Boosted by health consequences and the cost of falls in the elderly, this work<br />develops and tests a novel algorithm and methodology to detect human impacts that will<br />act as triggers of a two-layer fall monitor. The two main requirements demanded by<br />socio-healthcare providers—unobtrusiveness and reliability—defined the objectives of the<br />research. We have demonstrated that a very agile, adaptive, and energy-based anisotropic<br />algorithm can provide 100% sensitivity and 78% specificity, in the task of detecting<br />impacts under demanding laboratory conditions. The algorithm works together with an<br />unsupervised real-time learning technique that addresses the adaptive capability, and this is<br />also presented. The work demonstrates the robustness and reliability of our new algorithm,<br />which will be the basis of a smart falling monitor. This is shown in this work to underline<br />the relevance of the results.
Prado-Velasco, M., Marín, R. O., & Cidoncha, G. del R. (2013). Detection of human impacts by an adaptive energy-based anisotropic algorithm. International Journal of Environmental Research and Public Health, 10(10), 4767–4789. https://doi.org/10.3390/ijerph10104767