基于量子计算多Agent的人工神经网络训练方法

人工神经网络是可用于建模和求解各种复杂非线性现象的工具.针对传统神经网络训练时间长、节点数目受计算机能力限制等缺点,提出了一种新的多Agent系统理论(MAS)和量子算法的人工神经网络.在人工神经网络训练方法中,每个神经元或节点是一个量子Agent,通过强化学习算法后具有学习能力,然后用QCMAS强化学习算法作为新的神经网络的学习规则.这种新的人工神经网络法具有很好的并行工作能力而且训练时间比经典算法短,实验结果证明了方法的有效性.     

几种改进的人工神经网络算法比较

文章分别介绍了模拟退火算法与BP网络结合的模拟退火人工神经网络,遗传算法和BP网络结合的遗传人工神经网络以及遗传退火人工神经网络算法。通过仿真实验比较证明,遗传退火人工神经网络和模拟退火人工神经网络的逼近精度高于遗传算法人工神经网络,而遗传算法人工神经网络收敛速度最快。并且随着求解变量个数的增加,基于遗传退火人工神经网络收敛速度高于改进的模拟退火人工神经网络。     

分布式遗传退火算法求解分布式配置问题

利用分布式约束满足的方法求解分布式配置问题时,在过约束和欠约束条件下都不能得到令人满意的结果,文中将分布式配置问题抽象为分布式组合最优化问题,把遗传退火算法扩展到分布式计算环境以求解分布式配置问题,以SOAP为基础搭建实验平台,在各种约束情况下,文中算法都给出了令人满意的实验结果,可见分布式遗传退火算法可以求解各种约束条件下的分布式配置问题。     

一种多属性目标监测的无线感知网络覆盖算法

本文研究了一种无线感知网络应用中多属性目标的覆盖问题。这种覆盖问题与单一类型数据的目标不同,其待测区域中的每个目标同时包含多种类型的现场数据。如果布置一个无线感知网络去担任监测任务,其节点需要配置多种不同类型的传感器单元。针对这种需要采集多种类型的数据才能对目标进行监测的无线感知网络的应用,节能而有效的的覆盖目标更是一个突出的问题。本文首先用ILP模型将问题进行了形式化,然后通过设计一种分布式算法求得问题了模拟仿真。仿真结果表明,这种分布式算法比直接求解ILP求出的网络寿命很接近。由于直接求解ILP问题必须依靠中心节点完成,对于节点较多并且电量受限的无线感知网络,这种分布式算法更适合。     

分布式预测控制算法的性能分析

分布式求解策略是为了降低大规模预测控制系统实施的计算量和计算复杂性而提出的一种有效算法，在算法收敛的条件下，分析了分布式求解和集中求解两种方法在单步时域上的性能偏差，给出了标称情况下分布式预测控制系统名义稳定的充分条件，为更好地理解所提出的分布式预测控制算法和算法的实施提供了理论依据。     

一种节能多属性目标监测的感知网络覆盖算法

研究了一种多属性目标的覆盖问题,这种覆盖问题与单一类型数据的目标不同,其待测区域中的每个目标同时包含多种类型的现场数据。如果布置一个无线感知网络去担任监测任务,其节点需要配置多种不同类型的传感器单元。针对这种需要采集多种类型的数据才能对目标进行监测的无线感知网络的应用,节能而有效的覆盖目标更是一个突出的问题。首先用ILP模型将问题进行了形式化,然后通过设计一种分布式算法求得问题的解。最后,在不同的节点密度下,对网络的使用寿命进行了模拟仿真;仿真结果表明,这种分布式算法比直接求解ILP求出的网络寿命很接近。由于直接求解ILP问题必须依靠中心节点完成,对于节点较多并且电量受限的无线感知网络,这种分布式算法更适合。     

基于KOHONEN神经网络的模拟退火算法

本文提出了一种基于分布式知识的广义优化方法----基于KOHONEN神经网络的模拟退火算法。采用人工神经网络积累搜索区域信息,利用其学习的分布式寻优知识指导搜索过程的优化。研究了各种优化策略,给出了算法流程和结构框图。典型算例的仿真研究结果显示了新算法在寻优性能上的优越性。     

带时间窗车辆路径问题的分布式多Agent蚁群算法

带时间窗车辆路径问题(VRPTW)多年来一直受到人们关注。针对以往研究中求解效率有限、求解复杂度有限、难以求解较大规模问题的不足,本文以提高精度和速度为目标,在传统蚁群算法的基础上,改进了状态转移规则,结合了邻域搜索算法;同时将本算法设计为分布式结构。利用多分布式agent系统实现了分布式求解VRPTW问题。针对国际标准算例设计了四个实验,结果表明：本算法在精确度、速度、可靠性以及求解大规模问题方面具有明显优势。     

分布式约束优化方法研究进展

多agent系统作为分布式人工智能研究领域的重要分支,已被广泛应用于多个领域中复杂系统的建模.而分布式约束优化作为一种多agent系统求解的关键技术,已成为约束推理研究的热点.首先对其适用性进行分析,并基于对已有算法的研究,总结出采用该方法解决问题的基本流程,在此基础上,从解的质量保证、求解策略等角度对算法进行了完整的分类;其次,根据算法分类结果以及执行机制,对大量经典以及近年来的分布式约束优化算法进行了深入分析,并从通信、求解质量、求解效率等方面对典型算法进行了实验对比;最后,结合分布式约束优化技术的求解优势给出了分布式约束优化问题的实际应用特征,总结了目前存在的一些问题,并对下一步工作进行了展望.     

基于分布式环境下的机器人的路径规划及实现

在研究机器人的运动规划中发现，分布式环境中路径规划问题是一个很复杂的问题。该文通过基于Snake模型的蚁群优化算法，顺利解决了这一难题。文中根据Snake的特点构建了一种新的蚁群求解算法，在分布式环境中可以顺利解决在有固定障碍物的情况下的最优路径的搜索问题。并且，结合我们本身的实验环境，我们在对上述算法稍微进行了一些修改后．使这种算法可以在我们的嵌入式硬件平台上运行，最终验证了这种算法的可行性和稳定性。     

An evidential extension of the MRII training algorithm fordetecting erroneous MADALINE responses

This paper integrates the evidential reasoning methodology with the parallel distributed learning paradigm of artificial neural networks (ANN). As such, this work presents an algorithm for the detection and, if possible, subsequent correction of the errors in the neuron responses in the output layer of the multiple adaptive linear element (MADALINE) ANN. A geometrical perspective of the MADALINE ANN processing methodology is provided. This perspective is then used to formulate a statistical specification to identify and quantify the sources of uncertainties in the MADALINE processing methodology. A new algorithm, EMRII, is then developed as an extension to the original MRII (MADELINE rule II) algorithm, to formulate support and plausibility measures based on the statistical specification. The support and plausibility measures, thus formulated, are indicative of the degree of confidence of the ANN, in regards to the correctness of its outputs. Based on the support measure, a scheme utilizing two thresholds is proposed to facilitate the interpretation of the support values for error prediction in the ANN responses. Finally, simulation results for the application of the EMRII algorithm in the prediction of erroneous responses in an example problem is presented. These simulation results highlight the error detection capabilities of the EMRII algorithm.     

基于人工神经网络的智能热电测温技术研究

本文用前向网络结构和BP学习算法，将人工神经网络用于智能热电温度在线测量系统中，说明人工神经网络用于智能测量领域的方法和可行性。     

Damage assessment of prestressed concrete beams using artificial neural network (ANN) approach

An artificial neural network (ANN) based approach is presented for the assessment of damage in prestressed concrete beams from natural frequency measurements. The details of an experimental programme suitably designed and carried out to induce the desired extents of damages in the prestressed concrete beams and generate the training and test data for the ANN are presented. The analysis of the static and dynamic behavior of perfect and damaged prestressed concrete beams reveal that there exists a close relationship among the natural frequency, deflection, crack width, first crack load, ultimate load and degree of damage. Therefore, these parameters were mainly used as input data for training and testing the ANN. A feed forward ANN learning by back propagation algorithm implemented using MATLAB has been employed in this study. The main focus of this work has been to study the feasibility of using an ANN trained with only natural frequency data to assess the damage in prestressed concrete beams. This is explored by comparing the performance of an ANN trained only with natural frequency data with other ANNs trained with a mix of static and dynamic data. It has been demonstrated that an ANN trained only with dynamic data can assess the damage with less than 10% error, when the error is the difference between the actual damage in percent and predicted damage in percent. The shortcomings of this study have also been presented.     

基于离散灰色预测模型与人工神经网络混合智能模型的时尚销售预测

时尚销售预测对零售领域十分重要,准确的销售情况预测有助于大幅度提高最终时尚销售利润。针对目前时尚销售预测数据量有限并且数据波动大导致难以进行准确预测的问题,提出了一种结合人工神经网络（ANN）算法和离散灰色预测模型（DGM（1,1））算法的混合智能预测算法。该算法通过关联度分析得到关联度大的影响变量,在利用DGM（1,1）+ANN预测之后,引入二次残差的思想,将实际销售数据与DGM（1,1）+ANN预测结果的残差加入影响变量利用ANN进行第二次残差预测。最后通过真实的时尚销售数据验证算法预测的可行性及准确性。实验结果表明,该算法在时尚销售数据的预测中,预测平均绝对百分误差（MAPE）在25%左右,预测性能优于自回归积分滑动平均模型（ARIMA）、扩展极限学习机（EELM）、DGM（1,1）、DGM（1,1）+ANN算法,相较于以上几种算法平均预测精度大约提高8个百分点。所提混合智能算法可用于时尚销售即时预测,且能够大幅度提高销售的效益。     

Globally optimal bounding ellipsoid algorithm for parameter estimation using artificial neural networks

This paper develops a real-time implementation of a globally optimal bounding ellipsoid (GOBE) algorithm for parameter estimation of linear-in-parameter models with unknown but bounded (UBB)errors. A recently proposed recursively optimal bounding ellipsoid (ROBE) algorithm is introduced, and a GOBE algorithm is derived through repeating this ROBE algorithm. An analogue artificial neural network (ANN) is provided to implement the GOBE algorithm in real time. Convergence analyses on the ROBE, the GOBE algorithms, and the analogue ANN implementation of the GOBE algorithm are presented. No persistent excitation condition is required to ensure the convergence. Simulation results show the good performances of these algorithms and the ANN implementation.     

Improved estimation of electricity demand function by using of artificial neural network,principal component analysis and data envelopment analysis

Due to various seasonal and monthly changes in electricity consumption and difficulties in modeling it with the conventional methods, a novel algorithm is proposed in this paper. This study presents an approach that uses Artificial Neural Network (ANN), Principal Component Analysis (PCA), Data Envelopment Analysis (DEA) and ANOVA methods to estimate and predict electricity demand for seasonal and monthly changes in electricity consumption. Pre-processing and post-processing techniques in the data mining field are used in the present study. We analyze the impact of the data pre-processing and post-processing on the ANN performance and a 680 ANN-MLP is constructed for this purpose. DEA is used to compare the constructed ANN models as well as ANN learning algorithm performance. The average, minimum, maximum and standard deviation of mean absolute percentage error (MAPE) of each constructed ANN are used as the DEA inputs. The DEA helps the user to use an appropriate ANN model as an acceptable forecasting tool. In the other words, various error calculation methods are used to find a robust ANN learning algorithm. Moreover, PCA is used as an input selection method, and a preferred time series model is chosen from the linear (ARIMA) and nonlinear models. After selecting the preferred ARIMA model, the Mcleod–Li test is applied to determine the nonlinearity condition. Once the nonlinearity condition is satisfied, the preferred nonlinear model is selected and compared with the preferred ARIMA model, and the best time series model is selected. Then, a new algorithm is developed for the time series estimation; in each case an ANN or conventional time series model is selected for the estimation and prediction. To show the applicability and superiority of the proposed ANN-PCA-DEA-ANOVA algorithm, the data regarding the Iranian electricity consumption from April 1992 to February 2004 are used. The results show that the proposed algorithm provides an accurate solution for the problem of estimating electricity consumption.     

Combination of artificial neural-network forecasters for predictionof natural gas consumption

The focus of this paper is on combination of artificial neural-network (ANN) forecasters with application to the prediction of daily natural gas consumption needed by gas utilities. ANN forecasters can model the complex relationship between weather parameters and previous gas consumption with the future consumption. A two-stage system is proposed with the first stage containing two ANN forecasters, a multilayer feedforward ANN and a functional link ANN. These forecasters are initially trained with the error backpropagation algorithm, but an adaptive strategy is employed to adjust their weights during online forecasting. The second stage consists of a combination module to mix the two individual forecasts produced in the first stage. Eight different combination algorithms are examined, they are based on: averaging, recursive least squares, fuzzy logic, feedforward ANN, functional link ANN, temperature space approach, Karmarkar's linear programming algorithm (1984) and adaptive mixture of local experts (modular neural networks). The performance is tested on real data from six different gas utilities. The results indicate that combination strategies based on a single ANN outperform the other approaches.     

Distributed Receding Horizon Control of Dynamically Coupled Nonlinear Systems

This paper considers the problem of distributed control of dynamically coupled nonlinear systems that are subject to decoupled constraints. Examples of such systems include certain large scale process control systems, chains of coupled oscillators and supply chain management systems. Receding horizon control (RHC) is a method of choice in these venues as constraints can be explicitly accommodated. In addition, a distributed control approach is sought to enable the autonomy of the individual subsystems and reduce the computational burden of centralized implementations. In this paper, a distributed RHC algorithm is presented for dynamically coupled nonlinear systems that are subject to decoupled input constraints. By this algorithm, each subsystem computes its own control locally. Provided an initially feasible solution can be found, subsequent feasibility of the algorithm is guaranteed at every update, and asymptotic stabilization is established. The theoretical conditions for feasibility and stability are shown to be satisfied for a set of coupled Van der Pol oscillators that model a walking robot experiment. In simulations, distributed and centralized receding horizon controllers are employed for stabilization of the oscillators. The numerical experiments show that the controllers perform comparably, while the computational savings of the distributed implementation over the centralized implementation is clearly demonstrated.     

An integrated Data Envelopment Analysis–Artificial Neural Network–Rough Set Algorithm for assessment of personnel efficiency

Personnel specifications have greatest impact on total efficiency. They can help us to design work environment and enhance total efficiency. Determination of critical personnel attributes is a useful procedure to overcome complication associated with multiple inputs and outputs. The proposed algorithm assesses the impact of personnel efficiency attributes on total efficiency through Data Envelopment Analysis (DEA), Artificial Neural Network (ANN) and Rough Set Theory (RST). DEA has two roles in the proposed integrated algorithm of this study. It provides data ANN and finally it selects the best reduct through ANN result. Reduct is described as a minimum subset of attributes, completely discriminating all objects in a data set. The reduct selection is achieved by RST. ANN has two roles in the integrated algorithm. ANN results are basis for selecting the best reduct and it is also used for forecasting total efficiency. The proposed integrated approach is applied to an actual banking system and its superiorities and advantages are discussed.     

ANN构造性设计中基于GA优选神经元激活函数类型

构造性设计是ANN设计的发展方向之一。全面的高质量的ANN学习应包括神经元激活函数类型的自动优化。该文在构造性设计的框架内讨论了如何实现典型前馈网络的包括神经元激活函数类型在内的全面学习。首先,提出了典型前馈网络的一种构造性设计方法的原理和算法框架,把整个网络的设计分解成了一个个单个神经元的设计问题;然后提出了基于GA的能实现激活函数类型优选的单个神经元的设计方法。大量函数拟合的仿真实验显示:与其它几种激活函数类型不优选的常见ANN设计方法相比,该文提出的方法更有效,能用较小的网络结构获得较好的泛化性能。