Verification of contact force estimation method for the bone-conducted sound transducer with human subjects

Abstract

In this study, we evaluated a method of estimating the contact force of a bone-conducted sound transducer using human subjects. The method was previously proposed and evaluated only with a human model. First, the relationship between the contact force and the electrical impedance was validated for 12 human subjects from 10 Hz to 60 kHz. The results showed that the electrical impedance shows four peaks and that the peaks change with contact force for all subjects in the same manner. A method of estimating the contact force was implemented with a three-layered neural network and evaluated with the data from 12 human subjects. The estimation results showed that 90% of the estimation error was within ±0.43 N, which shows that the estimation of contact force is possible. This result enables the estimation of contact force only from the electrical impedance and may support reproducible fitting of the bone-conducted sound transducer.

Method of estimating contact force of bone-conducted sound transducer with a two-degrees-of-freedom vibrating model

“…Note that this result was achieved with calibration at only 0.3 N and 0.5 N. With such a small amount of data, the previous method using a neural network 37) is not applicable, as thousands of parameters are required before learning converges. The 90th percentile of the estimation error in the previous method was 0.4 N with 770 sets of calibration data.…”

“…The 90th percentile of the estimation error was 0.4 N. This estimation error is reasonably low compared to the 90th percentile error of 0.4 N by the previously proposed method using a neural network. 37) The variation in the error was attributable to the variation of c h shown in Fig. 5.…”

“…m d represents the mass of the diaphragm and skin. From a previous examination, 37) it is known that the proposed model can reproduce the change in electrical impedance by the contact force. The model is used to estimate c h by the least-squares method in this paper.…”

“…We propose a method that uses the electrical impedance of the transducer [36][37][38] to solve this problem of contact force estimation. The electrical impedance of the transducer shows a characteristic change according to the contact force.…”

“…This estimation method was implemented with a neural network to estimate the nonlinear relationship between electrical impedance and contact force. 37) However, the method depends entirely on the measured data, since the structure of the neural network does not reflect the physical vibration. If the variation of the data is limited, the neural network fails to learn the correct relationship between impedance and force.…”