• The Korean Journal of Applied Statistics
• /
• v.30 no.3
• /
• pp.441-451
• /
• 2017

In this paper, we review principal component analysis (PCA) procedures in the frequency domain and apply them to analyze sea surface temperature data. The classical PCA defined in the time domain is a popular dimension reduction technique. Extending the conventional PCA to the frequency domain makes it possible to define PCA in the frequency domain, which is useful for dimension reduction as well as a feature extraction of multiple time series. We focus on two PCA methods in the frequency domain, Hilbert PCA (HPCA) and frequency domain PCA (FDPCA). We review these two PCAs in order for potential readers to easily understand insights as well as perform a numerical study for comparison with conventional PCA. Furthermore, we apply PCA methods in the frequency domain to sea surface temperature data on the tropical Pacific Ocean. Results from numerical experiments demonstrate that PCA in the frequency domain is effective for the analysis of time series data.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.8 no.3
• /
• pp.110-118
• /
• 2000

For reasonable fatigue design and estimation of fatigue durability considered fatigue strength and stiffness of the automotive body structure, many fatigue data must be insured according to the shapes, materials, and welding conditions of the spot welded lap joints. However, because it is actually difficult problem, there is need to establish a new method to be able to predict its fatigue life without any additional fatigue tests. Therefore, In order to improve such problems, in this study, the maximum stress function presenting the $\delta\sigma_{1max}―\delta P$ relation was defined form the relation between $\delta\sigma_{1max}-N_f$ and ${\delta}P-N_f$. By using the fatigue data on the IB type spot-welded lap joints previously obtained from the fatigue test results, fatigue life of the spot-welded lap joint previously obtained from the fatigue test results, fatigue life of the spot-welded lap joint having a certain dimension was tried to predict without any additional fatigue tests. And, its result was verified by ${\delta}P-$N_f$ curves. Obtained conclusion are as follows, 1) a maximum stress function considered the relation of the maximum principal stress, fatigue load, and the effects of geometrical factors of the IB type spot-welded lap joint was suggested. 2) the fatigue life predicted by the maximum principal stress function and the relation of $\delta\sigma_{1max}-N_f$ was well agreed with the fatigue life obtained through the actual fatigue test result. 3) the fatigue life of the IB type spot-welded lap joint having a certain dimension is able to be predicted without any additional fatigue tests from the fatigue life prediction method by the maximum principal stress function.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.393-400
• /
• 2006

There are many feature extraction methods for face recognition. We need a new method to overcome the small sample problem that the number of feature variables is larger than the sample size for face image data. The paper considers partial least squares(PLS) as a new dimension reduction technique for feature vector. Principal Component Analysis(PCA), a conventional dimension reduction method, selects the components with maximum variability, irrespective of the class information. So, PCA does not necessarily extract features that are important for the discrimination of classes. PLS, on the other hand, constructs the components so that the correlation between the class variable and themselves is maximized. Therefore PLS components are more predictive than PCA components in classification. The experimental results on Manchester and ORL databases shows that PLS is to be preferred over PCA when classification is the goal and dimension reduction is needed.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.957-968
• /
• 2021

Inverse censoring probability weighting (ICPW) is a popular technique in survival data analysis. In applications of the ICPW technique such as the censored regression, it is crucial to accurately estimate the censoring probability. A simulation study is undertaken in this article to see how censoring probability estimate influences model performance in censored regression using the ICPW scheme. We compare three censoring probability estimators, including Kaplan-Meier (KM) estimator, Cox proportional hazard model estimator, and local KM estimator. For the local KM estimator, we propose to reduce the predictor dimension to avoid the curse of dimensionality and consider two popular dimension reduction tools: principal component analysis and sliced inverse regression. Finally, we found that the Cox proportional hazard model estimator shows the best performance as a censoring probability estimator in both mean and median censored regressions.

• The Magazine of the Society of Air-Conditioning and Refrigerating Engineers of Korea
• /
• v.17 no.4
• /
• pp.408-417
• /
• 1988

This study optimized the condenser dimension of heat pump system with the heat sources which are solar irradiation and ambient air. At first, the author selected the principal design factors influencing the performance of heat pump system. And the author considered the variation of condenser dimension according to the variation of the selected design factors, that is, ambient air temperature, condenser temperature, degree of superheating, degree of sub-cooling and irradiation. As a result this study, among refrigerants R12, R22 and R500, refrigerant R22 has more heating output than R12 and R500, and the coefficient of performance on this heat pump system is not greatly influenced by the degree of superheating and degree of sub cooling. The ambient air temperature is below $5^{\circ}C$ at balance point and the optimal tube length of condenser dimension is about 3.8 m. Also the author gained the optimal design diagram for the optimization of condenser dimension according to various design factors.

• 한국석유지질학회:학술대회논문집
• /
• spring
• /
• pp.10-14
• /
• 1998

A systematic methodology is developed for the electrofacies determination from wireline log data using multivariate statistical analysis. To consider corresponding contribution of each log and reduce the computational dimension, multivariate logs are transformed into a single variable through principal components analysis. Resultant principal components logs are segmented using the statistical zonation method to enhance the efficiency and quality of the interpreted results. Hierarchical cluster analysis is then used to group the segments into electrofacies. Optimal number of groups is determined on the basis of the ratio of within-group variance to total variance and core data. This technique is applied to the wells in the Korea Continental Shelf. The results of field application demonstrate that the prediction of lithology based on the electrofacies classification matches well to the core and the cutting data with high reliability This methodology for electrofacies classification can be used to define the reservoir characteristics which are helpful to the reservoir management.

• The Korean Journal of Applied Statistics
• /
• v.8 no.2
• /
• pp.65-75
• /
• 1995

For the determination of dimension of e.d.r. space, both of Sliced Inverse Regression (SIR) and Principal Hessian Directions (PHD) proposed asymptotic test. But the asymptotic test requires the normality and large samples of explanatory variables. Cook and Weisberg(1991) suggested permutation tests instead. In this study permutation tests are actually made, and the power of them is compared with asymptotic test in the case of SIR and PHD.

• International Journal of Safety
• /
• v.11 no.2
• /
• pp.22-25
• /
• 2012

This paper deals with the problem of fault diagnosis for identifying a single fault when the number of assumed faults is larger than that of predictive variables. Principal component analysis (PCA) is employed to isolate and identify a single fault. PCA is a method to extract important information as reducing the number of large dimension in a process. The patterns of all assumed faults can be recognized by PCA and these can be employed whether a new fault is one of predefined faults or not. Through PCA, empirical models for analyzing patterns can be trained. When a single fault occurs, the pattern generated by PCA can be obtained and this is used to identify a fault. The performance of the proposed approach is illustrated in the actuator benchmark problem.

• Speech Sciences
• /
• v.12 no.2
• /
• pp.171-182
• /
• 2005

An efficient GMM (Gaussian mixture modeling) method based on LPCA (local principal component analysis) with VQ (vector quantization) for speaker identification is proposed. To reduce the dimension and correlation of the feature vector, this paper proposes a speaker identification method based on principal component analysis. The proposed method firstly partitions the data space into several disjoint regions by VQ, and then performs PCA in each region. Finally, the GMM for the speaker is obtained from the transformed feature vectors in each region. Compared to the conventional GMM method with diagonal covariance matrix, the proposed method requires less storage and complexity while maintaining the same performance requires less storage and shows faster results.

• Nuclear Engineering and Technology
• /
• v.33 no.5
• /
• pp.483-497
• /
• 2001

In this work, a neuro-fuzzy inference system combined with the wavelet denoising, PCA (principal component analysis) and SPRT (sequential probability ratio test) methods is developed to detect the relevant sensor failure using other sensor signals. The wavelet denoising technique is applied to remove noise components in input signals into the neuro-fuzzy system The PCA is used to reduce the dimension of an input space without losing a significant amount of information. The PCA makes easy the selection of the input signals into the neuro-fuzzy system. Also, a lower dimensional input space usually reduces the time necessary to train a neuro-fuzzy system. The parameters of the neuro-fuzzy inference system which estimates the relevant sensor signal are optimized by a genetic algorithm and a least-squares algorithm. The residuals between the estimated signals and the measured signals are used to detect whether the sensors are failed or not. The SPRT is used in this failure detection algorithm. The proposed sensor-monitoring algorithm was verified through applications to the pressurizer water level and the hot-leg flowrate sensors in pressurized water reactors.