Underwater Image Classification Based on EfficientnetB0 and Two-Hidden-Layer Random Vector Functional Link

The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.

On stability of discontinuous systems via vector Lyapunov functions

This paper deals with the stability of systems with discontinuous righthand side （with solutions in Filippov＇s sense） via locally Lipschitz continuous and regular vector Lyapunov functions. A new type of “set-valued derivative” of vector Lyapunov functions is introduced, some generalized comparison principles on discontinuous systems are shown. Furthermore, Lyapunov stability theory is developed for a class of discontinuous systems based on locally Lipschitz continuous and regular vector Lyapunov functions.

AN INEQUALITY ON THE ZEROS AND POLES OF VECTOR VALUED MEROMORPHIC FUNCTIONS

The author proves that if f ： C → C^n is a transcendental vector valued mero-morphic function of finite order and assume, This result extends the related results for meromorphic function by Singh and Kulkarni.

GREEN'S FUNCTIONS FOR ANISOTROPIC PIEZOELECTRIC BIMATERIALS WITH A SLIPPING INTERFACE

An explicit full-field expression of the Green's functions for anisotropic piezoeleetric bimateri- als with a slipping interface is derived.When the electro-elastic singularity reduces to a pray dislocation in displacement and electric potential,interaction energy,between the dislocation and the bimaterials is obtained explicitly while the generalized force on the disloeation is given in a real form whieh is also valid for degener- ate materials.The investigation demonstrates that the houndary conditions at lhe slipping interface between two piezoelectric materials will exert a prominent influence on the mobility of the dislocation.

Thermomagnetic viscoelastic responses in a functionally graded hollow structure

This paper presents an analytical solution for the interaction of electric potentials, electric displacements, elastic deformations, and thermoelasticity, and describes electromagnetoelastic responses and perturbation of the magnetic field vector in hollow structures （cylinder or sphere）, subjected to mechanical load and electric potential. The material properties, thermal expansion coefficient and magnetic permeability of the structure are assumed to be graded in the radial direction by a power law distribution. In the present model we consider the solution for the case of a hollow structure made of viscoelastic isotropic material, reinforced by elastic isotropic fibers, this material is considered as structurally anisotropic material. The exact solutions for stresses and perturbations of the magnetic field vector in FGM hollow structures are determined using the infinitesimal theory of magnetothermoelasticity, and then the hollow structure model with viscoelastic material is solved using the correspondence principle and Illyushin＇s approximation method. Finally, numerical results are carried out and discussed.

ON VECTOR VALUED FUNCTION APPROXIMATION USING A PEAK NORM

A peak norm is defined for Lp spaces of E-valued Bochner integrable functions, where E is a Banach space, and best approximations from a sun to elements of the space are characterized. Applications are given to some families of simultaneous best approximation problems.

Another Approach to Multiobjective Programming Problems with V-invex Functions

In this paper, optimality conditions for multiobjective programming problems having V-invex objective and constraint functions are considered. An equivalent multiobjective programming problem is constructed by a modification of the objective function.Furthermore, a (α, η)-Lagrange function is introduced for a constructed multiobjective programming problem, and a new type of saddle point is introduced. Some results for the new type of saddle point are given.

Analytical Solutions to Definite Integrals for Combinations of Legendre, Bessel and Trigonometric Functions Encountered in Propagation and Scattering Problems in Spherical Coordinates

Mie theory is a rigorous solution to scattering problems in spherical coordinate system. The first step in applying Mie theory is expansion of some arbitrary incident field in terms of spherical harmonics fields in terms of spherical which in turn requires evaluation of certain definite integrals whose integrands are products of Bessel functions, associated Legendre functions and periodic functions. Here we present analytical results for two specific integrals that are encountered in expansion of arbitrary fields in terms of summation of spherical waves. The analytical results are in terms of finite summations which include Lommel functions. A concise analytical expression is also derived for the special case of Lommel functions that arise, rendering expensive numerical integration or other iterative techniques unnecessary.

A Machine Learning Approach for Artifact Removal from Brain Signal

Electroencephalography(EEG),helps to analyze the neuronal activity of a human brain in the form of electrical signals with high temporal resolution in the millisecond range.To extract clean clinical information from EEG signals,it is essential to remove unwanted artifacts that are due to different causes including at the time of acquisition.In this piece of work,the authors considered the EEG signal contaminated with Electrocardiogram(ECG)artifacts that occurs mostly in cardiac patients.The clean EEG is taken from the openly available Mendeley database whereas the ECG signal is collected from the Physionet database to create artifacts in the EEG signal and verify the proposed algorithm.Being the artifactual signal is non-linear and non-stationary the Random Vector Functional Link Network(RVFLN)model is used in this case.The Machine Learning approach has taken a leading role in every field of current research and RVFLN is one of them.For the proof of adaptive nature,the model is designed with EEG as a reference and artifactual EEG as input.The peaks of ECG signals are evaluated for artifact estimation as the amplitude is higher than the EEG signal.To vary the weight and reduce the error,an exponentially weighted Recursive Least Square(RLS)algorithm is used to design the adaptive filter with the novel RVFLN model.The random vectors are considered in this model with a radial basis function to satisfy the required signal experimentation.It is found that the result is excellent in terms of Mean Square Error(MSE),Normalized Mean Square Error(NMSE),Relative Error(RE),Gain in Signal to Artifact Ratio(GSAR),Signal Noise Ratio(SNR),Information Quantity(IQ),and Improvement in Normalized Power Spectrum(INPS).Also,the proposed method is compared with the earlier methods to show its efficacy.

RVFLN-based online adaptive semi-supervised learning algorithm with application to product quality estimation of industrial processes

Direct online measurement on product quality of industrial processes is difficult to be realized,which leads to a large number of unlabeled samples in modeling data.Therefore,it needs to employ semi-supervised learning(SSL)method to establish the soft sensor model of product quality.Considering the slow time-varying characteristic of industrial processes,the model parameters should be updated smoothly.According to this characteristic,this paper proposes an online adaptive semi-supervised learning algorithm based on random vector functional link network(RVFLN),denoted as OAS-RVFLN.By introducing a L2-fusion term that can be seen a weight deviation constraint,the proposed algorithm unifies the offline and online learning,and achieves smoothness of model parameter update.Empirical evaluations both on benchmark testing functions and datasets reveal that the proposed OAS-RVFLN can outperform the conventional methods in learning speed and accuracy.Finally,the OAS-RVFLN is applied to the coal dense medium separation process in coal industry to estimate the ash content of coal product,which further verifies its effectiveness and potential of industrial application.

Analytical solution for electromagnetic scattering from a sphere of uniaxial left-handed material

Based on the analytical solution of electromagnetic scattering by a uniaxial anisotropic sphere in the spectral domain, an analytical solution to the electromagnetic scattering by a uniaxial left-handed materials (LHMs) sphere is obtained in terms of spherical vector wave functions in a uniaxial anisotropic LHM medium. The expression of the analytical solution contains only some one-dimensional integral which can be calculated easily. Numerical results show that Mie series of plane wave scattering by an isotropic LHM sphere is a special case of the present method. Some numerical results of electromagnetic scattering of a uniaxial anisotropic sphere by a plane wave are given.

Adaptive Control of Discrete-time Nonlinear Systems Using ITF-ORVFL

Random vector functional ink(RVFL)networks belong to a class of single hidden layer neural networks in which some parameters are randomly selected.Their network structure in which contains the direct links between inputs and outputs is unique,and stability analysis and real-time performance are two difficulties of the control systems based on neural networks.In this paper,combining the advantages of RVFL and the ideas of online sequential extreme learning machine(OS-ELM)and initial-training-free online extreme learning machine(ITFOELM),a novel online learning algorithm which is named as initial-training-free online random vector functional link algo rithm(ITF-ORVFL)is investigated for training RVFL.The link vector of RVFL network can be analytically determined based on sequentially arriving data by ITF-ORVFL with a high learning speed,and the stability for nonlinear systems based on this learning algorithm is analyzed.The experiment results indicate that the proposed ITF-ORVFL is effective in coping with nonparametric uncertainty.

Research on the Electromagnetic Scattering Near the Field

We calculate and analyze the scattering near the field from some simple and complex targets using the method of picture elements (PEL), based upon the method of high-frequency approximation. It introduces the critical distance of the near field and the far field which is related with the dimension of the target. The problem of the EMS near field from large size objects can be transformed to the problem of the far field by parting it to many very small size elements. By calculating the EMS near fields of some simple and complex targets based on the SCTE (scattering from complex targets and environments) system, the results show that there are much difference between the near field and the far field. And the characteristics of the near field are more complicated. This work has practical engineering value in the area of the electromagnetic compatibility (EMC), electromagnetic interference (EMI) prediction and electromagnetic scattering (EMS).

ON THE SCATTERING OF ARBITRARY SHAPE MICROSTRIP PATCH

In this letter, discrete complex image method is employed to compute the Green's functions in the spatial domain, which improves the speed of evaluating the impedance matrix.The triangle vector basis function--RWG, is used to simulate the current distribution in order to compute the scattering properties of arbitrary shape microstrip patch without the staircase approximation. The numerical result shows the validity of the proposed method.

On Vector Quasi-Variational Inequality Problems in H-Space

The purpose to this paper is to study the existence problem of solutions to the vector quasivariational inequality for vector-valued functions inH-space.

Transmission characteristics of terahertz Bessel vortex beams through a multi-layered anisotropic magnetized plasma slab

The transmission of terahertz(THz)Bessel vortex beams through a multi-layered anisotropic magnetized plasma slab is investigated by using a hybrid method of cylindrical vector wave functions(CVWFs)and Fourier transform.On the basis of the electromagnetic boundary conditions on each interface,a cascade form of expansion coefficients of the reflected and transmitted fields is obtained.Taking a double Gaussian distribution of the plasma density as an example,the influences of the applied magnetic field,the incident angle and polarization mode of the incident beams on the magnitude,OAM mode and polarization of the transmitted beams are analyzed in detail.The results indicate that the applied magnetic field has a major effect upon the polarization state of the transmitted fields but not upon the transmitted OAM spectrum.The incident angle has a powerful influence upon both the amplitude profile and the OAM spectrum of the transmitted beam.Furthermore,for multiple coaxial vortex beams,an increase of the maximum value of the plasma density causes more remarkable distortion of both the profile and OAM spectrum of the transmitted beam.This research makes a stable foundation for the THz OAM multiplexing/demultiplexing technology in a magnetized plasma environment.

CONVERGENCE RATE OF VECTOR SUBDIVISION SCHEME

In this paper, some characterizations on the convergence rate of both the homogeneous and nonhomogeneous subdivision schemes in Sobolev space are studied and given.

Generalized Maximum Fuzzy Entropy Methods with Applications on Wind Speed Data

This study is connected with new Generalized Maximum Fuzzy Entropy Methods （GMax（F）EntM） in the form of MinMax（F）EntM and MaxMax（F）EntM belonging to us. These methods are based on primary maximizing Max（F）Ent measure for fixed moment vector function in order to obtain the special functional with maximum values of Max（F）Ent measure and secondary optimization of mentioned functional with respect to moment vector functions. Distributions, in other words sets of successive values of estimated membership function closest to （furthest from） the given membership function in the sense of Max（F）Ent measure, obtained by mentioned methods are defined as （MinMax（F）Ent）m which is closest to a given membership function and （MaxMax（F）Ent）m which is furthest from a given membership function. The aim of this study consists of applying MinMax（F）EntM and MaxMax（F）EntM on given wind speed data. Obtained results are realized by using MATLAB programme. The performances of distributions （MinMax（F）En0m and （MaxMax（F）Ent）m generated by using Generalized Maximum Fuzzy Entropy Methods are established by Chi-Square, Root Mean Square Error criterias and Max（F）Ent measure.

Construction of Biorthgonal Multiwavelets

Biorthogonal multiwavelets are generated from related scaling function vectors via multiresolution analysis. In this paper, we first show how to derive even-length biorthogonal lowpass filter pair from odd-length biorthogonal multiwavelet system with such properties as symmetry-antisymmetry and compactly support. So based on this, odd-length biorthogonal multiwavelet system can be constructed.

A Kind of Boundary Value Problem for Hypermonogenic Function Vectors

By the Plemelj formula and the compressed fixed point theorem,this paper discusses a kind of boundary value problem for hypermonogenic function vectors in Clifford analysis.And the paper proves the existence and uniqueness of the solution to the boundary value problem for hypermonogenic function vectors in Clifford analysis.