Evaluation of Machine Learning algorithms applied to differentiate upper extremities from bioimpedance measurements

GERARDO AMES LASTRA; CONCU, A.; OSCAR REAL MORENO; RODRIGO KATAISHI; DELL'OSA, ANTONIO H.

2023 20th International Conference on Electrical Engineering, Computing Science and Automatic Control, CCE 2023

Institute of Electrical and Electronics Engineers Inc.

Año: 2023

Bioimpedance measurements provide every daymore information about the physiological functions and theanatomical state in applications on humans. In general, each ofthe applications on human beings differs in the configuration ofthe technique used and in the processing of the data. At the sametime, Machine Learning techniques are increasingly used invarious biomedical fields. This paper analyzes the application ofdifferent Machine Learning algorithms to differentiatedominant arms and non-dominant arms from bioimpedancespectroscopy measurements in bipolar configuration and in anon-invasive way. In this work, we use the same data as in aprevious work by our research group but with a differentpreconditioning and a reduced bioimpedance spectrum datasize. The metrics obtained are promising and the methodologyis suitable to include in studies focused on both arms of thesubjects, as it reduces the bias introduced by theanatophysiological development of one dominant extremity overthe other.