Improvements in seismic event locations in a deep western U.S. coal mine using tomographic velocity models and an evolutionary search algorithm

Methods of improving seismic event locations were investigated as part of a research study aimed at reducing ground control safety hazards. Seismic event waveforms collected with a 23-station three-dimensional sensor array during longwall coal mining provide the data set used in the analyses. A spatially variable seismic velocity model is constructed using seismic event sources in a passive tomographic method. The resulting three-dimensional velocity model is used to relocate seismic event positions. An evolutionary optimization algorithm is implemented and used in both the velocity model development and in seeking improved event location solutions. Results obtained using the different velocity models are compared. The combination of the tomographic velocity model development and evolutionary search algorithm provides improvement to the event locations.

Graphical model construction based on evolutionary algorithms

Using Bayesian networks to model promising solutions from the current population of the evolutionary algorithms can ensure efficiency and intelligence search for the optimum. However, to construct a Bayesian network that fits a given dataset is a NP-hard problem, and it also needs consuming mass computational resources. This paper develops a methodology for constructing a graphical model based on Bayesian Dirichlet metric. Our approach is derived from a set of propositions and theorems by researching the local metric relationship of networks matching dataset. This paper presents the algorithm to construct a tree model from a set of potential solutions using above approach. This method is important not only for evolutionary algorithms based on graphical models, but also for machine learning and data mining. The experimental results show that the exact theoretical results and the approximations match very well.

A Generic Design Model for Evolutionary Algorithms

A generic design model for evolutionary algorithms is proposed in this paper. The model, which was described by UML in details, focuses on the key concepts and mechanisms in evolutionary algorithms. The model not only achieves separation of concerns and encapsulation of implementations by classification and abstraction of those concepts, it also has a flexible architecture due to the application of design patterns. As a result, the model is reusable, extendible, easy to understand, easy to use, and easy to test. A large number of experiments applying the model to solve many different problems adequately illustrate the generality and effec-tivity of the model.

Financial Data Modeling by Using Asynchronous Parallel Evolutionary Algorithms

In this paper, the high-level knowledge of financial data modeled by ordinary differential equations (ODEs) is discovered in dynamic data by using an asynchronous parallel evolutionary modeling algorithm (APHEMA). A numerical example of Nasdaq index analysis is used to demonstrate the potential of APHEMA. The results show that the dynamic models automatically discovered in dynamic data by computer can be used to predict the financial trends.

Automatic Evolutionary Modeling by the Lattice-Boltzmann Method

The Lattice-Boltzmann method is an effective tool for solving fluid mechanics problems, but there isn't still a good scheme to determinate some parameters in Boltzmann equations. In this paper, a technique using evolutionary algorithm to automatically model Boltzmann equations is introduced. Numerical simulation shows that the designed scheme is fast and efficient.

Modeling of Canonical Switching Cell Converter Using Genetic Algorithm

The working of Canonical switching cell(CSC)converter was studied and its equivalent circuit during ON and OFF states were obtained.State space model of CSC converter in ON and OFF states were developed using the Kirchhoff laws.The state space matrices were used to construct the transfer functions of ON&OFF states.The step response of the converter was simulated using MATLAB.The step response curve was obtained using different values of circuit components(L,C1,C2 and RL)and optimized.The characteristic parameters such as rise time,overshoot,settling time,steady state error and stability were determined using the step response curve.The response curve shows that there is no overshoot;the rise time and settling time are very low as expected for a converter and its stability is very high but the amplitude is very.The circuit was tuned to attain the expected amplitude using PID controller with the help of Genetic algorithm.The excellent results of circuits’characteristic parameters are very useful guideline for constructing such CSC converters for DC-DC conversions.The circuit characteristic parameters are useful in constructing such CSC converters for DCDC conversions in driving solar energy using solar panel.

A Novel Quantum - inspired Multi - Objective Evolutionary Algorithm Based on Cloud Theory

In the previous papers,Quantum-inspired multi-objective evolutionary algorithm(QMEA) was proved to be better than conventional genetic algorithms for multi-objective optimization problem.To improve the quality of the non-dominated set as well as the diversity of population in multi-objective problems,in this paper,a Novel Cloud -based quantum -inspired multi-objective evolutionary Algorithm(CQMEA) is proposed.CQMEA is proposed by employing the concept and principles of Cloud theory.The algorithm utilizes the random orientation and stability of the cloud model,uses a self-adaptive mechanism with cloud model of Quantum gates updating strategy to implement global search efficient.By using the self-adaptive mechanism and the better solution which is determined by the membership function uncertainly,Compared with several well-known algorithms such as NSGA-Ⅱ,QMEA.Experimental results show that(CQMEA) is more effective than QMEA and NSGA -Ⅱ.

A Novel Attack on Complex APUFs Using the Evolutionary Deep Convolutional Neural Network

As the internet of things(IoT)continues to expand rapidly,the significance of its security concerns has grown in recent years.To address these concerns,physical unclonable functions(PUFs)have emerged as valuable tools for enhancing IoT security.PUFs leverage the inherent randomness found in the embedded hardware of IoT devices.However,it has been shown that some PUFs can be modeled by attackers using machine-learning-based approaches.In this paper,a new deep learning(DL)-based modeling attack is introduced to break the resistance of complex XAPUFs.Because training DL models is a problem that falls under the category of NP-hard problems,there has been a significant increase in the use of meta-heuristics(MH)to optimize DL parameters.Nevertheless,it is widely recognized that finding the right balance between exploration and exploitation when dealing with complex problems can pose a significant challenge.To address these chal-lenges,a novel migration-based multi-parent genetic algorithm(MBMPGA)is developed to train the deep convolutional neural network(DCNN)in order to achieve a higher rate of accuracy and convergence speed while decreas-ing the run-time of the attack.In the proposed MBMPGA,a non-linear migration model of the biogeography-based optimization(BBO)is utilized to enhance the exploitation ability of GA.A new multi-parent crossover is then introduced to enhance the exploration ability of GA.The behavior of the proposed MBMPGA is examined on two real-world optimization problems.In benchmark problems,MBMPGA outperforms other MH algorithms in convergence rate.The proposed model are also compared with previous attacking models on several simulated challenge-response pairs(CRPs).The simulation results on the XAPUF datasets show that the introduced attack in this paper obtains more than 99%modeling accuracy even on 8-XAPUF.In addition,the proposed MBMPGA-DCNN outperforms the state-of-the-art modeling attacks in a reduced timeframe and with a smaller number of required sets of CRPs.The area under the curve(AUC)of MBMPGA-DCNN outperforms other architectures.MBMPGA-DCNN achieved sensitivities,specificities,and accuracies of 99.12%,95.14%,and 98.21%,respectively,in the test datasets,establishing it as the most successful method.

Simultaneous Identification of Thermophysical Properties of Semitransparent Media Using a Hybrid Model Based on Artificial Neural Network and Evolutionary Algorithm

A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.

三阶段自适应采样和增量克里金辅助的昂贵高维优化算法

代理辅助进化算法已广泛应用于求解代价高昂的多目标优化问题,但大多数由于代理模型的局限性而仅限于解决决策变量低维的问题。为了解决高维的昂贵多目标优化问题,提出了一种基于三阶段自适应采样策略的改进增量克里金辅助的进化算法。该算法使用改进的增量克里金模型来近似每个目标函数,此模型的超参数根据预测的不确定性进行自适应更新,降低计算复杂度的同时保证模型在高维上的准确性;此外,在模型管理方面提出一种三阶段自适应采样的策略,将采样过程分为不同的优化阶段以更有针对性的选择个体,能够首先保证收敛性,提高算法的收敛速度。为了验证算法的有效性,在包含各种特征的两组测试问题DTLZ(deb-thiele-laumanns-zitzler)、MaF(many-objective function)和路径规划实际工程问题上与最新的同类型算法进行实验对比,结果表明该算法在解决决策变量高维的昂贵多目标优化问题上具有较强的竞争力。

代理模型辅助的复杂网络能控性鲁棒性优化方法

近年来,复杂网络的鲁棒性优化问题引起人们广泛关注.复杂网络暴露在外会受到各种各样的攻击,因此如何设计抗击能力较好的网络结构成为了研究热点.虽然现有的方法在小规模复杂网络的鲁棒性方面已经取得了显著成果,但大规模复杂网络的能控性鲁棒性优化的计算成本非常大.而代理模型可以以较低的计算成本来代替优化过程中对复杂网络能控性鲁棒性的评估,但一个代理模型不可能适用于评估所有类型的复杂网络能控性鲁棒性.文中将Dempster-Shafer理论应用于代理模型选择及其混合,并把选择出的代理模型用来辅助进化算法搜索能控性鲁棒性更优的网络结构.此方法在SF、ER、SW、RR、RT和QS 6种合成网络上的实验结果表明:在不同类型的复杂网络中选择合适的代理模型能更好的辅助进化算法找到能控性鲁棒性更优的网络结构.

基于进化集成学习的用户购买意向预测

在电子商务时代背景下,精准预测用户的购买意向已经成为提高销售效率和优化客户体验的关键因素。针对传统集成策略在模型设计阶段往往受人为因素限制的问题,构建了一种自适应进化集成学习模型用于预测用户的购买意向。该模型能够自适应地选择最优基学习器和元学习器,并融合基学习器的预测信息和特征间的差异性扩展特征维度,从而提高预测的准确性。此外,为进一步优化模型的预测效果,设计了一种二元自适应差分进化算法进行特征选择,旨在筛选出对预测结果有显著影响的特征。研究结果表明,与传统优化算法相比,二元自适应差分进化算法在全局搜索和特征选择方面表现优异。相较于六种常见的集成模型和DeepForest模型,所构建的进化集成模型在AUC值上分别提高了2.76%和2.72%,并且能够缓解数据不平衡所带来的影响。

自适应模型选用辅助的多种群进化算法

代理模型辅助的进化算法是求解目标函数评价昂贵优化问题的有效方法.在这类算法中,算法的搜索策略和填充采样策略是在有限评价次数下获得优化问题较好解的重要因素.为此,本文使用多种群搜索策略用于平衡种群搜索的多样性和收敛性,同时基于个体和训练样本之间目标函数值的距离自适应选择模型进行个体的目标函数值估计,以提高估值的准确度.为了验证算法的有效性,在CEC2005测试函数以及扩频雷达Polly编码优化设计问题上进行测试,并和现有求解昂贵优化问题的算法进行了结果对比.实验结果表明本文提出的算法在目标函数评价次数有限的情况下能够获得昂贵优化问题的较好解.

User Purchase Intention Prediction Based on Improved Deep Forest

Widely used deep neural networks currently face limitations in achieving optimal performance for purchase intention prediction due to constraints on data volume and hyperparameter selection.To address this issue,based on the deep forest algorithm and further integrating evolutionary ensemble learning methods,this paper proposes a novel Deep Adaptive Evolutionary Ensemble(DAEE)model.This model introduces model diversity into the cascade layer,allowing it to adaptively adjust its structure to accommodate complex and evolving purchasing behavior patterns.Moreover,this paper optimizes the methods of obtaining feature vectors,enhancement vectors,and prediction results within the deep forest algorithm to enhance the model’s predictive accuracy.Results demonstrate that the improved deep forest model not only possesses higher robustness but also shows an increase of 5.02%in AUC value compared to the baseline model.Furthermore,its training runtime speed is 6 times faster than that of deep models,and compared to other improved models,its accuracy has been enhanced by 0.9%.

自适应建模策略辅助的昂贵多目标进化算法

代理模型辅助的多目标进化算法广泛用于解决计算费时的多目标优化问题,然而现有的大部分建模方法都是为了嵌入到特定算法而设计的,适应于其他算法的能力并不强,为了能够依据数据特征自适应的建立模型,提出了一种基于自适应模型选择的建模方法。该方法的主要思想为:依据每个目标函数的样本特征,自适应的选择样本建立全局模型或者局部模型。为了验证所提出建模的方法的有效性,将提出的建模方法应用于基于高斯过程辅助的双存档费时多目标优化算法(KAT2)和基于高斯过程辅助的参考向量引导的费时多目标优化算法(K-RVEA),并且在DTLZ测试函数进行测试。通过实验证明,提出的建模方法可以有效的解决费时多目标优化问题。

智能台区低压故障定位及主动上报方法研究

针对传统低压台区配电网故障诊断方法存在适用范围有限、模型复杂等问题,提出一种基于计算智能的故障诊断模型。基于实时PMU数据诊断电力故障,根据故障内容上报智能控制中心,设计一种改进的多目标进化算法求解多目标故障诊断模型。实验阶段,以一个故障区域电力系统接线模型为例,对所提模型进行验证。仿真结果表明,所提模型可以有效地克服单个或多个保护继电器故障的影响,从而高效确定故障组件。同时,通过交叉对比分析,所提模型故障识别平均准确率为0.9171。仿真结果进一步验证了所提模型的鲁棒性和稳定性。

一种新的基于时间序列的谱聚类算法

时序网络研究是当前复杂网络分析中的重要领域。传统的复杂网络分析基于静态网络,没有考虑时间维度。针对社交网络中社区划分算法缺少历史信息的问题,文章提出了一种基于时序网络的谱聚类算法(TSNSC)。首先,利用时序网络数据建立时空邻接矩阵,并采用ARIMA时间序列方法确定演化特征值;其次,基于这些演化特征值构建相似度矩阵,并进行社区划分。通过对真实网络数据集进行实验验证,结果表明基于时序网络的谱聚类社区划分算法在轮廓系数上取得了较好的结果。

Data-driven evolutionary sampling optimization for expensive problems

Surrogate models have shown to be effective in assisting evolutionary algorithms(EAs)for solving computationally expensive complex optimization problems.However,the effectiveness of the existing surrogate-assisted evolutionary algorithms still needs to be improved.A data-driven evolutionary sampling optimization(DESO)framework is proposed,where at each generation it randomly employs one of two evolutionary sampling strategies,surrogate screening and surrogate local search based on historical data,to effectively balance global and local search.In DESO,the radial basis function(RBF)is used as the surrogate model in the sampling strategy,and different degrees of the evolutionary process are used to sample candidate points.The sampled points by sampling strategies are evaluated,and then added into the database for the updating surrogate model and population in the next sampling.To get the insight of DESO,extensive experiments and analysis of DESO have been performed.The proposed algorithm presents superior computational efficiency and robustness compared with five state-of-the-art algorithms on benchmark problems from 20 to 200 dimensions.Besides,DESO is applied to an airfoil design problem to show its effectiveness.

Multi-Knapsack Model of Collaborative Portfolio Configurations in Multi-Strategy Oriented

Aiming at constructing the multi-knapsack model of collaborative portfolio configurations in multi-strategy oriented, the hybrid evolutionary algorithm was designed based on greedy method, combining with the organization of the multiple strategical guidance and multi-knapsack model. Furthermore, the organizing resource utility and risk management of portfolio were considered. The experiments were conducted on three main technological markets which contain communication, transportation and industry. The results demonstrated that the proposed model and algorithm were feasible and reliable.

嵌入式智能计算机计算能力评测方法

计算能力评测方法是嵌入式智能计算机领域的研究热点之一.嵌入式智能计算机存在多种神经形态计算的优化方案和机器学习加速器,导致其评测难度大于通用计算机.基准测试是目前普遍采用的评测方法,但是在资源受限的嵌入式设备上,基准测试集和评价指标的复用能力有限,难以适应配置多样化的嵌入式智能系统;测试集中神经网络模型的计算强度存在一定的随机性,无法充分挖掘待测设备的计算潜力;评价指标不统一,难以对不同嵌入式智能计算机的计算能力进行对比分析.本文提出了一种基于神经进化算法的嵌入式智能计算机计算能力评测方法.首先,基于Roofline理论模型,融合计算潜力挖掘、资源适配和评价指标统一等优势,提出了一种适配各种嵌入式智能计算机的计算能力评测框架,并对其合理性进行分析;其次,提出了一种评测计算能力的神经网络模型生成算法,利用神经进化算法,使生成模型的计算强度逼近嵌入式智能计算机的计算强度上限,充分挖掘待测设备的计算潜力,使评测结果更客观;然后,采用环境固定的上位机作为对照,分别在待测设备和上位机交叉运行生成的神经网络模型,并以两次执行推断任务时的每秒浮点运算次数作为计算因子,给出计算能力评测的通用公式,可以实现不同嵌入式智能计算机计算能力的对比分析;最后,在Mindspore-cpu、Tensorflow-cpu和Mindspore-ascend310框架下评测华为Atlas200,相比基准测试中常用的5种神经网络模型,采用本文生成的神经网络模型的测评结果更合理,证实两个DaVinci核心的智能计算能力是八个Cortex-A55核心的42.37倍.