Pre-processing inputs for optimally-configured time-delay neural networks

Date

2005-02-01

Author

Taşkaya Temizel, Tuğba
Ahmad, K

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

210
views

0
downloads

A procedure for pre-processing non-stationary time series is proposed for modelling with a time-delay neural network (TDNN). The procedure stabilises the mean of the series and uses a fast Fourier transform to determine the TDNN input size. Results of applying this procedure on five well-known data sets are compared with existing hybrid neural network techniques, demonstrating improved prediction performance.

Subject Keywords

Electrical and Electronic Engineering

URI

https://hdl.handle.net/11511/70043

Journal

ELECTRONICS LETTERS

DOI

https://doi.org/10.1049/el:20058016

Collections

Graduate School of Informatics, Article

Suggestions

OpenMETU
Core

EFIE-Tuned Testing Functions for MFIE and CFIE Karaosmanoglu, Bariscan; Ergül, Özgür Salih (Institute of Electrical and Electronics Engineers (IEEE), 2017-01-01) A recently developed numerical technique for improving the accuracy of the magnetic-field integral equation and the combined-field integral equation with low-order discretizations using the Rao-Wilton-Glisson functions is demonstrated on iterative solutions of large-scale complex problems, in order to prove the effectiveness of the proposed strategy as an alternative way for accurate and efficient analysis of multifrequency applications.
Hierarchical parallelisation strategy for multilevel fast multipole algorithm in computational electromagnetics Ergül, Özgür Salih (Institution of Engineering and Technology (IET), 2008-01-03) A hierarchical parallelisation of the multilevel fast multipole algorithm (MLFMA) for the efficient solution of large-scale problems in computational electromagnetics is presented. The tree structure of MLFMA is distributed among the processors by partitioning both the clusters and the samples of the fields appropriately for each level. The parallelisation efficiency is significantly improved compared to previous approaches, where only the clusters or only the fields are partitioned in a level.
Singularity Cancellation for Accurate MoM Analysis of Periodic Planar Structures in Layered Media Adanir, Suleyman; Alatan, Lale (Institute of Electrical and Electronics Engineers (IEEE), 2020-08-01) One of the singularity cancellation schemes proposed in the literature is applied to calculate singular integrals arising in the method of moments (MoM) analysis of 2-D periodic planar structures in multilayered media. Discrete complex image method is utilized for the accurate approximation of Green's function which also makes possible the application of the Ewald transformation for the efficient computation of the series associated with the periodic structure. This approximation and transformation modifies...
CBFEM-MPI: A Parallelized Version of Characteristic Basis Finite Element Method for Extraction of 3-D Interconnect Capacitances Ozgun, Ozlem; Mittra, Raj; Kuzuoğlu, Mustafa (Institute of Electrical and Electronics Engineers (IEEE), 2009-02-01) In this paper, we present a novel, non-iterative domain decomposition method, which has been parallelized by using the message passing interface (MPI) library, and used to efficiently extract the capacitance matrixes of 3-D interconnect structures, by employing characteristic basis functions (CBFs) in the context of the finite element method (FEM). In this method, which is Failed CBFEM-MPI, the computational domain is partitioned into a number of nonoverlapping subdomains in which the CBFs are constructed b...
HMM topology for boundary refinement in automatic speech segmentation Akdemir, E.; Çiloğlu, Tolga (Institution of Engineering and Technology (IET), 2010-07-22) A boundary refinement method using a new hidden Markov model (HMM) topology is proposed for automatic phonetic speech segmentation. The proposed method has the ability to work at high frame rates and the training and boundary refinement stages are easy and fast. The method is data driven and can be adapted to any speech segmentation problem provided that a training set is available. Given an initial segmentation obtained by forced alignment using an HMM based phone recogniser, 20% decrease in boundary error...

Citation Formats

T. Taşkaya Temizel and K. Ahmad, “Pre-processing inputs for optimally-configured time-delay neural networks,” ELECTRONICS LETTERS, pp. 198–200, 2005, Accessed: 00, 2021. [Online]. Available: https://hdl.handle.net/11511/70043.