红外光谱结合最小二乘支持向量机掺杂牛奶判别方法研究

基于红外光谱和最小二乘支持向量机建立掺杂牛奶与纯牛奶的判别模型。分别配置含有葡萄糖牛奶(0.01~0.3gL-1)和三聚氰胺牛奶(0.01~0.3gL-1)样品各36个,采集纯牛奶及掺杂牛奶样品的红外光谱。采用最小二乘支持向量机分别建立掺杂葡萄糖、掺杂三聚氰胺、两种掺杂牛奶与纯牛奶的判别模型,并利用这些模型对未知样品进行判别,其判别正确率都为95.8%。研究结果表明:与线性的偏最小二乘判别建模方法相比,最小二乘支持向量机方法具有更强的预测能力。     

基于HOG纹理的全天时十字路口车尾检测算法

HOG纹理因其良好的鲁棒性,在纹理描述中被广泛使用。提出了一种将HOG纹理应用于十字路口全天候车尾检测的算法。即分别采集了白天和夜间该场景下的车尾作为正样本、非车辆和车辆的一部分作为负样本,经预处理后,提取较低维数的HOG纹理送入支持向量机进行训练,得到白天和夜间的识别模型,在检测中根据一定的条件进行切换。对多段视频进行测试证明,该种算法对不同时段的交通场景都具有较高的稳定的车尾识别率,且优于单模型的识别效果。     

A high order energy preserving scheme for the strongly coupled nonlinear Schrōdinger system

A high order energy preserving scheme for a strongly coupled nonlinear Schrōdinger system is roposed by using the average vector field method. The high order energy preserving scheme is applied to simulate the soliton evolution of the strongly coupled Schrōdinger system. Numerical results show that the high order energy preserving scheme can well simulate the soliton evolution, moreover, it preserves the discrete energy of the strongly coupled nonlinear Schrōdinger system exactly.     

Sum rates for multi-user MIMO vector perturbation precoding with regularization

In this paper, we analyze the sum rate performance of multiuser multi-antenna downlink channel. We consider Rayleigh fading environment when regularized vector perturbation precoding (R-VPP) method is used at the transmitter. We derive expressions for the sum rate in terms of the variance of the received signal. We also provide a closed form approximation for the mean squared error (MSE) which is shown to work well for the whole range of SNR. Further, we also propose a simpler expression for R-VPP sum rate based on MSE. The simulation results show that the proposed expressions for R-VPP sum rate closely match the sum rate found by the entropy estimation. Our results show that when compared with other linear and non-linear precoding methods (like zero-forcing precoder, linear minimum mean square error (MMSE) precoder and VPP), R-VPP sum rate performance is very close to DPC for all SNR values. It is also noted that the sum rate performance of the linear MMSE precoder is very close to the R-VPP at low to medium SNR range. Finally we also compared the merits of performing regularization for VPP as compared to the greedy rate maximizing user scheduling. It turns out that the R-VPP with or without user selection performs better than the VPP systems with user selection.     

Einstein-aether theory with a Maxwell field: General formalism

We extend the Einstein-aether theory to include the Maxwell field in a nontrivial manner by taking into account its interaction with the time-like unit vector field characterizing the aether. We also include a generic matter term. We present a model with a Lagrangian that includes cross-terms linear and quadratic in the Maxwell tensor, linear and quadratic in the covariant derivative of the aether velocity four-vector, linear in its second covariant derivative and in the Riemann tensor. We decompose these terms with respect to the irreducible parts of the covariant derivative of the aether velocity, namely, the acceleration four-vector, the shear and vorticity tensors, and the expansion scalar. Furthermore, we discuss the influence of an aether non-uniform motion on the polarization and magnetization of the matter in such an aether environment, as well as on its dielectric and magnetic properties. The total self-consistent system of equations for the electromagnetic and the gravitational fields, and the dynamic equations for the unit vector aether field are obtained. Possible applications of this system are discussed. Based on the principles of effective field theories, we display in an appendix all the terms up to fourth order in derivative operators that can be considered in a Lagrangian that includes the metric, the electromagnetic and the aether fields.     

An intelligent approach for engine fault diagnosis based on Hilbert–Huang transform and support vector machine

Based on the techniques of Hilbert–Huang transform (HHT) and support vector machine (SVM), a noise-based intelligent method for engine fault diagnosis (EFD), so-called HHT–SVM model, is developed in this paper. The noises of a sample engine under normal and several fault states are first measured and denoised by using the wavelet packet threshold method to initially lower the noise level with negligible signal distortion. To extract fault features of the engine, then, the HHT is selected and applied to the measured noise signals. A nine-dimensional vector, which consists of seven intrinsic mode functions (IMFs) from the empirical mode decomposition (EMD), maximum value of HHT marginal spectrum and its corresponding frequency component, is specified to represent each engine fault feature. Finally, an optimal SVM model is established and trained for engine failure classification by using the fault feature vectors of the noise signals. Cross-validation results show that the proposed noise-based HHT–SVM method is accurate and effective for engine fault diagnosis. Due to outstanding time–frequency characteristics and pattern recognition capacity of the HHT and SVM, the newly proposed HHT–SVM can be used to deal with both the stationary and nonstationary signals, and even the transient ones. In the view of applications, the HHT–SVM technique may be suggested not only to detect the abnormal states of vehicle engines, but also to be extended to other fields for failure diagnosis in engineering.     

The estimation of the degree of coherence of mutually orthogonal beams: New approaches

A theoretical model for calculating the motion dynamics of the particles of different light-scattering mechanisms in the energy inhomogeneous optical field is suggested. The direct relationship between the motion velocity of the tested particles in the created field and the degree of coherence of mutually orthogonal linearly polarized plane waves is demonstrated.     

A framework for classification with single feature kernel matrix

In this paper, we propose a novel classification framework using single feature kernel matrix. Different from the traditional kernel matrices which make use of the whole features of samples to build the kernel matrix, this research uses features of the same dimension of any two samples to build a sub-kernel matrix and sums up all the sub-kernel matrices to get the single feature kernel matrix. We also use single feature kernel matrix to build a new SVM classifier, and adapt SMO (Sequential Minimal Optimization) algorithm to solve the problem of SVM classifier. The results of the experiments on several artificial datasets and some challenging public cancer datasets display the classification performance of the algorithm. The comparisons between our algorithm and L₂-norm SVM on the cancer datasets demonstrate that the accuracy of our algorithm is higher, and the number of support vectors selected is fewer, indicating that our proposed framework is a more practical approach.     

Using Copula distributions to support more accurate imaging-based diagnostic classifiers for neuropsychiatric disorders

Many investigators have tried to apply machine learning techniques to magnetic resonance images (MRIs) of the brain in order to diagnose neuropsychiatric disorders. Usually the number of brain imaging measures (such as measures of cortical thickness and measures of local surface morphology) derived from the MRIs (i.e., their dimensionality) has been large (e.g. > 10) relative to the number of participants who provide the MRI data (< 100). Sparse data in a high dimensional space increase the variability of the classification rules that machine learning algorithms generate, thereby limiting the validity, reproducibility, and generalizability of those classifiers. The accuracy and stability of the classifiers can improve significantly if the multivariate distributions of the imaging measures can be estimated accurately. To accurately estimate the multivariate distributions using sparse data, we propose to estimate first the univariate distributions of imaging data and then combine them using a Copula to generate more accurate estimates of their multivariate distributions. We then sample the estimated Copula distributions to generate dense sets of imaging measures and use those measures to train classifiers. We hypothesize that the dense sets of brain imaging measures will generate classifiers that are stable to variations in brain imaging measures, thereby improving the reproducibility, validity, and generalizability of diagnostic classification algorithms in imaging datasets from clinical populations. In our experiments, we used both computer-generated and real-world brain imaging datasets to assess the accuracy of multivariate Copula distributions in estimating the corresponding multivariate distributions of real-world imaging data. Our experiments showed that diagnostic classifiers generated using imaging measures sampled from the Copula were significantly more accurate and more reproducible than were the classifiers generated using either the real-world imaging measures or their multivariate Gaussian distributions. Thus, our findings demonstrate that estimated multivariate Copula distributions can generate dense sets of brain imaging measures that can in turn be used to train classifiers, and those classifiers are significantly more accurate and more reproducible than are those generated using real-world imaging measures alone.