Efficient and Robust Detection of Local Impedance Changes Using Selected Electrical Excitation Conditions

Abstract

Bioelectrical impedance method is useful for evaluating tissue state such as muscle injury but there is a trade off between efficiency and robustness in detection of various local impedance changes. To solve this problem, we proposed a method using compressed electrical impedance sensing and discrimination analysis. We employed multiple excitation conditions like electrical impedance tomography, and investigated the effective excitation conditions. We then used both simulation and measurement data for efficient training process. In our experiment, we implemented a simulator and a measurement system with 16 electrodes and biological phantoms, and evaluated the discrimination rate for various impedance distribution by assuming muscle injury. As a result, we found that 6/120 excitation conditions are sufficient for detection of local impedance changes in a simple model and sufficient blending ratio of the measurement data to simulation data was 10.6% to perform 90% discrimination. The experimental result also indicated that the proposed method was robust for injury size, injury position, and body shape and 90% discrimination was achieved using 13/120 excitation conditions for complex models including skin, bone, and muscle area.

Development of Pinching Motion Classification Method Using EIT-Based Tactile Sensor

“…The results are presented in the confusion matrix. Some studies have reported the validity of classification using voltage vectors measured by the EIT method [37], [38]. Therefore, supplemental pinching classification was performed using one-dimensional measured voltage vectors consisting of 256 voltage points.…”

“…1) Supplement training data with simulation data A method for blending simulation data with measured data for classification has been reported [38]. By applying this method to simulate and reconstruct images with the same features as the reconstructed image generated from the motion to be classified, we believe that medium-to largescale data can be generated in a relatively short time and at low cost.…”