Citation

Chien, S.F. and Hermans, Julien J.M. and Kana, Austin A. and Zarakovitis, Charilaos. C. and Zavvos, Stathis and Lim, Heng Siong (2025) Quantum Neural Networks: A Path to Lower Emissions Through Fuel Consumption Prediction in Shipping. In: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 06-11 April 2025, Hyderabad, India.

Text 1.pdf - Published Version Restricted to Repository staff only Download (489kB)

Abstract

This paper proposes Quantum Neural Networks (QNNs) as a data-driven approach for predicting fuel consumption. We utilize various layer architecture designs available in the Torchquantum framework, including both entangled and non-entangled circuit designs. In general, QNNs can achieve comparable Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) with significantly fewer trainable parameters. Neither pure QNNs nor hybrid QNN models exhibit the underfitting tendencies seen in classical neural networks (CNNs). Notably, one of the most significant findings of this work is that hybridizing or ”dressing” the quantum circuit leads to substantial improvements in RMSE and MAPE for pure QNNs. These promising results suggest potential optimizations for reducing emissions in green shipping.

Item Type:	Conference or Workshop Item (Paper)
Uncontrolled Keywords:	Classical neural network, quantum neural network, parameterized quantum circuit, NISQ devices, digital twin, fuel consumption, modeling.
Subjects:	Q Science > QA Mathematics > QA71-90 Instruments and machines
Divisions:	Faculty of Engineering and Technology (FET)
Depositing User:	Ms Suzilawati Abu Samah
Date Deposited:	11 Jun 2025 02:36
Last Modified:	18 Jun 2025 05:00
URII:	http://shdl.mmu.edu.my/id/eprint/13901

Downloads

Edit (login required)