Parsimonious Mahalanobis kernel for the classification of high dimensional data
نویسندگان
چکیده
The classification of high dimensional data with kernel methods is considered in this article. Exploiting the emptiness property of high dimensional spaces, a kernel based on the Mahalanobis distance is proposed. The computation of the Mahalanobis distance requires the inversion of a covariance matrix. In high dimensional spaces, the estimated covariance matrix is ill-conditioned and its inversion is unstable or impossible. Using a parsimonious statistical model, namely the High Dimensional Discriminant Analysis model, the specific signal and noise subspaces are estimated for each considered class making the inverse of the class specific covariance matrix explicit and stable, leading to the definition of a parsimonious Mahalanobis kernel. A SVM based framework is used for selecting the hyperparameters of the parsimonious Mahalanobis kernel by optimizing the so-called radius-margin bound. Experimental results on three high dimensional data sets show that the proposed kernel is suitable for classifying high dimensional data, providing better classification accuracies than the conventional Gaussian kernel.
منابع مشابه
Nonparametric Spectral-Spatial Anomaly Detection
Due to abundant spectral information contained in the hyperspectral images, they are suitable data for anomalous targets detection. The use of spatial features in addition to spectral ones can improve the anomaly detection performance. An anomaly detector, called nonparametric spectral-spatial detector (NSSD), is proposed in this work which utilizes the benefits of spatial features and local st...
متن کاملClassification of Class Overlapping Datasets by Kernel-mts Method
Class overlapping is one of the bottlenecks in data mining and pattern recognition, and affects the classification accuracy and generalization ability directly. In Mahalanobis-Taguchi System (MTS), the normal samples are used to construct reference space, while the abnormal samples are used to verify the validity of the reference space. If there is a class overlapping between the normal samples...
متن کاملSupport Vector Machine Classification using Mahalanobis Distance Function
Support Vector Machine (SVM) is a powerful technique for data classification. The SVM constructs an optimal separating hyper-plane as a decision surface, to divide the data points of different categories in the vector space. The Kernel functions are used to extend the concept of the optimal separating hyper-plane for the non-linearly separable cases so that the data can be linearly separable. T...
متن کاملOutlier Detection for Support Vector Machine using Minimum Covariance Determinant Estimator
The purpose of this paper is to identify the effective points on the performance of one of the important algorithm of data mining namely support vector machine. The final classification decision has been made based on the small portion of data called support vectors. So, existence of the atypical observations in the aforementioned points, will result in deviation from the correct decision. Thus...
متن کاملSub-pixel classification of hydrothermal alteration zones using a kernel-based method and hyperspectral data; A case study of Sarcheshmeh Porphyry Copper Mine and surrounding area, Kerman, Iran
Remote sensing image analysis can be carried out at the per-pixel (hard) and sub-pixel (soft) scales. The former refers to the purity of image pixels, while the latter refers to the mixed spectra resulting from all objects composing of the image pixels. The spectral unmixing methods have been developed to decompose mixed spectra. Data-driven unmixing algorithms utilize the reference data called...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Pattern Recognition
دوره 46 شماره
صفحات -
تاریخ انتشار 2013