Satnam Singh

TL;DR: This paper develops near-optimal algorithms for dynamic multiple fault diagnosis (DMFD) problems in the presence of imperfect test outcomes by providing an approximate duality gap, which is a measure of the suboptimality of the DMFD solution.

TL;DR: In this article, a multi-dimensional matrix is constructed, with vehicles, DTCs, and parameter data comprising three dimensions of the matrix, and time can be added as a fourth dimension, providing an indication of whether a particular system or component is temporally degrading.

TL;DR: The results demonstrate that dynamic fusion and joint optimization, and class-specific Bayesian fusion outperform traditional fusion approaches, and learning the parameters of individual classifiers as part of the fusion architecture can provide better classification performance.

TL;DR: In this paper, a unified methodology to incrementally learn new information from evolving databases is presented and the performance of adaptive (or incremental learning) classification techniques is discussed when: 1) the new data has the same fault classes and same features and 2) thenew data has new fault classes, but with the same set of observed features.

TL;DR: The capabilities of hidden Markov models (HMMs), combined with feature-aided tracking, for the detection of asymmetric threats are illustrated and a transaction-based probabilistic model is proposed to combine hiddenMarkov models and feature- aided tracking.