Comparison of debris flow susceptibility assessment methods:support vector machine,particle swarm optimization,and feature selection techniques

The selection of important factors in machine learning-based susceptibility assessments is crucial to obtain reliable susceptibility results.In this study,metaheuristic optimization and feature selection techniques were applied to identify the most important input parameters for mapping debris flow susceptibility in the southern mountain area of Chengde City in Hebei Province,China,by using machine learning algorithms.In total,133 historical debris flow records and 16 related factors were selected.The support vector machine(SVM)was first used as the base classifier,and then a hybrid model was introduced by a two-step process.First,the particle swarm optimization(PSO)algorithm was employed to select the SVM model hyperparameters.Second,two feature selection algorithms,namely principal component analysis(PCA)and PSO,were integrated into the PSO-based SVM model,which generated the PCA-PSO-SVM and FS-PSO-SVM models,respectively.Three statistical metrics(accuracy,recall,and specificity)and the area under the receiver operating characteristic curve(AUC)were employed to evaluate and validate the performance of the models.The results indicated that the feature selection-based models exhibited the best performance,followed by the PSO-based SVM and SVM models.Moreover,the performance of the FS-PSO-SVM model was better than that of the PCA-PSO-SVM model,showing the highest AUC,accuracy,recall,and specificity values in both the training and testing processes.It was found that the selection of optimal features is crucial to improving the reliability of debris flow susceptibility assessment results.Moreover,the PSO algorithm was found to be not only an effective tool for hyperparameter optimization,but also a useful feature selection algorithm to improve prediction accuracies of debris flow susceptibility by using machine learning algorithms.The high and very high debris flow susceptibility zone appropriately covers 38.01%of the study area,where debris flow may occur under intensive human activities and heavy rainfall events.

A Reference Vector-Assisted Many-Objective Optimization Algorithm with Adaptive Niche Dominance Relation

It is still a huge challenge for traditional Pareto-dominatedmany-objective optimization algorithms to solve manyobjective optimization problems because these algorithms hardly maintain the balance between convergence and diversity and can only find a group of solutions focused on a small area on the Pareto front,resulting in poor performance of those algorithms.For this reason,we propose a reference vector-assisted algorithmwith an adaptive niche dominance relation,for short MaOEA-AR.The new dominance relation forms a niche based on the angle between candidate solutions.By comparing these solutions,the solutionwith the best convergence is found to be the non-dominated solution to improve the selection pressure.In reproduction,a mutation strategy of k-bit crossover and hybrid mutation is used to generate high-quality offspring.On 23 test problems with up to 15-objective,we compared the proposed algorithm with five state-of-the-art algorithms.The experimental results verified that the proposed algorithm is competitive.

OPTIMIZATION METHOD ON IMPELLER MERIDIONAL CONTOUR AND 3D BLADE

为 3D 片和南方的轮廓的一个优化方法离心或混合流动 impeller 基于 3D 粘滞计算液体动力学(CFD ) 分析被建议。片是间接地用尖动量的 parameterized 并且由反的设计方法计算。设计变量被分开成二个范畴：南方的轮廓设计变量和片设计变量。第一，仅仅片与南方的轮廓用基因算法被优化仍然是的常数。有根据实验理论的设计策划的训练样品数据的人工的神经网络(ANN ) 技术被采用构造在片设计变量和 impeller 性能之间的反应关系。然后，基于 ANN 接近了在南方的轮廓设计变量和 impeller 性能之间的关系，南方的轮廓被优化。更少设计变量和更少计算努力在这个方法被要求可以广泛地在三尺寸的 impellers 的优化被使用。在头和效率被 12.9% 和 4.5% 分别地提高的地方，在混合流动泵的优化 impeller 证实这个最新建议的方法的有效性。

An Optimization Approach of Rotor Contour for Variable Reluctance Resolver

An effective approach for optimizing the rotor contour for variable reluctance(VR)resolver is presented.Using this approach,the procedure for optimizing the rotor is divided into two parts:the establishment of initial shape curve,and then computation for the optimization.In order to simplify the process of the former,a shape function is constructed.And the latter is carried out by Taguchi optimization method and finite element method(FEM).An example of a 3-10 VR resolver is used to present the procedure of the optimization,and the testing results confirmed the effectivity of the approach.

Gradient-based optimization method for producing a contoured beam with single-fed reflector antenna

A gradient-based optimization method for producing a contoured beam by using a single-fed reflector antenna is presented. First, a quick and accurate pattern approximation formula based on physical optics(PO) is adopted to calculate the gradients of the directivity with respect to reflector's nodal displacements. Because the approximation formula is a linear function of nodal displacements, the gradient can be easily derived. Then, the method of the steepest descent is adopted, and an optimization iteration procedure is proposed. The iteration procedure includes two loops: an inner loop and an outer loop. In the inner loop, the gradient and pattern are calculated by matrix operation, which is very fast by using the pre-calculated data in the outer loop. In the outer loop, the ideal terms used in the inner loop to calculate the gradient and pattern are updated, and the real pattern is calculated by the PO method. Due to the high approximation accuracy, when the outer loop is performed once, the inner loop can be performed many times, which will save much time because the integration is replaced by matrix operation. In the end, a contoured beam covering the continental United States(CONUS) is designed, and simulation results show the effectiveness of the proposed algorithm.

Mango Pest Detection Using Entropy-ELM with Whale Optimization Algorithm

Image processing,agricultural production,andfield monitoring are essential studies in the researchfield.Plant diseases have an impact on agricultural production and quality.Agricultural disease detection at a preliminary phase reduces economic losses and improves the quality of crops.Manually identifying the agricultural pests is usually evident in plants;also,it takes more time and is an expensive technique.A drone system has been developed to gather photographs over enormous regions such as farm areas and plantations.An atmosphere generates vast amounts of data as it is monitored closely;the evaluation of this big data would increase the production of agricultural production.This paper aims to identify pests in mango trees such as hoppers,mealybugs,inflorescence midges,fruitflies,and stem borers.Because of the massive volumes of large-scale high-dimensional big data collected,it is necessary to reduce the dimensionality of the input for classify-ing images.The community-based cumulative algorithm was used to classify the pests in the existing system.The proposed method uses the Entropy-ELM method with Whale Optimization to improve the classification in detecting pests in agricul-ture.The Entropy-ELM method with the Whale Optimization Algorithm(WOA)is used for feature selection,enhancing mango pests’classification accuracy.Support Vector Machines(SVMs)are especially effective for classifying while users get var-ious classes in which they are interested.They are created as suitable classifiers to categorize any dataset in Big Data effectively.The proposed Entropy-ELM-WOA is more capable compared to the existing systems.

Smart Fraud Detection in E-Transactions Using Synthetic Minority Oversampling and Binary Harris Hawks Optimization

Fraud Transactions are haunting the economy of many individuals with several factors across the globe.This research focuses on developing a mechanism by integrating various optimized machine-learning algorithms to ensure the security and integrity of digital transactions.This research proposes a novel methodology through three stages.Firstly,Synthetic Minority Oversampling Technique(SMOTE)is applied to get balanced data.Secondly,SMOTE is fed to the nature-inspired Meta Heuristic(MH)algorithm,namely Binary Harris Hawks Optimization(BinHHO),Binary Aquila Optimization(BAO),and Binary Grey Wolf Optimization(BGWO),for feature selection.BinHHO has performed well when compared with the other two.Thirdly,features from BinHHO are fed to the supervised learning algorithms to classify the transactions such as fraud and non-fraud.The efficiency of BinHHO is analyzed with other popular MH algorithms.The BinHHO has achieved the highest accuracy of 99.95%and demonstrates amore significant positive effect on the performance of the proposed model.

Recognition model and algorithm of projectiles by combining particle swarm optimization support vector and spatial-temporal constrain

In order to improve the recognition rate and accuracy rate of projectiles in six sky-screens intersection test system,this work proposes a new recognition method of projectiles by combining particle swarm optimization support vector and spatial-temporal constrain of six sky-screens detection sensor.Based on the measurement principle of the six sky-screens intersection test system and the characteristics of the output signal of the sky-screen,we analyze the existing problems regarding the recognition of projectiles.In order to optimize the projectile recognition effect,we use the support vector machine and basic particle swarm algorithm to form a new recognition algorithm.We set up the particle swarm algorithm optimization support vector projectile information recognition model that conforms to the six sky-screens intersection test system.We also construct a spatial-temporal constrain matching model based on the spatial geometric relationship of six sky-screen intersection,and form a new projectile signal recognition algorithm with six sky-screens spatial-temporal information constraints under the signal classification mechanism of particle swarm optimization algorithm support vector machine.Based on experiments,we obtain the optimal penalty and kernel function radius parameters in the PSO-SVM algorithm;we adjust the parameters of the support vector machine model,train the test signal data of every sky-screen,and gain the projectile signal classification results.Afterwards,according to the signal classification results,we calculate the coordinate parameters of the real projectile by using the spatial-temporal constrain of six sky-screens detection sensor,which verifies the feasibility of the proposed algorithm.

Precise Multi-Class Classification of Brain Tumor via Optimization Based Relevance Vector Machine

The objective of this research is to examine the use of feature selection and classification methods for distinguishing different types of brain tumors.The brain tumor is characterized by an anomalous proliferation of brain cells that can either be benign or malignant.Most tumors are misdiagnosed due to the variabil-ity and complexity of lesions,which reduces the survival rate in patients.Diagno-sis of brain tumors via computer vision algorithms is a challenging task.Segmentation and classification of brain tumors are currently one of the most essential surgical and pharmaceutical procedures.Traditional brain tumor identi-fication techniques require manual segmentation or handcrafted feature extraction that is error-prone and time-consuming.Hence the proposed research work is mainly focused on medical image processing,which takes Magnetic Resonance Imaging(MRI)images as input and performs preprocessing,segmentation,fea-ture extraction,feature selection,similarity measurement,and classification steps for identifying brain tumors.Initially,the medianfilter is practically applied to the input image to reduce the noise.The graph-cut segmentation technique is used to segment the tumor region.The texture feature is extracted from the output of the segmented image.The extracted feature is selected by using the Ant Colony Opti-mization(ACO)algorithm to improve the performance of the classifier.This prob-abilistic approach is used to solve computing issues.The Euclidean distance is used to calculate the degree of similarity for each extracted feature.The selected feature value is given to the Relevance Vector Machine(RVM)which is a multi-class classification technique.Finally,the tumor is classified as abnormal or nor-mal.The experimental result reveals that the proposed RVM technique gives a better accuracy range of 98.87%when compared to the traditional Support Vector Machine(SVM)technique.

Moth Flame Optimization Based FCNN for Prediction of Bugs in Software

The software engineering technique makes it possible to create high-quality software.One of the most significant qualities of good software is that it is devoid of bugs.One of the most time-consuming and costly software proce-dures isfinding andfixing bugs.Although it is impossible to eradicate all bugs,it is feasible to reduce the number of bugs and their negative effects.To broaden the scope of bug prediction techniques and increase software quality,numerous causes of software problems must be identified,and successful bug prediction models must be implemented.This study employs a hybrid of Faster Convolution Neural Network and the Moth Flame Optimization(MFO)algorithm to forecast the number of bugs in software based on the program data itself,such as the line quantity in codes,methods characteristics,and other essential software aspects.Here,the MFO method is used to train the neural network to identify optimal weights.The proposed MFO-FCNN technique is compared with existing methods such as AdaBoost(AB),Random Forest(RF),K-Nearest Neighbour(KNN),K-Means Clustering(KMC),Support Vector Machine(SVM)and Bagging Clas-sifier(BC)are examples of machine learning(ML)techniques.The assessment method revealed that machine learning techniques may be employed successfully and through a high level of accuracy.The obtained data revealed that the proposed strategy outperforms the traditional approach.

基于贝叶斯优化支持向量回归的流线型箱梁颤振气动外形优化方法

为解决风洞试验耗时费力和计算流体动力学(CFD)计算量大的问题,提出了一套新型流线型箱梁断面颤振性能气动外形优化方法.以风嘴参数为设计变量,利用CFD获取断面三分力系数,以准定常理论估算的颤振临界风速为优化目标.根据贝叶斯优化支持向量回归构建代理模型,利用混合加点法更新模型,通过寻优算法确定最优断面.以虎门大桥为例,得到桥梁在可行域内颤振性能最佳的断面方案.结果表明,风嘴升高,颤振临界风速先增后减,相对高度为0.6时整体性能较优,相对高度为0.7时可获得最优断面.底板宽增加,颤振性能显著降低,下斜腹板倾角为14°~16°时颤振性能最优.断面优化后桥梁颤振临界风速相比原始断面提升约31%.

基于轴箱垂向振动加速度的地铁车轮失圆状态诊断方法

首先,建立卷积神经网络、深度置信网络、支持向量机和以一维卷积神经网络全连接层特征为输入的支持向量机模型(1DCNN-SVM),对比上述模型在地铁车轮失圆状态分类识别上的效果;其次,利用代理模型构建轴箱垂向加速度均方根与车速和多边形磨耗幅值之间的映射关系;最后,通过智能优化算法逆向求解幅值,对比不同代理模型和智能优化算法在多边形磨耗幅值识别上的适用性。研究结果表明:1DCNN-SVM模型在正常、低阶多边形、高阶多边形、随机非圆车轮4类典型的车轮不圆度状态分类识别中取得99.82%的准确性,相比另外3种分类方法,其泛化性能和强化学习能力都具有明显的优势。在车轮多边形磨耗幅值识别方面,基于克里金模型(KSM)和粒子群算法(PSO)的波深识别模型具有更好的预测稳定性和时效性。

基于特征融合和B-SVM的鸟鸣声识别算法

为了实现在野外通过低成本嵌入式系统识别鸟类,提出了基于特征融合和B-SVM的鸟鸣声识别方法。对鸟鸣声信号提取梅尔频率倒谱系数、翻转梅尔频率倒谱系数、短时能量和短时过零率组成特征参数,通过线性判别算法对特征参数进行特征融合。利用黑寡妇算法通过测试集对支持向量机模型的核参数和损失值进行优化得到B-SVM模型。利用Xeno-canto鸟鸣声数据集对本文算法进行了测试,结果表明该方法的识别准确率为93.23%。算法维度参数的大小和融合特征维度的高低是影响算法识别效果的重要因素。在相同条件下,文中所提的基于特征融合和B-SVM模型的鸟鸣声识别算法相较于其他特征参数和模型,识别的准确率更高,为野外鸟类识别提供了参考。

基于沙地猫群优化–最小二乘支持向量机的动态NOx排放预测

针对火电机组频繁调峰导致机组燃烧状态不稳,进而导致锅炉出口NOx浓度波动范围大的问题,提出一种基于沙地猫群优化(sand cat sarm optimization,SCSO)的最小二乘支持向量机(leastsquaressupportvectormachine,LSSVM) NOx动态预测模型。首先利用k近邻互信息计算时间延迟的同时筛选辅助变量。然后,基于SCSO算法进行输入变量阶次的选择。使用包含辅助变量时间延迟和阶次的信息作为模型的输入,SCSO算法优化最小二乘支持向量机参数,建立动态NOx排放最小二乘支持向量机预测模型(SCSO-LSSVM动态软测量模型)。最后将模型与未加入迟延的LSSVM模型,加入迟延的LSSVM模型和粒子群优化算法(particle swarm optimization,PSO)优化最小二乘支持向量机参数的动态软测量模型进行对比验证。结果表明,相较于其他模型,该文建立SCSO-LSSVM动态软测量模型均方根误差、平均绝对误差、平均绝对误差最小,预测精度最高,而且在NOx浓度剧烈波动时也能够较好地预测NOx浓度,具有很好的动态特性。

二元广义反码与最优LCD码

基于二元线性码的定义向量理论,引入广义反码及其定义向量概念,确立广义反码、它的参数与二元最优线性码之间的联系。利用广义反码的性质和参数研究对应二元最优线性码的线性补对偶(LCD)性质,证明11类二元最优线性码不是LCD码。该方法突破现有方法的局限性,为研究高维二元LCD的参数确定与构造问题提供了可借鉴的新理论和新方法。

基于PSO-SVR模型预测粮食孔隙率

利用自制粮食孔隙率测定仪,采用直接测量法对不同受压状态下的粮食单元体孔隙率进行测量,得到不同粮种、不同含水率和不同压力下的粮食单元体孔隙率。通过粒子群算法(PSO)优化支持向量回归(SVR),建立基于PSO-SVR粮食单元体孔隙率的预测模型,并与随机森林(RF)模型、SVR模型对比分析其性能。结果表明:PSO-SVR模型的各项性能指标均优于RF模型和SVR模型。PSO-SVR模型测试样本的均方误差(MSE)为0.0660、决定系数(R^(2))为0.9340、平均绝对误差(MAE)为0.2000,相较其他2种模型,该模型的预测结果误差小,具有较高的预测精度,可以有效预测粮食在不同压力下的孔隙率。

长向量处理器高效RNN推理方法

模型深度的不断增加和处理序列长度的不一致对循环神经网络在不同处理器上的性能优化提出巨大挑战。针对自主研制的长向量处理器FT-M7032,实现了一个高效的循环神经网络加速引擎。该引擎采用行优先矩阵向量乘算法和数据感知的多核并行方式,提高矩阵向量乘的计算效率;采用两级内核融合优化方法降低临时数据传输的开销;采用手写汇编优化多种算子,进一步挖掘长向量处理器的性能潜力。实验表明,长向量处理器循环神经网络推理引擎可获得较高性能,相较于多核ARM CPU以及Intel Golden CPU,类循环神经网络模型长短记忆网络可获得最高62.68倍和3.12倍的性能加速。

基于高维混合模型的离心泵叶轮子午面优化设计

为提高离心泵在设计工况下的运行效率和扬程,提出一种基于高维混合模型的离心泵叶轮优化设计方法.选取一台比转数为157的单级离心泵作为研究对象,通过CFturbo软件对优化变量进行参数化,然后结合数值模拟获得高维混合模型的训练集.在此基础上采用获取的训练集通过MATLAB机器学习得出效率、扬程与优化参数之间关于支持向量回归的高维模型,并采用遗传算法寻优.在设计工况下,所拟合的高维混合模型预测的效率和扬程值比原模型分别高1.5%和3.2 m,数值模拟验证优化方案的效率和扬程分别比原模型高0.9%和2.1 m.算例研究表明,将高维混合模型应用于离心泵叶轮的优化设计中可以实现快速寻优并提高离心泵水力性能.

基于FBG信号和DECE-PCA-BHOSVM的变压器绕组径向松动状态评估

变压器作为电力系统的关键设备,其绕组松动状态的识别对电网的稳定运行具有重要意义。针对传统监测方法环境干扰较大、应用复杂等问题,提出了使用两类不同的布拉格光纤光栅(Fiber bragg grating,FBG)传感器采集变压器绕组关键测点温度与应变信号,经快速解耦与自适应噪声完备集合经验模态分解后(Fast decoupling and complete ensemble empirical mode decomposition with adaptive noise,DECE),提取关键参数并进行主元分析(Principal component analysis,PCA)。对降维后的特征采用基于黑洞优化的支持向量机(Support vector machine based on black hole optimization,BHOSVM)进行分类,实现对变压器绕组径向松动状态的监测与定位。诊断结果表明,所提诊断方法对变压器绕组径向松动状态的识别准确率达到96.8%。

基于VMD和GA-SVM的矿井地震自适应噪声压制方法

煤矿井下地震信号往往呈现出复杂的波场特性且伴随着大量噪音干扰,导致地震信号的初至拾取精度降低,从而影响地震数据的反演与解释。针对复杂干扰环境下采集的低信噪比地震信号,提出了基于变分模态分解(VMD)和遗传算法优化支持向量机(GA-SVM)的地震噪声压制与初至提取方法,以提高煤矿井下复杂噪声条件下的地震信号质量。采用变分模态分解对含噪地震信号进行自适应分解,得到数个的变分模态分量(IMF);对VMD分解得到的IMF分量进行特征提取,将提取所得的信号特征作为信号有效性判别的依据;利用遗传算法对支持向量机模型进行优化,得到最优的惩罚因子c与核函数参数g;利用优化后的支持向量机模型对IMF分量进行有效性判别并将有效分量重构成高信噪比信号;通过对人工加噪的地震信号应用噪声压制算法,煤矿井下常见的不同类型噪声被有效地压制,验证了算法的可行性;对矿井巷道实采的地震记录进行噪声压制处理,有效地压制了数据中的干扰噪声,极大程度地提高了地震记录的信噪比,使初至拾取得更加准确。结果表明,基于VMD和GA-SVM的地震噪声压制方法可以很好地提取含噪地震记录中的有效信号,提高初至拾取精度,在矿井复杂干扰条件下具有显著的应用潜力,对解决矿井复杂干扰条件下的地震勘探问题有重要意义。