Detecting delays in motor skill development of children through data analysis of a smart play device

ABSTRACT

This paper describes experiments with a game device that was used for early detection of delays in motor skill development in primary school children. Children play a game by bi-manual manipulation of the device which continuously collects accelerometer data and game state data. Features of the data are used to discriminate between normal children and children with delays. This study focused on the feature selection. Three features were compared: mean squared jerk (time domain); power spectral entropy (fourier domain) and cosine similarity measure (quality of game play). The discriminatory power of the features was tested in an experiment where 28 children played games of different levels of difficulty. The results show that jerk and cosine similarity have reasonable discriminatory power to detect fine-grained motor skill development delays especially when taking the game level into account. Duration of a game level needs to be at least 30 seconds in order to achieve good classification results.

References

1. Ted Brown and Aislinn Lalor. 2009. The movement assessment battery for children-second edition (MABC-2): A review and critique. Physical & occupational therapy in pediatrics 29, 1 (2009), 86--103.
2. Dylan P Cliff, Anthony D Okely, Leif M Smith, and Kim McKeen. 2009. Relationships between fundamental movement skills and objectively measured physical activity in preschool children. Pediatric exercise science 21, 4 (2009), 436--449.
3. Nils Y Hammerla, Shane Halloran, and Thomas Ploetz. 2016. Deep, convolutional, and recurrent models for human activity recognition using wearables. arXiv preprint arXiv: 1604.08880 (2016).
4. VH Hildebrandt, WTM Ooijendijk, and M Hopman-Rock. 2008. Trendrapport bewegen en gezondheid 2006/2007. (2008).
5. Sepp Hochreiter and Jürgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780.
6. Neville Hogan and Dagmar Sternad. 2009. Sensitivity of smoothness measures to movement duration, amplitude, and arrests. Journal of motor behavior 41, 6 (2009), 529--534.
7. Motonaga Kojima, Shuichi Obuchi, Kousuke Mizuno, Osamu Henmi, and Noriaki Ikeda. 2008. Power spectrum entropy of acceleration time-series during movement as an indicator of smoothness of movement. Journal of physiological anthropology 27, 4 (2008), 193--200.
8. Shyamal Patel, Richard Hughes, Todd Hester, Joel Stein, Metin Akay, Jennifer G Dy, and Paolo Bonato. 2010. A novel approach to monitor rehabilitation outcomes in stroke survivors using wearable technology. Proc. IEEE 98, 3 (2010), 450--461.
9. Christina Strohrmann, Rob Labruyère, Corinna N Gerber, Hubertus J van Hedel, Bert Arnrich, and Gerhard Tröster. 2013. Monitoring motor capacity changes of children during rehabilitation using body-worn sensors. Journal of neuroengineering and rehabilitation 10, 1 (2013), 1.
10. Huub Toussaint, Antoine de Schipper, Tim van Kernebeek, and Ilse Kat. 2015. MAMBO Meten Amsterdamse Motoriek Basis Onderwijs. (2015). http://www.hva.nl/kc-bsv/projecten/content/projecten-algemeen/monitoring-gezonde-ontwikkelin-kinderen.html
11. Aihua Zhang, Bin Yang, and Ling Huang. 2008. Feature extraction of EEG signals using power spectral entropy. In 2008 International Conference on BioMedical Engineering and Informatics, Vol. 2. IEEE, 435--439.