• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.131-138
• /
• 2022

A Mobile Ad-hoc Network (MANET) is a collection of moving nodes that communicate and collaborate without relying on a pre-existing infrastructure. In this type of network, nodes can freely move in any direction. Routing in this sort of network has always been problematic because of the mobility of nodes. Most existing protocols use simple routing algorithms and criteria, while another important criterion is path selection. The existing protocols should be optimized to resolve these deficiencies. 'Particle Swarm Optimization (PSO)' is an influenced method as it resembles the social behavior of a flock of birds. Genetic algorithms (GA) are search algorithms that use natural selection and genetic principles. This paper applies these optimization models to the OLSR routing protocol and compares their performances across different metrics and varying node sizes. The experimental analysis shows that the Genetic Algorithm is better compared to PSO. The comparison was carried out with the help of the simulation tool NS2, NAM (Network Animator), and xgraph, which was used to create the graphs from the trace files.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.730-739
• /
• 2005

A common problem encountered in product or process design is the selection of optimal parameter levels which involve simultaneous consideration of multiresponse variables. A multiresponse problem is solved through three major stages: data collection, model building, and optimization. To date, various methods have been proposed for the optimization stage, including the desirability function approach and loss function approach. In this paper, we first propose a framework classifying the existing studies and then propose some promising directions for future research.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.484-486
• /
• 2002

본 논문은 여러 컬렉션에 대해 검색을 수행하는 분산 검색시스템에서 질의어가 들어 왔을 때 질의어에 적합한 컬렉션을 자동으로 선택할 수 있도록 하는 컬렉션 선택 모델과 브로커 구조를 제안하였다. 각 컬렉션마다 과거 질의에 대해 검색된 결과 문서들을 색인하여 인접단어를 고려한 불완전 인텍스를 생성한다. 이러한 불완전 인덱스를 이 용하여 컬렉션 선택하는 모델을 TREC 문서집합과 SMART 시스템을 이용하여 구현하였다.

• Journal of the Korean Society for information Management
• /
• v.23 no.1 s.59
• /
• pp.279-299
• /
• 2006

This study utilizes various approaches of machine learning in the process of automatically assigning descriptors to journal articles. The effectiveness of feature selection and the size of training set were examined, after selecting core journals in the field of information science and organizing test collection from the articles of the past 11 years. Regarding feature selection, after reducing the feature set using $x^2$ statistics(CHI) and criteria that prefer high-frequency features(COS, GSS, JAC), the trained Support Vector Machines(SVM) performed the best. With respect to the size of the training set, it significantly influenced the performance of Support Vector Machines(SVM) and Voted Perceptron(VTP). However, it had little effect on Naive Bayes(NB).

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2004.05a
• /
• pp.698-701
• /
• 2004

In many literatures, data mining has been used as a utilization of data warehouse and data collection. The biggest utilizations of data mining are for marketing and researches. This is solely because of the data available for this field is usually in large amount. The usability of the data mining is expandable also to the production process. While the object of research of the data mining in marketing is the customers and products, data mining in the production field is object to the so called 4MlE, man, machine, materials, method (recipe) and environment. All of the elements are important to the production process which determines the quality of the product. Because the final aim of the data mining in production field is the quality of the production, this data mining is commonly recognized as quality data mining. As the variables researched in quality data mining can be hundreds or more, it could take a long time to reveal the information from the data warehouse. Feature selection methodology is proposed to help the research take the best performance in a relatively short time. The usage of available simple statistical tools in this method can help the speed of the mining.

• Journal of the Korean Society for Library and Information Science
• /
• v.40 no.1
• /
• pp.373-395
• /
• 2006

The writer investigated the academic values of the titles based upon book annotations included in Gunseo-pyogi, or An Annotated Catalog of books written and edited by the goverment. This paper examined various types of evaluative methods adopted in Gunseo-pyogi, and then compare them to the modern general library criteria of book selection. The writer found the fact that the academic qualifies of books listed in Gunseo-pyogi were even more excellent than the modern criteria for good books in the point of level of authors and contents.

• The Korean Journal of Applied Statistics
• /
• v.29 no.5
• /
• pp.787-806
• /
• 2016

Mixed-mode (MM) designs in which data are collected by different modes in one design have become increasingly popular. An MM data collection has several advantages such as reductions of coverage error, non-response and cost. However, MM designs may introduce mode effects that are confounded by selection effects and measurement effects, which can make MM data quality poor. In order to investigate mode effects, SRI implemented a concurrent mixed-mode experiment in 2014 where respondents could choose between a self-administrated Web survey and a self-administrated paper survey. This paper separately estimates selection effects and measurement effects. We found that measurement effects on some items are large.

• Journal of Information Science Theory and Practice
• /
• v.10 no.2
• /
• pp.86-101
• /
• 2022

This research aimed at studying the factors that influence new media exposure of political news by youths in Isan society in Thailand. The target group comprised 1,200 individuals, obtained from multi-stage sampling from undergraduate students in Isan's autonomous universities, governmental universities, and private institutions. The data collection tool was a questionnaire, the content of which was validated by experts. The reliability of the tool was tested by the formula for Cronbach's alpha coefficient, which yielded a reliability of 0.83. Multiple regression analysis was applied to analyze the data. The results, regarding factors influencing the channels for political news exposure, showed that channels for political news exposure were mostly influenced by inner drives, followed by importance in political news exposure, influence from social networks, and specific characteristics of the Internet. This could explain the variation of channels for political news exposure at 46.5%. In terms of factors influencing political news selection, it was found that political news selection was influenced mostly from social networks, followed by inner drives, benefits from political news exposure, specific characteristics of the Internet, and the field of study. The variation of the political news selection could be explained at 44.6%. These results elaborate on the current situation in Thailand, especially in Isan region, where youths in higher education are playing an increasing role in demonstrating their political stance through various political activities.

• The Journal of Asian Finance, Economics and Business
• /
• v.9 no.9
• /
• pp.351-360
• /
• 2022

This study aims to determine the factors that can influence investors in selecting stocks in the Indonesian capital market to establish an optimal portfolio, and find phenomena that occurred during the COVID-19 pandemic so that buying interest / the number of investors increased in the Indonesian capital market. This study collection technique uses primary data obtained from the survey questionnaire and secondary data which is market data, stock price movement data sourced from the Indonesia Stock Exchange, Indonesian Central Securities Depository, and Bank Indonesia, as well as empirical literature on behavior finance, investment decision, and interest in buying stock. The method used in this research is the survey questionnaire analysis with the SEM (statistical approach). The results of the analysis using SEM show that investor behavior influences the stock-buying interest, investor behavior, and the stock-buying interest influences investor decision-making. However, risk management does not influence investor-decision making. This occurs when the investigator's psychological capacity produces more decision information by decreasing all potential biases, allowing the best stock selection model to be selected. When the investigator's psychological capacity creates more decision information by reducing biases, the optimum stock selection model can be chosen.

• The Research Journal of the Costume Culture
• /
• v.20 no.6
• /
• pp.811-825
• /
• 2012

The purpose of this study was to identify imported apparel selection behavior according to Mongol women's conspicuous consumption orientation. A self-administered questionnaire was used for data collection. First, factors of conspicuous consumption orientation were high price and luxury brand, fashion style, altruism, prestige, and brand. Mongol women were segmented into the price and prestige pursuit group, the fashion and brand pursuit group, the altruism pursuit group, and the conspicuous consumption retard group. Second, factors of motivating the selection of imported apparel were value, symbolism, and aesthetics, and Mongol women considered the aesthetics of imported apparel important. Married Mongol women in their 30's chose imported apparel because of its symbolism. More married women selected imported apparel because of its value and more educated women selected imported apparel because of its aesthetics. Women with higher apparel expenditure selected imported apparel because of its value and symbolism. Quality, diversity, and the fit of imported apparel were the selection criteria for Mongol women and they were satisfied with the quality, diversity, and fit of the imported apparel. Brand awareness was very important when selecting imported apparel but the women's satisfaction level was significantly low. Third, more women in their 30's, unmarried, or with a lower educational level were found in the price and the prestige pursuit group, and the price and prestige pursuit group and the altruism pursuit group selected imported apparel for its aesthetics. More unmarried women in their 30's with a higher educational level were found in the fashion and brand pursuit group and selected imported apparel for its value, symbolism, and aesthetics. More unmarried women in their 20's with a higher educational level were found in the altruism pursuit group, but unmarried women in their 20's with a lower educational level were found in the conspicuous consumption retard group.