Processing short-term and long-term information with a combination of polynomial approximation techniques and time-delay neural networks

Authors:
Erich Fuchs;Christian Gruber;Tobias Reitmaier;Bernhard Sick
Affiliations:
Faculty of Informatics and Mathematics, University of Passau, Passau, Germany;Elektrobit, Munich, Germany;Faculty of Informatics and Mathematics, University of Passau, Passau, Germany;Faculty of Informatics and Mathematics, University of Passau, Passau, Germany
Venue:
IEEE Transactions on Neural Networks
Year:
2009

Citing 20
Cited 1

Updating and downdating of orthogonal polynomials with data fitting applications

SIAM Journal on Matrix Analysis and Applications
Original Contribution: A scaled conjugate gradient algorithm for fast supervised learning

Neural Networks
Finite impulse response neural networks with applications in time series prediction

Finite impulse response neural networks with applications in time series prediction
Second-Order Methods for Neural Networks

Second-Order Methods for Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Feature Extraction, Construction and Selection: A Data Mining Perspective

Feature Extraction, Construction and Selection: A Data Mining Perspective
Feature Selection for Knowledge Discovery and Data Mining

Feature Selection for Knowledge Discovery and Data Mining
Recurrent Neural Network Architectures: An Overview

Adaptive Processing of Sequences and Data Structures, International Summer School on Neural Networks, "E.R. Caianiello"-Tutorial Lectures
Fast Least-Squares Polynomial Approximation in Moving Time Windows

ICASSP '97 Proceedings of the 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP '97)-Volume 3 - Volume 3
Learning precise timing with lstm recurrent networks

The Journal of Machine Learning Research
Probabilistic discovery of time series motifs

Proceedings of the ninth ACM SIGKDD international conference on Knowledge discovery and data mining
Fusion of soft and hard computing: multi-dimensional categorization of computationally intelligent hybrid systems

Neural Computing and Applications
Long Short-Term Memory

Neural Computation
A delay damage model selection algorithm for NARX neural networks

IEEE Transactions on Signal Processing
Fusion of hard and soft computing techniques in indirect, online tool wear monitoring

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Multiresolution FIR neural-network-based learning algorithm applied to network traffic prediction

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Learning long-term dependencies in NARX recurrent neural networks

IEEE Transactions on Neural Networks
Multiresolution forecasting for futures trading using wavelet decompositions

IEEE Transactions on Neural Networks
Adaptive multilayer perceptrons with long- and short-term memories

IEEE Transactions on Neural Networks
Training Recurrent Neurocontrollers for Real-Time Applications

IEEE Transactions on Neural Networks

Temporal data mining using shape space representations of time series

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Neural networks are often used to process temporal information, i.e., any kind of information related to time series. In many cases, time series contain short-term and long-term trends or behavior. This paper presents a new approach to capture temporal information with various reference periods simultaneously. A least squares approximation of the time series with orthogonal polynomials will be used to describe short-term trends contained in a signal (average, increase, curvature, etc.). Long-term behavior will be modeled with the tapped delay lines of a time-delay neural network (TDNN). This network takes the coefficients of the orthogonal expansion of the approximating polynomial as inputs such considering short-term and long-term information efficiently. The advantages of the method will be demonstrated by means of artificial data and two real-world application examples, the prediction of the user number in a computer network and online tool wear classification in turning.