Methodology form type classification and stepping in baropodometric systems
International Journal of Development Research
Methodology form type classification and stepping in baropodometric systems
Received 20th May, 2021; Received in revised form 11th June, 2021; Accepted 28th July, 2021; Published online 29th August, 2021
Copyright © 2021, Ernande F. Melo et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Baropodometric systems are using the area of Artificial Intelgence (AI), more specifically machine learning to classify type and step from data collected by sensors. We observed, in most of the works found in the literature, the use of MLP-type Neural Networks for the classification process, which requires a large amount of data and a high computational cost and processing time. This article proposes a methodology that goes in the opposite direction, that is, low data volume with low processing time and cost, in addition to a dynamic configuration of the classification environment, through the insertion or removal of modules, according to quantity and quality of the data collected by the sensors.
