D
Deovrat Kakde
Researcher at SAS Institute
Publications - 36
Citations - 210
Deovrat Kakde is an academic researcher from SAS Institute. The author has contributed to research in topics: Support vector machine & Gaussian function. The author has an hindex of 7, co-authored 34 publications receiving 141 citations.
Papers
More filters
Proceedings ArticleDOI
The Mean and Median Criteria for Kernel Bandwidth Selection for Support Vector Data Description
TL;DR: A new automatic, unsupervised method for selecting the Gaussian kernel bandwidth, which can be computed quickly, and it is competitive with existing bandwidth selection methods.
Journal ArticleDOI
Fast Incremental SVDD Learning Algorithm with the Gaussian Kernel
TL;DR: In this paper, an incremental learning algorithm for SVDD that uses the Gaussian kernel is proposed, which is based on the observation that all support vectors on the boundary have the same distance to the center of sphere in a higher-dimensional feature space.
Posted Content
Fast Incremental SVDD Learning Algorithm with the Gaussian Kernel
TL;DR: Experimental results on some real data sets indicate that FISVDD demonstrates significant gains in efficiency with almost no loss in either outlier detection accuracy or objective function value.
Proceedings ArticleDOI
Automatic Hyperparameter Tuning Method for Local Outlier Factor, with Applications to Anomaly Detection
TL;DR: In this paper, the authors proposed a novel, heuristic methodology to tune the hyperparameters in Local Outlier Factor (LOF) for anomaly detection in the Internet of Things (IoT).
Proceedings ArticleDOI
Peak criterion for choosing Gaussian kernel bandwidth in Support Vector Data Description
TL;DR: In this article, the authors proposed an empirical criteria to obtain a good value of Gaussian kernel bandwidth which provides a smooth boundary capturing the essential visual features of the data, which is used for single class classification and outlier detection.