A Hybrid Quantum Machine Learning Model for Multi-class Classifier

Quantum machine learning has gained attention due to the computational capabilities of quantum computers in solving complex problems that are challenging for classical computers. To increase processing power and efficiency, it integrates conventional machine learning approaches with quantum computing. The proposed model provide a hybrid quantum multi-class classifier that utilises quantum properties like superposition and entanglement. The Proposed model utilizes a unitary operation on a single qubit for state preparation, demonstrated on the IBMQX platform, and implemented on a quantum simulator for classification tasks. The protocol designed a quantum circuit for multi-class classification which is feasible to handle multiple classes. The experimental study of proposed model on iris dataset shows a promising accuracy of 96.26%, indicating the effectiveness of the QMCC model. The result obtained through qubit measurements, showcasing the effectiveness of the proposed model.