• Title/Summary/Keyword: regression factor

Search Result 6,632, Processing Time 0.037 seconds

A Comparative Study Between Linear Regression and Support Vector Regression Model Based on Environmental Factors of a Smart Bee Farm

  • Rahman, A. B. M. Salman;Lee, MyeongBae;Venkatesan, Saravanakumar;Lim, JongHyun;Shin, ChangSun
    • Smart Media Journal
    • /
    • v.11 no.5
    • /
    • pp.38-47
    • /
    • 2022
  • Honey is one of the most significant ingredients in conventional food production in different regions of the world. Honey is commonly used as an ingredient in ethnic food. Beekeeping is performed in various locations as part of the local food culture and an occupation related to pollinator production. It is important to conduct beekeeping so that it generates food culture and helps regulate the regional environment in an integrated manner in preserving and improving local food culture. This study analyzes different types of environmental factors of a smart bee farm. The major goal of this study is to determine the best prediction model between the linear regression model (LM) and the support vector regression model (SVR) based on the environmental factors of a smart bee farm. The performance of prediction models is measured by R2 value, root mean squared error (RMSE), and mean absolute error (MAE). From all analysis reports, the best prediction model is the support vector regression model (SVR) with a low coefficient of variation, and the R2 values for Farm inside temperature, bee box inside temperature, and Farm inside humidity are 0.97, 0.96, and 0.44.

An Empirical Study for University Educational Service Satisfaction Factors

  • Choi, Kyung-Ho
    • Journal of the Korean Data and Information Science Society
    • /
    • v.17 no.2
    • /
    • pp.279-289
    • /
    • 2006
  • This paper concerns with the effects of the specialized projected for the local W university on education which was planned and conducted in October 2004. From the empirical study using the correlation analysis, regression analysis, and structured equation model, we found some results that educational service satisfaction was highly correlated with general instruction factor and hard ware factor less correlated. Also we investigated that university educational service satisfaction was deeply correlated with word of mouth.

  • PDF

의식파악을 위한 설문지 설계 및 분석 사례 연구

  • 최용운;이강군;이상복
    • Proceedings of the Korean Society for Quality Management Conference
    • /
    • 2004.04a
    • /
    • pp.217-228
    • /
    • 2004
  • In this thesis, we suggest questionnaire which is designed to understand of what employees include executive think about 6 sigma management movement and to find important factor for strategic of success 6 sigma management movement of K. Corporation. This thesis is composed of 2 parts, one is questionnaire design and the other is questionnaire analysis. We find important factor for strategic of success 6 sigma management movement of K. Corporation by using correlation and regression analysis, which results very useful and great help for K's Co. In questionnaire analysis, we use by minitab package version 13.2.

  • PDF

A Study on the Significance of Spatial Interaction Model from the Urban Competitive Point of View (입지 경쟁력과 공간상호작용 모형의 유의성 검정)

  • Kim, Dong-Yoon
    • Journal of The Korean Digital Architecture Interior Association
    • /
    • v.12 no.1
    • /
    • pp.71-79
    • /
    • 2012
  • This study aims at finding relationships between the competitiveness of cities and the size or distance of them, based on some premises; (1) the competitiveness can be measured on the interval-ratio level, that is, factor scores, (2) a hypothesis that the spatial interaction model is valid for the relationships can be generally accepted. Based on the general recognition a research hypothesis that the more is the population or the nearer is the distance from a central city the higher is the competitiveness score is constructed. According to the premises 5-factor scores and composite score are calculated by means of regression method, and the scores are regressed on cities' populations and distances from Seoul city. Using bootstrapping method for the tests of significance is effective due to small sample of 21 cities. Results of the analyses show that most aspects of the hypothesis should be rejected or adjusted. Scores on Health-welfare factor, public service factor, and commercial vitality factor have no relation to the cities' sizes or distances. But the results also find the facts that the strong (negative) relationships exist between (1) educational base factor score and population, (2) density factor score and distance. Although this study improves systematic and analytic understanding of spatial interaction patterns, the understanding should be invalid for the general context because it has used the data on 21 cities in the capital region at the time of 2009.

Correlation Analysis of Korean Version of the Subhealth Questionnaire And Profile of Mood States Factors (아건강 설문지와 기분상태척도의 상관성 연구)

  • Ryu, Jae-Min;Park, Young-Jae;Park, Young-Bae
    • The Journal of the Society of Korean Medicine Diagnostics
    • /
    • v.15 no.1
    • /
    • pp.77-86
    • /
    • 2011
  • Objectives: With increased rate of chronic disease, concerns about preventive medicine has raised. Therefore questionnaire of subhealth status was developed and analysed in our previous study. A large number of chronic diseases is related to emotional issues. This study was to confirm a relationship between mood state and health status in terms of modern people's healthcare. Methods: Subhealth Questionnaire and Korean version of Profile of Mood States(k-POMS) were putted by 113 college students. And correlation and regression analysis was conducted. Results: Subhealth questionnaire and k-POMS proved a significant correlation. In particular, subhealth factor 3(mood) had a significant correlation with all factors of k-POMS. Subhealth factor 1(body), subhealth factor 2(life) and subhealth factor 6(society) had significant correlations with 5 factors of k-POMS. Subhealth factor 4(energy) and subhealth factor 5(heredity) did not show significant results. 'Fatigue' factor of k-POMS was proved to be the most important factor influencing the subhealth status and illness, indicating high correlations with all of subhealth status.

Response modification factor of mixed structures

  • Fanaie, Nader;Shamlou, Shahab O.
    • Steel and Composite Structures
    • /
    • v.19 no.6
    • /
    • pp.1449-1466
    • /
    • 2015
  • Mixed structures consist of two parts: a lower part and an upper part. The lower part is usually made of concrete while the upper part is made of steel. Analyzing these structures is complicated and code-based design of them has many associated problems. In this research, the seismic behavior of mixed structures which have reinforced concrete frames and shear walls in their lower storeys and steel frames with bracing in their upper storeys were studied. For this purpose, seventeen structures in three groups of 5, 9 and 15 storey structures with different numbers of concrete and steel storeys were designed. Static pushover analysis, linear dynamic analysis and incremental dynamic analysis (IDA) using 15 earthquake records were performed by OpenSees software. Seismic parameters such as period, response modification factor and ductility factor were then obtained for the mixed (hybrid) structures using more than 4600 nonlinear dynamic analysis and used in the regression analysis for achieving proper formula. Finally, some formulas, effective in designing such structures, are presented for the mentioned parameters. According to the results obtained from this research, the response modification factor values of mixed structures are lower compared to those of steel or concrete ones with the same heights. This fact might be due to the irregularities of stiffness, mass, etc., at different heights of the structure. It should be mentioned that for the first time, the performance and seismic response of such structures were studied against real earthquake accelerations using nonlinear dynamic analysis, andresponse modification factor was obtained by IDA.

Effects of Appearance Management Behaviors on Career Decision Level in Female College Students (여대생의 외모관리행동이 진로결정수준에 미치는 영향)

  • Kim, Mikyung
    • Journal of Fashion Business
    • /
    • v.20 no.4
    • /
    • pp.36-49
    • /
    • 2016
  • The objective of this study was to examine the effects of appearance management behaviors on career decision level among female college students. Based on previous studies on appearance management behaviors and career decision level, the items for a questionnaire were developed. For the study, we conducted a questionnaire survey among 292 students from women's university in Seoul. Factor analysis, correlation analysis and multiple regression analysis were performed using SPSS statistics 23. Results of this study are as follows. First, the factor structure of appearance management behavior had three factors: 'fashion & hair,' 'skin & plastic surgery,' and 'body shape.' The reliability and validity of the factor structure were proved. Second, a significant correlation was found between sub-factors in appearance management behaviors. Career decision level showed a significant correlation only with body management factor. Third, the appearance management behavior of female college students was found to have a partially significant effect on career decision level. For higher grade students, fashion & hair factor and body shape factor had positive effects on career decision level. For lower grade students, body shape factor had a positive effect on career decision level while skin & plastic surgery factor had a negative effect on career decision level. Therefore, to increase career decision level, managing appearance through keeping fit body shape is crucial. This study also suggests that as one elevates to a higher grade, the importance of management and keeping interest toward fashion is important.

Idiosyncratic Volatility, Conditional Liquidity, and Cross-section of Stock Returns in Korea (고유변동성, 조건부 유동성, 그리고 주식수익률의 횡단면에 관한 연구)

  • Yun, Sang-Yong;Cho, Seong-Soon;Park, Soon-hong
    • Asia-Pacific Journal of Business
    • /
    • v.12 no.1
    • /
    • pp.121-134
    • /
    • 2021
  • Purpose - This study examines whether flight-to-liquidity (FTL) explains the dynamic liquidity risk on stock returns, and whether it has a significant influence on determinants the cross-section of stock returns. Design/methodology/approach - This study suggests a new risk factor, dynamic liquidity hedge portfolio (DLP), to reflect the dynamic impact of liquidity risk on stock returns and the Fama-MacBeth 2 stage regression analysis is employed in order to analyze the data. Findings - First, the DLP factor shows more positive and significant beta for the small or illiquidity stocks. Second, the DLP shows a different influence than SMB (size risk factor), HML (value risk factor), NMP (liquidity risk factor), FTVOL (total volatility factor) in determining the cross-section of stock returns. In addition, the DLP has a statistically significant risk premium of around 5%, which is relatively larger than other risk factors. Research implications or Originality - This study has academic value in terms of newly confirming that the DLP factor has a more significant impact on cross-sectional determination of stock returns than other risk factors by proposing a conditional liquidity factor that can explain the FTL phenomenon.

Mobile Applications of Learning Management Systems and Student Acceptance: An Empirical Study in Saudi Arabia

  • BAHAJ, Saeed Ali Omer
    • The Journal of Asian Finance, Economics and Business
    • /
    • v.9 no.7
    • /
    • pp.93-99
    • /
    • 2022
  • Nowadays, learning management systems (LMS) are an effective and efficient tool for providing students with a high-quality education. The current study examines the effect of different factors on the use of the blackboard application on mobile phones. The study selects four important factors after factor analysis, such as facilitating factor, performance factor, satisfaction factor, and difficulties factor. The data was collected through a structured questionnaire from 45 students as a sample in the college of business administration at Prince Sattam Bin Abdulaziz University. The study uses a logistic regression model to examine the empirical relationship between LMS adoption and different factors associated with blackboard adoption. The results show that 71 percent of the respondents are between the age of 18-20 years, and 100 percent of students have experience in using blackboard. The empirical results show that the satisfaction factor is positive and significant at the 10 percent level of significance and the difficulties factor is also positive and significant at the 1 percent level of significance. The results conclude that the students are satisfied with using the blackboard on mobile, nevertheless, the difficulties factor which is positive and significant shows that students are facing some difficulties in using the blackboard on their mobile.

The Effect of e-CRM Factors on Customer Relationship Quality and Performance in B2B e-Marketplace -Focused on Moderating Effects of Switching Barriers (B2B e-마켓플레이스의 e-CRM요인이 고객관계의 질과 성과에 미치는 영향 -전환장벽의 조절효과를 중심으로-)

  • Song, Sun-Yok;Park, Kyu-Young
    • International Commerce and Information Review
    • /
    • v.13 no.4
    • /
    • pp.23-49
    • /
    • 2011
  • The of this study was to establish a theoretical basis for relationship marketing exercised in the mB e-Marketplace and to empirically analyze causal relationship among e-CRM factor, together with quality and the performance of the customer relationship. The population sample of this study was the companies who had experience for using the B2B e-Marketplace, and a data analysis was made through y analysis, factor analysis, multiple regression analysis and hierarchical regression analysis, utilizing statistical package of SPSS 18.0. The result of proving the are as follows; First, the e-CRM factors(e-Marketing, e-Service, e-Sales) of B2B e-Marketplace showed the positive influence on the customer relationship quality factor. the e-CRM factors of B2B e-Marketplace showed the positive influence on the customer relationship performance factor. Third, according to the test result on the relationship between quality factor and performance factor, customer relationship quality factor(satisfaction, trust) had positive effect on performance factor. Last, for the moderating effect of switching barrier in the customer relationship quality factor(satisfaction, trust) on the B2B e-Marketplace and its performance factor(reusing intention, long-term orientation) of maintaining the relation, the subordinate variables of switching barrier(alternative attraction, switching cost) showed the positive moderating effects.

  • PDF