Scholarlink

<p>Quantum computing has emerged as a transformative technology with the potential to address complex computational problems more efficiently than classical methods. In healthcare, drug discovery, and other complex datasets, Quantum Variational Circuits (QVCs) present the most promising techniques to analyze high-dimensional nonlinear data in a highly optimized manner. The proposed work focuses on choosing the best-fit encoding method that can be used in feature mapping circuits for QVC. Various QVC ansatz selections are iterated until the best fit is reached. From the results obtained, the QVC parameters are updated to optimize the model performance. By selecting the Pauli Feature map with different angle rotation and the EfficientSU2 method as QVC classifier, the cost value, accuracy, and processing time of the proposed algorithm are obtained on wine data as (0.5755, 94.44, 0.2624s), Heart data as (0.598, 81.81, 0.288s), HCV data as (0.58, 85.11, 0.363s) and Electric grid data as (0.65597.42, 0.586s). The comparative analysis is carried out by running the simulation on Local Quantum simulators and classical machines. Other performances were also analyzed to check the model’s performance. The proposed QVC algorithm is executed using IBM Qiskit Quantum Labs by extracting real backends, Quantum simulators <Emphasis FontCategory="NonProportional">IBMQ_qasm_simulator</Emphasis>, <Emphasis FontCategory="NonProportional">simulator_statevector</Emphasis>, and also on local machines.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Optimizing Quantum Variational Circuits for Enhanced Performance in Healthcare and Multidisciplinary Data Analysis

  • 期刊论文

  • 发表日期：

    2026年2月24日

查看全文
  • S. S. Kavitha,
  • Narasimha Kaulgud,
  • B. S. Sharmila

摘要

Quantum computing has emerged as a transformative technology with the potential to address complex computational problems more efficiently than classical methods. In healthcare, drug discovery, and other complex datasets, Quantum Variational Circuits (QVCs) present the most promising techniques to analyze high-dimensional nonlinear data in a highly optimized manner. The proposed work focuses on choosing the best-fit encoding method that can be used in feature mapping circuits for QVC. Various QVC ansatz selections are iterated until the best fit is reached. From the results obtained, the QVC parameters are updated to optimize the model performance. By selecting the Pauli Feature map with different angle rotation and the EfficientSU2 method as QVC classifier, the cost value, accuracy, and processing time of the proposed algorithm are obtained on wine data as (0.5755, 94.44, 0.2624s), Heart data as (0.598, 81.81, 0.288s), HCV data as (0.58, 85.11, 0.363s) and Electric grid data as (0.65597.42, 0.586s). The comparative analysis is carried out by running the simulation on Local Quantum simulators and classical machines. Other performances were also analyzed to check the model’s performance. The proposed QVC algorithm is executed using IBM Qiskit Quantum Labs by extracting real backends, Quantum simulators IBMQ_qasm_simulator, simulator_statevector, and also on local machines.