A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method

Q. Zhang; X. Bai; M. Akutagawa; H. Nagashino; Y. Kinouchi; F. Shichijo; S. Nagahiro; L. Ding

A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method

Q. Zhang^*
, X. Bai
, M. Akutagawa
, H. Nagashino
, Y. Kinouchi
, F. Shichijo
, S. Nagahiro
, L. Ding

^*Corresponding author for this work

Tokushima University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

5 Scopus citations

Abstract

EEG source localization is well known as an important inverse problem of electrophysiology. Usually there is no closed-form solution for this v problem and it requires iterative techniques such as the Levenberg-Marquardt algorithm. However, the method requires long computing times, huge memory and large number of electrodes to avoid local minima. To overcome these problems, a method combining back propagation neural network (BPNN) with nonlinear least square method (NLS) is therefore proposed in this study. The new method shows how to estimate an approximate solution of the inverse problem by the BPNN method, and how to select the initial value of the NLS method due to the results of BPNN to obtain the optimum solution, where the problem is solved by POWELL iterative algorithm.

Original language	English
Title of host publication	Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002
Pages	536-541
Number of pages	6
State	Published - 2002
Externally published	Yes
Event	Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002 - Singapore, Singapore Duration: 2 Dec 2002 → 5 Dec 2002

Publication series

Name	Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002

Conference

Conference	Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002
Country/Territory	Singapore
City	Singapore
Period	2/12/02 → 5/12/02

Cite this

Zhang, Q., Bai, X., Akutagawa, M., Nagashino, H., Kinouchi, Y., Shichijo, F., Nagahiro, S., & Ding, L. (2002). A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method. In Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002 (pp. 536-541). (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).

Zhang, Q. ; Bai, X. ; Akutagawa, M. et al. / A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method. Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. 2002. pp. 536-541 (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).

@inproceedings{db56957835bd4a058487968a6970f3d2,

title = "A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method",

abstract = "EEG source localization is well known as an important inverse problem of electrophysiology. Usually there is no closed-form solution for this v problem and it requires iterative techniques such as the Levenberg-Marquardt algorithm. However, the method requires long computing times, huge memory and large number of electrodes to avoid local minima. To overcome these problems, a method combining back propagation neural network (BPNN) with nonlinear least square method (NLS) is therefore proposed in this study. The new method shows how to estimate an approximate solution of the inverse problem by the BPNN method, and how to select the initial value of the NLS method due to the results of BPNN to obtain the optimum solution, where the problem is solved by POWELL iterative algorithm.",

author = "Q. Zhang and X. Bai and M. Akutagawa and H. Nagashino and Y. Kinouchi and F. Shichijo and S. Nagahiro and L. Ding",

year = "2002",

language = "英语",

isbn = "9810474806",

series = "Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002",

pages = "536--541",

booktitle = "Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002",

note = "Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002 ; Conference date: 02-12-2002 Through 05-12-2002",

}

Zhang, Q, Bai, X, Akutagawa, M, Nagashino, H, Kinouchi, Y, Shichijo, F, Nagahiro, S & Ding, L 2002, A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method. in Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002, pp. 536-541, Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002, Singapore, Singapore, 2/12/02.

A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method. / Zhang, Q.; Bai, X.; Akutagawa, M. et al.
Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. 2002. p. 536-541 (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method

AU - Zhang, Q.

AU - Bai, X.

AU - Akutagawa, M.

AU - Nagashino, H.

AU - Kinouchi, Y.

AU - Shichijo, F.

AU - Nagahiro, S.

AU - Ding, L.

PY - 2002

Y1 - 2002

N2 - EEG source localization is well known as an important inverse problem of electrophysiology. Usually there is no closed-form solution for this v problem and it requires iterative techniques such as the Levenberg-Marquardt algorithm. However, the method requires long computing times, huge memory and large number of electrodes to avoid local minima. To overcome these problems, a method combining back propagation neural network (BPNN) with nonlinear least square method (NLS) is therefore proposed in this study. The new method shows how to estimate an approximate solution of the inverse problem by the BPNN method, and how to select the initial value of the NLS method due to the results of BPNN to obtain the optimum solution, where the problem is solved by POWELL iterative algorithm.

AB - EEG source localization is well known as an important inverse problem of electrophysiology. Usually there is no closed-form solution for this v problem and it requires iterative techniques such as the Levenberg-Marquardt algorithm. However, the method requires long computing times, huge memory and large number of electrodes to avoid local minima. To overcome these problems, a method combining back propagation neural network (BPNN) with nonlinear least square method (NLS) is therefore proposed in this study. The new method shows how to estimate an approximate solution of the inverse problem by the BPNN method, and how to select the initial value of the NLS method due to the results of BPNN to obtain the optimum solution, where the problem is solved by POWELL iterative algorithm.

UR - https://www.scopus.com/pages/publications/2342442931

M3 - 会议稿件

AN - SCOPUS:2342442931

SN - 9810474806

SN - 9789810474805

T3 - Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002

SP - 536

EP - 541

BT - Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002

T2 - Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARC 2002

Y2 - 2 December 2002 through 5 December 2002

ER -

Zhang Q, Bai X, Akutagawa M, Nagashino H, Kinouchi Y, Shichijo F et al. A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method. In Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002. 2002. p. 536-541. (Proceedings of the 7th International Conference on Control, Automation, Robotics and Vision, ICARCV 2002).

A Method for Two EEC Sources Localization by Combining BP Neural Networks with Nonlinear Least Square Method

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this