采用神经网络和支持向量机预测啤酒中乙酸含量

啤酒中的乙酸大多是酵母在发酵过程中产生的。乙酸含量对啤酒风味的影响显著，尤其是含量高于闽值时。因此，控制乙酸的含量对保证啤酒风味一致性非常重要。在本项研究中，采用人工神经网络和支持向量机（SVM）来预测啤酒发酵结束时的乙酸含量。啤酒发酵过程参数和啤酒中乙酸含量之间的关系采用偏最小二乘（PLS）回归法、反向传播神经网络（BP—NN）、径向基函数神经网络（RBF—NN）和最小二乘支持向量机（LS-SVM）进行建模。本研究中所使用的数据来自同一品牌啤酒的146个生产批次。LS—SVM和RBF预测乙酸含量要优于RBP—NN和PLS。对比RBF—NN和LS—SVM，RBF—NN构建的模型可靠性更好，但预测的准确性要低一些。SVM有较好的泛化性，但是模型的可靠性较低。总之，在这项研究中，预测大生产啤酒发酵中的乙酸含量时，LS-SVM模型要优于RBF。

基于形态学小波理论和SVM神经网络的人脸识别

主要研究了快速识别人脸的基本算法,它包括人脸检测和人脸识别两部分.人脸检测部分利用肤色电平的聚类特性和形态学处理检测出准人脸图像,再利用小波特征提取出特征进行人脸认证.人脸识别部分采用支持向量机(SVM)神经网络进行人脸识别.支持向量机神经网络对二类判别具有很强的识别能力.对于N类判别需连续使用N次.该方法识别速度快,且不受发型、头饰、眼镜等的影响.仿真证明了该方法的有效性.

一种基于支持向量机的齿轮箱故障诊断方法

提出了一种基于多分类支持向量机(简称MSVM)的齿轮箱故障诊断方法。先根据齿轮箱故障机理和振动特点,探讨了齿轮箱故障诊断试验方案。再测取齿轮箱振动信号,并提取了能反映齿轮箱运转信息的时频域特征参数。通过结合投票法和决策树的基本思想,有针对性地构造了多分类支持向量机决策结构并将其应用于齿轮箱故障诊断。实际齿轮箱故障诊断试验结果表明,该决策结构较好地解决了小样本学习问题,避免了人工神经网络进行诊断时出现的过学习、收敛速度慢、泛化能力弱等缺点,能有效应用于齿轮箱故障诊断。

基于SVM-BP混合网络的输电线路安全评价模型研究

为了能够科学、客观地评价输电线路安全状态,提出了基于SVM-BP混合网络的输电线路安全分析模型。首先,对天气数据、输电线路标准文件和缺陷数据等进行处理和分析,利用关联规则和主成分分析法对输电线路缺陷数据进行整合,建立输电线路安全状态评价体系;然后,提出了SVM-BP混合网络模型挖掘各因素与缺陷状态间的关联,评价输电线路的安全状态;最后,以某地区输电线路为数据集进行验证,该评价模型的准确率达到97.4%,可以快速准确地评价输电的安全状态,并在灾害性天气下提前做好应对措施,保证输电线路的稳定运行。

基于暂态时-频特征差异的配电网高阻接地故障识别方法

高阻接地故障发生时,故障特征微弱,传统故障识别方法存在特征提取困难、阈值选取灵活性较差的技术瓶颈,导致极端故障场景下出现漏判。为此,提出基于暂态时-频特征差异的配电网高阻接地故障识别方法。首先,结合小波包香农熵量化分析高阻接地故障与正常扰动工况暂态信号的时频分布,发现二者存在显著差异:频域上,扰动工况信号的能量集中于低频,而高阻故障信号能量分布相对均匀;时域上,扰动工况信号能量集中于时间窗的前半段,高阻故障信号能量在整个时间窗内均匀分布。在此基础上,以暂态信号时-频域波形作为输入样本,将传统卷积神经网络(convolutional neural networks,CNN)模型中的softmax分类器改进为支持向量机(support vector machine,SVM)分类器,构建适应配电网高阻接地故障识别小样本场景下的CNN-SVM复合分类模型,以卷积层作为特征提取器,以SVM作为分类器,实现高阻接地故障识别。最后,为论证所提方法具有强适应性的内在原因,利用LIME可解释性分析算法可视化展现模型训练过程中的高关注度区域,从模型分类原理层面证明所提方法不受各种故障条件的影响,克服了传统故障识别方法在极端故障场景下出现漏判的缺陷,能准确识别配电线路末端10 kΩ高阻接地故障。

基于CNN-SVM性别组合分类的单通道语音分离

实际语音分离时,混合语音的说话人性别组合相关信息往往是未知的。若直接在普适的模型上进行分离,语音分离效果欠佳。为了更好地进行语音分离,本文提出一种基于卷积神经网络-支持向量机(CNN-SVM)的性别组合判别模型,来确定混合语音的两个说话人是男-男、男-女还是女-女组合,以便选用相应性别组合的分离模型进行语音分离。为了弥补传统单一特征表征性别组合信息不足的问题,本文提出一种挖掘深度融合特征的策略,使分类特征包含更多性别组合类别的信息。本文的基于CNN-SVM性别组合分类的单通道语音分离方法,首先使用卷积神经网络挖掘梅尔频率倒谱系数和滤波器组特征的深度特征,融合这两种深度特征作为性别组合的分类特征,然后利用支持向量机对混合语音性别组合进行识别,最后选择对应性别组合的深度神经网络/卷积神经网络(DNN/CNN)模型进行语音分离。实验结果表明,与传统的单一特征相比,本文所提的深度融合特征可以有效提高混合语音性别组合的识别率;本文所提的语音分离方法在主观语音质量评估(PESQ)、短时客观可懂度(STOI)、信号失真比(SDR)指标上均优于普适的语音分离模型。

特高压线路工程的工程量组合预测研究

在分析特高压(ultra high voltage,UHV)线路工程的工程量影响因素基础上,根据已有特高压线路工程相关数据特点,提出支持向量机、BP神经网络以及工程相似度三种工程量预测方法,针对单一预测方法的局限性,为进一步提高预测精度,构建基于偏差平方和最小的组合预测模型,组合预测模型可以多角度搜集数据信息,实现各种预测模型之间的取长补短。通过样本测试表明该组合预测模型明显降低了最大误差,缩小了误差波动范围。同时考虑到不可量化因素对特高压线路工程量的影响,利用数理统计中置信区间的估计得到工程量的区间预测值,为特高压线路工程量管控提供技术支撑。

Analyses and predictions of rock cuttabilities under different confining stresses and rock properties based on rock indentation tests by conical pick

The rock indentation tests by a conical pick were conducted to investigate the rock cuttability correlated to confining stress conditions and rock strength.Based on the test results,the regression analyses,support vector machine(SVM)and generalized regression neural network(GRNN)were used to find the relationship among rock cuttability,uniaxial confining stress applied to rock,uniaxial compressive strength(UCS)and tensile strength of rock material.It was found that the regression and SVM-based models can accurately reflect the variation law of rock cuttability,which presented decreases followed by increases with the increase in uniaxial confining stress and the negative correlation to UCS and tensile strength of rock material.Based on prediction models for revealing the optimal stress condition and determining the cutting parameters,the axial boom roadheader with many conical picks mounted was satisfactorily utilized to perform rock cutting in hard phosphate rock around pillar.

Joint application of feature extraction based on EMD-AR strategy and multi-class classifier based on LS-SVM in EMG motion classification

This paper presents an effective and efficient combination of feature extraction and multi-class classifier for motion classification by analyzing the surface electromyografic(sEMG) signals. In contrast to the existing methods,considering the non-stationary and nonlinear characteristics of EMG signals,to get the more separable feature set,we introduce the empirical mode decomposition(EMD) to decompose the original EMG signals into several intrinsic mode functions(IMFs) and then compute the coefficients of autoregressive models of each IMF to form the feature set. Based on the least squares support vector machines(LS-SVMs) ,the multi-class classifier is designed and constructed to classify various motions. The results of contrastive experiments showed that the accuracy of motion recognition is improved with the described classification scheme. Furthermore,compared with other classifiers using different features,the excellent performance indicated the potential of the SVM techniques embedding the EMD-AR kernel in motion classification.

SVM model for estimating the parameters of the probability-integral method of predicting mining subsidence

A new mathematical model to estimate the parameters of the probability-integral method for mining subsidence prediction is proposed.Based on least squares support vector machine(LS-SVM) theory, it is capable of improving the precision and reliability of mining subsidence prediction.Many of the geological and mining factors involved are related in a nonlinear way.The new model is based on statistical theory(SLT) and empirical risk minimization(ERM) principles.Typical data collected from observation stations were used for the learning and training samples.The calculated results from the LS-SVM model were compared with the prediction results of a back propagation neural network(BPNN) model.The results show that the parameters were more precisely predicted by the LS-SVM model than by the BPNN model.The LS-SVM model was faster in computation and had better generalized performance.It provides a highly effective method for calculating the predicting parameters of the probability-integral method.

Daily and Monthly Suspended Sediment Load Predictions Using Wavelet Based Artificial Intelligence Approaches

In the current study, the efficiency of Wavelet-based Least Square Support Vector Machine （WLSSVM） model was examined for prediction of daily and monthly Suspended Sediment Load （SSL） of the Mississippi River. For this purpose, in the first step, SSL was predicted via ad hoc LSSVM and Artificial Neural Network （ANN） models; then, streamflow and SSL data were decomposed into sub- signals via wavelet, and these decomposed sub-time series were imposed to LSSVM and ANN to simulate discharge-SSL relationship. Finally, the ability of WLSSVM was compared with other models in multi- step-ahead SSL predictions. The results showed that in daily SSL prediction, LSSVM has better outcomes with Determination Coefficient （DC）=o.92 than ad hoc ANN with DC=o.88. However unlike daily SSL, in monthly modeling, ANN has a bit accurate upshot. WLSSVM and wavelet-based ANN （WANN） models showed same consequences in daily and different in monthly SSL predictions, and adding wavelet led to more accuracy of LSSVM and ANN. Furthermore, conjunction of wavelet to LSSVM and ANN evaluated via multi-step-ahead SSL predictions and, e.g., DCLssVM=0.4 was increased to the DCwLsSVM=0.71 in 7- day ahead SSL prediction. In addition, WLSSVM outperformed WANN by increment of time horizon prediction.

Support vector regression-based internal model control

This paper proposes a design of internal model control systems for process with delay by using support vector regression(SVR).The proposed system fully uses the excellent nonlinear estimation performance of SVR with the structural risk minimization principle.Closed-system stability and steady error are analyzed for the existence of modeling errors.The simulations show that the proposed control systems have the better control performance than that by neural networks in the cases of the training samples with small size and noises.

Fault detection in flotation processes based on deep learning and support vector machine

Effective fault detection techniques can help flotation plant reduce reagents consumption,increase mineral recovery,and reduce labor intensity.Traditional,online fault detection methods during flotation processes have concentrated on extracting a specific froth feature for segmentation,like color,shape,size and texture,always leading to undesirable accuracy and efficiency since the same segmentation algorithm could not be applied to every case.In this work,a new integrated method based on convolution neural network(CNN)combined with transfer learning approach and support vector machine(SVM)is proposed to automatically recognize the flotation condition.To be more specific,CNN function as a trainable feature extractor to process the froth images and SVM is used as a recognizer to implement fault detection.As compared with the existed recognition methods,it turns out that the CNN-SVM model can automatically retrieve features from the raw froth images and perform fault detection with high accuracy.Hence,a CNN-SVM based,real-time flotation monitoring system is proposed for application in an antimony flotation plant in China.

Forecasting model of residential load based on general regression neural network and PSO-Bayes least squares support vector machine

Firstly,general regression neural network(GRNN) was used for variable selection of key influencing factors of residential load(RL) forecasting.Secondly,the key influencing factors chosen by GRNN were used as the input and output terminals of urban and rural RL for simulating and learning.In addition,the suitable parameters of final model were obtained through applying the evidence theory to combine the optimization results which were calculated with the PSO method and the Bayes theory.Then,the model of PSO-Bayes least squares support vector machine(PSO-Bayes-LS-SVM) was established.A case study was then provided for the learning and testing.The empirical analysis results show that the mean square errors of urban and rural RL forecast are 0.02% and 0.04%,respectively.At last,taking a specific province RL in China as an example,the forecast results of RL from 2011 to 2015 were obtained.

Flame image recognition of alumina rotary kiln by artificial neural network and support vector machine methods

Based on the Fourier transform, a new shape descriptor was proposed to represent the flame image. By employing the shape descriptor as the input, the flame image recognition was studied by the methods of the artificial neural network(ANN) and the support vector machine(SVM) respectively. And the recognition experiments were carried out by using flame image data sampled from an alumina rotary kiln to evaluate their effectiveness. The results show that the two recognition methods can achieve good results, which verify the effectiveness of the shape descriptor. The highest recognition rate is 88.83% for SVM and 87.38% for ANN, which means that the performance of the SVM is better than that of the ANN.

Yarn Properties Prediction Based on Machine Learning Method

Although many works have been done to construct prediction models on yarn processing quality,the relation between spinning variables and yarn properties has not been established conclusively so far.Support vector machines(SVMs),based on statistical learning theory,are gaining applications in the areas of machine learning and pattern recognition because of the high accuracy and good generalization capability.This study briefly introduces the SVM regression algorithms,and presents the SVM based system architecture for predicting yarn properties.Model selection which amounts to search in hyper-parameter space is performed for study of suitable parameters with grid-research method.Experimental results have been compared with those of artificial neural network(ANN)models.The investigation indicates that in the small data sets and real-life production,SVM models are capable of remaining the stability of predictive accuracy,and more suitable for noisy and dynamic spinning process.

Intelligent prediction on performance of high-temperature heat pump systems using different refrigerants

Two new binary near-azeotropic mixtures named M1 and M2 were developed as the refrigerants of the high-temperature heat pump(HTHP).The experimental research was used to analyze and compare the performance of M1 and M2-based in the HTHP in different running conditions.The results demonstrated the feasibility and reliability of M1 and M2 as new high-temperature refrigerants.Additionally,the exploration and analyses of the support vector machine(SVM)and back propagation(BP)neural network models were made to find a practical way to predict the performance of HTHP system.The results showed that SVM-Linear,SVM-RBF and BP models shared the similar ability to predict the heat capacity and power input with high accuracy.SVM-RBF demonstrated better stability for coefficient of performance prediction.Finally,the proposed SVM model was used to assess the potential of the M1 and M2.The results indicated that the HTHP system using M1 could produce heat at the temperature of 130°C with good performance.

Prostate Cancer Risk Prediction and Online Calculation Based on Machine Learning Algorithm

Objective To build a prostate cancer(PCa) risk prediction model based on common clinical indicators to provide a theoretical basis for the diagnosis and treatment of PCa and to evaluate the value of artificial intelligence(AI) technology under healthcare data platforms.Methods After preprocessing of the data from Population Health Data Archive,smuothly clipped absolute deviation(SCAD) was used to select features.Random forest(RF),support vector machine(SVM),back propagation neural network(BP),and convolutional neural network(CNN) were used to predict the risk of PCa,among which BP and CNN were used on the enhanced data by SMOTE.The performances of models were compared using area under the curve(AUC) of the receiving operating characteristic curve.After the optimal model was selected,we used the Shiny to develop an online calculator for PCa risk prediction based on predictive indicators.Results Inorganic phosphorus,triglycerides,and calcium were closely related to PCa in addition to the volume of fragmented tissue and free prostate-specific antigen(PSA).Among the four models,RF had the best performance in predicting PCa(accuracy:96.80%;AUC:0.975,95% CI:0.964-0.986).Followed by BP(accuracy:85.36%;AUC:0.892,95% CI:0.849-0.934) and SVM(accuracy:82.67%;AUC:0.824,95% CI:0.805-0.844).CNN performed worse(accuracy:72.37%;AUC:0.724,95% CI:0.670-0.779).An online platform for PCa risk prediction was developed based on the RF model and the predictive indicators.Conclusions This study revealed the application value of traditional machine learning and deep learning models in disease risk prediction under healthcare data platform,proposed new ideas for PCa risk prediction in patients suspected for PCa and had undergone core needle biopsy.Besides,the online calculation may enhance the practicability of AI prediction technology and facilitate medical diagnosis.

Hybrid Features for an Arabic Word Recognition System

This research proposes and implements an Arabic Sub-Words Recognition System （ASWR）. The system focuses on employing a combination of statistical and structural features to provide complete pattern＇s description and enhances the recognition rate. Support Vector Machines （SVMs） is utilized as a promising pattern recognition tool. In addition to that, the problems of dots and holes are solved in a completely different way from the ones previously employed. The proposed system proceeds in several phases as follows： （1） image acquisition, （2） binarisation, （3） morphological processing, （4） feature extraction, which includes statistical features, i.e., moment invariants, and structural features, i.e., dot number, dot position, and number of holes, features, and （5） classification, using multi-class SVMs and applying a one-against-all technique. The proposed system has been tested using different sets of words and subwords and has achieved a nearly 98.90% recogiaition rate. Comparative results with NNs are also presented.

Application of artificial intelligent systems for real power transfer allocation

The application of various artificial intelligent(AI) techniques,namely artificial neural network(ANN),adaptive neuro fuzzy interface system(ANFIS),genetic algorithm optimized least square support vector machine(GA-LSSVM) and multivariable regression(MVR) models was presented to identify the real power transfer between generators and loads.These AI techniques adopt supervised learning,which first uses modified nodal equation(MNE) method to determine real power contribution from each generator to loads.Then the results of MNE method and load flow information are utilized to estimate the power transfer using AI techniques.The 25-bus equivalent system of south Malaysia is utilized as a test system to illustrate the effectiveness of various AI methods compared to that of the MNE method.