 |
General: 663 |
P4: Anomaly Detection through Bayesian SVM
Author: Vasilis A. Sotiris, Advisor: Michael Pecht (CALCE: Electronic Products and Systems Center; ECE Department)
Problem Statement Presentation
Project Proposal
Abstract
The goal of this project is to use support vector machines (SVMs) to detect amonalies and isolate faults and failures in electronic systems. The output of the SV Classifier is calibrated to posterior probabilities thus improving the classical SVM deterministic predictor model to a more probabilistic "soft" predictor model. This result is desirable because it is anticipated to reduce the false alarm rate in the presence of outliers and allow for more realistic interpretation of the system health. This report also investigates the use of a linear Karhunen-Loeve decomposition of the input data into two lower dimension subspaces in order to decouple competing failure modes in the system parameters and uncover hiden features. The SV classification is then used in the two extracted orthonormal subspaces to determine a predictor model for each subspace respectively. A final decision is constructed with the joint output of the two predictor models. The approach is tested on simulated and real data and the results are compared to the popular libVM software results.
MidYear Progress Report and Presentation
Final Presentation , Final Report
