Time-series forecasting with evolvable partially connected artificial neural network

Mina Moradi Kordmahalleh; Mohammad Gorji Sefidmazgi; Abdollah Homaifar; B. K.C. Dukka; Anthony Guiseppi-Elie

doi:10.1145/2598394.2598435

Time-series forecasting with evolvable partially connected artificial neural network

Mina Moradi Kordmahalleh, Mohammad Gorji Sefidmazgi, Abdollah Homaifar, B. K.C. Dukka, Anthony Guiseppi-Elie

Academic Institute

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

6 Scopus citations

Abstract

In nonlinear and chaotic time series prediction, constructing the mathematical model of the system dynamics is not an easy task. Partially connected Artificial Neural Network with Evolvable Topology (PANNET) is a new paradigm for prediction of chaotic time series without access to the dynamics and essential memory depth of the system. Evolvable topology of the PANNET provides flexibility in recognition of systems in contrast to fixed layered topology of the traditional ANNs. This evolvable topology guides the relationship between observation nodes and hidden nodes, where hidden nodes are extra nodes that play the role of memory or internal states of the system. In the proposed variable-length Genetic Algorithm (GA), internal neurons can be connected arbitrarily to any type of nodes. Besides, number of neurons, inputs and outputs for each neuron, origin and weight of each connection evolve in order to find the best configuration of the network.

Original language	English (US)
Title of host publication	GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference
Publisher	Association for Computing Machinery
Pages	79-80
Number of pages	2
ISBN (Print)	9781450328814
DOIs	https://doi.org/10.1145/2598394.2598435
State	Published - 2014
Event	16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion - Vancouver, BC, Canada Duration: Jul 12 2014 → Jul 16 2014

Publication series

Name	GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

Conference

Conference	16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion
Country/Territory	Canada
City	Vancouver, BC
Period	7/12/14 → 7/16/14

Keywords

Artificial Neural Networks
Evolutionary computation
Evolvable Topology
Genetic algorithms
Time series forecasting

ASJC Scopus subject areas

Computational Theory and Mathematics
Applied Mathematics

Access to Document

10.1145/2598394.2598435

Cite this

Kordmahalleh, M. M., Sefidmazgi, M. G., Homaifar, A., Dukka, B. K. C., & Guiseppi-Elie, A. (2014). Time-series forecasting with evolvable partially connected artificial neural network. In GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference (pp. 79-80). (GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference). Association for Computing Machinery. https://doi.org/10.1145/2598394.2598435

Time-series forecasting with evolvable partially connected artificial neural network. / Kordmahalleh, Mina Moradi; Sefidmazgi, Mohammad Gorji; Homaifar, Abdollah et al.
GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, 2014. p. 79-80 (GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference).

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

Kordmahalleh, MM, Sefidmazgi, MG, Homaifar, A, Dukka, BKC & Guiseppi-Elie, A 2014, Time-series forecasting with evolvable partially connected artificial neural network. in GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference. GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference, Association for Computing Machinery, pp. 79-80, 16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion, Vancouver, BC, Canada, 7/12/14. https://doi.org/10.1145/2598394.2598435

Kordmahalleh MM, Sefidmazgi MG, Homaifar A, Dukka BKC, Guiseppi-Elie A. Time-series forecasting with evolvable partially connected artificial neural network. In GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference. Association for Computing Machinery. 2014. p. 79-80. (GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference). doi: 10.1145/2598394.2598435

Kordmahalleh, Mina Moradi ; Sefidmazgi, Mohammad Gorji ; Homaifar, Abdollah et al. / Time-series forecasting with evolvable partially connected artificial neural network. GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference. Association for Computing Machinery, 2014. pp. 79-80 (GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference).

@inproceedings{95318a82b8fa4b02a492228a94b72bda,

title = "Time-series forecasting with evolvable partially connected artificial neural network",

abstract = "In nonlinear and chaotic time series prediction, constructing the mathematical model of the system dynamics is not an easy task. Partially connected Artificial Neural Network with Evolvable Topology (PANNET) is a new paradigm for prediction of chaotic time series without access to the dynamics and essential memory depth of the system. Evolvable topology of the PANNET provides flexibility in recognition of systems in contrast to fixed layered topology of the traditional ANNs. This evolvable topology guides the relationship between observation nodes and hidden nodes, where hidden nodes are extra nodes that play the role of memory or internal states of the system. In the proposed variable-length Genetic Algorithm (GA), internal neurons can be connected arbitrarily to any type of nodes. Besides, number of neurons, inputs and outputs for each neuron, origin and weight of each connection evolve in order to find the best configuration of the network.",

keywords = "Artificial Neural Networks, Evolutionary computation, Evolvable Topology, Genetic algorithms, Time series forecasting",

author = "Kordmahalleh, {Mina Moradi} and Sefidmazgi, {Mohammad Gorji} and Abdollah Homaifar and Dukka, {B. K.C.} and Anthony Guiseppi-Elie",

year = "2014",

doi = "10.1145/2598394.2598435",

language = "English (US)",

isbn = "9781450328814",

series = "GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference",

publisher = "Association for Computing Machinery",

pages = "79--80",

booktitle = "GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference",

note = "16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion ; Conference date: 12-07-2014 Through 16-07-2014",

}

TY - GEN

T1 - Time-series forecasting with evolvable partially connected artificial neural network

AU - Kordmahalleh, Mina Moradi

AU - Sefidmazgi, Mohammad Gorji

AU - Homaifar, Abdollah

AU - Dukka, B. K.C.

AU - Guiseppi-Elie, Anthony

PY - 2014

Y1 - 2014

N2 - In nonlinear and chaotic time series prediction, constructing the mathematical model of the system dynamics is not an easy task. Partially connected Artificial Neural Network with Evolvable Topology (PANNET) is a new paradigm for prediction of chaotic time series without access to the dynamics and essential memory depth of the system. Evolvable topology of the PANNET provides flexibility in recognition of systems in contrast to fixed layered topology of the traditional ANNs. This evolvable topology guides the relationship between observation nodes and hidden nodes, where hidden nodes are extra nodes that play the role of memory or internal states of the system. In the proposed variable-length Genetic Algorithm (GA), internal neurons can be connected arbitrarily to any type of nodes. Besides, number of neurons, inputs and outputs for each neuron, origin and weight of each connection evolve in order to find the best configuration of the network.

AB - In nonlinear and chaotic time series prediction, constructing the mathematical model of the system dynamics is not an easy task. Partially connected Artificial Neural Network with Evolvable Topology (PANNET) is a new paradigm for prediction of chaotic time series without access to the dynamics and essential memory depth of the system. Evolvable topology of the PANNET provides flexibility in recognition of systems in contrast to fixed layered topology of the traditional ANNs. This evolvable topology guides the relationship between observation nodes and hidden nodes, where hidden nodes are extra nodes that play the role of memory or internal states of the system. In the proposed variable-length Genetic Algorithm (GA), internal neurons can be connected arbitrarily to any type of nodes. Besides, number of neurons, inputs and outputs for each neuron, origin and weight of each connection evolve in order to find the best configuration of the network.

KW - Artificial Neural Networks

KW - Evolutionary computation

KW - Evolvable Topology

KW - Genetic algorithms

KW - Time series forecasting

UR - http://www.scopus.com/inward/record.url?scp=84905669395&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905669395&partnerID=8YFLogxK

U2 - 10.1145/2598394.2598435

DO - 10.1145/2598394.2598435

M3 - Conference contribution

AN - SCOPUS:84905669395

SN - 9781450328814

T3 - GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

SP - 79

EP - 80

BT - GECCO 2014 - Companion Publication of the 2014 Genetic and Evolutionary Computation Conference

PB - Association for Computing Machinery

T2 - 16th Genetic and Evolutionary Computation Conference Companion, GECCO 2014 Companion

Y2 - 12 July 2014 through 16 July 2014

ER -

Time-series forecasting with evolvable partially connected artificial neural network

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this