Time-Series Segmentation Using Predictive Modular Neural Networks

Authors:
Athanasios Kehagias;Vassilios Petridis
Affiliations:
Department of Electrical Engineering, Aristotle University of Thessaloniki, GR 54006, Thessaloniki, Greece, and Department of Mathematics, American College of Thessaloniki, GR 55510 Pylea, Thessal ...;Department of Electrical Engineering, Aristotle University of Thessaloniki, GR 54006, Thessaloniki, Greece
Venue:
Neural Computation
Year:
1997

Citing 9
Cited 1

Self-organization and associative memory: 3rd edition

Self-organization and associative memory: 3rd edition
Introduction to the theory of neural computation

Introduction to the theory of neural computation
Hierarchical mixtures of experts and the EM algorithm

Neural Computation
Convergence results for the EM approach to mixtures of experts architectures

Neural Networks
Predictive modular neural networks for time series classification

Neural Networks
Annealed competition of experts for a segmentation and classification of switching dynamics

Neural Computation
A recurrent network implementation of time series classification

Neural Computation
On convergence properties of the em algorithm for gaussian mixtures

Neural Computation
Modular neural networks for MAP classification of time series and the partition algorithm

IEEE Transactions on Neural Networks

Efficient algorithms for segmentation of item-set time series

Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

A predictive modular neural network method is applied to the problem of unsupervised time-series segmentation. The method consists of the concurrent application of two algorithms: one for source identification, the other for time-series classification. The source identification algorithm discovers the sources generating the time series, assigns data to each source, and trains one predictor for each source. The classification algorithm recursively computes a credit function for each source, based on the competition of the respective predictors, according to their predictive accuracy; the credit function is used for classification of the time-series observation at each time step. The method is tested by numerical experiments.