A new adaptive mutative scale chaos optimization algorithm and its application

Based on results of chaos characteristics comparing one-dimensional iterative chaotic self-map x = sin（2/x） with infinite collapses within the finite region[-1, 1] to some representative iterative chaotic maps with finite collapses （e.g., Logistic map, Tent map, and Chebyshev map）, a new adaptive mutative scale chaos optimization algorithm （AMSCOA） is proposed by using the chaos model x = sin（2/x）. In the optimization algorithm, in order to ensure its advantage of speed convergence and high precision in the seeking optimization process, some measures are taken： 1） the searching space of optimized variables is reduced continuously due to adaptive mutative scale method and the searching precision is enhanced accordingly; 2） the most circle time is regarded as its control guideline. The calculation examples about three testing functions reveal that the adaptive mutative scale chaos optimization algorithm has both high searching speed and precision.

A hybrid genetic algorithm based on mutative scale chaos optimization strategy

In order to avoid such problems as low convergent speed and local optimalsolution in simple genetic algorithms, a new hybrid genetic algorithm is proposed. In thisalgorithm, a mutative scale chaos optimization strategy is operated on the population after agenetic operation. And according to the searching process, the searching space of the optimalvariables is gradually diminished and the regulating coefficient of the secondary searching processis gradually changed which will lead to the quick evolution of the population. The algorithm hassuch advantages as fast search, precise results and convenient using etc. The simulation resultsshow that the performance of the method is better than that of simple genetic algorithms.

Spectral matching algorithm based on nonsubsampled contourlet transform and scale-invariant feature transform

A new spectral matching algorithm is proposed by us- ing nonsubsampled contourlet transform and scale-invariant fea- ture transform. The nonsubsampled contourlet transform is used to decompose an image into a low frequency image and several high frequency images, and the scale-invariant feature transform is employed to extract feature points from the low frequency im- age. A proximity matrix is constructed for the feature points of two related images. By singular value decomposition of the proximity matrix, a matching matrix （or matching result） reflecting the match- ing degree among feature points is obtained. Experimental results indicate that the proposed algorithm can reduce time complexity and possess a higher accuracy.

Betweenness-based algorithm for a partition scale-free graph

Many real-world networks are found to be scale-free. However, graph partition technology, as a technology capable of parallel computing, performs poorly when scale-free graphs are provided. The reason for this is that traditional partitioning algorithms are designed for random networks and regular networks, rather than for scale-free networks. Multilevel graph-partitioning algorithms are currently considered to be the state of the art and are used extensively. In this paper, we analyse the reasons why traditional multilevel graph-partitioning algorithms perform poorly and present a new multilevel graph-partitioning paradigm, top down partitioning, which derives its name from the comparison with the traditional bottom-up partitioning. A new multilevel partitioning algorithm, named betweenness-based partitioning algorithm, is also presented as an implementation of top-down partitioning paradigm. An experimental evaluation of seven different real-world scale-free networks shows that the betweenness-based partitioning algorithm significantly outperforms the existing state-of-the-art approaches.

Analytic Theory of Finite Asymptotic Expansions in the Real Domain. Part II-C: Constructive Algorithms for Canonical Factorizations and a Special Class of Asymptotic Scales

This part II-C of our work completes the factorizational theory of asymptotic expansions in the real domain. Here we present two algorithms for constructing canonical factorizations of a disconjugate operator starting from a basis of its kernel which forms a Chebyshev asymptotic scale at an endpoint. These algorithms arise quite naturally in our asymptotic context and prove very simple in special cases and/or for scales with a small numbers of terms. All the results in the three Parts of this work are well illustrated by a class of asymptotic scales featuring interesting properties. Examples and counterexamples complete the exposition.

Robust Hybrid Artificial Fish Swarm Simulated Annealing Optimization Algorithm for Secured Free Scale Networks against Malicious Attacks

Due to the recent proliferation of cyber-attacks,highly robust wireless sensor networks(WSN)become a critical issue as they survive node failures.Scale-free WSN is essential because they endure random attacks effectively.But they are susceptible to malicious attacks,which mainly targets particular significant nodes.Therefore,the robustness of the network becomes important for ensuring the network security.This paper presents a Robust Hybrid Artificial Fish Swarm Simulated Annealing Optimization(RHAFS-SA)Algorithm.It is introduced for improving the robust nature of free scale networks over malicious attacks(MA)with no change in degree distribution.The proposed RHAFS-SA is an enhanced version of the Improved Artificial Fish Swarm algorithm(IAFSA)by the simulated annealing(SA)algorithm.The proposed RHAFS-SA algorithm eliminates the IAFSA from unforeseen vibration and speeds up the convergence rate.For experimentation,free scale networks are produced by the Barabási–Albert(BA)model,and real-world networks are employed for testing the outcome on both synthetic-free scale and real-world networks.The experimental results exhibited that the RHAFS-SA model is superior to other models interms of diverse aspects.

A Review of the Current Task Offloading Algorithms,Strategies and Approach in Edge Computing Systems

Task offloading is an important concept for edge computing and the Internet of Things(IoT)because computationintensive tasksmust beoffloaded tomore resource-powerful remote devices.Taskoffloading has several advantages,including increased battery life,lower latency,and better application performance.A task offloading method determines whether sections of the full application should be run locally or offloaded for execution remotely.The offloading choice problem is influenced by several factors,including application properties,network conditions,hardware features,and mobility,influencing the offloading system’s operational environment.This study provides a thorough examination of current task offloading and resource allocation in edge computing,covering offloading strategies,algorithms,and factors that influence offloading.Full offloading and partial offloading strategies are the two types of offloading strategies.The algorithms for task offloading and resource allocation are then categorized into two parts:machine learning algorithms and non-machine learning algorithms.We examine and elaborate on algorithms like Supervised Learning,Unsupervised Learning,and Reinforcement Learning(RL)under machine learning.Under the non-machine learning algorithm,we elaborate on algorithms like non(convex)optimization,Lyapunov optimization,Game theory,Heuristic Algorithm,Dynamic Voltage Scaling,Gibbs Sampling,and Generalized Benders Decomposition(GBD).Finally,we highlight and discuss some research challenges and issues in edge computing.

Enhanced Sentiment Analysis Algorithms for Multi-Weight Polarity Selection on Twitter Dataset

Sentiment analysis is based on the orientation of user attitudes and satisfaction towards services and subjects.Different methods and techniques have been introduced to analyze sentiments for obtaining high accuracy.The sentiment analysis accuracy depends mainly on supervised and unsupervised mechanisms.Supervised mechanisms are based on machine learning algorithms that achieve moderate or high accuracy but the manual annotation of data is considered a time-consuming process.In unsupervised mechanisms,a lexicon is constructed for storing polarity terms.The accuracy of analyzing data is considered moderate or low if the lexicon contains small terms.In addition,most research methodologies analyze datasets using only 3-weight polarity that can mainly affect the performance of the analysis process.Applying both methods for obtaining high accuracy and efficiency with low user intervention during the analysis process is considered a challenging process.This paper provides a comprehensive evaluation of polarity weights and mechanisms for recent sentiment analysis research.A semi-supervised framework is applied for processing data using both lexicon and machine learning algorithms.An interactive sentiment analysis algorithm is proposed for distributing multi-weight polarities on Arabic lexicons that contain high morphological and linguistic terms.An enhanced scaling algorithm is embedded in the multi-weight algorithm to assign recommended weight polarities automatically.The experimental results are conducted on two datasets to measure the over-all accuracy of proposed algorithms that achieved high results when compared to machine learning algorithms.

铁路周界入侵目标多尺度特征感知算法

准确识别侵入周界范围内的人和大型牲畜是铁路周界入侵视频智能分析技术的重点内容,对保障铁路安全运营具有重要意义。基于现有目标检测算法难以处理铁路监控场景中入侵目标呈现显著尺度变化的状况,提出一种多输入双输出神经网络(Multiple Input Double Output Network,MIDO-Net)和基于自适应特征加权融合的目标多尺度特征感知算法。首先,通过MIDO-Net多层级联的多输入和双输出网络结构,提取图像目标更丰富的多尺度特征信息;其次,依据骨干网络多阶段的特点,先将多级特征上采样至统一分辨率,再利用注意力模块和自适应参数对多级特征进行加权;然后,将特征输入到检测头中完成铁路周界入侵的识别;最后,通过视觉目标类别(Visual Object Classes,VOC)公共数据集和制作的多场景、多尺度铁路异物侵限数据集,对算法进行验证。结果表明:提出的多尺度特征感知算法在VOC公共数据集中的检测精确率达83.3%,在多场景、多尺度铁路异物侵限数据集中的检测精确率达91.1%,平均召回率达56.2%,均优于当前广泛使用的各种特征提取骨干网络;算法检测速率为45帧·s^(-1),优于同类型的骨干网络,且能满足铁路场景的行人实时监测需求。

基于改进YOLOv网络的外观检测研究

外观检测涉及对图像或视频中的物体进行准确和高效的识别和定位,为了解决物体表面小尺寸目标检测的问题,研究通过优化YOLOv3网络模型,引入多尺度检测和深度可分离卷积技术来提高检测精度和模型效率,以增强对小尺寸目标的识别能力,再采用深度可分离卷积技术来减少计算量,并提高模型的训练效果;实验结果表明,研究模型在物体表面小尺寸检测方面取得显著提升;与其他金属表面损伤检测算法相比,优化后的YOLOv3实现了71.52%的检测精度,超越Faster R-CNN 6.83%;尽管Faster R-CNN在准确性方面优异但速度慢,SSD速度较快但不及YOLOv2;而YOLOv2虽速度快但精度稍低;相对于原始模型,研究算法的平均精度提升了7.77个百分点,达到了79.21%;虽然网络深度的提升稍增计算量,略有检测速率下降,但引入深度可分离卷积后,检测速度达到36.2帧/秒,仅较原模型稍低2.4帧/秒;研究可以优化算法,提高小尺寸目标检测的准确性和鲁棒性,推动其在计算机视觉领域的广泛应用。

结合遗传算子的并行萤火虫算法及在车间调度中的应用

论文提出了一种结合遗传算子的并行萤火虫算法,该算法借鉴了萤火虫闪烁移动的思想,对两个种群进行同步并行迭代求解,以提升算法的求解速度和质量;在其中一个种群中引入多尺度协同变异算子,利用不同大小方差的自适应高斯变异机制使整个种群以尽量分散的变异尺度来对解空间进行更详尽的探索,从而使整个种群进行有效变异。函数优化结果表明了该算法的有效性,该算法用于求解以最小化最大完工时间为优化目标的流水车间调度问题,实验结果表明,较传统的单一算法而言,结合遗传算子的并行萤火虫算法在求解车间调度问题方面具有更好的性能。

光钟与氢钟联合的时间尺度算法研究

光钟的频率稳定度和不确定度达到了10-18量级,使其有望成为下一代的时间频率标准,并可能用来重新定义国际单位“秒”.时间尺度作为准确、连续标记时间流逝过程的基准,是高精度时间产生的基础.时间尺度的产生需要依赖连续稳定运行的原子钟,而光钟作为实验室原型设备,一般不能连续运行,因此光钟参与时间尺度计算是个难点问题.提出将Vondrak-Cepek组合滤波算法应用在光钟与氢钟联合计算的时间尺度,以解决间歇运行的光钟参与时间尺度计算的难点问题.首先利用氢钟的时差数据,采用ALGOS算法计算获得连续稳定的氢钟时间尺度.其次利用Vondrak-Cepek组合滤波算法将氢钟时间尺度与光钟的数据综合,获得光钟参与计算的联合时间尺度.最终试验结果证明, Vondrak-Cepek组合滤波算法有效提升光钟与氢钟联合时间尺度的性能,该时间尺度与协调世界时(Coordinated Universal Time, UTC)的时间偏差达到亚纳秒量级.

Misp-YOLO:加油站场景目标检测

针对Yolov3-Tiny算法在加油站监控场景检测时由于数据特征提取不充分而导致检测精度低、漏检率高等问题,提出一种基于加油站场景的Misp-YOLO(You Only Look Once)目标检测算法。首先引入Mosaic数据增强算法,使图片包含更多特征信息;其次使用InceptionV2和PSConv(Poly-Scale Convolution)多尺度特征提取方法提升网络多尺度预测能力;最后结合scSE(Concurrent Spatial and Channel ‘Squeeze&Excitation’)注意力机制,重构主干网络输出特征。实验结果证明该算法具有较高检测准确度,并且检测速度满足实际需求。优化后的算法性能得到极大提升,可推广应用于其他目标检测中。

基于ACE与YOLOv5的电力遥感图像检测算法

针对电力遥感图像采集时存在大量浓烟以及数据样本少等问题,提出一种基于对数变换的改进型自动色彩均衡与改进后YOLOv5s模型的遥感图像去雾检测算法,旨在通过提高数据集的图像质量进而提高检测网络的检测精度。构建的改进型自动色彩均衡对电力遥感图像去雾增强,并通过图像质量和特征提取两方面进行了实验数据对比,实验结果表明改进的自动色彩均衡算法优于其它算法。其次,通过YOLOv5s检测算法对增强后的数据集进行训练,引入mosaic数据增强算法,并通过构建ghost卷积模块和NAM注意力模块降低了网络参数、提升了网络检测精度。

基于社团结构的网络空间复杂网络多尺度构建算法

网络空间要素及要素间关系构成的复杂网络进行可视化对感知网络结构和发现网络空间规律具有重要意义。针对网络空间复杂网络可视化时出现的大量节点和连边相互压盖造成的视觉混乱问题和基于层次聚类思想的社团划分算法构建的多尺度网络只能得到有限的尺度问题,提出一种基于社团结构的网络空间复杂网络多尺度构建方法。该方法基于改进的LFM社团发现算法,结合节点综合重要性进行社团核心节点的选取和依据社团间连边数量设定阈值建立重要节点不同层次连边,通过调整参数实现网络空间复杂网络多尺度构建。实验结果表明,该方法在构建多尺度网络过程中能够保留网络空间中的重要节点,相较于基于层次聚类思想的Louvain社团发现算法能够发现更多尺度的网络结构,且具有较好的连续性。

一种时频尺度下的多元短期电力负荷组合预测方法

随机因素的增加导致电力负荷数据成分日渐复杂,使短期负荷预测的难度逐渐增大。针对该问题,提出一种时频尺度下的时间卷积网络与多元线性回归相融合的组合预测模型。利用自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)在时频域上将负荷数据分解为若干个频率特征不同的本征模态分量,在模糊熵准则下聚类为随机项和趋势项。采用皮尔逊系数从诸多影响因素中筛选出与电力负荷高度相关的特征,鉴于小时间尺度分析更易于挖掘局部细节特征,分别构建了随机项与趋势项的细颗粒度特征集。利用具有强非线性处理能力的时间卷积网络(temporal convolutional network,TCN)去预测随机项,利用结构简单及线性拟合效果好的多元线性回归(multiplelinearregression,MLR)去预测趋势项,将二者的预测结果进行叠加重构后获得最终预测值。在新加坡和比利时两组数据集上的实验结果证明:所提模型具有较高的预测精度、较好的泛化性能及鲁棒性。

NIM5驾驭氢钟守时能力分析

时间频率量值源头的独立自主是建设我国综合PNT体系的重要基础。为进一步评估基于我国国家秒长基准的原子时标守时能力,利用改进的有限脉冲响应钟差预测与频率调控方法,对激光冷却铯原子喷泉钟与氢钟的频差实测数据进行后处理,分别产生了自主型时标和溯源型时标。通过国际原子时合作链路将两个时标与协调世界时进行了长期比对实验,结果表明:2021年12月~2022年12月期间,两个时标的时间偏差均优于±4 ns、频率稳定度均优于8×10^(-16)/5 d。

基于遗传-模式搜索算法的微尺度管控区域大气污染物PM2.5溯源

针对微尺度管控区域可能发生的大气污染提出有效的靶向诊断方法-结合高斯烟羽模型和遗传-模式搜索算法的大气污染物分布式溯源方法.将污染源反算模型得到的污染物理论质量浓度与传感器网络观测值的数据对应关系作为目标函数,使用模式搜索算法嵌入遗传算法加快反算模型的搜索过程,反算得到污染源强度和位置.依托杭州市亚运板球场馆大气感知器网络进行实验验证,监测2021年10月PM2.5质量浓度、气象数据,对所提出的混合式大气污染溯源方法进行实验验证.实验结果表明:改进遗传-模式搜索算法对于多维变量的搜索效果较好,能快速精准地反算污染源的位置和强度,可以为微尺度管控区域突发性气体污染防治提供应急决策参考.

数据驱动的半无限介质裂纹识别模型研究

缺陷识别是结构健康监测的重要研究内容,对评估工程结构的安全性具有重要的指导意义,然而,准确确定结构缺陷的尺寸十分困难.论文提出了一种创新的数据驱动算法,将比例边界有限元法(scaled boundary finite element methods,SBFEM)与自编码器(autoencoder,AE)、因果膨胀卷积神经网络(causal dilated convolutional neural network,CDCNN)相结合用于半无限介质中的裂纹识别.在该模型中,SBFEM用于模拟波在含不同裂纹状缺陷半无限介质中的传播过程,对于不同的裂纹状缺陷,仅需改变裂纹尖端的比例中心和裂纹开口处节点的位置,避免了复杂的重网格过程,可高效地生成足够的训练数据.模拟波在半无限介质中传播时,建立了基于瑞利阻尼的吸收边界模型,避免了对结构全域模型进行计算.搭建了CDCNN,确保了时序数据的有序性,并获得更大的感受野而不增加神经网络的复杂性,可捕捉更多的历史信息,AE具有较强的非线性特征提取能力,可将高维的原始输入特征向量空间映射到低维潜在特征向量空间,以获得低维潜在特征用于网络模型训练,有效提升了网络模型的学习效率.数值算例表明:提出的模型能够高效且准确地识别半无限介质中裂纹的量化信息,且AE-CDCNN模型的识别效率较单CDCNN模型提高了约2.7倍.