Multi-Objective Equilibrium Optimizer for Feature Selection in High-Dimensional English Speech Emotion Recognition

Speech emotion recognition(SER)uses acoustic analysis to find features for emotion recognition and examines variations in voice that are caused by emotions.The number of features acquired with acoustic analysis is extremely high,so we introduce a hybrid filter-wrapper feature selection algorithm based on an improved equilibrium optimizer for constructing an emotion recognition system.The proposed algorithm implements multi-objective emotion recognition with the minimum number of selected features and maximum accuracy.First,we use the information gain and Fisher Score to sort the features extracted from signals.Then,we employ a multi-objective ranking method to evaluate these features and assign different importance to them.Features with high rankings have a large probability of being selected.Finally,we propose a repair strategy to address the problem of duplicate solutions in multi-objective feature selection,which can improve the diversity of solutions and avoid falling into local traps.Using random forest and K-nearest neighbor classifiers,four English speech emotion datasets are employed to test the proposed algorithm(MBEO)as well as other multi-objective emotion identification techniques.The results illustrate that it performs well in inverted generational distance,hypervolume,Pareto solutions,and execution time,and MBEO is appropriate for high-dimensional English SER.

Quantum-Inspired Equilibrium Optimizer for Linear Antenna Array

With the rapid development of communication technology,the problem of antenna array optimization plays a crucial role.Among many types of antennas,line antenna arrays(LAA)are the most commonly applied,but the side lobe level(SLL)reduction is still a challenging problem.In the radiation process of the linear antenna array,the high side lobe level will interfere with the intensity of the antenna target radiation direction.Many conventional methods are ineffective in obtaining the maximumside lobe level in synthesis,and this paper proposed a quantum equilibrium optimizer(QEO)algorithm for line antenna arrays.Firstly,the linear antenna array model consists of an array element arrangement.Array factor(AF)can be expressed as the combination of array excitation amplitude and position in array space.Then,inspired by the powerful computing power of quantum computing,an improved quantum equilibrium optimizer combining quantum coding and quantum rotation gate strategy is proposed.Finally,the proposed quantum equilibrium optimizer is used to optimize the excitation amplitude of the array elements in the linear antenna array model by numerical simulation to minimize the interference of the side lobe level to the main lobe radiation.Six differentmetaheuristic algorithms are used to optimize the excitation amplitude in three different arrays of line antenna arrays,the experimental results indicated that the quantum equilibrium optimizer is more advantageous in obtaining the maximum side lobe level reduction.Compared with other metaheuristic optimization algorithms,the quantum equilibrium optimizer has advantages in terms of convergence speed and accuracy.

基于FCM和EO-SVM水轮机尾水管压力脉动特征识别

为有效识别水轮机尾水管压力脉动特征,提出了一种基于模糊C均值聚类、平衡优化器算法与支持向量机的识别方法。该方法首先采用平衡优化器算法优化SVM的惩罚因子和核函数以获得更好的SVM参数组合,构建EO-SVM识别模型以实现其在水轮机尾水管压力脉动特征识别中的应用。然后采用模糊C均值聚类算法将待分类的压力脉动特征进行初始聚类,将其分为四类,并依据聚类结果选择最靠近每类中心的样本作为EO-SVM模型的训练样本。将SVM和EO-SVM两种模型的识别分类结果进行比较,验证了所提EO-SVM模型的有效性。

An Enhanced Equilibrium Optimizer for Solving Optimization Tasks

The equilibrium optimizer(EO)represents a new,physics-inspired metaheuristic optimization approach that draws inspiration from the principles governing the control of volume-based mixing to achieve dynamic mass equilibrium.Despite its innovative foundation,the EO exhibits certain limitations,including imbalances between exploration and exploitation,the tendency to local optima,and the susceptibility to loss of population diversity.To alleviate these drawbacks,this paper introduces an improved EO that adopts three strategies:adaptive inertia weight,Cauchy mutation,and adaptive sine cosine mechanism,called SCEO.Firstly,a new update formula is conceived by incorporating an adaptive inertia weight to reach an appropriate balance between exploration and exploitation.Next,an adaptive sine cosine mechanism is embedded to boost the global exploratory capacity.Finally,the Cauchy mutation is utilized to prevent the loss of population diversity during searching.To validate the efficacy of the proposed SCEO,a comprehensive evaluation is conducted on 15 classical benchmark functions and the CEC2017 test suite.The outcomes are subsequently benchmarked against both the conventional EO,its variants,and other cutting-edge metaheuristic techniques.The comparisons reveal that the SCEO method provides significantly superior results against the standard EO and other competitors.In addition,the developed SCEO is implemented to deal with a mobile robot path planning(MRPP)task,and compared to some classical metaheuristic approaches.The analysis results demonstrate that the SCEO approach provides the best performance and is a prospective tool for MRPP.

Magnetic diagnostics layout design for CFETR plasma equilibrium reconstruction

Plasma equilibrium reconstruction provides essential information for tokamak operation and physical analysis.An extensive and reliable set of magnetic diagnostics is required to obtain accurate plasma equilibrium.This study designs and optimizes the magnetic diagnostics layout for the reconstruction of the equilibrium of the plasma according to the scientific objectives,engineering design parameters,and limitations of the Chinese Fusion Engineering Test Reactor(CFETR).Based on the CFETR discharge simulation,magnetic measurement data are employed to reconstruct consistent plasma equilibrium parameters,and magnetic diagnostics'number and position are optimized by truncated Singular value decomposition,verifying the redundancy reliability of the magnetic diagnostics layout design.This provides a design solution for the layout of the magnetic diagnostics system required to control the plasma equilibrium of CFETR,and the developed design and optimization method can provide effective support to design magnetic diagnostics systems for future magnetic confinement fusion devices.

Enhanced Hybrid Equilibrium Strategy in Fog-Cloud Computing Networks with Optimal Task Scheduling

More devices in the Intelligent Internet of Things(AIoT)result in an increased number of tasks that require low latency and real-time responsiveness,leading to an increased demand for computational resources.Cloud computing’s low-latency performance issues in AIoT scenarios have led researchers to explore fog computing as a complementary extension.However,the effective allocation of resources for task execution within fog environments,characterized by limitations and heterogeneity in computational resources,remains a formidable challenge.To tackle this challenge,in this study,we integrate fog computing and cloud computing.We begin by establishing a fog-cloud environment framework,followed by the formulation of a mathematical model for task scheduling.Lastly,we introduce an enhanced hybrid Equilibrium Optimizer(EHEO)tailored for AIoT task scheduling.The overarching objective is to decrease both the makespan and energy consumption of the fog-cloud system while accounting for task deadlines.The proposed EHEO method undergoes a thorough evaluation against multiple benchmark algorithms,encompassing metrics likemakespan,total energy consumption,success rate,and average waiting time.Comprehensive experimental results unequivocally demonstrate the superior performance of EHEO across all assessed metrics.Notably,in the most favorable conditions,EHEO significantly diminishes both the makespan and energy consumption by approximately 50%and 35.5%,respectively,compared to the secondbest performing approach,which affirms its efficacy in advancing the efficiency of AIoT task scheduling within fog-cloud networks.

EO-REEVMD-BILSTM的两阶段超短期风电功率预测

为提升风电功率的预测精度,提出一种基于平衡优化器优化算法的两阶段超短期风电功率预测方法。通过建立一种适用于风电功率预测的回归包络熵适应度目标模型,利用平衡优化器算法寻优VMD分解参数,实现对原始风电功率信号的合理分解,有效减小分解损失。基于BILSTM神经网络模型分别预测分解的模态分量,根据叠加各分量的预测结果获得初步风电预测功率序列,利用误差预测值纠正上一阶段预测结果。以土耳其某地区提供的风电功率数据作为实际算例,通过仿真实验与实测风电功率比较。结果表明:文中所提方法的RMSE与MAE仅为28.3781与17.4297,R^(2)为0.9986,明显低于BILSTM等单一预测模型与其他组合预测方法,验证了文中方法的有效性。

基于改进EO-BP神经网络的高压线损预测

针对高压线损预测精度不高的问题,提出一种基于均衡优化器(Equilibrium Optimizer,EO)和BP神经网络相结合的线损预测模型。首先,为了提高EO算法的寻优能力,利用多种混沌映射关系初始化种群,使种群多样性增加,全局搜索能力得到改善;同时,采用物竞天择概率跳脱策略改进EO算法,使模型依概率跳出局部最优而收敛于全局最优解。其次,采用改进的EO算法对BP神经网络的权值和偏置进行优化,进而改善BP神经网络的预测效果。最后,实验结果证明,所提线损预测模型相对于回归模型、BP神经网络模型、模拟退火算法优化BP神经网络模型和EO优化BP神经网络模型具有更高的预测精度。

Theoretical calculation of equilibrium Mg isotope fractionation between silicate melt and its vapor

Isotope fractionation during the evaporation of silicate melt and condensation of vapor has been widely used to explain various isotope signals observed in lunar soils, cosmic spherules, calcium-aluminum-rich inclu- sions, and bulk compositions of planetary materials. During evaporation and condensation, the equilibrium isotope fractionation factor （α） between high-temperature silicate melt and vapor is a fundamental parameter that can con- strain the melt＇s isotopic compositions. However, equilib- rium a is difficult to calibrate experimentally. Here we used Mg as an example and calculated equilibrium Mg isotope fractionation in MgSiO3 and Mg2SiO4 melt-vapor systems based on first-principles molecular dynamics and the high- temperature approximation of the Bigeleisen-Mayer equation. We found that, at 2500 K, 625Mg values in the MgSiO3 and Mg2SiO4 melts were 0.141 ±0.004 and 0.143 ±0.003‰ more positive than in their respective vapors. The corresponding 626Mg values were 0.270 ± 0.008 and 0.274 ± 0.006‰ more positive than in vapors, respectively. The general α - T equations describing the equilibrium Mg α in MgSiO3 and Mg2SiO4 melt-vapor systems were： αMg（l）-Mg（g） = 1 ＋ 5.264×10^5/T^2 （1/m - 1/m＇） and αmg（l）-Mg（g） = 1 ＋ 5.340×10^5/T^2 （1/m - 1/m＇）, respectively, Where m is the mass of light isotope, ^25Mg or ^26Mg. These results offer a necessary parameter for mechanistic under- standing of Mg isotope fractionation during evaporation and condensation that commonly occurs during the early stages of planetary formation and evolution.

THE OPTIMAL DEDUCTIBLE AND COVERAGE IN INSURANCE CONTRACTS AND EQUILIBRIUM RISK SHARING POLICIES

In this paper, we consider the optimal risk sharing problem between two parties in the insurance business: the insurer and the insured. The risk is allocated between the insurer and the insured by setting a deductible and coverage in the insurance contract. We obtain the optimal deductible and coverage by considering the expected product of the two parties' utilities of terminal wealth according to stochastic optimal control theory. An equilibrium policy is also derived for when there are both a deductible and coverage;this is done by modelling the problem as a stochastic game in a continuous-time framework. A numerical example is provided to illustrate the results of the paper.

基于EO优化SVM的农产品重金属超标概率预测

农产品中的重金属来源十分广泛,其与每一个来源都非简单的线性关系。支持向量机模型在非线性情况下表现良好,能比线性回归法达到更好的预测效果。以宜昌市详查农产品点位为研究对象,选择水稻农产品和土壤中重金属As、Cr、Pb、ph含量为自变量,以农产品中重金属镉是否超标为因变量,使用平衡优化器算法(EO)优化的支持向量机模型(SVM)来预测农产品镉是否超标并预测超标概率值。结果表明:使用改进的平衡优化器算法优化的支持向量机模型来预测农产品镉是否超标拥有更高的预测准确率。因此基于EO优化的SVM模型(EO_SVM)可作为一种农产品重金属超标概率预测的一种有效方法,为农产品重金属监管提供有效理论支持。

SCR脱硝系统的RBF条件积分滑模参数优化控制

针对选择性催化还原(SCR)脱硝系统在火电机组深度调峰下因系统特性随着机组负荷改变而难以控制的问题,提出基于径向基函数(RBF)的条件积分滑模优化控制方案,用条件积分滑模减少抖振与调节时间,用RBF实时逼近SCR脱硝系统特性改变下的未知扰动以提高系统鲁棒性。并提出一种纳什均衡量子粒子群寻优(NEQPSO)算法,以获得RBF条件积分滑模控制方案的最优参数,并在20%~100%的机组负荷下进行仿真实验。结果表明:优化后的RBF条件积分滑模控制与传统控制方案相比超调量降低50.26%、调节时间缩短13.55%,在干扰信号下超调量仅有1.50%,其响应速度更快、抗干扰能力更强、鲁棒性更好。

一种基于伪谱法的助推-补能跳跃滑翔轨迹优化方法

针对大气层边缘补能-跳跃滑翔运动,建立了一种助推-补能跳跃滑翔全程空间运动模型以及补能滑翔段无量纲运动方程。提出了一种基于Gauss伪谱法的动态分段串行优化策略,可对助推段俯仰程序角、补能-跳跃滑翔段飞行攻角、倾侧角以及补能时刻等轨迹控制变量进行求解,实现含连续/离散控制变量的轨迹优化一体化设计。分别对助推-补能跳跃滑翔和助推-拟平衡滑翔轨迹优化开展仿真,验证了针对补能-跳跃滑翔轨迹的分段串行优化策略的有效性,同时分析了相同助推规模和飞行器质量条件下,补能跳跃轨迹相较拟平衡滑翔轨迹在增大飞行时间、航程和机动过载能力上更具优势。

多品种电力市场交易下负荷聚合商投标策略及市场均衡分析

中国新型电力系统建设正面临灵活资源短缺等问题,亟须发挥负荷侧调节能力。随着电网与负荷双向交互越发频繁,更多负荷聚合商通过整合辖区灵活资源参与市场交易,导致以往由发电侧占主导的市场均衡被打破。为研究多主体负荷聚合商博弈策略,构建了能量-备用电力市场下负荷聚合商双层投标模型,并引入多场景描述非决策者投标不确定性对市场均衡的影响。通过强平稳算法(SSM)将多个双层模型转化为带均衡约束的均衡问题(EPEC)模型,并采用大M法、二进制展开法等线性化方法进行线性化。算例结果验证了模型及求解算法的合理性和有效性,表明基于EPEC模型的负荷聚合商最优投标策略更加契合实际市场规则,有助于系统优化负荷曲线,缓解灵活资源供需紧张。

基于可变生成概率和多差分柯西变异的均衡优化算法

针对标准均衡优化算法(EO)存在全局搜索和局部搜索的平衡能力不足以及易陷入局部最优的问题,提出了一种基于可变生成概率和多差分柯西变异的均衡优化算法(Variable generation probability and multi-difference Cauchy variation equilib-rium optimization algorithm,VDEO)。首先,结合Tent混沌映射增加初始化种群的多样性,为寻优提供基础;其次,引入可变的生成概率代替原始的固定值,使算法在迭代前期增加全局搜索能力,后期关注求解精度,以提升全局搜索和局部搜索的平衡能力;最后,融合多种差分策略和柯西变异帮助寻优过程跳出局部最优。针对包含单峰、多峰和固定维多峰在内的15个基准测试函数和CEC2022测试函数,将VDEO在多种维数下与EO,GWO,WOA,SCA,MFO,AOA,AVOA,BWO,AHA,POA这10个启发式算法进行仿真对比实验,并对基准测试函数的实验结果进行Wilcoxon秩和检验,实验结果表明,VDEO实现了更好的全局搜索和局部搜索的平衡,并具有更好的跳出局部最优的能力以及更高的收敛精度。

山区铁路桥隧工程关键节材要素均衡优化

为在经济可承受范围内提升山区铁路的节材性能,提出了一种基于NSGA-Ⅱ的关键节材要素双目标均衡优化方法。首先,以断面超挖、喷射混凝土类型选择、围岩变形预留、桩基扩孔、桩头超封5个桥隧工程关键节材要素为决策变量,以CO_(2)减排量最大、建造成本增加值最小为优化目标,构建山区铁路桥隧工程关键节材要素均衡优化模型;其次,采用带精英策略的非支配排序遗传算法(NSGA-Ⅱ)求出Pareto均衡解集;再次,耦合主客观元素组合的综合赋权法与TOPSIS法对Pareto均衡解集进行科学决策,得到考虑决策者偏好的关键节材要素最佳组合,并分析决策者偏好对最佳组合的影响;最后,以某山区铁路工程某标段为例,系统地验证了该方法的科学性及适用性。研究结果表明:与优化前相比,最佳组合能实现CO_(2)减排12.622万t,对应建造成本增加了24.833万元,优化效率达到50.826%。

不确定环境下收费与信息对路径选择行为影响的实验研究

在不确定环境下考虑信息发布与拥挤收费两种措施,基于交通网络均衡,推导了两路径简单路网的最优收费模型,并推广至一般路网。基于两路径路网设计逐日路径选择行为实验,分析了两种措施对路径选择行为的影响。结果表明:完美信息与收费的实施均能减少流量波动,单独实施收费的效果最佳,但只有两种措施相结合时,路网流量趋于用户均衡的趋势最稳定;完美信息会增加路径切换行为,而收费可有效抑制大幅的路径切换;无收费时路径切换往往会造成出行成本增加,而收费时则相反;收费与信息结合时的出行时间比两种措施单独实施时小。

开放经济动态随机一般均衡模型下最优货币政策和货币状况指数研究——基于1992—2022年中国数据的理论和实证分析

本文构建开放经济下的新凯恩斯动态随机一般均衡模型,模拟显示在外部冲击下,利率、汇率和最终目标高度相关。以理论模型为基础对最优货币政策进行探究,发现其政策权重受消费者、生产者和中央银行的行为等模型参数的影响。进一步构建货币状况指数(MCI),其权重不仅取决于商品市场、货币市场和利率平价参数等的变化,还依赖于最优货币政策参数的变化。根据1992—2022年数据进行实证研究发现,最优货币政策参数为1.1823,意味着我国央行的货币政策是逆周期操作的,且赋予经济增长以更大的权重;估计出MCI的权重为0.7867,意味着实际利率上升1%相当于实际汇率下降0.79%,实际利率变动的影响弱于实际汇率。最后本文研究表明货币状况指数可以作为宏观经济目标变动的先行指标。

一种连续型不确定性复杂系统博弈理论及算法研究

当前对于不确定性复杂系统博弈的研究,通常情况下有关策略集是离散的,而非连续和随机的。而在复杂经济社会系统中,常常会遇到连续性随机博弈问题,以及系统中数据的确权问题。在此背景下,提出了一种随机博弈的概念,给出连续策略集下N人非合作随机博弈模型均衡解存在性定理,以及复杂信息系统随机博弈模型的构建及其纳什均衡解算法。给出连续策略下不确定性N人非合作随机博弈概念,建立以局中人的最大收益为目标函数的N人非合作随机博弈模型,提出了均衡解的存在性定理;构建了Wasserstein模糊集,之后融合分布鲁棒优化方法以及投资组合优化方法将该模型转化为有限凸规划,并运用遗传算法求解局中人的近似混合策略,最后构建了基于回归分析的纳什均衡求解算法并将纳什均衡解归一化进行确权。实证分析表明,所构建的理论与算法是有效可行的。

路径交叉测绘任务规划问题

不同于传统多旅行商问题,小型飞机测绘任务规划问题的每个测绘目标需要测绘多个测绘载荷,同时多次测绘间要有时间间隔,称之为路径交叉的多旅行商路径规划问题。针对点目标测绘任务场景,将最少飞机数量的求解目标转化为求解最短航行路径。在采用遗传算法求解最短路径的基础上,结合探测载荷约束、探测任务时长约束等条件,进一步规划出最优的调度方案。针对点目标和区域目标测绘任务规划问题,考虑各机场测绘任务工作量的均衡,定义测绘工作量指标为每个机场完成的测绘目标点和目标道路的数目,求解调度策略和飞机数量。在此基础上求解均衡性,使3个机场探测的目标点和目标道路数量相当。结果表明,所提方案兼顾了测绘代价与任务分配的均衡性。