A Generative Learning Approach to Sensor Fusion and Change Detection

We present a system for performing multi-sensor fusion that learns from experience, i.e., from training data and propose that learning methods are the most appropriate approaches to real-world fusion problems, since they are largely model-free and therefore suited for a variety of tasks, even where...

Full description

Saved in:
Bibliographic Details
Published in:Cognitive computation 2016-10, Vol.8 (5), p.806-817
Main Authors: Gepperth, Alexander R. T., Hecht, Thomas, Gogate, Mandar
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Bayesian analysis
Biomedical and Life Sciences
Biomedicine
Computation by Abstract Devices
Computational Biology/Bioinformatics
Computer Science
Coordinate transformations
Data analysis
Empirical analysis
Learning
Machine Learning
Multisensor fusion
Neurosciences
Optimization
Outliers (statistics)
Physiology
Probabilistic models
Sensors
Statistical analysis
Statistical inference
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a system for performing multi-sensor fusion that learns from experience, i.e., from training data and propose that learning methods are the most appropriate approaches to real-world fusion problems, since they are largely model-free and therefore suited for a variety of tasks, even where the underlying processes are not known with sufficient precision, or are too complex to treat analytically. In order to back our claim, we apply the system to simulated fusion tasks which are representative of real-world problems and which exhibit a variety of underlying probabilistic models and noise distributions. To perform a fair comparison, we study two additional ways of performing optimal fusion for these problems: empirical estimation of joint probability distributions and direct analytical calculation using Bayesian inference. We demonstrate that near-optimal fusion can indeed be learned and that learning is by far the most generic and resource-efficient alternative. In addition, we show that the generative learning approach we use is capable of improving its performance far beyond the Bayesian optimum by detecting and rejecting outliers and that it is capable to detect systematic changes in the input statistics.
ISSN:1866-9956
1866-9964
DOI:10.1007/s12559-016-9390-z