Optimized Efficient Predefined Time Adaptive Neural Network for Identifying Parameters in Quantum Bit Error Rate

Abstract

An Optimized Efficient Predefined Time Adaptive Neural Network for Identifying Parameters in Quantum Bit Error Rate (EPTANN-IP-QBER) is proposed in this manuscript. Here, the input signals are gathered from 6G wireless networks that face obstacles channel. To execute this, the High-Level Target Navigation Pigeon-Inspired Optimization (HLTNPIO) is used to extend the maximum transmission distances and improve the secret key rates of input signals. Then, improved secret key rates input signals are fed to EPTANN for effectively identifying the parameters such as laser linewidth, channel dispersion, decoy states, error correction rate, privacy amplification efficiency, eavesdropping detection, scalability, and photon encoding optimization in quantum bit error rates (QBERs). Generally, EPTANN does not adapt any optimization approaches to determine optimal parameters to identify the parameters in QBER. Hence, the Snow Avalanches Algorithm (SAA) is employed to optimize the EPTANN, which accurately identifies the parameter in QBER reduction. The proposed EPTANN-IP-QBER is implemented in Python. The performance metrics, like accuracy, precision, secure key rate, QBER, transmission distance, and computational time, are analyzed. The performance of the EPTANN-IP-QBER approach attains 20.25%, 18.36%, and 23.28% lower QBER; 29.56%, 19.42%, and 27.74% higher accuracy; and 16.21%, 20.26%, and 26.96% higher precision when analyzed to the existing methods: Millimeter-Waves to Terahertz SISO along MIMO Continuous-Variable Quantum Key Distribution (TSISO-MIMO-VQKD), MIMO Terahertz QKD utilizing Restricted Eavesdropping (MIMO-QKD-URE), and single-emitter quantum key distribution more than 175 km of fiber by optimized finite key rates (SEQKD-FKR) methods, respectively.