Particle Swarm Optimization (PSO) is a popular algorithm used for optimization problems in various domains. However, the PSO algorithm suffers from some limitations, e.g., premature convergence and slow convergence rate. In this paper, we propose a new algorithm called Quantum Rotation Gate Particle Swarm Optimization (QPSO), which is based on the quantum rotation gate to address these shortcomings. The proposed QPSO algorithm aims to improve the optimization capability of the original PSO. We applied QPSO to optimize the neural network architecture for numerical anomaly detection on the self-noise aerodynamic wind tunnel test data set. Good results are achieved and the effectiveness of the proposed method is demonstrated. Compared to the original PSO algorithm, QPSO outperforms it in terms of convergence rate and accuracy.
Particle Swarm Optimization (PSO) is a popular algorithm used for optimization problems in various domains. However, the PSO algorithm suffers from some limitations, e.g., premature convergence and slow convergence rate. In this paper, we propose a new algorithm called Quantum Rotation Gate Particle Swarm Optimization (QPSO), which is based on the quantum rotation gate to address these shortcomings. The proposed QPSO algorithm aims to improve the optimization capability of the original PSO. We applied QPSO to optimize the neural network architecture for numerical anomaly detection on the self-noise aerodynamic wind tunnel test data set. Good results are achieved and the effectiveness of the proposed method is demonstrated. Compared to the original PSO algorithm, QPSO outperforms it in terms of convergence rate and accuracy.
In this work, the Particle Swarm Optimization (PSO) algorithm has been used to train various Variational Quantum Circuits (VQCs). This approach is motivated by the fact that commonly used gradient-based optimization methods can suffer from the barren plateaus problem. PSO is a stochastic optimization technique inspired by the collective behavior of a swarm of birds. The dimension of the swarm, the number of iterations of the algorithm, and the number of trainable parameters can be set. In this study, PSO has been used to train the entire structure of VQCs, allowing it to select which quantum gates to apply, the target qubits, and the rotation angle, in case a rotation is chosen. The algorithm is restricted to choosing from four types of gates: Rx, Ry, Rz, and cNOT. The proposed optimization approach has been tested on various datasets of the MedMNIST, which is a collection of biomedical image datasets designed for image classification tasks. Performance has been compared with the results achieved by classical stochastic gradient descent applied to a predefined VQC. The results show that the PSO can achieve comparable or even better classification accuracy across multiple datasets, despite the PSO using a lower number of quantum gates than the VQC used with gradient descent optimization.
: In financial systems, abnormal activities in securities transactions pose significant risks due to which there is a requirement of smart and accurate anomaly detection procedures. The presented work in this paper employs a Particle Swarm Optimization (PSO)-tuned Quantum Neural Network (QNN) for anomaly detection. The QNN proposed here is designed using variational quantum circuits to process PSO optimized features and utilises the quantum advantage in neural computing. Performance of the proposed system is evaluated by executing on the IEEE-CIS Fraud Detection dataset. QNN’s weights and biases are optimized by using PSO to enhance capability of the designed network to escape from local optima and to enhance prediction accuracy. The results presented demonstrate the performance of proposed PSO-QNN model and these outcomes are compared with the conventional algorithms- Long Short-Term Memory (LSTM), k-Nearest Neighbours (KNN), and Support Vector Machines (SVM). The work proposed in this paper achieves a precision of 98.55% with improved sensitivity, specificity, recall and attained an impressive Matthews Correlation Coefficient (MCC) of 0.94. As presented in the results, reduced values of FP and FN rates, showcase the reliability of the proposed PSO-QNN model for anomaly detection. For anomaly detection, adopting QNN and optimising it by PSO, represents a significant advancement and this offers a progressive and functional solution for securities transactions in financial systems.
This paper proposes a new quantum particle swarm optimization algorithm with local attracting (LAQPSO), which is based on quantum-inspired evolutionary algorithm (QEA) and particle swarm optimization algorithm (PSO).In the proposed LAQPSO, a novel quantum bit expression mechanism called quantum angle is employed to encode the solution onto particle, and a new local attractor is proposed to determine the rotation angle of quantum rotation gate automatically.During the process of seeking the global solution, the magnitude of rotation angle is adjusted by an important parameter called contraction coefficient, which can quantitatively determine the tradeoff between exploration ability and exploitation ability.The simulation results for different contraction coefficients are helpful for selecting the key parameter.A set of benchmark functions are used to evaluate the performance of LAQPSO, QEA and QBPSO, and the results show that the proposed algorithm has a fast convergence rate and can effectively avoid premature convergence.
Abstract This paper introduces a rotational quantum particle swarm optimizer (RQPSO) that updates particles via quantum rotation–gate dynamics on a compact phase representation. Real-valued amplitudes decoded from phases are mapped feasibly by construction into the decision space, removing the need for bound repair. Lightweight π -flip perturbations and brief stagnation-triggered reseeding sustain diversity, and a short local polish consolidates the incumbent near termination. RQPSO is benchmarked against Particle Swarm Optimization (PSO), Quantum Particle Swarm Optimization (QPSO), Grey Wolf Optimizer (GWO), Mayfly Algorithm (MA), self-adaptive Differential Evolution (jDE), and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) under a common protocol of 3000 function evaluations with 30 independent runs per problem. Reporting uses median [interquartile range (IQR)] as the primary statistic with Friedman/Nemenyi global tests and Holm-corrected Wilcoxon pairwise tests; effect sizes are summarized by Cliff’s δ . Experiments cover 23 classical functions and 10 CEC-2019 functions. On the classical suite, RQPSO attains the best or tied-best median on a majority of functions and achieves a leading global rank under the fixed budget. On CEC-2019, it records three best medians (including one tie) and a top mean rank; post-hoc tests show significant gains over MA and jDE and broadly comparable performance to PSO, QPSO, GWO, and CMA-ES. A combined economic–emission dispatch (CEED) study on a six-unit system with cubic cost and emission models further demonstrates budget-efficient performance. The RQPSO attains the lowest mean operating cost and the smallest dispersion at all loads versus PSO and QPSO. A percentage-recovery repair enforces generator limits and power balance without penalty functions by proportionally rescaling outputs. Together, the rotation-gate updates, feasibility-preserving decoding, and proportional repair provide a robust alternative to classical swarms for both benchmark and power-system optimization under tight evaluation budgets. The source code of RQPSO is publicly available at: (https://github.com/Naagdant/rotational-quantum-pso)
In view of the shortcomings of particle swarm optimization such as premature convergence to local optimization, particle swarm optimization algorithm based on quantum gate and particle swarm optimization algorithm based on quantum behavior are studied in this paper. The first algorithm uses the random observation method of quantum bit coding particles to simulate quantum particle collapse for generating a population and uses the quantum rotating gate to generate a new population. The adaptive mutation operator is used for ensuring the diversity of the population, effectively reducing the impact of local optimization; therefore, the robustness of the algorithm is improved. The second algorithm uses the probability density function of quantum computation to make the particles jump out of the local extreme points and fulfils the global search, which is more suitable for continuous optimization. The results of computational experiments show that both the two particle swarm optimization algorithms based on quantum technology have a good global convergence.
In the field of finding ground and excited states, where quantum computation holds significant promise, using a variational quantum eigensolver (VQE) is a typical approach. However, the success of this approach is vulnerable to two factors: classical optimization for the ansätz parameters and noise from quantum devices. To address these challenges, we adopted particle swarm optimization (PSO) based on swarm intelligence for VQE and presented its performance. Furthermore, a modified PSO, gradient-based adaptive quantum-behaved particle swarm optimization (GAQPSO), is proposed. This algorithm adaptively upgrades parameters based on gradients or shared information within the swarm, enhancing optimization capability and noise resistance. We tested this algorithm using VQE simulations on several molecular systems with different geometries and found that, when using random initial values, GAQPSO achieves accurate results even in the presence of noise, whereas traditional PSO, QPSO, COBYLA, and gradient-based algorithms (GD and L-BFGS-B) fail. The GAQPSO algorithm presents a novel approach to optimizing VQE, demonstrating superior performance in parameter optimization and noise resilience compared to traditional optimization algorithms. This effectively advances the process of achieving a quantum advantage for quantum computing in quantum chemistry problems.