Eardrum-inspired soft viscoelastic diaphragms for CNN-based speech recognition with audio visualization images.

In this study, we present initial efforts for a new speech recognition approach aimed at producing different input images for convolutional neural network (CNN)-based speech recognition. We explored the potential of the tympanic membrane (eardrum)-inspired viscoelastic membrane-type diaphragms to deliver audio visualization images using a cross-recurrence plot (CRP). These images were formed by the two phase-shifted vibration responses of viscoelastic diaphragms.

Crack Monitoring in Rotating Shaft Using Rotational Speed Sensor-Based Torsional Stiffness Estimation with Adaptive Extended Kalman Filters.

In this study, we present an alternative solution for detecting crack damages in rotating shafts under torque fluctuation by directly estimating the reduction in torsional shaft stiffness using the adaptive extended Kalman filter (AEKF) algorithm. A dynamic system model of a rotating shaft for designing AEKF was derived and implemented. An AEKF with a forgetting factor () update was then designed to effectively estimate the time-varying parameter (torsional shaft stiffness) owing to cracks.