A
Anthony J. Bagnall
Researcher at University of East Anglia
Publications - 113
Citations - 6853
Anthony J. Bagnall is an academic researcher from University of East Anglia. The author has contributed to research in topics: Dynamic time warping & Euclidean distance. The author has an hindex of 31, co-authored 107 publications receiving 4807 citations. Previous affiliations of Anthony J. Bagnall include Norwich University.
Papers
More filters
Book ChapterDOI
Scalable Dictionary Classifiers for Time Series Classification
TL;DR: Changes to the way BOSS chooses classifiers for its ensemble are evaluated, replacing its parameter search with random selection, achieving a significant reduction in build time without a significant change in accuracy on average when compared to BOSS.
Proceedings Article
A multi-adaptive agent model of generator bidding in the UK market in electricity
TL;DR: A model of the UK market in electricity combining key factors influencing generator bidding is proposed and a hierarchical multi-objective adaptive agent architecture using case based reasoning and learning classifier systems is described.
Book ChapterDOI
Alternative quality measures for time series shapelets
Jason Lines,Anthony J. Bagnall +1 more
TL;DR: It is shown that when compared to information gain, these two quality measures can speed up shapelet extraction whilst still producing classifiers that are as accurate as the original.
Journal ArticleDOI
On Time Series Classification with Dictionary-Based Classifiers
TL;DR: It is concluded that BOSS represents the state of the art for dictionary-based TSC, and using Spatial Pyramids in conjunction with BOSS (SP) produces a significantly more accurate classifier.
Book ChapterDOI
A likelihood ratio distance measure for the similarity between the fourier transform of time series
TL;DR: This paper describes an alternative distance measure based on the likelihood ratio statistic to test the hypothesis of difference between series, and compares the new distance measure to Euclidean distance on five types of data with varying levels of compression.