Quantum Particle Swarm Optimization with Deep Learning-Based Arabic Tweets Sentiment Analysis

Sentiment Analysis(SA),a Machine Learning(ML)technique,is often applied in the literature.The SA technique is specifically applied to the data collected from social media sites.The research studies conducted earlier upon the SA of the tweets were mostly aimed at automating the feature extraction process.In this background,the current study introduces a novel method called Quantum Particle Swarm Optimization with Deep Learning-Based Sentiment Analysis on Arabic Tweets(QPSODL-SAAT).The presented QPSODL-SAAT model determines and classifies the sentiments of the tweets written in Arabic.Initially,the data pre-processing is performed to convert the raw tweets into a useful format.Then,the word2vec model is applied to generate the feature vectors.The Bidirectional Gated Recurrent Unit(BiGRU)classifier is utilized to identify and classify the sentiments.Finally,the QPSO algorithm is exploited for the optimal finetuning of the hyperparameters involved in the BiGRU model.The proposed QPSODL-SAAT model was experimentally validated using the standard datasets.An extensive comparative analysis was conducted,and the proposed model achieved a maximum accuracy of 98.35%.The outcomes confirmed the supremacy of the proposed QPSODL-SAAT model over the rest of the approaches,such as the Surface Features(SF),Generic Embeddings(GE),Arabic Sentiment Embeddings constructed using the Hybrid(ASEH)model and the Bidirectional Encoder Representations from Transformers(BERT)model.

Parameters estimation online for Lorenz system by a novel quantum-behaved particle swarm optimization

This paper proposes a novel quantum-behaved particle swarm optimization （NQPSO） for the estimation of chaos＇ unknown parameters by transforming them into nonlinear functions＇ optimization. By means of the techniques in the following three aspects： contracting the searching space self-adaptively; boundaries restriction strategy; substituting the particles＇ convex combination for their centre of mass, this paper achieves a quite effective search mechanism with fine equilibrium between exploitation and exploration. Details of applying the proposed method and other methods into Lorenz systems are given, and experiments done show that NQPSO has better adaptability, dependability and robustness. It is a successful approach in unknown parameter estimation online especially in the cases with white noises.

Integration of uniform design and quantum-behaved particle swarm optimization to the robust design for a railway vehicle suspension system under different wheel conicities and wheel rolling radii

This paper proposes a systematic method, integrating the uniform design (UD) of experiments and quantum-behaved particle swarm optimization (QPSO), to solve the problem of a robust design for a railway vehicle suspension system. Based on the new nonlinear creep model derived from combining Hertz contact theory, Kalker's linear theory and a heuristic nonlinear creep model, the modeling and dynamic analysis of a 24 degree-of-freedom railway vehicle system were investigated. The Lyapunov indirect method was used to examine the effects of suspension parameters, wheel conicities and wheel rolling radii on critical hunting speeds. Generally, the critical hunting speeds of a vehicle system resulting from worn wheels with different wheel rolling radii are lower than those of a vehicle system having original wheels without different wheel rolling radii. Because of worn wheels, the critical hunting speed of a running railway vehicle substantially declines over the long term. For safety reasons, it is necessary to design the suspension system parameters to increase the robustness of the system and decrease the sensitive of wheel noises. By applying UD and QPSO, the nominal-the-best signal-to-noise ratio of the system was increased from -48.17 to -34.05 dB. The rate of improvement was 29.31%. This study has demonstrated that the integration of UD and QPSO can successfully reveal the optimal solution of suspension parameters for solving the robust design problem of a railway vehicle suspension system.

Improved Quantum-Behaved Particle Swarm Optimization

To enhance the performance of quantum-behaved PSO, some improvements are proposed. First, an encoding method based on the Bloch sphere is presented. In this method, each particle carries three groups of Bloch coordinates of qubits, and these coordinates are actually the approximate solutions. The particles are updated by rotating qubits about an axis on the Bloch sphere, which can simultaneously adjust two parameters of qubits, and can automatically achieve the best matching of two adjustments. The optimization process is employed in the n-dimensional space [-1, 1]n, so this approach fits to many optimization problems. The experimental results show that this algorithm is superior to the original quantum-behaved PSO.

Multiobjective optimal dispatch of microgrid based on analytic hierarchy process and quantum particle swarm optimization

Owing to the rapid development of microgrids(MGs)and growing applications of renewable energy resources,multiobjective optimal dispatch of MGs need to be studied in detail.In this study,a multiobjective optimal dispatch model is developed for a standalone MG composed of wind turbines,photovoltaics,diesel engine unit,load,and battery energy storage system.The economic cost,environmental concerns,and power supply consistency are expressed via subobjectives with varying priorities.Then,the analytic hierarchy process algorithm is employed to reasonably specify the weight coefficients of the subobjectives.The quantum particle swarm optimization algorithm is thereafter employed as a solution to achieve optimal dispatch of the MG.Finally,the validity of the proposed model and solution methodology are con firmed by case studies.This study provides refere nee for mathematical model of multiojective optimizati on of MG and can be widely used in current research field.

Chaos quantum particle swarm optimization for reactive power optimization considering voltage stability

The reactive power optimization considering voltage stability is an effective method to improve voltage stablity margin and decrease network losses,but it is a complex combinatorial optimization problem involving nonlinear functions having multiple local minima and nonlinear and discontinuous constraints. To deal with the problem,quantum particle swarm optimization (QPSO) is firstly introduced in this paper,and according to QPSO,chaotic quantum particle swarm optimization (CQPSO) is presented,which makes use of the randomness,regularity and ergodicity of chaotic variables to improve the quantum particle swarm optimization algorithm. When the swarm is trapped in local minima,a smaller searching space chaos optimization is used to guide the swarm jumping out the local minima. So it can avoid the premature phenomenon and to trap in a local minima of QPSO. The feasibility and efficiency of the proposed algorithm are verified by the results of calculation and simulation for IEEE 14-buses and IEEE 30-buses systems.

Quantum Particle Swarm Optimization Based Convolutional Neural Network for Handwritten Script Recognition

Even though several advances have been made in recent years,handwritten script recognition is still a challenging task in the pattern recognition domain.This field has gained much interest lately due to its diverse application potentials.Nowadays,different methods are available for automatic script recognition.Among most of the reported script recognition techniques,deep neural networks have achieved impressive results and outperformed the classical machine learning algorithms.However,the process of designing such networks right from scratch intuitively appears to incur a significant amount of trial and error,which renders them unfeasible.This approach often requires manual intervention with domain expertise which consumes substantial time and computational resources.To alleviate this shortcoming,this paper proposes a new neural architecture search approach based on meta-heuristic quantum particle swarm optimization(QPSO),which is capable of automatically evolving the meaningful convolutional neural network(CNN)topologies.The computational experiments have been conducted on eight different datasets belonging to three popular Indic scripts,namely Bangla,Devanagari,and Dogri,consisting of handwritten characters and digits.Empirically,the results imply that the proposed QPSO-CNN algorithm outperforms the classical and state-of-the-art methods with faster prediction and higher accuracy.

Damping Controller Based Quantum Particle Swarm Optimization for VSC HVDC to Improve Power System Stability

The use of the supplementary controllers of a High Voltage Direct Current (HVDC) based on Voltage Source Converter (VSC) to damp low Frequency oscillations in a weakly connected system is surveyed. Also, singular value decomposition (SVD)-based approach is used to analyze and assess the controllability of the poorly damped electromechanical modes by VSC-HVDC different control channels. The problem of supplementary damping controller based VSC-HVDC system is formulated as an optimization problem according to the time domain-based objective function which is solved using quantum-behaved particle swarm optimization (QPSO). Individual designs of the HVDC controllers using QPSO method are evaluated. The effectiveness of the proposed controllers on damping low frequency oscillations is checked through eigenvalue analysis and non-linear time simulation under various disturbance conditions over a wide range of loading.

Quantum-Inspired Particle Swarm Optimization Algorithm Encoded by Probability Amplitudes of Multi-Qubits

To enhance the optimization ability of particle swarm algorithm, a novel quantum-inspired particle swarm optimization algorithm is proposed. In this method, the particles are encoded by the probability amplitudes of the basic states of the multi-qubits system. The rotation angles of multi-qubits are determined based on the local optimum particle and the global optimal particle, and the multi-qubits rotation gates are employed to update the particles. At each of iteration, updating any qubit can lead to updating all probability amplitudes of the corresponding particle. The experimental results of some benchmark functions optimization show that, although its single step iteration consumes long time, the optimization ability of the proposed method is significantly higher than other similar algorithms.

Quantum particle swarm optimization for micro-grid system with consideration of consumer satisfaction and benefit of generation side

Considering comprehensive benefit of micro-grid system and consumers,we establish a mathematical model with the goal of the maximum consumer satisfaction and the maximum benefit of power generation side in the view of energy management.An improved multi-objective local mutation adaptive quantum particle swarm optimization(MO-LM-AQPSO)algorithm is adopted to obtain the Pareto frontier of consumer satisfaction and the benefit of power generation side.The optimal solution of the non-dominant solution is selected with introducing the power shortage and power loss to maximize the benefit of power generation side,and its reasonableness is verified by numerical simulation.Then,translational load and time-of-use electricity price incentive mechanism are considered and reasonable peak-valley price ratio is adopted to guide users to actively participate in demand response.The simulation results show that the reasonable incentive mechanism increases the benefit of power generation side and improves the consumer satisfaction.Also the mechanism maximizes the utilization of renewable energy and effectively reduces the operation cost of the battery.

钻孔瞬变电磁法扫描探测RCQPSO-LMO组合算法2.5D反演

利用钻孔进行超前探测地质构造及含水体是地下开挖工程中的常规手段,如何利用这些钻孔进行钻孔瞬变电磁法扫描探测,从而实现钻孔孔壁外围地质异常体的精细探测,对实现地下工程地质透明化具有重要的指导意义.本文提出钻孔瞬变电磁法扫描探测2.5D反演的数据解译方法,首先针对随机性反演算法时效性低,易陷入局部最优解,而确定性反演算法依赖初始模型的问题,提出了组合策略的量子粒子群优化算法用来随机搜索最优初始模型.在此基础上,利用Levenberg-Marquarat方法求解Occam反演的目标函数,形成了RCQPSO-LMO组合算法进行2.5D反演,通过对比组合算法和单一算法,验证了组合算法具有更精确的反演结果.其次结合屏蔽条件下扫描探测,对比分析了有无屏蔽的2.5D反演结果,通过设定屏蔽系数对非探测方向信号进行部分压制,可以较好地解决钻孔径向扫描探测中对非探测方向信号部分屏蔽下的反演及成像.最后建立三组理论模型进行组合算法2.5D反演,结果表明:组合算法反演结果与理论模型的一致性较好,对低阻异常体的反演精度较高,验证了组合算法对钻孔孔壁外围低阻异常体具有较高的反演精度和分辨能力.

基于IQPSO-EKF的多传感器融合姿态测量方法研究

为解决自动化竖井掘进设备的定位调姿精度对竖井、孔桩挖掘效率与质量的影响,提出了一种基于改进量子粒子群(IQPSO)-扩展卡尔曼滤波(EKF)的姿态测量算法,以提高微机电系统(MEMS)传感器测量精度。首先,对MEMS传感器数据进行了预处理(除噪、滤波、校准等);然后,参考现有飞行器的坐标系,建立了姿态解算模型,通过姿态角数学模型及运动学分析,构建了EFK状态方程,针对EKF方法参数估计不准确的问题,以分段混沌映射优化初始种群,引入平均位置最优值来避免陷入局部最优的IQPSO-EFK算法,优化EKF的系统、测量噪声的协方差参数;最后,对改进算法和三组姿态误差估计进行了对比实验。研究结果表明:对比三种典型目标函数,IQPSO-EFK相较于普通粒子群算法(QPSO-EFK)具有更强的寻优能力与收敛精度;对比三组旋转速度姿态测量误差,基于IQPSO-EKF算法的姿态测量方法在测量误差时比真实测量误差减少了约86.3%,比扩展卡尔曼滤波减少了约68.7%,比普通粒子群算法减少了约28.2%,证明该算法有效地提高了MEMS传感器测量精度。

ACCQPSO:一种改进的量子粒子群优化算法及其应用

针对量子粒子群优化算法前期易陷入局部极值点、后期寻优精度不高等问题,文章提出一种自适应交叉算子的混沌量子粒子群优化算法,并将其应用于BP神经网络超参数寻优。首先,利用Logistics映射初始种群为混沌序列进行最优解搜索,增强初始种群的随机性与遍历性,提高算法寻优能力;然后,通过纵向交叉操作进行种群中个体的信息交换,并引入自适应交叉概率公式,增加种群多样性,提高算法的寻优精度;最后,在实验中,一方面,选取8个函数在高低两个维度进行验证,同时进行Wilcoxon秩和检验分析以及消融实验,验证该算法相较其他算法的有效性;另一方面,通过算法优化BP神经网络应用到网络安全态势预测任务中,实验结果表明该算法收敛速度相较于对比算法有大幅度提升。

基于IQPSO-GA优化ANFIS模型的服务器故障预警方法

针对服务器底层部分业务类硬件故障对系统稳定运行的影响,提出一种改进的量子行为粒子群优化(IQPSO)与遗传算法(GA)相结合的混合元启发式优化算法对自适应神经模糊推理系统(ANFIS)参数进行训练,以获得更准确的ANFIS规则进行硬件故障预警的方法;首先,通过分析服务器业务与硬件相关参数之间的映射关系,通过采集的数据集对ANFIS模型进行训练构造预测模型;其次,考虑ANFIS在梯度计算过程中存在容易陷入局部最优值的问题,设计了一种IQPSO算法结合GA中的交叉和变异算子操作混合元启发算法全局搜索ANFIS规则参数;最后,通过一组后处理样本数据集对所提方法有效性和稳定性进行了检验;实验结果表明,该方法可有效预警服务器硬件故障,基于所提混合元启发优化算法获得的ANFIS模型具备更快的收敛速度和更高的全局搜索精度,与传统ANFIS模型相比泛化精度提高了47%以上。

A novel mapping algorithm for three-dimensional network on chip based on quantum-behaved particle swarm optimization

Mapping of three-dimensional network on chip is a key problem in the research of three-dimensional network on chip. The quality of the mapping algorithm used di- rectly affects the communication efficiency between IP cores and plays an important role in the optimization of power consumption and throughput of the whole chip. In this paper, ba- sic concepts and related work of three-dimensional network on chip are introduced. Quantum-behaved particle swarm op- timization algorithm is applied to the mapping problem of three-dimensional network on chip for the first time. Sim- ulation results show that the mapping algorithm based on quantum-behaved particle swarm algorithm has faster con- vergence speed with much better optimization performance compared with the mapping algorithm based on particle swarm algorithm. It also can effectively reduce the power consumption of mapping of three-dimensional network on chip.

基于QPSO LSTM模型的锂电池剩余容量预测

为克服锂离子电池容量预测精度低的问题,提出了一种量子粒子群改进长短期记忆神经网络(QPSO LSTM)的电池容量预测技术。分析了量子粒子群改进(QPSO)和长短期记忆神经网络(LSTM)算法的基本原理,利用QPSO算法对LSTM模型神经元个数、学习率等主要超参数进行寻优,解决长时序数据预测精度差和预测模型超参数难以确定的问题,构建了QPSO LSTM模型。最后,以NASA电池为分析对象,分别采用QPSO LSTM、PSO LSTM、LSTM和GA BP这4种预测模型对2种不同型号的电池进行剩余容量预测,预测结果表明,QPSO LSTM模型预测精度高,误差在1.5%范围内,为电池剩余容量的预测提供了一种有效的方法。

Quantum control based on three forms of Lyapunov functions

This paper introduces the quantum control of Lyapunov functions based on the state distance, the mean of imaginary quantities and state errors.In this paper, the specific control laws under the three forms are given.Stability is analyzed by the La Salle invariance principle and the numerical simulation is carried out in a 2D test system.The calculation process for the Lyapunov function is based on a combination of the average of virtual mechanical quantities, the particle swarm algorithm and a simulated annealing algorithm.Finally, a unified form of the control laws under the three forms is given.

Optimal operation of Internet Data Center with PV and energy storage type of UPS clusters

With the development of green data centers,a large number of Uninterruptible Power Supply(UPS)resources in Internet Data Center(IDC)are becoming idle assets owing to their low utilization rate.The revitalization of these idle UPS resources is an urgent problem that must be addressed.Based on the energy storage type of the UPS(EUPS)and using renewable sources,a solution for IDCs is proposed in this study.Subsequently,an EUPS cluster classification method based on the concept of shared mechanism niche(CSMN)was proposed to effectively solve the EUPS control problem.Accordingly,the classified EUPS aggregation unit was used to determine the optimal operation of the IDC.An IDC cost minimization optimization model was established,and the Quantum Particle Swarm Optimization(QPSO)algorithm was adopted.Finally,the economy and effectiveness of the three-tier optimization framework and model were verified through three case studies.

基于QPSO改进LSTM发动机怠速预测的FPID控制

以北京现代伊兰特G4GD发动机为试验台,将电控系统故障作为实验变量,测得规定时间内双传感器组合发生故障时的发动机怠速,并选原车ECU较难控制的6种组合怠速故障进行分析。基于量子粒子群算法(QPSO)对长短时记忆神经网络(LSTM)隐含层节点、训练次数与学习率进行寻优预测,将预测结果与多种神经网络进行对比,并通过均方根误差(RMSE)评价指标进行判断。使用Origin数据拟合将预测输出结果进行数值拟合,之后输入Matlab中使用Simulink搭建控制单元模型,由模糊常量-积分-微分(FPID)控制器对输出结果进行怠速控制。结果表明:基于量子粒子群算法改进的长短时记忆神经网络预测效果最好;模糊常量-积分-微分控制器对怠速的控制可有效缩短电子控制单元(ECU)的控制时间,无超调,且可有效调节至规定怠速。

基于QPSO-SVR算法的SF_(6)断路器触头烧蚀状态评估

高压SF6断路器弧触头的接触电阻和质量损失预测在断路器状态评估中起着重要作用。该文提出了一种基于量子粒子群优化和支持向量回归(quantum particle swarms optimization and support vector regression,QPSO-SVR)的方法,能够有效预测断路器弧触头在不同电弧电流条件下的接触电阻增量和质量损失,并结合实验数据获得了SVR算法的最佳训练参数。将该文方法与其他预测方法进行比较,QPSO-SVR方法对不同电弧电流条件下的实验数据表现出良好的预测能力。其中,对于接触电阻增量的预测相对误差为3.023%,而对于质量损失的预测相对误差为4.61%,均表现出较好的鲁棒性。最后将QPSO-SVR预测得到的质量损失和接触电阻增量以及监测到的累积电弧能量进行模糊逻辑推理,构建了基于QPSO-SVR算法的触头烧蚀状态评估系统,将触头烧蚀状态分为O级烧蚀、Ⅰ级烧蚀、Ⅱ级烧蚀、Ⅲ级烧蚀4等级,可为高压SF6断路器检修提供参考。