 42 medical chart of patients presented to the emergency department with chest pain were used. The collected data were analyzed with a frequency of items in the medical records. Results: In a frequency analysis of recorded items for doctors' chest pain assessment during history taking, the history/risk factors was the highest rank. The following ranks were 'commenced with when/timing, extra symptoms, place, nature, stay/radiate, alleviate/aggravate, intensity' in sequence. In a frequency of recorded items in nurse's progress notes according to nursing actions, the 'checking/monitoring' was the highest rank. The following ranks were 'performing, administering/injecting, referring/arranging, testing, preparing/catheterizing, teaching/informing' in sequence. Chest pain care records for the emergency department was designed, based upon data analysis and literature review. Conclusion: The designed records can be a rapid and effective approach tool for assessment and recording of patients with chest pain. Further research is necessary for evaluating the designed chest pain care records.

• The Journal of Asian Finance, Economics and Business
• /
• v.7 no.7
• /
• pp.113-121
• /
• 2020

Multi-criteria stock selection is a critical issue for effective investment since the improper stock investment might cause many problems affecting investors negatively. Investors need a range of financial indicators while they are choosing the optimal set of stocks to invest. This study aims to rank the stock of agriculture companies indexed on the Vietnam Stock Exchange Market. The data of 13 agriculture companies during the 2016-2019 periods was analyzed by analytical hierarchy process (AHP) integrated with grey relational analysis (GRA), multi-objective optimization ratio analysis (MOORA), and technique for order performance by similarity to ideal solution (TOPSIS). The AHP method is employed to determine the weights of the proposed financial ratios, and GRA, TOPSIS, and MOORA approaches are used to obtain final ranking. The results indicated that HSL is the top stock with the highest rank and GRA, MOORA, and TOPSIS rankings have strong correlation values between 0.78-1. The findings suggest that the integrated model could be implemented effectively to specific analysis of industries such as oil and gas, textiles, food, and electronics in future research. Further, other techniques like COPRAS, KEMIRA, and EDAS could be employed to evaluate the financial performance of other companies to solve investment problems.

• Journal of the Korean Society for information Management
• /
• v.30 no.1
• /
• pp.179-191
• /
• 2013

Since information scientists have begun trying to quantify significant research trends in scientific publications, '-metrics' research such as 'bibliometrics', 'scientometrics', 'informetrics', 'webometrics', and 'citation analysis' have been identified as crucial areas of information science. To illustrate the dynamic research activities in these areas, this study investigated the major contributors of '-metrics' research for the last decade at three levels: nations, institutions, and documents. '-metrics' literature of this study was obtained from the Science Citation Index for the years 2001-2011. In this analysis, we used Pathfinder network, PNNC algorithm, PageRank and several indicators based on h-index. In terms of international collaborations, USA and England were identified as major countries. At the institutional level, Katholieke University, Leuven and the University of Amsterdam in Europe and Indiana University and the Office of Naval Research in the USA have led co-research projects in informetrics areas. At the document level, Hirsch's h-index paper and Ingwersen's web impact factor paper were identified as the most influential work by two methods: PageRank and single paper h-index.

• The Journal of Fisheries Business Administration
• /
• v.46 no.2
• /
• pp.111-125
• /
• 2015

This study is to analyze the efficiency of Korean sea food manufacturing using Data Envelopment Analysis. Firstly, based on an output oriented traditional CCR, BCC model, the study estimated the efficiency scores. The average estimates of technical, pure technical, and scale efficiency turned out 0.6517, 0.7184, 0.9074 respectively, which are separated for 50 marine corporations. The 10 DMUs were efficient under CCR model while the 17 DMUs under BCC model. Also, the study suggested that the operating profit of the two output factors should be more increased relatively and averagely from the viewpoint of efficiency improvement. Secondly, super efficiency scores are estimated under super efficiency and SBM model. As a result, it came to be possible to distinguish and rank the efficiency of the efficient DMUs. The highest score was 4.2975 under Super-CCR, was 2.4947 under Super-BCC, was 2.7160 under SBM-Super-CCR, and was 1.5319 under SBM-Super-BCC model. The average estimates of super efficiency were 0.76 and 0.82 under Super-CCR and Super-BCC model respectively, and were 0.61 and 0.67 under SBM-Super-CCR and SBM-Super-BCC model. Finally, the study conducted a rank-sum test, Wilcoxon-Mann-Whitney test, to find a statistical significance of heterogeneity existing in efficiencies among the sample corporations. The result showed that there was a significant difference in average efficiency between Dried, Salted product manufacturing and Frozen product manufacturing under BCC-Super efficiency model at 10% level of significance. Furthermore, TOBIT model was applied to find out the potential factors that might influence the efficiency, Wilcoxonand the results showed debt and sales cost influenced all of the technical, pure technical, and scale efficiency, while net profit influenced only the technical efficiency.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.4 no.1
• /
• pp.119-131
• /
• 1997

This study was conducted to analyze the nursing diagnoses applied for case studies of nursing students through their clinical practices, and to provide the educational basis of nursing diagnoses with its results. The data were collected for two years(1995 and 1996) from 70 case studies reported by the 2nd and 3rd year nursing junior college students. The students made 259 nursing diagnoses among which 230 diagnoses qualified NANDA classification and were taken for analysis. The results of the analysis were as follows : 1. The number of diagnoses indicating response patterns was 35(35.7%), whereas 98 diagnoses in NANDA table. Among the 35 diagnoses, the pattern of exchange was most frequent, then feeling, moving, knowing in rank. 2. The diagnoses were analyzed in the categories of response patterns. For Instance, 'Altered in Nutrition' was most frequent in exhange, then Risk for Infection', 'Ineffective Airway Clearance', in rank. 3. Among 230 diagnoses, 'Knowle Deficit' was most frequently mentioned, then 'Activity Intolerance' 'Anxiety', 'Pain', 'Altered in Nutrition', 'Risk for Infection', 'Ineffective airway clearance', in rank. 4. The types of word expression of each diagnoses were various. 'Activity Intolerance' was expressed in 6 types. 5. The relating factors applied to each diagnosis were analyzed. For Instance, the relating factor of 'Knowledge Deficit' were illness, and therapeutic process, lack of motivation, occurrance of complication, short experience, operation, and so on. From the above study, the researcher would like to recommend as follows : 1) The current diagnoses need to be verified its content validity, when they are applied to our culture. 2) The most effective educational method for applying nursing diagnoses should be explored. 3) Further study could be focused on not only 'relating factors' but also 'sign and symptoms'.