Constrained LMS for Dynamic Flow Networks. / Eftaxias, Konstantinos ; Cheong Took, Clive; Venturini, Bruno ; Arscott, David .

2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 2017. p. 3254-3258.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Published

Standard

Constrained LMS for Dynamic Flow Networks. / Eftaxias, Konstantinos ; Cheong Took, Clive; Venturini, Bruno ; Arscott, David .

2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 2017. p. 3254-3258.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Harvard

Eftaxias, K, Cheong Took, C, Venturini, B & Arscott, D 2017, Constrained LMS for Dynamic Flow Networks. in 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, pp. 3254-3258. https://doi.org/10.1109/IJCNN.2017.7966263

APA

Eftaxias, K., Cheong Took, C., Venturini, B., & Arscott, D. (2017). Constrained LMS for Dynamic Flow Networks. In 2017 International Joint Conference on Neural Networks (IJCNN) (pp. 3254-3258). IEEE. https://doi.org/10.1109/IJCNN.2017.7966263

Vancouver

Eftaxias K, Cheong Took C, Venturini B, Arscott D. Constrained LMS for Dynamic Flow Networks. In 2017 International Joint Conference on Neural Networks (IJCNN). IEEE. 2017. p. 3254-3258 https://doi.org/10.1109/IJCNN.2017.7966263

Author

Eftaxias, Konstantinos ; Cheong Took, Clive ; Venturini, Bruno ; Arscott, David . / Constrained LMS for Dynamic Flow Networks. 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, 2017. pp. 3254-3258

BibTeX

@inproceedings{fec2c572661645c38dc5b511027780e0,
title = "Constrained LMS for Dynamic Flow Networks",
abstract = "In this era of climate change, there is a growing need to offer adaptive learning algorithms in the optimisation of natural resources. These resources are typically optimised by evolutionary algorithms. However, evolutionary algorithms (EAs) are no longer adequate due to the `drift' component introduced by environmental factors such as flash flooding. We therefore propose a novel constrained Least Mean Squares (LMS) algorithm for the optimisation of flow networks. For rigor, we provide a stability analysis of our adaptive algorithm, which enables us to interpret the physical meaning of the network at equilibrium. We evaluate our proposed method against genetic algorithm (GA), the most common evolutionary algorithm. The results are promising: not only the proposed constrained LMS has a performance advantage over GA, but its computational cost is significantly lower making it more suitable for real-time applications.",
author = "Konstantinos Eftaxias and {Cheong Took}, Clive and Bruno Venturini and David Arscott",
year = "2017",
month = jul,
day = "3",
doi = "10.1109/IJCNN.2017.7966263",
language = "English",
isbn = "978-1-5090-6183-9",
pages = "3254--3258",
booktitle = "2017 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Constrained LMS for Dynamic Flow Networks

AU - Eftaxias, Konstantinos

AU - Cheong Took, Clive

AU - Venturini, Bruno

AU - Arscott, David

PY - 2017/7/3

Y1 - 2017/7/3

N2 - In this era of climate change, there is a growing need to offer adaptive learning algorithms in the optimisation of natural resources. These resources are typically optimised by evolutionary algorithms. However, evolutionary algorithms (EAs) are no longer adequate due to the `drift' component introduced by environmental factors such as flash flooding. We therefore propose a novel constrained Least Mean Squares (LMS) algorithm for the optimisation of flow networks. For rigor, we provide a stability analysis of our adaptive algorithm, which enables us to interpret the physical meaning of the network at equilibrium. We evaluate our proposed method against genetic algorithm (GA), the most common evolutionary algorithm. The results are promising: not only the proposed constrained LMS has a performance advantage over GA, but its computational cost is significantly lower making it more suitable for real-time applications.

AB - In this era of climate change, there is a growing need to offer adaptive learning algorithms in the optimisation of natural resources. These resources are typically optimised by evolutionary algorithms. However, evolutionary algorithms (EAs) are no longer adequate due to the `drift' component introduced by environmental factors such as flash flooding. We therefore propose a novel constrained Least Mean Squares (LMS) algorithm for the optimisation of flow networks. For rigor, we provide a stability analysis of our adaptive algorithm, which enables us to interpret the physical meaning of the network at equilibrium. We evaluate our proposed method against genetic algorithm (GA), the most common evolutionary algorithm. The results are promising: not only the proposed constrained LMS has a performance advantage over GA, but its computational cost is significantly lower making it more suitable for real-time applications.

UR - https://core.ac.uk/download/pdf/80846095.pdf

U2 - 10.1109/IJCNN.2017.7966263

DO - 10.1109/IJCNN.2017.7966263

M3 - Conference contribution

SN - 978-1-5090-6183-9

SP - 3254

EP - 3258

BT - 2017 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

ER -