Monitoreo de la Actividad Física a Partir de un Modelo Basado en Redes Neuronales, con Dispositivo "Wearable"
Abstract
The smart devices used for health and physical activities monitoring are elements with high presence in the market of wearables. This work presents an estimaton method for walking speed based on a multilayer artificial neural netwok, which has been trained to obtain the ratio between this speed and the frequency of the arms motion, characteristics of each person. In spite of using only 3 input variables (hight weight and gender), errors than less than 10% were obtained for the mentioned ratio. In addition, the estimation algorith has been incorporated into a low cost, wrist weareable device, ehich uses a inertial measurement unit (IMU) to measure the angular velocity of one arm. These IMUs are not common for these type of devices, but can be used to obtain more accurate speed measures than those obtained by meas of GPS units. Thus, the system can be used to record the physical activity with higher accuracy.
Keywords: Artificial neural network, walking speed measurement, health monitoring, IMU, GPS.
References
[1] Brodie, M., Walmsley, A. and Page, W.” Fusion motion capture using IMU and GPS to biomechanical analysis of ski racing”,Sport Tecnology, 2008.
[2] Leardini, A., Lullini, G. and Gianini, A,” Validation of the angular measurement of a new IMU based rehabilitation System”, Journal of Neuroengineering and Rehabilitation,2014.
[3] Marin, F., Fradet, L. Lepetit, K. and Han-sen, C., “Inertial Measurement Unit in Biomechanics and sport Biomechanics: Past, Present and Future”, 33rd International Conference on Biomechanics in Sport, Poiter, France,2015.
[4] Tan, H. and Wilson, A., “Measurement of stride parameters using a wearable GPS and IMU”, Journal of Biomechanics, 2008.
[5] Yang, S. and Li, Q., “Inertial Sensor-Based Methods in Walking Speed Estimation: A Systematic Review. Sensors “(Basel). 2012; 12(5): 6102–6116.
[6] He, Z. and Zhang, W. “Estimation of Walking Speed Using Accelerometer and Artificial Neural Networks”. In: Yu Y., Yu Z., Zhao J. (eds) Computer Science for Environmental Engineering and EcoInformatics. Communications in Computer and Information Science, vol 159. Springer, Berlin, Heidelberg.
[7] Peruzzi, A., Della, U. and Cereatti, C.”Estimation of stride length in level walking using an IMU attached to the foot: A validation of zero assumption during Stance”,Journal of Biomechanics, 2011.
[8] Knight, J.F.; Deen-Williams, D.; Arvanitis, T.N.; Baber, C.; Sotiriou, S.; Anastopoulou, S.; Gargalakos, M. Assessing the wearability of wearable computers. In Proceedings of the 2006 10th IEEE International Symposium on Wearable Computers, Montreux, Switzerland, 11–14 October 2006; pp. 75–82.
[9] K. Levenberg, A method for the solution of certain problems in least squares, Quarterly of Applied Mathematics, 5, 164–168, 1944.
[10] D. Marquardt, An algorithm for least-squares estimation of nonlinear parameters, SIAM Journal on Applied Mathematics, 11(2), 431–441, June 1963.