| Description: | The original data include 10 subjects, each perform 10 gestures 10 times. The gesture acquisition device is a Nintendo Wiimote remote controller with built-in three-axis accelerometer. Time series are of different lengths. There are no missing values. Each time series in text file is padded with NaN to the length of the longest time series in the dataset. ARFF files are padded with missing number symbol (the symbol ?) Data is acceleration in z-axis dimension. Each subject performs "pick-up" gesture multiple times. Classes are based on subject. Note that data are shuffled and randomly sampled so that instances across datasets do not sychronized by dimension or subject. Data created by Guna Joze et al. (see [1]). Data edited by Hoang Anh Dau. [1] Guna, Joze, Iztok Humar, and Matevz Pogacnik. "Intuitive gesture based user identification system." Telecommunications and Signal Processing (TSP), 2012 35th International Conference on. IEEE, 2012. |
