Using airborne multispectral digital camera imagery, we compared a number of feature combination techniques in image classification to distinguish vineyard from non-vineyard land-cover types in northern California. Image processing techniques were applied to raw images to generate feature images including grey level co-occurrence based texture measures, low pass and Laplacian filtering results,...

Over the last years, numerous equalization schemes for multiple-input/multiple-output (MIMO) channels have been studied in literature. In particular, techniques known from intersymbol-interference channels have been transferred to the MIMO setting, such as linear equalization, decision-feedback equalization (DFE, also known as successive interference cancellation, SIC, and the main ingredient o...

The deep active-subspace method is a neural-network based tool for the propagation of uncertainty through computational models with high-dimensional input spaces. Unlike original method, it does not require access to gradient model. It relies on an orthogonal projection matrix constructed Gram–Schmidt orthogonalization reduce dimensionality. This incorporated into neural network as weight first...

In this article, a special type of orthogonalization is obtained to construct a multiple input transfer function model. By using this technique, construction of a transfer function model is divided to sequential construction of transfer function models with less input time series. Furthermore, based on real and simulated time series we provide an instruction to adequately perform the stages of ...

— In this paper, we propose an equivalent Wiener-Hopf equation. The proposed algorithm can obtain the weight vector of a TDL(tapped-delay-line) filter and the error simultaneously if the inputs are orthogonal to each other. The equivalent Wiener-Hopf equation was analyzed theoretically based on the MMSE(minimum mean square error) method. The results present that the proposed algorithm is equiva...

A BCI system, using orthogonalized EEG data sets and multiple multilayer neural networks (MLNNs) in a parallel form, is proposed. In order to emphasize feature of multi-channel EEG data, Gram-Schmidt orthogonalization has been applied. Since there are many channel orders to be orthogonalized, many kinds of orthogonalized data sets can be generated for the same EEG data set by changing the chann...

Lanczos vectors computed in nite precision arithmetic by the three-term recurrence tend to lose their mutual biorthogonality. One either accepts this loss and takes more steps or re-biorthogonalizes the Lanczos vectors at each step. For the symmetric case, there is a compromise approach. This compromise, known as maintaining semi-orthogonality, minimizes the cost of re-orthogonalization. This p...

Two methods for solving the generalized Stokes problems that occur in viscous, incompressible ows are described and tested. Both are based on some type of linear algebraic orthogonaliza-tion process. The rst, EMGS, is a preconditioner derived from an incomplete Gram{Schmidt factorization, and it is proven to exist whenever the matrix being preconditioned can be factored using Gaussian eliminati...

This paper deals with a new technique for multi-channel separation of speech signals from convolutive mixtures under coherent noise. We demonstrate how the scaled transfer functions from the sources to the microphones can be estimated even in the presence of stationary coherent noise. The key to this are generalized eigenvalue decompositions of the power spectral density (PSD) matrices of the n...

Let μ be a probability measure on the real line with finite moments of all orders. Apply the Gram-Schmidt orthogonalization process to the system {1, x, x, . . . , xn, . . . } to get orthogonal polynomials Pn(x), n ≥ 0, which have leading coefficient 1 and satisfy (x − αn)Pn(x) = Pn+1(x) + ωnPn−1(x). In general it is almost impossible to use this process to compute the explicit form of these po...