Classification of Wideband Tympanometry by Deep Transfer Learning With Data Augmentation for Automatic Diagnosis of Otosclerosis.

Otosclerosis is a common disease of the middle ear leading to stapedial fixation. Its rapid and non-invasive diagnosis could be achieved through wideband tympanometry (WBT), but the interpretation of the raw data provided by this tool is complex and time-consuming. Convolutional neural networks (CNN) could potentially be applied to this situation to help the clinicians categorize WBT data. A dataset containing 135 samples from 80 patients with otosclerosis and 55 controls was obtained. We designed a lightweight CNN to categorize samples into the otosclerosis and control. Receiver operating characteristic (ROC) analysis showed an area under the curve (AUC) of 0.95 ±0.011, and the F1-score was 0.89 ±0.031 ( r=10). The performance was further improved by data augmentation schemes and transfer learning strategies (AUC: 0.97 ±0.010, F1-score: 0.94 ±0.016, , ANOVA). Finally, the most relevant diagnostic features employed by the CNN were assessed via the activation pattern heatmaps. These results are crucial for the visual interpretation of WBT graphic outputs which clinicians use in routine, and for a better understanding of the WBT signal in relation to the ossicular mechanics.

Mapping Relation between Rail and Bridge Deformation Considering Nonlinear Contact of Interlayer.

This paper examines the effect of structural deformation on the unit slab-type ballastless track structure of high-speed railway. The principle of stationary potential energy was used to map the relation between girder vertical deformation and rail deformation considering the effect of subgrade boundary conditions and the nonlinear contact of interlayer. The theoretical model was verified by comparing with the finite element analysis and experimental results. The theoretical model was used to analyze the effects of several key parameters on the rail deformation, such as vertical deformation amplitude, elastic modulus of the mortar layer, and vertical stiffness of the fasteners. The results show that the track slabs suffered significant disengagement, which makes the deformation of the track structure at the position of the beam joint tend to be gentle when nonlinear contact between the mortar layer and the track slabs was considered. The track slabs disengagement mainly occurs near the beam joints (the side of the deformed beam). As the deflection amplitude of the girder increases, the track deformation, the fastener forces and the disengagement length of the track slabs are obviously nonlinear. When the vertical stiffness of the fastener and/or the elastic modulus of the mortar layer increase, the fastener force and the track plate disengagement length increase monotonically and nonlinearly, which will adversely affect the life and safety of the track structure.