In this paper, we present a method that utilizes supportvectormachines (SVM) to identify linear parameter-varying (LPV) auto-regressive exogenous input (ARX) models corrupted by not only noise, but also uncertaintie...
详细信息
ISBN:
(纸本)9783952426913
In this paper, we present a method that utilizes supportvectormachines (SVM) to identify linear parameter-varying (LPV) auto-regressive exogenous input (ARX) models corrupted by not only noise, but also uncertainties in the LPV scheduling variables. The proposed method employs SVM and takes advantage of the so-called "kernel trick" to allow for the identification of the LPV-ARX model structure solely based on the input-output data. The objective function, as defined in this paper, allows to consider uncertainties related to the LPV scheduling parameters, and hence results in a new formulation that provides a more accurate estimation of the LPV model in the presence of scheduling uncertainties. We further demonstrate the viability of the proposed LPV identification method through numerical examples, where we show that higher best fit rate (BFR) can be achieved under realistic noise conditions using the proposed method compared to the method initially proposed in [6].
Recently, hyperspectral imaging has attracted more and more considerable research attention because of its discriminative information. This study proposes a robust approach to adaptively extract the hyperspectral palm...
详细信息
Recently, hyperspectral imaging has attracted more and more considerable research attention because of its discriminative information. This study proposes a robust approach to adaptively extract the hyperspectral palmprint region of interest (ROI) captured by a hyperspectral palmprint acquisition device, which is considered one of the most important stages in palmprint recognition. For different spectral wavelengths, the image has different illuminations and unbalanced shadows. In particular, mean grey values of palm images in different bands have large variations, such that binarisation of the palm image can be considered a challenging task to accurately separate the contour of the palm from the original image. To solve these problems, this study proposes an adaptive ROI segmentation algorithm, whereby a support vector machine-based method is used to detect the palm from the image and a coordinate established to ensure the accuracy of the ROI. The proposed method has been tested on a hyperspectral palm data set which covers spectrums from 530-1030 nm with 20 nm intervals. The experimental results showed that the proposed algorithm is effective and efficient at locating the ROI in hyperspectral palmprint images, where local binary pattern features were extracted from the ROIs achieving an equal error rate (EER) of 1.49% and an accuracy of 99.51% in recognition.
暂无评论