• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.773-794
• /
• 2021

Prediction of vehicle traffic volume is very important in planning municipal administration. It may help promote social and economic interests and also prevent traffic congestion costs. Traffic volume as a time-varying trajectory is considered as functional data. In this paper we study three functional regression models that can be used to predict an unseen trajectory of traffic volume based on already observed trajectories. We apply the methods to highway tollgate traffic volume data collected at some tollgates in Seoul, Chuncheon and Gangneung. We compare the prediction errors of the three models to find the best one for each of the three tollgate traffic volumes.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.383-396
• /
• 2017

The model in our approach assumes that computer responses are a realization of a Gaussian processes superimposed on a regression model called a Gaussian process regression model (GPRM). Selecting a subset of variables or building a good reduced model in classical regression is an important process to identify variables influential to responses and for further analysis such as prediction or classification. One reason to select some variables in the prediction aspect is to prevent the over-fitting or under-fitting to data. The same reasoning and approach can be applicable to GPRM. However, only a few works on the variable selection in GPRM were done. In this paper, we propose a new algorithm to build a good prediction model among some GPRMs. It is a post-work of the algorithm that includes the Welch method suggested by previous researchers. The proposed algorithms select some non-zero regression coefficients (${\beta}^{\prime}s$) using forward and backward methods along with the Lasso guided approach. During this process, the fixed were covariance parameters (${\theta}^{\prime}s$) that were pre-selected by the Welch algorithm. We illustrated the superiority of our proposed models over the Welch method and non-selection models using four test functions and one real data example. Future extensions are also discussed.

• Atmosphere
• /
• v.25 no.4
• /
• pp.591-600
• /
• 2015

We have analyzed wind and eddy covariance data collected within roughness sublayer over sloping terrain. The study site is located on non-flat terrain with slopes in both south-north and east-west directions. The surface elevation change is smaller than the height of roughness element such as building and tree. This study examines the directional wind shear for data collected at three levels in the lowest 10 m in the roughness sublayer. The wind direction shear is caused by drag of roughness element and terrain-induced motions at this site. Small directional shear occurs when wind speed at 10 m is strong and wind direction at 10 m is southerly which is the same direction as upslope flow near surface at this site during daytime. Correlation between vertical shear of lateral momentum and lateral momentum flux is smaller over steeply sloped surface compared to mildly sloped surface and lateral momentum flux is not down-gradient over steeply sloped surface. Quadrant analysis shows that the relative contribution of four quadrants to momentum flux depends on both surface slope and wind direction shear.

• Journal of KIISE:Software and Applications
• /
• v.28 no.2
• /
• pp.192-200
• /
• 2001

본 논문은 조명 변화, 표정 변화, 부분적인 오클루전이 있는 얼굴 영상에 강인하고 적은 메모리양과 계산량을 갖는 효율적인 얼굴 인식 방법을 제안한다. SKKUface(Sungkyunkwan University face)라 명명한 이 방법은 먼저 훈련 영상에 PCA(principal component analysis)를 적용하여 차원을 줄일 때 구해지는 특징 벡터 공간에서 조명 변화, 얼굴 표정 변화 등에 해당되는 공간이 최대한 제외된 새로운 특징 벡터 공간을 생성한다. 이러한 특징 벡터 공간은 얼굴의 고유특징만을 주로 포함하는 벡터 공간이므로 이러한 벡터 공간에 Fisher linear discriminant를 적용하면 클래스간의 더욱 효과적인 분리가 이루어져 인식률을 획기적으로 향상시킨다. 또한, SKKUface 방법은 클래스간 분산(between-class covariance) 행렬과 클래스내 분산(within-class covariance) 행렬을 계산할 때 문제가 되는 메모리양과 계산 시간을 획기적으로 줄이는 방법을 제안하여 적용하였다. 제안된 SKKUface 방법의 얼굴 인식 성능을 평가하기 위하여 YALE, SKKU, ORL(Olivetti Research Laboratory) 얼굴 데이타베이스를 가지고 기존의 얼굴 인식 방법으로 널리 알려진 Eigenface 방법, Fisherface 방법과 함께 인식률을 비교 평가하였다. 실험 결과, 제안된 SKKUface 방법이 조명 변화, 부분적인 오클루전이 있는 얼굴 영상에 대해서 Eigenface 방법과 Fisherface 방법에 비해 인식률이 상당히 우수함을 알 수 있었다.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.36 no.5
• /
• pp.455-461
• /
• 2008

In this paper, the performance of a scalar filter and a scalar adaptive filter are analyzed. In order to make indoor experimental environment similar to outdoor test, ultrasonic sensors are used instead of GPS. The scalar adaptive filter, which is continuously estimating velocity error covariance and measurement noise covariance by using adaptive method, is different from the scalar filter. Experimental results show that the scalar adaptive filter has better position estimating performance than the scalar filter by estimating above two parameters with an adaptive method.

• The Korean Journal of Applied Statistics
• /
• v.20 no.2
• /
• pp.395-407
• /
• 2007

Outliers distort many measures for data analysis. We can propose dandelion seed plot as a graphical tool for evaluating the effect of outliers in one-and two-variate data. We can draw mean-variance dandelion seed plots using linked curves which are made by changing weights from 1 to 0 for each datum. Similarly we can also draw covariance-correlation-coefficient dandelion seed plots. This graphical method can be a useful tool for elementary statistics education in college.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.23 no.1
• /
• pp.85-95
• /
• 2012

In this thesis, we develop a spectral analysis scheme to eliminate the spurious peaks generated in HRR Millimeterwave Seeker based on FMICW system. In contrast to FMCW system, FMICW system generates spurious peaks in the spectrum of its IF signal, caused by the periodic discontinuity of the signal. These peaks make the accuracy of the system depend on the previously estimated range if a band pass filter is utilized to eliminate them and noise floor go to high level if random interrupted sequence is utilized and in case of using staggering process, we must transmit several waveforms to obtain overlapped information. Using the spectral analysis one of the schemes such as IAA(Iterative Adaptive Approach) and SPICE(SemiParametric Iterative Covariance-based Estimation method) which were introduced recently, the spurious peaks can be eliminated effectively. In order to utilize IAA and SPICE, since we must distinguish between reliable data and unreliable data and only use reliable data, STFT(Short Time Fourier Transform) is applied to the distinguishment process.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.17 no.7
• /
• pp.629-640
• /
• 2016

This study was conducted to investigate the influence of job stress, fatigue symptoms and job satisfaction on turnover intention among dental hygienists. Overall, 516 dental hygienists who work in dental clinics were surveyed using a standardized self-administered questionnaire from April 1 to June 30, 2015. Mean turnover intention was compared to each independent variable tested by t-tests and ANOVA, correlation among turnover intention, job stress, fatigue symptoms and job satisfaction was calculated by Pearson's correlation coefficient, and covariance structure analysis was used to evaluate whether turnover intention was associated with job stress, fatigue symptoms and job satisfaction. Turnover intention was significantly higher among subjects with higher job stress and fatigue, as well as those with lower job satisfaction. Additionally, turnover intention was significantly positively correlated with job stress and fatigue symptoms, while turnover intention was negatively correlated with job satisfaction. Covariance structure analysis revealed job stress had a greater impact on turnover intention than fatigue and job satisfaction, high job stress and fatigue, the lower the job satisfaction showed that the effect of increasing the turnover intention. Overall, these results indicate that turnover intention of dental hygienists are more heavily influenced by job satisfaction and job stress than fatigue. Therefore, efforts are needed to reduce job stress and fatigue, as well as to improve job satisfaction to reduce the degree of turnover intention among dental hygienists.

• Journal of muscle and joint health
• /
• v.5 no.1
• /
• pp.7-25
• /
• 1998

Rheumatoid arthritis, unlike other chronic diseases, causes the patients to experience uncertainty in their daily lives and thus to feel threat on their emotional comfort because of inconsistent and unpredictable symptoms such as pain. Therefore, a theoretical framework is needed for explanation of uncertainty in patients having rheumatoid arthritis. A hypothetical model was constructed on the basis of Mishel's Uncertainty Theory and other literature review. The model included 9 theoretical concepts and 19 paths. Subjects of the study constituted 330 partients who visited outpatient clinics of two university hospitals and one general hospital in Seoul. Self report questionnaires were used to measure the variables affecting uncertainty. Reliability coefficients of these instruments were found Cronbach's Alpha=$.70{\sim}.94$. In data analysis, SAS program and PC-LISREL 8.03 computer program were utilized for descriptive statistics and covariance structure analysis. The results of covariance structure analysis for model fitness were as follows : 1) Hypothetical model showed a good fit to the empirical data : Chi-square($X^2$)=41.81 (df=11, P=.000), Goodness of Fit Index=.974, Root Mean Square Residual=.049, Normed Fit Index=.928, Non Normed Fit Index=.814. 2) For the validity and the parcimony of model, a modified model was constructed by appending 2 paths and deleting 5 paths according to the criteria of statistical significance and meaningfulness. 3) The results of hypothesis testing were as follows : (1) Educational level, event familiarity and severity of illness had a direct effect on uncertainty : Event congruency had both direct and indirect effect on uncertainty : Credible authority and symptom consistency had a nonsignificant direct effect on uncertainty, (2) Illness duration, symptom consistency, and event congruency had a direct effect on severity of illness ; Credible authority had a both direct and indirect effect on severity of illness ; Event congruency had the greatest effect on severity of illness, and event familiarity had a nonsignificant direct effect on severity of illness.

• Journal of Preventive Medicine and Public Health
• /
• v.40 no.5
• /
• pp.351-362
• /
• 2007

Objectives: The present study was intended to assess the mental health of nurses working for university hospitals and to establish which factors determine their mental health. Methods: Self-administered questionnaires were given to 1,486 nurses employed in six participating hospitals located in Daejeon City and Chungnam Province between July 1 st and August 31st, 2006. The questionnaire items included sociodemographic, job-related, and psychosocial factors, with job stress factors (JCQ) as independent variables and indices of mental health status (PWI, SDS and MFS) as dependent variables. For statistical analysis, the Chi-square test was used for categorical variables, with hierarchical multiple regression used for determining the factors effecting mental health. The influence of psychosocial and job-related factors on mental health status was assessed by covariance structure analysis. The statistical significance was set at p<0.05. Results: The factors influencing mental health status among subject nurses included sociodemographic characteristics such as age, number of hours of sleep, number of hours of leisure, and subjective health status; job-related characteristics such as status, job satisfaction, job suitability, stresses such as demands of the job, autonomy, and coworker support; and psychosocial factors such as self-esteem, locus of control and type A behavior patterns. Psychosocial factors had the greatest impact on mental health. Covariance structure analysis determined that psychosocial factors affected job stress levels and mental health status, and that the lower job stress levels were associated with better mental health. Conclusions: Based on the study results, improvement of mental health status among nurses requires the development and application of programs to manage job stress factors and/or psychosocial factors as well as sociodemographic and job-related characteristics.