Quantum Machine Learning (QML) for Irregular Complex Modulation of 8-QAM
It is shown that the proposed QML-based demapping technique requires fewer qubits compared to existing techniques and achieves a lower estimated processing time than the classical demapping for higher constellation number.
Abstract
This paper proposes a quantum machine learning (QML) algorithm with compact amplitude encoding technique for future complex modulations. We develop a quantum algorithm that leverages the empty state to evaluate the probabilities of the measured qubits based on a given received signal. This paper determines the bit based on the smallest probability obtained from the amplitude of quantum states. We show that the proposed QML-based demapping technique requires fewer qubits compared to existing techniques and achieves a lower estimated processing time than the classical demapping for higher constellation number. We successfully trained and tested complex binary phase-shift keying (CBPSK) modulation using only three qubits and the addition of one qubit for a higher constellation number. A complex constellation is also detectable using QML-based demapping for irregular complex modulation, such as 8-quadrature amplitude modulation (QAM). The results of this paper are expected to contribute to the advancement and development of sixth generation (6G) technology.