混沌背景中微弱信号检测的回声状态网络方法

对复杂非线性系统的相空间重构理论进行了研究分析,提出了混沌背景中微弱信号检测的回声状态网络方法。针对回声状态网络模型参数选取困难这一问题,采用遗传算法对其模型参数进行优化。将回声状态网络模型参数作为遗传算法的个体,混沌时间序列预测均方根误差的倒数作为适应度函数,通过选择、交叉、变异等操作获得适合数据特点的最优模型参数。根据回声状态网络强大的学习和非线性处理能力,利用得到的回声状态网络模型最优参数建立混沌背景噪声的单步预测模型,将淹没在混沌背景噪声中的微弱瞬态信号和周期信号从预测误差中检测出来。以Lorenz系统和实测的海杂波数据作为混沌背景噪声进行仿真实验,仿真结果表明,本文所提方法在预测精度和训练速度方面均优于支持向量机和神经网络模型,能够有效地检测出混沌背景噪声中的微弱目标信号,且具有较小的预测误差。      

基于BP神经网络的智能电网配电系统改进算法的研究

提出一种基于BP神经网络的智能电网配电系统改进算法.由于BP网络是一种按误差逆传播算法训练的多层前馈网络,具有学习性,可以根据已有的配电参数样本集进行训练,从中分析出内蒙古各地区根据时间不同所配电的分配情况的内在联系,实现对以后配电系统进行自适应控制.该算法的优点就是在构造过程考虑了BP的预测精度和训练时间,采用了梯度下降法的方法,进行Matlab仿真实验,获得了较为准确的预测结果.     

Network traffic prediction model based on improved VMD and PSO-ELM

The rapid update of computing power leads to exponential data traffic growth, and the incidence of network attacks is also increasing. It is significantly important to analyze and predict network traffic accurately in the early stage and take corresponding preventive measures. The existing network flow integrated forecasting models still have some bottlenecks that are difficult to solve, for example, the slow optimization speed of modal decomposition parameters, easy falling into local optimal solutions, the slow convergence speed of the training process, and poor generalization capability. In this paper, particle swarm optimization (PSO) is utilized to improve the parameters selection process of the variational mode decomposition (VMD) algorithm and the extreme learning machine (ELM) algorithm. First, the PSO-VMD combined with multi-scale permutation entropy (MPE) is utilized to decompose the original network flow, and multiple eigenmode components are obtained. Second, the PSO-ELM is utilized to train the network traffic prediction model, and the PSO parameters in PSO-ELM are updated through adaptive weight adjustment and synchronous learning factors to increase the training and prediction speed, and the component prediction results are reconstructed to get a high-precision network flow forecasting result. Finally, through the prediction and verification of the public network flow data of the WIDE backbone, the result of this experiment indicates that the VMD-PSO-ELM can break through the bottlenecks of slow optimization speed of VMD decomposition parameters, reduce the computational complexity of ELM, accelerate the convergence speed, and increase the forecasting accuracy.     

利用无监督预训练的轨迹深度关联

针对时空相似度算法关联轨迹的局限性,采用深度学习方法进行轨迹关联,并提出了一种基于无监督预训练的匹配神经网络训练方式。利用Geohash向量嵌入对轨迹信号做特征工程处理,构建自注意力机制神经网络结构,使用无标注轨迹数据基于遮蔽预测任务进行模型预训练;然后构建孪生匹配网络结构,加载预训练模型参数;最后使用标注轨迹对数据基于均方差损失函数微调预训练模型参数得到轨迹对匹配模型。采用Geolife GPS轨迹数据集作为评估数据集进行模型训练与测试,实验结果显示,利用无监督预训练的轨迹关联方法较现有最优算法匹配准确率提高了5个百分点,达到了96.3%,充分证明了该方法的有效性。目前轨迹关联领域基于深度学习预训练模型的研究较少,该方法具有重要的参考意义。     

Network traffic prediction method based on improved ABC algorithm optimized EM-ELM

In order to overcome the poor generalization ability and low accuracy of traditional network traffic prediction methods, a prediction method based on improved artificial bee colony (ABC) algorithm optimized error minimized extreme learning machine (EM-ELM) is proposed. EM-ELM has good generalization ability. But many useless neurons in EM-ELM have little influences on the final network output, and reduce the efficiency of the algorithm. Based on the EM-ELM, an improved ABC algorithm is introduced to optimize the parameters of the hidden layer nodes, decrease the number of useless neurons. Network complexity is reduced. The efficiency of the algorithm is improved. The stability and convergence property of the proposed prediction method are proved. The proposed prediction method is used in the prediction of network traffic. In the simulation, the actual collected network traffic is used as the research object. Compared with other prediction methods, the simulation results show that the proposed prediction method reduces the training time of the prediction model, decreases the number of hidden layer nodes. The proposed prediction method has higher prediction accuracy and reliable performance. At the same time, the performance indicators are improved.     

一种基于改进教学优化的微弱信号检测方法

为了快速准确地检测混沌背景中的微弱信号,提高网络泛化能力,文中利用改进教学优化算法优化贝叶斯回声状态网络的模型参数,提出了一种改进教学优化的混沌背景中微弱信号检测方法。通过建立混沌序列单步预测模型,分析预测误差的幅值,检测混沌背景中微弱瞬态信号和周期信号。对Lorenz系统和实测的海杂波数据进行实验研究,验证预测模型的有效性,结果表明,贝叶斯回声状态网络模型的预测结果比支持向量机和径向基神经网络模型的均方根误差降低了2个数量级,缩短了预测时间,提高了预测精度和预测效率,能快速有效地检测混沌背景中微弱信号,且具有更低的门限。     

基于随机森林的流处理检查点性能预测

物联网(IoT)的发展引起流数据在数据量和数据类型两方面不断增长。由于实时处理场景的不断增加和基于经验知识的配置策略存在缺陷,流处理检查点配置策略面临着巨大的挑战,如费事费力,易导致系统异常等。为解决这些挑战,该文提出基于回归算法的检查点性能预测方法。该方法首先分析了影响检查点性能的6种特征,然后将训练集的特征向量输入到随机森林回归算法中进行训练,最后,使用训练好的算法对测试数据集进行预测。实验结果表明,与其它机器学习算法相比,随机森林回归算法在CPU密集型基准测试,内存密集型基准测试和网络密集型基准测试上针对检查点性能的预测具有误差低,准确率高和运行高效的优点。     

URLM: Utilising reinforcement learning to schedule subflows in MPTCP

Parallel transmission in multiple access networks using MultiPath TCP (MPTCP) greatly enhances the throughput. However, critical packet disorder is commonly observed due to traffic fluctuation and path diversity. Although several predictive scheduling algorithms have been proposed to solve this problem, they cannot accommodate prediction accuracy and real-time adaptation simultaneously in a dynamic network environment. The time overhead in modifying scheduling parameters to adapt to network changes leads to performance degradation in throughput and packet disorder. In this study, we propose a scheduling algorithm called U tilising R einforcement L earning to Schedule Subflows in M PTCP (URLM). We apply reinforcement learning to select an optimal scheduling parameter in real time, which brings significant time benefits for modifying the parameters. The simulation comparison experiments show that URLM reduces the average number of out-of-order packets and the time overhead in adapting to network changes while improving global throughput.     

Forecasting chaotic cardiovascular time series with an adaptive slope multilayer perceptron neural network

A multilayer perceptron (MLP) network architecture has been formulated in which two adaptive parameters, the scaling and translation of the postsynaptic function at each node, are allowed to adjust iteratively by gradient-descent. The algorithm has been employed to predict experimental cardiovascular time series, following systematic reconstruction of the strange attractor of the training signal. Comparison with a standard MLP employing identical numbers of nodes and weight learning rates demonstrates that the adaptive approach provides an efficient modification of the MLP that permits faster learning. Thus, for an equivalent number of training epochs there was improved accuracy and generalization for both one- and k-step ahead prediction. The applicability of the methodology is demonstrated for a set of monotonic postsynaptic functions (sigmoidal, upper bounded, and nonbounded). The approach is computationally inexpensive as the increase in the parameter space of the network compared to a standard MLP is small.     

基于VGGNet卷积神经网络的蓝印花布纹样分类

为了数字化传承与创新传统的蓝印花布纹样,需 要将蓝印花布纹样进行分类。为此,提出一种改进的VGGNet卷 积神经网络模型的纹样分类方法。首先,采集原始的蓝印花布图案,通过图像增强技术扩充 样本,形成训练数据集。其次, 改进经典的VGGNet 16卷积神经网络结构,增加卷积组及调整网络参 数,增加丢弃层。同时,分析、验证训练优化策略对 蓝印花布纹样分类的影响。最后,利用训练集及验证集中的图像样本,通过自动学习获取网 络模型参数,得到纹样分类的最 佳网络模型并获得较为理想的分类结果。实验结果显示,改进的卷积神经网络模型针对5类 蓝印花布纹样进行分类训练,其 平均分类准确率达89.73%,为蓝印花布纹样的继承和创新研究提供了 新思路。     

基于神经网络的宽带激光熔覆熔池特征参数预测

为了实现宽带激光熔覆熔池特征的准确预测,从 而对激光熔覆工艺过程进行实时监测、评价及反馈 控制。通过宽带激光熔覆全因素工艺试验采集熔池特征参数样本数据,采用遗传算法优化BP 神经网络的 初始权值和初始阈值,建立激光熔覆工艺参数(激光功率、粉末厚度、扫描速度)与熔池特 征参数之间的 BP神经网络预测模型。利用训练集数据对所建立的神经网络进行训练,形成输入与输出之间 的映射关系, 并利用测试集数据对网络进行测试。试验结果表明,宽带激光熔覆熔池特征参数神经网络预 测模型具有很 高的精度。该神经网络预测模型对激光熔覆过程监测及熔覆层质量控制具有重要意义。     

飞秒激光环切加工不锈钢微孔工艺及其质量控制神经网络模型

利用飞秒激光微纳加工系统开展环切加工喷油器微孔的理论和实验研究。以06Cr19Ni10不锈钢为靶材,选取影响飞秒激光环切制孔过程的主要参数,基于L₂₅(55)的正交表设计了5因素5水平的正交实验,分析激光功率、重复频率、离焦量、扫描速度和扫描次数对微孔加工影响的显著性水平,探究微孔的成形演化规律以及各参数对微孔几何精度和形貌的影响,最终得到相对最优的参数水平组合为:激光功率 1.0 W,重复频率 9.0 kHz,离焦量200 μm,扫描速度1.0 mm/s,扫描次数40次;基于BP神经网络建立关于上述5个参数为输入,微孔出入口孔径为输出的映射模型,通过对正交实验数据的迭代训练以及验证,最终建立出相对误差保持在7.6%以内的神经网络预测模型。     

Defect detection method of magnetic disk image based on improved convolutional neural network

This paper proposes an efficient method for defect detection of magnetic disk image based on improved convolutional neural network. We build a model named DiskNet on the basis of VGGNet-19, in which the optimal activation function is selected predictively through a weighted probability learning curve model (WP-Model). First, we use Markov Chain Monte Carlo (MCMC) to infer the predicted value and determine prediction probability. Then, the evaluation point (EP) is determined by the effective information of training curve. In the process of DiskNet training, when the prediction probability is higher than the threshold, the neural network will select the current activation function. If the training epochs exceed the EP and the threshold is not reached, the original activation function will be used. The experimental results show that the accuracy of the proposed method in detecting defects on the magnetic disk image data set is 96.9%.     

Cloud security situation prediction method based on grey wolfoptimization and BP neural network

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed.Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve theconvergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the positionupdate formula of GWO algorithm, which is used to select the features of the cloud security situation prediction dataand optimize the parameters of the BP neural network prediction model to minimize the prediction output error.Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm toincrease the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloudplatform are predicted. The simulation results show that the proposed method has lower mean square error (MSE)and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm(GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based onGWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.     

基于BP神经网络的光纤激光切割切口粗糙度预测

为了研究工艺参量对光纤激光切割切口质量的影响,进行了切割T4003不锈钢试验,分析了工艺参量与切口质量之间的关系。采用基于误差反向传播算法的人工神经网络,建立了激光功率、切割速率、辅助气体压力等工艺参量与切口粗糙度之间的预测模型。对切割试验采集的训练样本进行了网络训练,并利用测试样本对训练模型进行验证。结果表明,随着激光功率增加,切口粗糙度增大;随着切割速率和辅助气体压力增加,切口粗糙度减小。神经网络预测模型精度较高,网络训练效果良好,预测值与试验样本值间的最大相对误差为2.4%。训练后检验精度较高,检验样本最大相对误差仅为6.23%。该模型可有效预测激光切割切口表面粗糙度,同时为合理选择及优化工艺参量,提高激光切割质量提供试验依据。     

Evolutionary fuzzy neural networks for hybrid financial prediction

In this paper, an evolutionary fuzzy neural network using fuzzy logic, neural networks (NNs), and genetic algorithms (GAs) is proposed for financial prediction with hybrid input data sets from different financial domains. A new hybrid iterative evolutionary learning algorithm initializes all parameters and weights in the five-layer fuzzy NN, then uses GA to optimize these parameters, and finally applies the gradient descent learning algorithm to continue the optimization of the parameters. Importantly, GA and the gradient descent learning algorithm are used alternatively in an iterative manner to adjust the parameters until the error is less than the required value. Unlike traditional methods, we not only consider the data of the prediction factor, but also consider the hybrid factors related to the prediction factor. Bank prime loan rate, federal funds rate and discount rate are used as hybrid factors to predict future financial values. The simulation results indicate that hybrid iterative evolutionary learning combining both GA and the gradient descent learning algorithm is more powerful than the previous separate sequential training algorithm described in.     

基于YOLOv5网络模型的人员口罩佩戴实时检测

近年来,随着硬件算力的提升和人工智能算法的创新发展,使得深度学习算法在目标检测方面有着广泛的应用。针对现有人工方式查看人员口罩佩戴情况的不足,提出了一种基于深度学习YOLOv5算法实现对口罩佩戴情况的实时检测。算法首先将数据集进行归一化处理,再将数据接入YOLOv5网络进行迭代训练,并将最优权重数据保存用作测试集测试,算法通过tensorboard可视化显示训练和测试结果。实验结果表明,所提算法检测的准确性高,实时性强,满足实际使用需求。     

基于生物免疫优化支持向量机算法的居民区负荷预测

针对居民区用电负荷随机性强、稳定性差等问题,综合考虑各因素对居民用电负荷的影响,提出一种免疫支持向量机(support vector machine,SVM)算法负荷预测模型。以居民区历史用电量及相关气候数据为处理对象,使用PCA(principal component analysis)算法对电网历史数据进行处理,并结合免疫算法对电网历史数据进行预处理,形成数据簇并划定标签提供给预测模型进行训练。为提高模型精度,采用生物免疫优化算法对SVM模型参数进行优化,并在负荷预测环节,将预测误差作为调优依据,对预测模型进行反馈调优。将预测效果与常用于负荷预测的BP(back propagation)神经网络、SVM算法模型进行对比,免疫SVM算法负荷预测模型的短期、中期预测精准度均在98%以上,具有较好的精度与鲁棒性。     

图像分类问题的几种深度学习策略

针对图像分类学习不够深入的问题,提出图像分类问题的几种深度学习策略研究。通过分析当前主流的主动深度学习图像、多标签图像和多尺度网络图像三种深度学习方法的工作原理和存在的优势与不足,探讨图像分类问题的优化学习策略。随后采用图像分类问题的几种深度学习策略实验的方式加以对比,实验结果表明,参数共享的深度学习图像分类方法不仅提高了预测速度,而且还能确保模型的准确性。