Sequential non-stationary dynamic classification with sparse feedback

Authors:
D. R. Lowne;S. J. Roberts;R. Garnett
Affiliations:
Pattern Analysis and Machine Learning Research Group, Department of Engineering Science, University of Oxford, Parks Road, Oxford OX1 3PJ, UK;Pattern Analysis and Machine Learning Research Group, Department of Engineering Science, University of Oxford, Parks Road, Oxford OX1 3PJ, UK;Pattern Analysis and Machine Learning Research Group, Department of Engineering Science, University of Oxford, Parks Road, Oxford OX1 3PJ, UK
Venue:
Pattern Recognition
Year:
2010

Citing 8
Cited 3

A practical Bayesian framework for backpropagation networks

Neural Computation
Discriminant Adaptive Nearest Neighbor Classification

IEEE Transactions on Pattern Analysis and Machine Intelligence
A unifying review of linear Gaussian models

Neural Computation
Kalman Filtering and Neural Networks

Kalman Filtering and Neural Networks
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Binary Classification Trees for Multi-class Classification Problems

ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
Time Series Analysis and Its Applications (Springer Texts in Statistics)

Time Series Analysis and Its Applications (Springer Texts in Statistics)
Sequential Bayesian computation of logistic regression models

ICASSP '99 Proceedings of the Acoustics, Speech, and Signal Processing, 1999. on 1999 IEEE International Conference - Volume 02

Bayesian inference for an adaptive Ordered Probit model: An application to Brain Computer Interfacing

Neural Networks
A sequential dynamic multi-class model and recursive filtering by variational bayesian methods

PAKDD'11 Proceedings of the 15th Pacific-Asia conference on Advances in knowledge discovery and data mining - Volume Part I
GDTW-P-SVMs: Variable-length time series analysis using support vector machines

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Many data analysis problems require robust tools for discerning between states or classes in the data. In this paper we consider situations in which the decision boundaries between classes are potentially non-linear and subject to ''concept drift'' and hence static classifiers fail. The applications for which we present results are characterized by the requirement that robust online decisions be made and by the fact that target labels may be missing, so there is very often no feedback regarding the system's performance. The inherent non-stationarity in the data is tracked using a non-linear dynamic classifier, the parameters of which evolve under an extended Kalman filter framework, derived using a sequential Bayesian-learning paradigm. The method is extended to take into account missing and incorrectly labeled targets and to actively request target labels. The method is shown to work well in simulation as well as when applied to sequential decision problems in medical signal analysis.