The data was collected from the written Java codes by the authors, and Weka packages for executing ECA* on 32 heterogenous and multi-featured datasets against its counterpart algorithms (KM, KM++, EM, LVQ, and GENCLUST++). Each of these algorithms was run thirty times on each of the 32 benchmarking dataset problems to evaluate the performance of ECA* against its competitve algorithms.

Context

This dataset is partly associated to the "Hand Tremor Based Biometric Recognition Using Leap Motion Device" paper (doi: 10.1109/ACCESS.2017.2764471 ). Objective is to investigate whether hand jitter can be treated as a new behavioral biometric recognition trait in the filed od security so that imitating and/or reproducing artificially can be avoided.

Content

Dataset contains five subjects. 1024 samples each subject's spatiotemporal hand tremor signals as a time series data were acquired via leap motion device. Features are X, Y, Z and Mixed (Average) channels. Channel represents displacement value of adjacent frames (difference between current and previous positions) and finally the last item is class label having value from 1 to 5.

Acknowledgements

I would like to thanks to our volunteer donor who provides us valuable hand tremor data.

Inspiration

Please read the "Hand Tremor Based Biometric Recognition Using Leap Motion Device" paper for more details and feature extraction methods. If you have any questions related to the preprocessing and/or processing the dataset please do not hesitate to contact with me via e-mail: hakmesyo@gmail.com . It should be noted that, data acquisition software was implemented in Java (Netbeans) and I utilized Processing, Open Cezeri Library and Weka tools alongside.

This dataset is partly associated to the "Hand Tremor Based Biometric Recognition Using Leap Motion Device" paper (doi: 10.1109/ACCESS.2017.2764471 ). If you think this new dataset is useful for your studies please cite our paper above. Objective is to investigate whether hand jitter can be treated as a new behavioral biometric recognition trait in the filed od security so that imitating and/or reproducing artificially can be avoided.Dataset contains five subjects. 1024 samples each subject's spatiotemporal hand tremor signals as a time series data were acquired via leap motion device. Features are X, Y, Z and Mixed (Average) channels. Channel represents displacement value of adjacent frames (difference between current and previous positions) and finally the last item is class label having value from 1 to 5.lease read the "Hand Tremor Based Biometric Recognition Using Leap Motion Device" paper for more details and feature extraction methods. If you have any questions related to the preprocessing and/or processing the dataset please do not hesitate to contact with me via e-mail: hakmesyo@gmail.com . It should be noted that, data acquisition software was implemented in Java (Netbeans) and I utilized Processing, Open Cezeri Library and Weka tools alongside.