作者: C.K. Chan , W.P. Loh , I. Abd Rahim
DOI: 10.1016/J.SBSPRO.2013.08.411
关键词: Decision table 、 Data mining 、 Data pre-processing 、 Imputation (statistics) 、 Body segment 、 Preprocessor 、 Human motion 、 Missing data 、 Computer science
摘要: Abstract The missing information from raw human motion data due to occlusion and hidden postures during motions has influenced the quality of input data. This study proposes a novel idea preprocessing with elimination cum interpolation for imputation treat information. was implemented on three sets public available concerning jumping, walking running activities obtained YouTube ( www.youtube.com ). video were transformed into numerical aid Photoshop tool in order obtain body segment markers form rotation angles coordinates 2-dimensional format. proposed approach compared numerically conventional approaches: elimination, averaging, values. efficiencies confirmed by classification accuracies through BayesNet, Lazy Kstar, Decision table Part method classifiers specifically chosen WEKA tool. findings demonstrated that using coupling enhances better accuracy.