Analyzing the Impact of Traffic Congestion Mitigation: From an Explainable Neural Network Learning Framework to Marginal Effect Analyses.

Computational graphs (CGs) have been widely utilized in numerical analysis and deep learning to represent directed forward networks of data flows between operations. This paper aims to develop an explainable learning framework that can fully integrate three major steps of decision support: Synthesis of diverse traffic data, multilayered traffic demand estimation, and marginal effect analyses for transport policies. Following the big data-driven transportation computational graph (BTCG) framework, which is an emerging framework for explainable neural networks, we map different external traffic measurements collected from household survey data, mobile phone data, floating car data, and sensor networks to multilayered demand variables in a CG.

Love wave propagation in piezoelectric layered structure with dissipation.

We investigate analytically the effect of the viscous dissipation of piezoelectric material on the dispersive and attenuated characteristics of Love wave propagation in a layered structure, which involves a thin piezoelectric layer bonded perfectly to an unbounded elastic substrate. The effects of the viscous coefficient on the phase velocity of Love waves and attenuation are presented and discussed in detail. The analytical method and the results can be useful for the design of the resonators and sensors.

Thickness vibration of piezoelectric plates of 6mm crystals with tilted six-fold axis and two-layered thick electrodes.

We perform a theoretical analysis of thickness vibrations in piezoelectric plates of crystals with 6mm symmetry. The six-fold axis is tilted with respect to the plate surfaces. The major surfaces of the plate are covered with two layers of electrodes of different metals.

SH surface acoustic wave propagation in a cylindrically layered piezomagnetic/piezoelectric structure.

SH surface acoustic wave (SH-SAW) propagation in a cylindrically layered magneto-electro-elastic structure is investigated analytically, where a piezomagnetic (or piezoelectric) material layer is bonded to a piezoelectric (or piezomagnetic) substrate. By means of transformation, the governing equations of the coupled waves are reduced to Bessel equation and Laplace equation. The boundary conditions imply that the displacements, shear stresses, electric potential, and electric displacements are continuous across the interface between the layer and the substrate together with the traction free at the surface of the layer.

Love wave propagation in functionally graded piezoelectric material layer.

An exact approach is used to investigate Love waves in functionally graded piezoelectric material (FGPM) layer bonded to a semi-infinite homogeneous solid. The piezoelectric material is polarized in z-axis direction and the material properties change gradually with the thickness of the layer. We here assume that all material properties of the piezoelectric layer have the same exponential function distribution along the x-axis direction.