Kernel Principal Component Analysis for Identification of Between-Group Differences and Changes in Running Gait Patterns

被引:2
|
作者
Phinyomark, A. [1 ]
Osis, S. T. [1 ,3 ]
Hettinga, B. A. [1 ]
Ferber, R. [1 ,2 ,3 ]
机构
[1] Univ Calgary, Fac Kinesiol, 2500 Univ Dr NW, Calgary, AB, Canada
[2] Univ Calgary, Fac Nursing, Calgary, AB, Canada
[3] Running Injury Clin, Calgary, AB, Canada
关键词
ageing; feature extraction; gender; kinematics; non-linear analysis; FEATURE-EXTRACTION; GENDER-DIFFERENCES; KINEMATICS; BIOMECHANICS; RECOGNITION; RUNNERS;
D O I
10.1007/978-3-319-32703-7_1113
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
The identification of between-group differences and changes in gait mechanics are useful for injury prevention. Previous studies suggest the differences in gait biomechanical variables may interact in a complex non-linear fashion rather than a simple linear fashion. A non-linear multivariate analysis technique is therefore necessary to unravel the inherent structure in the gait data. Kernel principal component analysis (KPCA) is an extension of principal component analysis (PCA), the most widely used method in this field, and can provide inside into non-linear relationships of the variables of interest. Despite the growing use of PCA in running gait research, no prior studies have evaluated the utility of KPCA in determining the between-group differences in running gait patterns. Therefore, the objective of this study was to compare the performance of KPCA and PCA in identifying differences between male and female runners and as well between young and older runners in running gait kinematics. Running kinematic data were analysed on a gender group (female, n = 50; male, n = 50) and an age group (young, n = 50; older, n = 50) for discrete variables and waveform data. The following key results were obtained: (1) the performance of the KPCA for the identification of gender and age differences in running gait kinematics increased as compared to using the linear PCA; (2) the Gaussian function often performed better than the polynomial function for these two experiments; (3) there was no consistent optimal value of either the width s of the Gaussian kernel or the degree d of the polynomial kernel for different data types and experiments. These results suggest that non-linear features extracted by KPCA could be potentially useful in identifying and discriminating between-group differences and changes in running gait patterns, and could provide useful information about the intrinsic non-linear dynamics of running movement.
引用
收藏
页码:580 / 585
页数:6
相关论文
共 50 条
  • [1] BETWEEN-GROUP ANALYSIS WITH HETEROGENEOUS COVARIANCE MATRICES - THE COMMON PRINCIPAL COMPONENT MODEL
    KRZANOWSKI, WJ
    JOURNAL OF CLASSIFICATION, 1990, 7 (01) : 81 - 98
  • [2] IDENTIFICATION OF KNEE FRONTAL PLANE KINEMATIC PATTERNS IN NORMAL GAIT BY PRINCIPAL COMPONENT ANALYSIS
    Mezghani, Neila
    Fuentes, Alexandre
    Gaudreault, Nathaly
    Mitiche, Amar
    Aissaoui, Rachid
    Hagmeister, Nicola
    De Guise, Jacques A.
    JOURNAL OF MECHANICS IN MEDICINE AND BIOLOGY, 2013, 13 (03)
  • [3] Application of principal component analysis in clinical gait research: Identification of systematic differences between healthy and medial knee-osteoarthritic gait
    Federolf, P. A.
    Boyer, K. A.
    Andriacchi, T. P.
    JOURNAL OF BIOMECHANICS, 2013, 46 (13) : 2173 - 2178
  • [4] The identification of age-related differences in kinetic gait parameters using principal component analysis
    Chester, Victoria L.
    Wrigley, Allan T.
    CLINICAL BIOMECHANICS, 2008, 23 (02) : 212 - 220
  • [5] RADAR TARGET IDENTIFICATION BY KERNEL PRINCIPAL COMPONENT ANALYSIS ON RCS
    Chan, S-C
    Lee, K-C
    JOURNAL OF ELECTROMAGNETIC WAVES AND APPLICATIONS, 2012, 26 (01) : 64 - 74
  • [6] Identification of severe weather outbreaks using kernel principal component analysis
    Mercer, Andrew E.
    Richman, Michael B.
    Leslie, Lance M.
    COMPLEX ADAPTIVE SYSTEMS, 2011, 6
  • [7] Fault identification for process monitoring using kernel principal component analysis
    Cho, JH
    Lee, JM
    Choi, SW
    Lee, D
    Lee, IB
    CHEMICAL ENGINEERING SCIENCE, 2005, 60 (01) : 279 - 288
  • [8] Robust Speaker Identification Using Ensembles of Kernel Principal Component Analysis
    Yang, Il-Ho
    Kim, Min-Seok
    So, Byung-Min
    Kim, Myung-Jae
    Yu, Ha-Jin
    HYBRID ARTIFICIAL INTELLIGENT SYSTEMS, PT I, 2012, 7208 : 71 - 78
  • [9] Feature selection for noisy variation patterns using kernel principal component analysis
    Sahu, Anshuman
    Apley, Daniel W.
    Runger, George C.
    KNOWLEDGE-BASED SYSTEMS, 2014, 72 : 37 - 47
  • [10] Adaptive Subset Kernel Principal Component Analysis for Time-Varying Patterns
    Washizawa, Yoshikazu
    IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2012, 23 (12) : 1961 - 1973