Research on Rosewood Micro Image Classification Method Based on Feature Fusion and ELM

Rosewood is a kind of high-quality and precious wood in China.The correct identification of rosewood species is of great significance to the import and export trade and species identification of furniture materials.In this paper,micro CT was used to obtain the micro images of CTOSS sections,radial sections and tangential sections of 24 kinds of rosewood,and the data sets were constructed.PCA method was used to reduce the dimension of four features including logical binary pattern,local configuration pattern,rotation invariant LBP,uniform LBP.These four fea-tures and one feature not reducing dimension(rotation invariant uniform LBP)was fused with Gray Level Co-Occurrence Matrix and Tamura features,respectively,a total of five fused features LBP+GLCM+Tamura,LCP+GLCM+Tamura,LBP_(P,R)^(u2)+GLCM+Tamura,LBP_(P,R)^(ri)+GLCM+Tamura and LBP_(P,R)^(riu2)+GLCM+Tamura were obtained.The five fused features were classified by extreme learning machine and BP neural network.The clas-sification effect of feature LBP_(P,R)^(u2)+GLCM+Tamura combined with extreme learning machine was the best,and the classification accuracy of CroSS,radial and tangential sections reached 100%,97.63%and 94.72%,respectively,which is 0.83%,2.77%and 5.70%higher than that of BP neural network.The classification running time of ELM is less than 1 s,and the classfcation eficiency is high.In condusion,the LBP_(P,R)^(u2)+GLCM+Tamura method com-bined with extreme learning machine can be used as a quick and acurate classifier,providing an efficient and feasible class ification method of rosewood.

Surface-enhanced Raman spectroscopy chips based on two-dimensional materials beyond graphene

Surface-enhanced Raman spectroscopy(SERS) based on two-dimensional(2 D) materials has attracted great attention over the past decade. Compared with metallic materials, which enhance Raman signals via the surface plasmon effect, 2 D materials integrated on silicon substrates are ideal for use in the fabrication of plasmon-free SERS chips, with the advantages of outstanding fluorescence quenching capability, excellent biomolecular compatibility, tunable Fermi levels, and potentially lowcost material preparation. Moreover, recent studies have shown that the limits of detection of 2 D-material-based SERS may be comparable with those of metallic substrates, which has aroused significant research interest. In this review, we comprehensively summarize the advances in SERS chips based on 2 D materials. As several excellent reviews of graphene-enhanced Raman spectroscopy have been published in the past decade, here, we focus only on 2 D materials beyond graphene, i.e., transition metal dichalcogenides, black phosphorus, hexagonal boron nitride, 2 D titanium carbide or nitride, and their heterostructures. We hope that this paper can serve as a useful reference for researchers specializing in 2 D materials, spectroscopy, and diverse applications related to chemical and biological sensing.

Automatic differentiation based discrete adjoint method for aerodynamic design optimization on unstructured meshes

A systematic methodology for formulating,implementing,solving and verifying discrete adjoint of the compressible Reynolds-averaged Navier-Stokes（RANS） equations for aerodynamic design optimization on unstructured meshes is proposed.First,a general adjoint formulation is constructed for the entire optimization problem,including parameterization,mesh deformation,flow solution and computation of the objective function,which is followed by detailed formulations of matrix-vector products arising in the adjoint model.According to this formulation,procedural components of implementing the required matrix-vector products are generated by means of automatic differentiation（AD） in a structured and modular manner.Furthermore,a duality-preserving iterative algorithm is employed to solve flow adjoint equations arising in the adjoint model,ensuring identical convergence rates for the tangent and the adjoint models.A three-step strategy is adopted to verify the adjoint computation.The proposed method has several remarkable features：the use of AD techniques avoids tedious and error-prone manual derivation and programming;duality is strictly preserved so that consistent and highly accurate discrete sensitivities can be obtained;and comparable efficiency to hand-coded implementation can be achieved.Upon the current discrete adjoint method,a gradient-based optimization framework has been developed and applied to a drag reduction problem.

Enhancing magnetic dipole emission with magnetic metamaterials

Magnetic dipole（MD） transitions are important for a range of technologies from quantum light sources and displays to lasers and bio-probes. However, the typical MD transitions are much weaker than their electric counterparts and are usually neglected in practical applications. Herein, we experimentally demonstrate that the MD transitions can be significantly enhanced by the well-developed magnetic metamaterials in the visible optical range. The magnetic metamaterials consist of silver nanostrips and a thick silver film, which are separated with an Eu3＋：polymethyl methacrylate（PMMA） film. By controlling the thickness of the Eu3＋：PMMA film, the magnetic resonance has been tuned to match the emission wavelength of MDs. Consequently,the intensity of MD emission has been significantly increased by around 30 times at the magnetic resonance wavelength, whereas the intensity of electric dipole emission is well-preserved. The corresponding numerical calculations reveal that the enhancement is directly generated by the magnetic resonance, which strongly increases the magnetic local density of states around the MD emitter and can efficiently radiate the MD emission into the far field. This is the first demonstration, to the best of our knowledge, that MD transitions can be improved by an additional degree of magnetic freedom, and we believe this research shall pave a new route towards bright magnetic emitters and their potential applications.