• Title/Summary/Keyword: Functional principal component analysis

Search Result 73, Processing Time 0.025 seconds

Classification via principal differential analysis

  • Jang, Eunseong;Lim, Yaeji
    • Communications for Statistical Applications and Methods
    • /
    • v.28 no.2
    • /
    • pp.135-150
    • /
    • 2021
  • We propose principal differential analysis based classification methods. Computations of squared multiple correlation function (RSQ) and principal differential analysis (PDA) scores are reviewed; in addition, we combine principal differential analysis results with the logistic regression for binary classification. In the numerical study, we compare the principal differential analysis based classification methods with functional principal component analysis based classification. Various scenarios are considered in a simulation study, and principal differential analysis based classification methods classify the functional data well. Gene expression data is considered for real data analysis. We observe that the PDA score based method also performs well.

Principal component analysis for Hilbertian functional data

  • Kim, Dongwoo;Lee, Young Kyung;Park, Byeong U.
    • Communications for Statistical Applications and Methods
    • /
    • v.27 no.1
    • /
    • pp.149-161
    • /
    • 2020
  • In this paper we extend the functional principal component analysis for real-valued random functions to the case of Hilbert-space-valued functional random objects. For this, we introduce an autocovariance operator acting on the space of real-valued functions. We establish an eigendecomposition of the autocovariance operator and a Karuhnen-Loève expansion. We propose the estimators of the eigenfunctions and the functional principal component scores, and investigate the rates of convergence of the estimators to their targets. We detail the implementation of the methodology for the cases of compositional vectors and density functions, and illustrate the method by analyzing time-varying population composition data. We also discuss an extension of the methodology to multivariate cases and develop the corresponding theory.

Interpretation of Agronomic Traits Variation of Sesame Cultivar Using Principal Component Analysis

  • Shim, Kang-Bo;Hwang, Chung-Dong;Pae, Suk-Bok;Park, Jang-Whan;Byun, Jae-Cheon;Park, Keum-Yong
    • KOREAN JOURNAL OF CROP SCIENCE
    • /
    • v.54 no.1
    • /
    • pp.24-28
    • /
    • 2009
  • This study was conducted to evaluate the growth characters and yield components of 18 collected sesame cultivars to get basic information on the variation for the sesame breeding using principal component analysis. All characters except days to flowering, days to maturity and 1,000 seed weight showed significantly different. Seed weight per 10 are showed higher coefficient of variance. Capsule bearing stem length and liter weight showed positive correlation with seed yield per 10 are. The principal components analysis grouped the estimated sesame cultivars into four main components which accounted for 83.7% of the total variation at the eigenvalue and its contribution to total variation obtained from principal component analysis. The first principal component ($Z_1$) was applicable to increase plant height, capsule bearing stem length and 1,000-seed weight. The second principal component ($Z_2$) negatively correlated with days to flowering and maturity by which it was applicable to shorten flowering and maturity date of sesame. At the scatter diagram, Yangbaek, Ansan, M1, M2, M4, M7 and M9 were classified as same group, but M10, Yanghuk, Kanghuk, M5, M6, M12 and M13 were classified as different group. This results would be helpful for sesame breeder to understand genetic relationship of some agronomic characters and select promising cross lines for the development of new sesame variety.

Functional Data Analysis of Temperature and Precipitation Data (기온 강수량 자료의 함수적 데이터 분석)

  • Kang, Kee-Hoon;Ahn, Hong-Se
    • The Korean Journal of Applied Statistics
    • /
    • v.19 no.3
    • /
    • pp.431-445
    • /
    • 2006
  • In this paper we review some methods for analyzing functional data and illustrate real application of functional data analysis. Representing methods for functional data by using basis function, analyzing functional variation by functional principal component analysis and functional linear models are reviewed. For a real application, we use temperature and precipitation data measured in Korea from the January of 1970 to the May of 2004. We apply functional principal component analysis for each data and test the significance of regional division done by using shining hours. We also estimate functional regression model for temperature and precipitation.

Functional Forecasting of Seasonality (계절변동의 함수적 예측)

  • Lee, Geung-Hee
    • The Korean Journal of Applied Statistics
    • /
    • v.28 no.5
    • /
    • pp.885-893
    • /
    • 2015
  • It is important to improve the forecasting accuracy of one-year-ahead seasonal factors in order to produce seasonally adjusted series of the following year. In this paper, seasonal factors of 8 monthly Korean economic time series are examined and forecast based on the functional principal component regression. One-year-ahead forecasts of seasonal factors from the functional principal component regression are compared with other forecasting methods based on mean absolute error (MAE) and mean absolute percentage error (MAPE). Forecasting seasonal factors via the functional principal component regression performs better than other comparable methods.

Exploring COVID-19 in mainland China during the lockdown of Wuhan via functional data analysis

  • Li, Xing;Zhang, Panpan;Feng, Qunqiang
    • Communications for Statistical Applications and Methods
    • /
    • v.29 no.1
    • /
    • pp.103-125
    • /
    • 2022
  • In this paper, we analyze the time series data of the case and death counts of COVID-19 that broke out in China in December, 2019. The study period is during the lockdown of Wuhan. We exploit functional data analysis methods to analyze the collected time series data. The analysis is divided into three parts. First, the functional principal component analysis is conducted to investigate the modes of variation. Second, we carry out the functional canonical correlation analysis to explore the relationship between confirmed and death cases. Finally, we utilize a clustering method based on the Expectation-Maximization (EM) algorithm to run the cluster analysis on the counts of confirmed cases, where the number of clusters is determined via a cross-validation approach. Besides, we compare the clustering results with some migration data available to the public.

Long-term Energy Demand Forecast in Korea Using Functional Principal Component Analysis (함수 주성분 분석을 이용한 한국의 장기 에너지 수요예측)

  • Choi, Yongok;Yang, Hyunjin
    • Environmental and Resource Economics Review
    • /
    • v.28 no.3
    • /
    • pp.437-465
    • /
    • 2019
  • In this study, we propose a new method to forecast long-term energy demand in Korea. Based on Chang et al. (2016), which models the time varying long-run relationship between electricity demand and GDP with a function coefficient panel model, we design several schemes to retain objectivity of the forecasting model. First, we select the bandwidth parameters for the income coefficient based on the out-of-sample forecasting performance. Second, we extend the income coefficient using the functional principal component analysis method. Third, we proposed a method to reflect the elasticity change patterns inherent in Korea. In the empirical analysis part, we forecasts the long-term energy demand in Korea using the proposed method to show that the proposed method generates more stable long term forecasts than the existing methods.

Classification of papers using IR and NIR spectra and principal component analysis (IR 및 NIR 스펙트럼과 주성분 분석을 통한 지종의 분류)

  • Kim, Kang-Jae;Eom, Tae-Jin
    • Journal of Korea Technical Association of The Pulp and Paper Industry
    • /
    • v.48 no.1
    • /
    • pp.34-42
    • /
    • 2016
  • In this study, we classified three copying papers and Korean, Chinese, and Japanese traditional papers using IR and/or NIR spectra and principal component analysis. Various chemicals are used when producing fine papers. In this case, the IR method to analyze functional groups is suitable for the classification of paper. On the other hand, NIR analysis is more suitable for the classification of traditional papers, as it uses nearly raw materials (pulp). Therefore, principal component analysis using IR and NIR depending on the paper production process will be the classification tool of paper.

Analysis of Functional Connectivity in Human Working Memory using Positron Emission Tomography and Principal Component Analysis

  • Lee, J.S.;Ahn, J.Y.;Jang, M.J.;Lee, D.S.;Chung, J.K.;Lee, M.C.;Park, K.S.
    • Proceedings of the KOSOMBE Conference
    • /
    • v.1998 no.11
    • /
    • pp.257-258
    • /
    • 1998
  • To reveal the interconnected brain regions involved in human working memory, their functional connectivity was analyzed using principal component analysis (PCA). rCBF PET scans were peformed on 5 normal volunteers during the verbal and visual working memory tasks and PCA was applied. PCA produced the first principal components related with the increase of the difficulty and the second one which demonstrate the dissociation of verbal and visual memory system.

  • PDF

Functional Data Classification of Variable Stars

  • Park, Minjeong;Kim, Donghoh;Cho, Sinsup;Oh, Hee-Seok
    • Communications for Statistical Applications and Methods
    • /
    • v.20 no.4
    • /
    • pp.271-281
    • /
    • 2013
  • This paper considers a problem of classification of variable stars based on functional data analysis. For a better understanding of galaxy structure and stellar evolution, various approaches for classification of variable stars have been studied. Several features that explain the characteristics of variable stars (such as color index, amplitude, period, and Fourier coefficients) were usually used to classify variable stars. Excluding other factors but focusing only on the curve shapes of variable stars, Deb and Singh (2009) proposed a classification procedure using multivariate principal component analysis. However, this approach is limited to accommodate some features of the light curve data that are unequally spaced in the phase domain and have some functional properties. In this paper, we propose a light curve estimation method that is suitable for functional data analysis, and provide a classification procedure for variable stars that combined the features of a light curve with existing functional data analysis methods. To evaluate its practical applicability, we apply the proposed classification procedure to the data sets of variable stars from the project STellar Astrophysics and Research on Exoplanets (STARE).