[PDF][PDF] An Extension on" Statistical Comparisons of Classifiers over Multiple Data Sets" for all Pairwise Comparisons.

S Garcia, F Herrera - Journal of machine learning research, 2008 - jmlr.org
In a recently published paper in JMLR, Demšar (2006) recommends a set of non-parametric
statistical tests and procedures which can be safely used for comparing the performance of …

The clustree: indexing micro-clusters for anytime stream mining

P Kranen, I Assent, C Baldauf, T Seidl - Knowledge and information …, 2011 - Springer
Clustering streaming data requires algorithms that are capable of updating clustering results
for the incoming data. As data is constantly arriving, time for processing is limited. Clustering …

Faster and more accurate classification of time series by exploiting a novel dynamic time warping averaging algorithm

F Petitjean, G Forestier, GI Webb, AE Nicholson… - … and Information Systems, 2016 - Springer
A concerted research effort over the past two decades has heralded significant
improvements in both the efficiency and effectiveness of time series classification. The …

Indexing and classifying gigabytes of time series under time warping

CW Tan, GI Webb, F Petitjean - Proceedings of the 2017 SIAM international …, 2017 - SIAM
Time series classification maps time series to labels. The nearest neighbour algorithm (NN)
using the Dynamic Time Warping (DTW) similarity measure is a leading algorithm for this …

Learning by extrapolation from marginal to full-multivariate probability distributions: decreasingly naive Bayesian classification

GI Webb, JR Boughton, F Zheng, KM Ting, H Salem - Machine learning, 2012 - Springer
Abstract Averaged n-Dependence Estimators (A n DE) is an approach to probabilistic
classification learning that learns by extrapolation from marginal to full-multivariate …

Self-adaptive anytime stream clustering

P Kranen, I Assent, C Baldauf… - 2009 Ninth IEEE …, 2009 - ieeexplore.ieee.org
Clustering streaming data requires algorithms which are capable of updating clustering
results for the incoming data. As data is constantly arriving, time for processing is limited …

A naive bayes baseline for early gesture recognition

HJ Escalante, EF Morales, LE Sucar - Pattern Recognition Letters, 2016 - Elsevier
Early gesture/action recognition is the task of determining the identity of a gesture/action with
as few information as possible. Although the topic is relatively new, there are some methods …

A novel approximation to dynamic time warping allows anytime clustering of massive time series datasets

Q Zhu, G Batista, T Rakthanmanon, E Keogh - Proceedings of the 2012 SIAM …, 2012 - SIAM
Given the ubiquity of time series data, the data mining community has spent significant time
investigating the best time series similarity measure to use for various tasks and domains …

Indexing density models for incremental learning and anytime classification on data streams

T Seidl, I Assent, P Kranen, R Krieger… - Proceedings of the 12th …, 2009 - dl.acm.org
Classification of streaming data faces three basic challenges: it has to deal with huge
amounts of data, the varying time between two stream data items must be used best …

A lazy bagging approach to classification

X Zhu, Y Yang - Pattern Recognition, 2008 - Elsevier
In this paper, we propose lazy bagging (LB), which builds bootstrap replicate bags based on
the characteristics of test instances. Upon receiving a test instance xk, LB trims bootstrap …