Data driven stochastic approximation for change detection

Online change detection has many applications, ranging from finance and manufacturing, to security and computer vision. Designing a change detector for use in a given domain can be very time consuming, and model-based algorithms often require knowledge of the underlying stochastic model. To address...

Full description

Saved in:
Bibliographic Details
Published in2017 Winter Simulation Conference (WSC) pp. 2279 - 2290
Main Authors Flynn, Thomas, Hadjiliadis, Olympia, Stamos, Ioannis, Vazquez-Abad, Felisa J.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.12.2017
Subjects
Change detection algorithms
Computational modeling
Delays
Detectors
Optimization
Stochastic processes
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Online change detection has many applications, ranging from finance and manufacturing, to security and computer vision. Designing a change detector for use in a given domain can be very time consuming, and model-based algorithms often require knowledge of the underlying stochastic model. To address these issues, in this work we explore a supervised learning approach to a change detector. We implement a gradient based procedure to find the optimal parameters for a change detector. We demonstrate the methodology on both synthetic and real world data for classifying 3D laser range image data in real-time.
ISSN:1558-4305
DOI:10.1109/WSC.2017.8247959