Home > Research > Publications & Outputs > Optimizing prediction accuracy in dynamic syste...

Links

Text available via DOI:

View graph of relations

Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters. / Khan, Junaid; Zaman, Umar; Lee, Eunkyu et al.
In: PLoS One, Vol. 19, No. 10, e0311734, 16.10.2024.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Khan, J, Zaman, U, Lee, E, Balobaid, AS, Aburasain, RY, Bilal, M, Kim, K & Deng, M (ed.) 2024, 'Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters', PLoS One, vol. 19, no. 10, e0311734. https://doi.org/10.1371/journal.pone.0311734

APA

Khan, J., Zaman, U., Lee, E., Balobaid, A. S., Aburasain, R. Y., Bilal, M., Kim, K., & Deng, M. (Ed.) (2024). Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters. PLoS One, 19(10), Article e0311734. https://doi.org/10.1371/journal.pone.0311734

Vancouver

Khan J, Zaman U, Lee E, Balobaid AS, Aburasain RY, Bilal M et al. Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters. PLoS One. 2024 Oct 16;19(10):e0311734. doi: 10.1371/journal.pone.0311734

Author

Khan, Junaid ; Zaman, Umar ; Lee, Eunkyu et al. / Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters. In: PLoS One. 2024 ; Vol. 19, No. 10.

Bibtex

@article{fb925db19b3448eeb8a66314c38ac6c2,
title = "Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters",
abstract = "In the realm of dynamic system analysis, the Kalman filter and the alpha-beta filter are widely recognized for their tracking and prediction capabilities. However, their performance is often limited by static parameters that cannot adapt to changing conditions. Addressing this limitation, this paper introduces innovative neural network-based prediction models that enhance the adaptability and accuracy of these conventional filters. Our approach involves the integration of neural networks within the filtering algorithms, enabling the dynamic augmentation of parameters in response to performance feedback. We present two modified filters: a neural network-based Kalman filter and an alpha-beta filter, each augmented to incorporate neural network-driven parameter tuning. The alpha-beta filter is enhanced with neural network outputs for its α and β parameters, while the Kalman filter employs a neural network to optimize its internal parameter R and noise factor F. We assess these advanced models using the root mean square error (RMSE) metric, where our neural network-based alpha-beta filter demonstrates a significant 38.2% improvement in prediction accuracy, and the neural network-based Kalman filter achieves a 53.4% enhancement. Hence, our novel approach of integrating neural networks into filtering algorithms stands out as an effective strategy to significantly enhance their performance in dynamic environments.",
author = "Junaid Khan and Umar Zaman and Eunkyu Lee and Balobaid, {Awatef Salim} and Aburasain, {R. Y.} and Muhammad Bilal and Kyungsup Kim and Mingsen Deng",
year = "2024",
month = oct,
day = "16",
doi = "10.1371/journal.pone.0311734",
language = "English",
volume = "19",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "10",

}

RIS

TY - JOUR

T1 - Optimizing prediction accuracy in dynamic systems through neural network integration with Kalman and alpha-beta filters

AU - Khan, Junaid

AU - Zaman, Umar

AU - Lee, Eunkyu

AU - Balobaid, Awatef Salim

AU - Aburasain, R. Y.

AU - Bilal, Muhammad

AU - Kim, Kyungsup

A2 - Deng, Mingsen

PY - 2024/10/16

Y1 - 2024/10/16

N2 - In the realm of dynamic system analysis, the Kalman filter and the alpha-beta filter are widely recognized for their tracking and prediction capabilities. However, their performance is often limited by static parameters that cannot adapt to changing conditions. Addressing this limitation, this paper introduces innovative neural network-based prediction models that enhance the adaptability and accuracy of these conventional filters. Our approach involves the integration of neural networks within the filtering algorithms, enabling the dynamic augmentation of parameters in response to performance feedback. We present two modified filters: a neural network-based Kalman filter and an alpha-beta filter, each augmented to incorporate neural network-driven parameter tuning. The alpha-beta filter is enhanced with neural network outputs for its α and β parameters, while the Kalman filter employs a neural network to optimize its internal parameter R and noise factor F. We assess these advanced models using the root mean square error (RMSE) metric, where our neural network-based alpha-beta filter demonstrates a significant 38.2% improvement in prediction accuracy, and the neural network-based Kalman filter achieves a 53.4% enhancement. Hence, our novel approach of integrating neural networks into filtering algorithms stands out as an effective strategy to significantly enhance their performance in dynamic environments.

AB - In the realm of dynamic system analysis, the Kalman filter and the alpha-beta filter are widely recognized for their tracking and prediction capabilities. However, their performance is often limited by static parameters that cannot adapt to changing conditions. Addressing this limitation, this paper introduces innovative neural network-based prediction models that enhance the adaptability and accuracy of these conventional filters. Our approach involves the integration of neural networks within the filtering algorithms, enabling the dynamic augmentation of parameters in response to performance feedback. We present two modified filters: a neural network-based Kalman filter and an alpha-beta filter, each augmented to incorporate neural network-driven parameter tuning. The alpha-beta filter is enhanced with neural network outputs for its α and β parameters, while the Kalman filter employs a neural network to optimize its internal parameter R and noise factor F. We assess these advanced models using the root mean square error (RMSE) metric, where our neural network-based alpha-beta filter demonstrates a significant 38.2% improvement in prediction accuracy, and the neural network-based Kalman filter achieves a 53.4% enhancement. Hence, our novel approach of integrating neural networks into filtering algorithms stands out as an effective strategy to significantly enhance their performance in dynamic environments.

U2 - 10.1371/journal.pone.0311734

DO - 10.1371/journal.pone.0311734

M3 - Journal article

VL - 19

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 10

M1 - e0311734

ER -