Classification using wavelet packet decomposition and support vector machine for digital modulations

To make the modulation classification system more suitable for signals in a wide range of signal to noise rate （SNR）, a feature extraction method based on signal wavelet packet transform modulus maxima matrix （WPTMMM） and a novel support vector machine fuzzy network （SVMFN） classifier is presented. The WPTMMM feature extraction method has less computational complexity, more stability, and has the preferable advantage of robust with the time parallel moving and white noise. Further, the SVMFN uses a new definition of fuzzy density that incorporates accuracy and uncertainty of the classifiers to improve recognition reliability to classify nine digital modulation types （i.e. 2ASK, 2FSK, 2PSK, 4ASK, 4FSK, 4PSK, 16QAM, MSK, and OQPSK）. Computer simulation shows that the proposed scheme has the advantages of high accuracy and reliability （success rates are over 98% when SNR is not lower than 0dB）, and it adapts to engineering applications.

Protein domain boundary prediction by combining support vector machine and domain guess by size algorithm

Successful prediction of protein domain boundaries provides valuable information not only for the computational structure prediction of muhi-domain proteins but also for the experimental structure determination. A novel method for domain boundary prediction has been presented, which combines the support vector machine with domain guess by size algorithm. Since the evolutional information of multiple domains can be detected by position specific score matrix, the support vector machine method is trained and tested using the values of position specific score matrix generated by PSI-BLAST. The candidate domain boundaries are selected from the output of support vector machine, and are then inputted to domain guess by size algorithm to give the final results of domain boundary, prediction. The experimental results show that the combined method outperforms the individual method of both support vector machine and domain guess by size.

Kernel matrix learning with a general regularized risk functional criterion

Kernel-based methods work by embedding the data into a feature space and then searching linear hypothesis among the embedding data points. The performance is mostly affected by which kernel is used. A promising way is to learn the kernel from the data automatically. A general regularized risk functional （RRF） criterion for kernel matrix learning is proposed. Compared with the RRF criterion, general RRF criterion takes into account the geometric distributions of the embedding data points. It is proven that the distance between different geometric distdbutions can be estimated by their centroid distance in the reproducing kernel Hilbert space. Using this criterion for kernel matrix learning leads to a convex quadratically constrained quadratic programming （QCQP） problem. For several commonly used loss functions, their mathematical formulations are given. Experiment results on a collection of benchmark data sets demonstrate the effectiveness of the proposed method.

Binary Image Steganalysis Based on Distortion Level Co-Occurrence Matrix

In recent years,binary image steganography has developed so rapidly that the research of binary image steganalysis becomes more important for information security.In most state-of-the-art binary image steganographic schemes,they always find out the flippable pixels to minimize the embedding distortions.For this reason,the stego images generated by the previous schemes maintain visual quality and it is hard for steganalyzer to capture the embedding trace in spacial domain.However,the distortion maps can be calculated for cover and stego images and the difference between them is significant.In this paper,a novel binary image steganalytic scheme is proposed,which is based on distortion level co-occurrence matrix.The proposed scheme first generates the corresponding distortion maps for cover and stego images.Then the co-occurrence matrix is constructed on the distortion level maps to represent the features of cover and stego images.Finally,support vector machine,based on the gaussian kernel,is used to classify the features.Compared with the prior steganalytic methods,experimental results demonstrate that the proposed scheme can effectively detect stego images.

Using position specific scoring matrix and auto covariance to predict protein subnuclear localization

The knowledge of subnuclear localization in eukaryotic cells is indispensable for under-standing the biological function of nucleus, genome regulation and drug discovery. In this study, a new feature representation was pro-posed by combining position specific scoring matrix (PSSM) and auto covariance (AC). The AC variables describe the neighboring effect between two amino acids, so that they incorpo-rate the sequence-order information;PSSM de-scribes the information of biological evolution of proteins. Based on this new descriptor, a support vector machine (SVM) classifier was built to predict subnuclear localization. To evaluate the power of our predictor, the benchmark dataset that contains 714 proteins localized in nine subnuclear compartments was utilized. The total jackknife cross validation ac-curacy of our method is 76.5%, that is higher than those of the Nuc-PLoc (67.4%), the OET- KNN (55.6%), AAC based SVM (48.9%) and ProtLoc (36.6%). The prediction software used in this article and the details of the SVM parameters are freely available at http://chemlab.scu.edu.cn/ predict_SubNL/index.htm and the dataset used in our study is from Shen and Chou’s work by downloading at http://chou.med.harvard.edu/ bioinf/Nuc-PLoc/Data.htm.

基于拉普拉斯卷积网络和SMM分类器的小麦麦粒识别

为了提高小麦麦粒识别的识别率,采用了拉普拉斯卷积网络(Convolution Network Based on Laplacian Eigenmap,LENet)和支持矩阵机(Support Matrix Machines,SMM)分类器相结合的方法对小麦麦粒进行识别。拉普拉斯卷积网络是一种无反馈的轻量型级联卷积神经网络,可以用来提取小麦麦粒的特征,该网络通过拉普拉斯特征映射来学习网络的参数,输出层通过块直方图编码和矩阵化处理实现,最终提取的特征使用SMM分类器进行分类。通过在建立的小麦麦粒图像数据库上的实验表明,该麦粒识别方法要优于一些传统特征提取分类方法,取得了较好的识别效果。

Using the improved position specific scoring matrix and ensemble learning method to predict drug-binding residues from protein sequences

Identification of the drug-binding residues on the surface of proteins is a vital step in drug discovery and it is important for understanding protein function. Most previous researches are based on the structural information of proteins, but the structures of most proteins are not available. So in this article, a sequence-based method was proposed by combining the support vector machine (SVM)-based ensemble learning and the improved position specific scoring matrix (PSSM). In order to take the local environment information of a drug-binding site into account, an improved PSSM profile scaled by the sliding window and smoothing window was used to improve the prediction result. In addition, a new SVM-based ensemble learning method was developed to deal with the imbalanced data classification problem that commonly exists in the binding site predictions. When performed on the dataset of 985 drug-binding residues, the method achieved a very promising prediction result with the area under the curve (AUC) of 0.9264. Furthermore, an independent dataset of 349 drug- binding residues was used to evaluate the pre- diction model and the prediction accuracy is 84.68%. These results suggest that our method is effective for predicting the drug-binding sites in proteins. The code and all datasets used in this article are freely available at http://cic.scu.edu.cn/bioinformatics/Ensem_DBS.zip.

On Eigen-Matrix Translation Method for Classification of Biological Data

Driven by the challenge of integrating large amount of experimental data, classification technique emerges as one of the major and popular tools in computational biology and bioinformatics research. Machine learning methods, especially kernel methods with Support Vector Machines （SVMs） are very popular and effective tools. In the perspective of kernel matrix, a technique namely Eigen- matrix translation has been introduced for protein data classification. The Eigen-matrix translation strategy has a lot of nice properties which deserve more exploration. This paper investigates the major role of Eigen-matrix translation in classification. The authors propose that its importance lies in the dimension reduction of predictor attributes within the data set. This is very important when the dimension of features is huge. The authors show by numerical experiments on real biological data sets that the proposed framework is crucial and effective in improving classification accuracy. This can therefore serve as a novel perspective for future research in dimension reduction problems.

基于EWT-SVM的雨量识别方法

为了从雨声信号中识别出雨量的大小,提出了一种基于经验小波变换和支持向量机的雨量识别算法。对于采集到的雨声信号先进行去噪,接着对信号进行经验小波变换分解,分解后得到数个经验小波函数分量,然后通过Matlab编程对各个经验小波函数分量进行特征提取,在时域和频域范围内组成评价特征矩阵,最后通过SVM对特征矩阵进行分类识别。通过仿真实验发现,对于同一个信号,经验小波函数相较于经验模态分解有更好的自适应性并且克服了经验模态分解的混叠现象和端点效应。实验结果表明基于经验小波变换和支持向量机的雨量识别方法在雨量识别领域具有良好的效果,研究方法为雨量识别、智能雨量计的发展奠定了良好的基础。

基于改进YOLOv8和多元特征的对虾发病检测方法

[目的/意义]对虾病害严重危害对虾养殖业。针对对虾病害发病快、死亡率高等特点,高密度的工厂化养殖等模式需要一种高效率对虾发病检测方法替代传统人工检查方法,实现对虾发病的及时预警。[方法]提出一种基于改进YOLOv8(You Only Look Once)和多元特征的对虾发病检测方法。首先利用改进YOLOv8网络从对虾夜间水面红外图像中进行前景提取,再利用Farneback光流法和灰度共生矩阵(Gray Level Co-occurrence Matrix,GLCM)提取对虾视频片段的运动特征与图像纹理特征,利用提取到的特征参数构建训练数据集,训练支持向量机(Support Vector Machine,SVM)作为分类器用于检测对虾视频片段,实现对正常与发病的对虾视频片段的检测分类。[结果和讨论]训练好的SVM分类器在300个测试样本上的表现为检测准确率平均值为83%,检测效果达到设计要求。检测误差主要是将发病片段错误地检测为正常片段。该误差主要受水面对虾数量和视频影响。[结论]本研究实现了对对虾发病的检测,提供了一种基于计算机视觉的检测方法。但受条件限制,仅在工厂化养殖环境下进行了实验,尚不能适用于多种养殖环境,仍有改进空间。

Novel approach of crater detection by crater candidate region selection and matrix-pattern-oriented least squares support vector machine

Impacted craters are commonly found on the surface of planets, satellites, asteroids and other solar system bodies. In order to speed up the rate of constructing the database of craters, it is important to develop crater detection algorithms. This paper presents a novel approach to automatically detect craters on planetary surfaces. The approach contains two parts： crater candidate region selection and crater detection. In the first part, crater candidate region selection is achieved by Kanade-Lucas-Tomasi （KLT） detector. Matrix-pattern-oriented least squares support vector machine （MatLSSVM）, as the matrixization version of least square support vector machine （SVM）, inherits the advantages of least squares support vector machine （LSSVM）, reduces storage space greatly and reserves spatial redundancies within each image matrix compared with general LSSVM. The second part of the approach employs MatLSSVM to design classifier for crater detection. Experimental results on the dataset which comprises 160 preprocessed image patches from Google Mars demonstrate that the accuracy rate of crater detection can be up to 88%. In addition, the outstanding feature of the approach introduced in this paper is that it takes resized crater candidate region as input pattern directly to finish crater detection. The results of the last experiment demonstrate that MatLSSVM-based classifier can detect crater regions effectively on the basis of KLT-based crater candidate region selection.

基于正则化正交非负矩阵分解的旋转目标检测方法

小样本的旋转目标检测是指在样本数少的情况下进行旋转目标检测模型的训练,深度学习在旋转目标检测领域往往需要庞大的样本数和计算算力。现有的基于机器学习的旋转目标检测方法大多有着对目标尺度和姿态敏感的缺点。因此提出一种基于正则化正交非负矩阵分解的旋转目标检测方法,来解决小样本的旋转目标检测难题。首先,针对样本不具有各种角度的图片,对样本进行旋转后进行背景填充,这样便于更好的表征学习。其次,提出一种基于正则化正交非负矩阵分解算法对旋转样本的梯度直方图特征进行表征学习。最后,为了测试算法在特征学习后的有效性,利用支持向量机对特征提取后的数据进行训练和测试。实验结果表明本文的目标检测方法在多个数据集中可以取得不错的效果。

基于三维荧光光谱耦合平行因子法的菊花特征组分快速无损鉴别

为提高菊花特征组分的检测效率,提出一种基于三维荧光光谱(three-dimensional excitation emission matrix spectroscopy,3DEEM)耦合平行因子分析(parallel factor analysis,PARAFAC)的快速鉴别方法。以4种菊花为研究对象,在分别获取样品3DEEM矩阵(EEMs)后,首先通过数据预处理去除如拉曼散射和瑞利散射等干扰数据,并剔除异常值,分析光谱特征。然后,采用PARAFAC进行特征提取,通过方差解释率和残差分析法,确定菊花两种特征荧光组分为氨基酸和黄酮类化合物。最后利用支持向量机(support vector machines,SVM)和BP神经网络(back propagation neural network,BPNN)对特征变量进行分析,建立菊花快速无损鉴别模型。SVM和BPNN训练集结果分别为100%、95.93%,测试集结果分别为94.50%、89.61%。结果表明,3DEEM-PARAFAC结合SVM可以实现对菊花特征组分的定性定量分析,能够对菊花进行快速鉴别。

含感应加热电源的电网电压畸变信号智能判别研究

感应加热电源运行过程中,受光伏电网周边环境扰动的影响,造成线路谐波引起电压畸变。提出含感应加热电源的光伏电网母线电压畸变信号判别方法,以期保证光伏电网的稳定运行。建立谐波耦合导纳矩阵模型,完成含感应加热电源的电网电压畸变情况分析;通过波形包络阈值线在时域、小波域、频域上提取电网电压扰动信号特征;基于支持向量机方法完成电压畸变信号的判别。实验结果表明,所提方法在单一扰动信号和多种扰动信号情况下,均具有较高的电压畸变信号识别正确率和效率。

基于SDP和2DLNMF的变压器偏磁状态识别方法

为了有效检测变压器直流偏磁状态,从多通道振动信号融合的角度出发,提出了一种基于对称点模式(SDP)和二维局部非负矩阵分解(2DLNMF)的变压器偏磁状态识别方法。利用SDP算法将采集的多通道振动信号融合成SDP图像特征;然后应用2DLNMF算法对其进行了降维优化,据此构建了基于支持向量机(SVM)算法变压器偏磁状态识别模型。研究结果表明:基于SDP-2DLNMF的信息融合方法充分了展现不同信号间的特征差异,获取的低维特征可有效反映变压器直流偏磁程度,据此建立的SVM状态识别模型具有较高的识别精度,为变压器的状态监测提供了技术支撑。

基于支持向量机的兼类文本分类算法研究

针对兼类文本,提出了两种基于支持向量的分类算法。一种是采用1-a-1方法训练子分类器,通过子分类器得到待分类样本的隶属度矩阵,依据隶属度矩阵每行元素和判定该文本所属类别。另一种是采用1-a-r方法训练子分类器,通过子分类器得到待分类样本的隶属度向量,根据隶属度向量判定该文本所属的类别。实验结果表明,这两种算法都具有较好的准确率、召回率和F1值。

构造稀疏最小二乘支持向量机的快速剪枝算法

为了减少最小二乘支持向量机基本剪枝算法的计算量,提出一种快速剪枝算法。在分析剪枝前后两个最小二乘支持向量机对应线性方程组系数矩阵之间关系的基础上,利用置换矩阵的逆等于其转置的性质和分块矩阵求逆公式,导出两个系数矩阵的子阵的逆之间的递推关系,避免剪枝过程中多次进行高阶矩阵求逆,从而减少计算量。在不考虑计算误差时,该算法理论上得出与基本剪枝算法相同结果的稀疏最小二乘支持向量机。仿真结果表明该算法比基本剪枝算法速度快,而且初始训练样本越多,加速比越大。

基于纹理特征和SVM的QuickBird影像苹果园提取

为提高高空间分辨率遥感影像(高分影像)中苹果园提取精度,基于Quick Bird遥感数据,研究综合光谱特征和纹理特征的苹果园自动提取方法。该方法首先采用最佳指数因子(OIF)获取多光谱波段最佳组合,然后采用不同大小滑动窗口(从3像素×3像素到13像素×13像素)提取全色波段的灰度共生矩阵(GLCM)、分形和空间自相关3种纹理特征并分别与光谱特征组合,最后通过支持向量机(SVM)分类进行苹果园分类识别。研究表明:在分类特征上,与单一光谱或纹理特征相比,光谱特征结合纹理特征能有效提高苹果园提取精度(Fa)和总体分类精度(OA),其中光谱+GLCM纹理(9像素×9像素)分类精度最高,Fa和OA分别为96.99%和96.16%,比光谱+分形纹理分别提高0.63个百分点和1.56个百分点,比光谱+空间自相关纹理显著提高11.92个百分点和9.20个百分点。在分类方法上,通过对比分析SVM、最大似然和神经网络3种方法的分类结果,探明SVM分类识别苹果园精度最高。最后对苹果园提取结果进行面积统计,结果表明GLCM纹理结合SVM分类的苹果园面积估算与目视解译结果的一致性超过98%。

基于多分类器融合的玉米叶部病害识别

针对单分类器识别的局限性和玉米叶部病害的复杂性,该文提出了一种基于自适应加权的多分类器融合的玉米叶部病害识别方法。首先,对采集的玉米叶部病害图像的病害区域分别提取颜色、颜色共生矩阵和颜色完全局部二值模式3种特征,并相应地构建3个基于支持向量机的单分类器;然后,利用K近邻和聚类分析的方法计算各单分类器的自适应动态权值;最后,通过线性加权的方式进行融合判决,得到最终的分类结果。利用该方法对7种常见的玉米叶部病害图片进行了试验,平均识别率达94.71%。结果表明,其性能优于目前常见的单一特征或特征组合构建的同类分类器及多分类器融合方法。研究结果为其他农作物病害诊断提供了借鉴和参考。

基于多光谱图像的不同品种绿茶的纹理识别

为了提高茶叶加工的智能化水平,提出一种基于多光谱图像纹理分析的快速识别不同品种绿茶的方法.通过3CCD成像仪同时获得绿茶样本的红光、绿光和近红外三个通道的图像,采用灰度共生矩阵和纹理滤波相结合来提取图像纹理特征,分析了不同品种绿茶的各个通道图像的纹理特征.非监督聚类分析表明,基于组合方法提取的纹理特征优于仅依靠灰度共生矩阵得到的纹理特征.优化和筛选后得到10个特征参数作为支持向量机模型的输入,建立模式识别模型.结果表明,对于126个建模样本的识别正确率达到94.4%,对于未知64个预测样本的识别正确率达到93.8%,说明提出的组合纹理特征提取和模式识别方法能够较好地识别不同品种的绿茶.