A new approach to qualitative learning in time series

Authors:
L. Gonzalez-Abril;F. Velasco;J. A. Ortega;F. J. Cuberos
Affiliations:
Applied Economics I Dept., Seville University, 41018 Seville, Spain;Applied Economics I Dept., Seville University, 41018 Seville, Spain;Computer Languages and Systems Dept., Seville University, 41012 Seville, Spain;Planning Dept. - R.T.V.A., Jose Galvez s/n, 41092 Seville, Spain
Venue:
Expert Systems with Applications: An International Journal
Year:
2009

Citing 8
Cited 1

On Changing Continuous Attributes into Ordered Discrete Attributes

EWSL '91 Proceedings of the European Working Session on Machine Learning
Efficient Similarity Search In Sequence Databases

FODO '93 Proceedings of the 4th International Conference on Foundations of Data Organization and Algorithms
On the need for time series data mining benchmarks: a survey and empirical demonstration

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
A symbolic representation of time series, with implications for streaming algorithms

DMKD '03 Proceedings of the 8th ACM SIGMOD workshop on Research issues in data mining and knowledge discovery
CAIM Discretization Algorithm

IEEE Transactions on Knowledge and Data Engineering
Multi-Classification by Using Tri-Class SVM

Neural Processing Letters
Support vector machines for interval discriminant analysis

Neurocomputing
Ameva: An autonomous discretization algorithm

Expert Systems with Applications: An International Journal

Time series labeling algorithms based on the K-nearest neighbors' frequencies

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

In this paper the k-nearest-neighbours (KNN) based method is presented for the classification of time series which use qualitative learning to identify similarities using kernels. To this end, time series are transformed into symbol strings by means of several discretization methods and a distance based on a kernel between symbols in ordinal scale is used to calculate the similarity between time series. Hence, the idea proposed is the consideration of the simultaneous use of symbolic representation together with a kernel based approach for classification of time series. The methodology has been tested and compared with quantitative learning from a television-viewing shared data set and has yielded a high success identification ratio.