Classification of physical activity by accelerometry signals
Abstract
The present work addresses the problem associated with pattern recognition of signals from accelerometers to identify and classify a set of 12 physical activities, the signals were collected by accelerometers placed in three different anthropometric positions: chest, right wrist, left ankle. An Artificial Neural Network (ANN) model was developed that classifies this set of activities using only accelerometry signals as input. A performance comparison of the feedforward neural network (RNAf) is presented. The evaluation was performed in four different classification scenarios, concluding that the chest was the most effective position for classification, achieving 77% accuracy. However, by adopting an integrated approach that considers signals from all three sensors, the accuracy increased significantly, reaching 90%.
Downloads
References
Acevedo, E., Serna, A., & Serna, E. (2017). Principios y características de las redes neuronales artificiales. Desarrollo e innovación en ingeniería, 173.
AlShorman, O., Alshorman, B., & Masadeh, M. S. (2020). A review of physical human activity recognition chain using sensors. Indonesian Journal of Electrical Engineering and Informatics (IJEEI), 8(3), 560-573.
Banos,Oresti, Garcia,Rafael, and Saez,Alejandro. (2014). MHEALTH Dataset. UCI Machine Learning
Bulling, A., Blanke, U., & Schiele, B. (2014). A tutorial on human activity recognition using body-worn inertial sensors. ACM Computing Surveys (CSUR), 46(3), 1-33.
Carpenter, A., Pencharz, P., & Mouzaki, M. (2015). Accurate estimation of energy requirements of young patients. Journal of Pediatric Gastroenterology and Nutrition, 60(1), 4-10.
Demrozi, F., Pravadelli, G., Bihorac, A., & Rashidi, P. (2020). Human activity recognition using inertial, physiological and environmental sensors: A comprehensive survey. IEEE access, 8, 210816-210836.
Disse, E., Ledoux, S., Bétry, C., Caussy, C., Maitrepierre, C., Coupaye, M., ... & Simon, C. (2018). An artificial neural network to predict resting energy expenditure in obesity. Clinical Nutrition, 37(5), 1661-1669.
Garnotel, M., Simon, C., & Bonnet, S. (2019, July). Physical activity estimation from accelerometry. In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) (pp. 6-10). IEEE.
Grossi, E., & Buscema, M. (2007). Introduction to artificial neural networks. European journal of gastroenterology & hepatology, 19(12), 1046-1054.
Preece, S. J., Goulermas, J. Y., Kenney, L. P., & Howard, D. (2008). A comparison of feature extraction methods for the classification of dynamic activities from accelerometer data. IEEE Transactions on Biomedical Engineering, 56(3), 871-879.
San-Segundo, R., Montero, J. M., Barra-Chicote, R., Fernández, F., & Pardo, J. M. (2016). Feature extraction from smartphone inertial signals for human activity segmentation. Signal Processing, 120, 359-372.
Shcherbina, A., Mattsson, C. M., Waggott, D., Salisbury, H., Christle, J. W., Hastie, T., ... & Ashley, E. A. (2017). Accuracy in wrist-worn, sensor-based measurements of heart rate and energy expenditure in a diverse cohort. Journal of personalized medicine, 7(2), 3.
Shoaib, M., Bosch, S., Incel, O. D., Scholten, H., & Havinga, P. J. (2016). Complex human activity recognition using smartphone and wrist-worn motion sensors. Sensors, 16(4), 426.
Van Nguyen, N. H., Pham, M. T., Dai Ung, N., & Tachibana, K. (2018). Human activity recognition based on weighted sum method and combination of feature extraction methods. International Journal of Intelligent Information Systems, 7(1), 9.
Copyright (c) 2024 Elizabeth Cavita-Huerta, Juan Reyes-Reyes
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
