Converting SVDD Scores into Probability Estimates
نویسندگان
چکیده
To enable post-processing, the output of a support vector data description (SVDD) should be a calibrated probability as done for SVM. Standard SVDD does not provide such probabilities. To create probabilities, we first generalize the SVDD model and propose two calibration functions. The first one uses a sigmoid model and the other one is based on a generalized extreme distribution model. To estimate calibration parameters, we use the consistency property of the estimator associated with a single SVDD model. A synthetic dataset and datasets from the UCI repository are used to compare the performance against a robust kernel density estimator.
منابع مشابه
Research on SVDD Applied in Speaker Verification
In tradition probability statistics model, speaker verification threshold is instability in different test situations. A novel speaker verification method based on Support Vector Data Description (SVDD) is proposed to remedy the defect of probability statistics model. To simplify the threshold value setting and improve the robustness and recognition accuracy of the verification system, traditio...
متن کاملTechnical Note: PAV and the ROC Convex Hull
Classifier calibration is the process of converting classifier scores into reliable probability estimates. Recently, a calibration technique based on isotonic regression has gained attention within machine learning as a flexible and effective way to calibrate classifiers. We show that, surprisingly, isotonic regression based calibration using the Pool Adjacent Violators algorithm is equivalent ...
متن کاملRobust outlier detection with L0-SVDD
The problem of outlier detection consists in finding data that is not representative of the population from which it was ostensibly derived. Recently, to solve this problem, Liu et al. [1] proposed a two steps hypersphere-based approach, taking into account a confidence score pre-calculated for each input data. Defining these scores in a first step, independently from the second one, makes this...
متن کاملNonparametric Control Chart Using Density Weighted Support Vector Data Description
In manufacturing industries, development of measurement leads to increase the number of monitoring variables and eventually the importance of multivariate control comes to the fore. Statistical process control (SPC) is one of the most widely used as multivariate control chart. Nevertheless, SPC is restricted to apply in processes because its assumption of data as following specific distribution...
متن کاملA Revisit to Support Vector Data Description
Support vector data description (SVDD) is a useful method for outlier detection and has been applied to a variety of applications. However, in the existing optimization procedure of SVDD, there are some issues which may lead to improper usage of SVDD. Some of the issues might already be known in practice, but the theoretical discussion, justification and correction are still lacking. Given the ...
متن کامل