Article: A radial basis function neural network algorithm based on quantum controlled NOT gate and orthogonal least squares theory Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.48 pp.80 - 102 Abstract: Temperature compensation is crucial for improving sensor accuracy and stability in high-precision measurement. Although radial basis function (RBF) neural networks perform well in nonlinear modelling, they face slow convergence, long training time, and limited accuracy. To address these issues, this paper proposes an improved RBF algorithm (QOLS-RBF) by combining quantum controlled-NOT (C-NOT) gates with orthogonal least squares (OLS) theory. The method quantises input data and applies quantum superposition, entanglement, and interference to enhance feature extraction and centre aggregation. It further integrates OLS screening with the maximum error compression ratio, using C-NOT gate evolution to reduce hidden layer nodes and accelerate convergence. Experiments with 85 training and 170 testing sensor datasets show that QOLS-RBF outperforms RBF, OLS-RBF, K-means RBF, and FCM-RBF in convergence speed, training time, error accuracy, and network compactness. This approach enables efficient temperature compensation and offers a promising tool for modelling complex nonlinear systems. Inderscience Publishers - linking academia, business and industry through research

Title: A radial basis function neural network algorithm based on quantum controlled NOT gate and orthogonal least squares theory

Authors: Wei Peng; Guoqing Hu; Jiahang Li; Chengzhi Lyu

Addresses: School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, Guangdong, 510640, China ' School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, Guangdong, 510640, China ' School of Aeronautical Manufacturing and Mechanical Engineering, Nanchang Hangkong University, Nanchang, Jiangxi, 330063, China ' School of Mechanical and Automotive Engineering, South China University of Technology, Guangzhou, Guangdong, 510640, China

Abstract: Temperature compensation is crucial for improving sensor accuracy and stability in high-precision measurement. Although radial basis function (RBF) neural networks perform well in nonlinear modelling, they face slow convergence, long training time, and limited accuracy. To address these issues, this paper proposes an improved RBF algorithm (QOLS-RBF) by combining quantum controlled-NOT (C-NOT) gates with orthogonal least squares (OLS) theory. The method quantises input data and applies quantum superposition, entanglement, and interference to enhance feature extraction and centre aggregation. It further integrates OLS screening with the maximum error compression ratio, using C-NOT gate evolution to reduce hidden layer nodes and accelerate convergence. Experiments with 85 training and 170 testing sensor datasets show that QOLS-RBF outperforms RBF, OLS-RBF, K-means RBF, and FCM-RBF in convergence speed, training time, error accuracy, and network compactness. This approach enables efficient temperature compensation and offers a promising tool for modelling complex nonlinear systems.

Keywords: neural network algorithm; orthogonal least squares; OLS; sensors.

DOI: 10.1504/IJICT.2025.150950

International Journal of Information and Communication Technology, 2025 Vol.26 No.48, pp.80 - 102

Received: 16 Oct 2025
Accepted: 31 Oct 2025
Published online: 05 Jan 2026 *

Title: A radial basis function neural network algorithm based on quantum controlled NOT gate and orthogonal least squares theory

Keep up-to-date