Classification of multivariate time series using two-dimensional singular value decomposition

Combining Dynamic Time Warping and Single Hidden Layer Feedforward Neural Networks for Temporal Sign Language Recognition

“…ELM network system shows that the accuracy for sign language classification is up to 98.667% and training times and testing time are just about 27.015 seconds and 0.1771 seconds. Besides, referring to related works section, our proposed method demonstrates a reasonable accuracy in classification which is higher than previous reported classification results as Xiaoqing Weng [4] demonstrated the accuracy for classification on 25 signs of Australia sign language dataset is 95%.…”

“…Another approach was taken by Xiaoqing Weng and Junyi Shen who extracted feature of temporal sign languages by using two dimensional singular values decomposition [4]. They extended standard SVD by proposing a new approach called 2dSVD, the method captured explicitly the two dimensional nature of time series samples.…”

Early classification on multivariate time series

“…Time series classification is an important problem in time series data mining and has attracted great interest in recent years [21][22][23][24][25][26][27].…”

Selective Subsequence Time Series clustering

“…Time series clustering [2,6,15,13,24] is one of the most popular tasks in time series data mining community [5,16,18,25,26,20]. Most algorithms generally perform whole time series clustering [24,15].…”