CL2ES-KDBC:A Novel Covariance Embedded Selection Based on Kernel Distributed Bayes Classifier for Detection of Cyber-Attacks in IoT Systems

The Internet of Things(IoT)is a growing technology that allows the sharing of data with other devices across wireless networks.Specifically,IoT systems are vulnerable to cyberattacks due to its opennes The proposed work intends to implement a new security framework for detecting the most specific and harmful intrusions in IoT networks.In this framework,a Covariance Linear Learning Embedding Selection(CL2ES)methodology is used at first to extract the features highly associated with the IoT intrusions.Then,the Kernel Distributed Bayes Classifier(KDBC)is created to forecast attacks based on the probability distribution value precisely.In addition,a unique Mongolian Gazellas Optimization(MGO)algorithm is used to optimize the weight value for the learning of the classifier.The effectiveness of the proposed CL2ES-KDBC framework has been assessed using several IoT cyber-attack datasets,The obtained results are then compared with current classification methods regarding accuracy(97%),precision(96.5%),and other factors.Computational analysis of the CL2ES-KDBC system on IoT intrusion datasets is performed,which provides valuable insight into its performance,efficiency,and suitability for securing IoT networks.

Image Motion Deblurring Based on Salient Structure Selection and L0-2 Norm Kernel Estimation

Single image motion deblurring has been a very challenging problem in the field of image processing. Although there are many researches had been proposed to solve this problem, it still has problems on kernel accuracy. In order to improve the kernel accuracy, an effective structure selection method was used to select the salient structure of the blur image. Then a novel kernel estimation method based on L0-2 norm was proposed. To guarantee the sparse kernel and eliminate the negative influence of details L0-norm was used. And L2-norm was used to ensure the continuity of kernel. Many experiments were done to compare proposed method and state-of-the-art methods. The results show that our method can estimate a better kernel and use less time than previous work, especially when the size of blur kernel is large.

Adaptive Kernel Firefly Algorithm Based Feature Selection and Q-Learner Machine Learning Models in Cloud

CC’s(Cloud Computing)networks are distributed and dynamic as signals appear/disappear or lose significance.MLTs(Machine learning Techniques)train datasets which sometime are inadequate in terms of sample for inferring information.A dynamic strategy,DevMLOps(Development Machine Learning Operations)used in automatic selections and tunings of MLTs result in significant performance differences.But,the scheme has many disadvantages including continuity in training,more samples and training time in feature selections and increased classification execution times.RFEs(Recursive Feature Eliminations)are computationally very expensive in its operations as it traverses through each feature without considering correlations between them.This problem can be overcome by the use of Wrappers as they select better features by accounting for test and train datasets.The aim of this paper is to use DevQLMLOps for automated tuning and selections based on orchestrations and messaging between containers.The proposed AKFA(Adaptive Kernel Firefly Algorithm)is for selecting features for CNM(Cloud Network Monitoring)operations.AKFA methodology is demonstrated using CNSD(Cloud Network Security Dataset)with satisfactory results in the performance metrics like precision,recall,F-measure and accuracy used.

Kernelized Correlation Filter Target Tracking Algorithm Based on Saliency Feature Selection

To address the problem of using fixed feature and single apparent model which is difficult to adapt to the complex scenarios, a Kernelized correlation filter target tracking algorithm based on online saliency feature selection and fusion is proposed. It combined the correlation filter tracking framework and the salient feature model of the target. In the tracking process, the maximum Kernel correlation filter response values of different feature models were calculated respectively, and the response weights were dynamically set according to the saliency of different features. According to the filter response value, the final target position was obtained, which improves the target positioning accuracy. The target model was dynamically updated in an online manner based on the feature saliency measurement results. The experimental results show that the proposed method can effectively utilize the distinctive feature fusion to improve the tracking effect in complex environments.

Dynamic model for predicting nitrogen oxide concentration at outlet of selective catalytic reduction denitrification system based on kernel extreme learning machine

To solve the increasing model complexity due to several input variables and large correlations under variable load conditions,a dynamic modeling method combining a kernel extreme learning machine(KELM)and principal component analysis(PCA)was proposed and applied to the prediction of nitrogen oxide(NO_(x))concentration at the outlet of a selective catalytic reduction(SCR)denitrification system.First,PCA is applied to the feature information extraction of input data,and the current and previous sequence values of the extracted information are used as the inputs of the KELM model to reflect the dynamic characteristics of the NO_(x)concentration at the SCR outlet.Then,the model takes the historical data of the NO_(x)concentration at the SCR outlet as the model input to improve its accuracy.Finally,an optimization algorithm is used to determine the optimal parameters of the model.Compared with the Gaussian process regression,long short-term memory,and convolutional neural network models,the prediction errors are reduced by approximately 78.4%,67.6%,and 59.3%,respectively.The results indicate that the proposed dynamic model structure is reliable and can accurately predict NO_(x)concentrations at the outlet of the SCR system.

增强Kernel学习优化最大边缘投影的人脸识别

针对传统的流形学习算法通常只考虑样本类内几何结构而忽略类间判别信息的问题,提出一种基于增强核学习的最大边缘投影(MMP)算法。首先使用基于增强核学习非线性扩展的MMP采集人脸图像的非线性结构;然后利用核变换技术加强原始输入核函数的判别能力,并且借助于特征向量选择算法改善算法的计算效率;最后,利用基于乘性规则训练的支持向量机完成人脸的识别。在Yale、ORL、PIE三大通用人脸数据库的组合数据集及AR上的实验验证了该算法的有效性。实验结果表明,相比其他几种核学习算法,该算法取得了更好的识别效果。

Selective ensemble modeling based on nonlinear frequency spectral feature extraction for predicting load parameter in ball mills

Strong mechanical vibration and acoustical signals of grinding process contain useful information related to load parameters in ball mills. It is a challenge to extract latent features and construct soft sensor model with high dimensional frequency spectra of these signals. This paper aims to develop a selective ensemble modeling approach based on nonlinear latent frequency spectral feature extraction for accurate measurement of material to ball volume ratio. Latent features are first extracted from different vibrations and acoustic spectral segments by kernel partial least squares. Algorithms of bootstrap and least squares support vector machines are employed to produce candidate sub-models using these latent features as inputs. Ensemble sub-models are selected based on genetic algorithm optimization toolbox. Partial least squares regression is used to combine these sub-models to eliminate collinearity among their prediction outputs. Results indicate that the proposed modeling approach has better prediction performance than previous ones.

Research on Chinese place name recognition based on kernel classifier

A SVMs (Support Vector Machines) based method to identify Chinese place names is presented. In our approach, place name candidate is located according to a rational forming assumption, then SVMs based identification strategy is used to distinguish whether one candidate is true place name or not. Referring to linguistic knowledge, basic semanteme of a contextual word and frequency information of words inside place name candidate are selected as features in our methodology. So dimension in the feature space is reduced dramatically and processing procedure is performed more efficiently. Result of open testing on unregistered place names achieves F-measure 83.25 in 8.17 million words news based on this project.

Network Traffic Prediction Using Radial Kernelized-Tversky Indexes-Based Multilayer Classifier

Accurate cellular network traffic prediction is a crucial task to access Internet services for various devices at any time.With the use of mobile devices,communication services generate numerous data for every moment.Given the increasing dense population of data,traffic learning and prediction are the main components to substantially enhance the effectiveness of demand-aware resource allocation.A novel deep learning technique called radial kernelized LSTM-based connectionist Tversky multilayer deep structure learning(RKLSTM-CTMDSL)model is introduced for traffic prediction with superior accuracy and minimal time consumption.The RKLSTM-CTMDSL model performs attribute selection and classification processes for cellular traffic prediction.In this model,the connectionist Tversky multilayer deep structure learning includes multiple layers for traffic prediction.A large volume of spatial-temporal data are considered as an input-to-input layer.Thereafter,input data are transmitted to hidden layer 1,where a radial kernelized long short-term memory architecture is designed for the relevant attribute selection using activation function results.After obtaining the relevant attributes,the selected attributes are given to the next layer.Tversky index function is used in this layer to compute similarities among the training and testing traffic patterns.Tversky similarity index outcomes are given to the output layer.Similarity value is used as basis to classify data as heavy network or normal traffic.Thus,cellular network traffic prediction is presented with minimal error rate using the RKLSTM-CTMDSL model.Comparative evaluation proved that the RKLSTM-CTMDSL model outperforms conventional methods.

A Sparse Kernel Approximate Method for Fractional Boundary Value Problems

In this paper,the weak pre-orthogonal adaptive Fourier decomposition(W-POAFD)method is applied to solve fractional boundary value problems(FBVPs)in the reproducing kernel Hilbert spaces(RKHSs)W_(0)^(4)[0,1] and W^(1)[0,1].The process of the W-POAFD is as follows:(i)choose a dictionary and implement the pre-orthogonalization to all the dictionary elements;(ii)select points in[0,1]by the weak maximal selection principle to determine the corresponding orthonormalized dictionary elements iteratively;(iii)express the analytical solution as a linear combination of these determined dictionary elements.Convergence properties of numerical solutions are also discussed.The numerical experiments are carried out to illustrate the accuracy and efficiency of W-POAFD for solving FBVPs.

Autonomous Kernel Based Models for Short-Term Load Forecasting

The application of support vector machines to forecasting problems is becoming popular, lately. Several comparisons between neural networks trained with error backpropagation and support vector machines have shown advantage for the latter in different domains of application. However, some difficulties still deteriorate the performance of the support vector machines. The main one is related to the setting of the hyperparameters involved in their training. Techniques based on meta-heuristics have been employed to determine appropriate values for those hyperparameters. However, because of the high noneonvexity of this estimation problem, which makes the search for a good solution very hard, an approach based on Bayesian inference, called relevance vector machine, has been proposed more recently. The present paper aims at investigating the suitability of this new approach to the short-term load forecasting problem.

基于改进SKNet-SVM的网络安全态势评估

为提高网络安全态势评估的准确率,增强稳定性与鲁棒性,提出一种基于改进选择性卷积核卷积神经网络和支持向量机的网络安全态势评估模型。首先,使用改进选择性卷积核代替传统卷积核进行特征提取,提高卷积神经网络感受野变化的自适应性,增强特征之间关联性。然后,将提取的特征输入到支持向量机中进行分类,并使用网格优化算法对支持向量机中的参数进行全局寻优。最后,根据网络攻击影响指标计算网络安全态势值。实验表明,基于改进选择性卷积核卷积神经网络和支持向量机的态势评估模型与传统的卷积神经网络搭建的态势评估模型相比,准确率更高,并且具有更强的稳定性和鲁棒性。

小波DehazeFormer网络的道路交通图像去雾

针对道路交通雾图像对比度低、细节丢失、模糊和失真的问题,提出了一种小波DehazeFormer模型的道路交通图像去雾方法。为提升模型去雾能力,构建了编解码结构的小波DehazeFormer网络,编码器以DehazeFormer与选择性核特征融合模块(Selective kernel feature fusion,SKFF)级联作为骨干网络的基本单元,编码部分由三级这样的基本单元构成,以融合图像的原始信息和去雾后的信息,更好地捕获雾图中关键特征;中间特征层采用局部残差结构,并加入卷积注意力机制(Convolutional Block Attention Module,CBAM),对不同级别的特征赋予不同权重,同时融入内容引导注意力混合方案(Content-guided Attention based Mixup Fusion Scheme,CGAFusion),通过学习空间权重来调整特征;解码部分由DehazeFormer和SKFF构成,采用逐点卷积,在保证网络性能同时,减少网络的参数量;跳跃连接引入小波变换,对不同尺度的特征图进行小波分析,获取不同尺度的高、低频特征,放大交通雾图的细节使得复原图像保留纹理;最后,将原始图像和经解码后输出的特征图融合,获取更多的细节信息。实验结果表明,本文方法相比于基线DehazeFormer网络,其PSNR指标在公开数据集中提升1.32以上,在合成数据集中提升0.56,SSIM指标提升了0.015以上,MSE值有较大幅度降低,下降了23.15以上;Entropy指标提升0.06以上。本文去雾算法对提升交通雾图像的对比度、降低雾图模糊和失真及细节丢失等方面均表现出优良的性能,有助于后续道路交通的智能视觉监控与管理。

复杂场景下一种改进的单目标跟踪算法研究

针对部分复杂场景下目标跟踪存在跟踪框漂移问题,基于孪生候选区域生成网络(SiamRPN),融合通道注意力模块和选择核心模块(SK Module),提出一种单目标跟踪算法CAKSiamRPN。特征提取部分引入高效通道注意模块(ECAM)和基于标准化的通道注意力模块(NCAM),在不降低通道维度的情况下,摒弃相似信息,突出显著特征,关注并提取特定信息;在候选区域生成网络(RPN)嵌入SK Module,增强全局信息嵌入,减少填充操作的影响。将改进算法与SiamRPN及其它经典单目标跟踪算法在OTB100和UAV123数据集上进行实验对比。实验结果表明:跟踪精度和成功率明显提高,能更好地适应复杂场景,具有更强的鲁棒性。

基于Gram-Schmidt正交化和HSIC的核函数选择方法

核方法是一种解决非线性、异构数据的有效方法,核函数的选择问题是核方法中的一个重要课题,对于不同的应用问题,如何选择合适的核函数还没有足够的理论基础,不适当的核函数选取会降低核方法的性能。由此,提出了一种基于Gram-Schmidt正交化(GSO)和Hilbert-Schmidt独立准则的核选择方法(HSIC-GSO),该方法考虑了核函数选择过程中存在的不相关冗余信息。首先,利用GSO消除核函数之间的冗余信息;然后,使用HSIC度量核函数与理想核之间的相似性;最后,得到一组判别能力强、多样性大的基核函数。实验结果表明,HSIC-GSO方法选择的核函数泛化性好,并且提高了MKL的分类性能,验证了所提方法的有效性。

边缘优化和注意力融合的遥感地物分割算法

针对遥感地物图像种类众多且目标边缘较复杂的特点,以及现有分割网络中局部卷积的感受野有限,对图像上下文信息利用不足,导致分割目标边缘模糊以及分割精度低等问题,提出一种基于UNet3+网络的遥感地物分割算法。在解码过程中引入相似性感知点关联算子作为上采样方式,通过聚合特征金字塔中的多个建议,改善目标边界细节的分割能力;在编码过程中引入选择性内核模块,优化下采样方式,以实现神经元的自适应感受野大小,充分地获取目标特征的多尺度信息,精准捕捉有用的细节语义信息;在跳跃连接阶段添加双多尺度注意力模块,对不同尺度的特征进行加权融合,使模型更好地关注局部细节和全局上下文信息。在WHDLD、ISPRS Potsdam数据集上的实验表明,改进算法的平均交并比分别达到了64.4%、75.4%,较基线模型分别提升了约2.6个百分点、3.2个百分点,同时验证了改进算法在分割边缘模糊问题上的有效性。

基于改进灰狼优化核极限学习机的疾病诊断模型

为提高疾病诊断的效率,本文提出一种改进的灰狼优化算法与核极限学习机的混合模型。通过引入一种新的机制提高灰狼优化算法的探索与利用能力,改进的灰狼优化算法在进行特征选择的同时,也对核极限学习机的2个关键参数进行优化,模型在2个疾病数据集上进行实验验证。实验结果显示:提出的模型在准确率、敏感性、特异性等评价指标方面相对于其他混合模型高出约1%~2%,带特征选择的优化模型相对于没有特征选择的模型在评价指标上也高出约1%~2%。结果表明提出的模型具有一定的优势。

基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别

针对多基地水下小目标分类识别问题,本文提出了一种基于核空间联合稀疏表示和指数平滑的多基地水下小目标识别方法 .对水下目标多角度散射信号提取6种典型的具有信息互补性和关联性的特征,提出一种随机森林(Random Forest,RF)和最小冗余最大相关(minimum Redundancy and Maximum Relevance,mRMR)相结合的特征选择方法(RF-mRMR),得出综合的特征重要性排序结果 .通过实验得出分类模型所需的最优特征子集,达到降低数据处理复杂度和提高目标分类结果的目的 .为了捕捉到数据中的高阶结构,在联合稀疏表示模型的基础上,使用核函数将线性不可分的特征数据映射到高维核特征空间.为了充分挖掘稀疏重构后包含在残差波段中的有用信息,使用指数平滑公式对具有一定意义的残差信息进行再利用,最后由核特征空间下的最小误差准则判定目标的类别.应用本文提出的方法对4类目标的海试数据进行识别,结果表明,相较于其他7种对比算法,本文提出的改进方法具有更好的分类性能,而且大多数情况下,本文提出的算法在双基地声呐模式下具有比单基地声呐更高的识别准确率和更低的虚警率.

概率-非概率调查样本的整合推断问题研究:核匹配方法

基于网络便利调查、大数据平台的数据收集方式,在实践中得到了广泛的发展,但获得的样本本质上均是非概率样本。利用非概率样本推断目标总体特征面临着潜在的偏差,如涵盖偏差、自我选择偏差等。近年来,对融合概率调查和非概率调查的数据资源,以估计有限总体特征问题的讨论较多,但依然存在较多问题。在已有研究的基础上,对非概率样本和概率样本均测量了辅助变量,但只有非概率样本测量了研究变量的背景下,介绍基于倾向得分框架的权数构造方法;在倾向得分核匹配方法的基础上,提出了基于融合概率和非概率样本协变量平衡的核函数带宽选择方法,为非概率样本构造倾向得分核匹配权数。模拟结果显示基于倾向得分核匹配的方法能够显著降低非概率样本的偏差,提出的融合样本协变量平衡的带宽方法能够有效减少估计量的相对偏差、绝对相对偏差和标准差。

高光谱结合哈里斯鹰优化核极限学习机鉴别化橘红胎切片年份

化橘红胎是药用历史悠久的广东省道地中药材,由于其制品收藏年份越久远价格越高,市面上常有以次充好的现象。为此,采用高光谱成像技术,结合哈里斯鹰优化核极限学习机对四组不同年份的化橘红胎切片样品进行鉴别。采集四个年份共193个化橘红胎切片样本400~1000 nm的高光谱图像。首先采用主成分分析法(PCA)分析化橘红胎切片的原始反射光谱,然后分别采用Savitzky-Golay平滑(S-G平滑)、多元散射校正(MSC)、标准正态变量交换(SNV)对样本光谱进行预处理并建立核极限学习机(KELM)模型;发现经SNV处理的样本光谱的判别准确率最高,训练集达到99.24%,测试集95.56%;进一步用竞争性自适应重加权算法(CARS)、蒙特卡洛无信息变量消除法(MCUVE)对样本光谱进行特征波长的选择;最后,采用KELM建立判别模型,同时使用哈里斯鹰算法(HHO)优化KELM参数选择并比较建模效果。结果表明:基于HHO-KELM的判别效果相较KELM有0.76%~4.44%的提升,通过MCUVE筛选所得特征波段信息冗余明显减少且精度提升,训练集和测试集最佳准确率均可达100%,故采用高光谱成像技术可以实现对不同年份的化橘红胎切片进行无损鉴别。