多标记学习自编码网络无监督维数约简

多标记学习是针对一个实例同时与一组标签相关联而提出的一种机器学习框架,是该领域研究热点之一,降维是多标记学习一个重要且具有挑战性的工作。针对有监督的多标记维数约简方法,提出一种无监督自编码网络的多标记降维方法。首先,通过构建自编码神经网络,对输入数据进行编码和解码输出;然后,引入稀疏约束计算总体成本,使用梯度下降法进行迭代求解;最后,通过深度学习训练获得自编码网络学习模型,提取数据特征实现维数约简。实验中使用多标记算法ML-kNN做分类器,在6个公开数据集上与其他4种方法对比。实验结果表明,该方法能够在不使用标记的情况下有效提取特征,降低多标记数据维度,稳定提高多标记学习性能。     

基于改进多隐层极限学习机的电网虚假数据注入攻击检测

虚假数据注入攻击(False data injection attacks, FDIA)严重威胁了电力信息物理系统(Cyber-physical system,CPS)的状态估计,而目前大多数检测方法侧重于攻击存在性检测,无法获取准确的受攻击位置.故本文提出了一种基于灰狼优化(Gray wolf optimization, GWO)多隐层极限学习机(Multi layer extreme learning machine, ML-ELM)的电力信息物理系统虚假数据注入攻击检测方法.所提方法将攻击检测看作是一个多标签二分类问题,不仅将用于特征提取与分类训练的极限学习机由单隐层变为多隐层,以解决极限学习机特征表达能力有限的问题,且融入了具有强全局搜索能力的灰狼优化算法以提高多隐层极限学习机分类精度和泛化性能.进而自动识别系统各个节点状态量的异常,获取受攻击的精确位置.通过在不同场景下对IEEE-14和57节点测试系统上进行大量实验,验证了所提方法的有效性,且分别与极限学习机、未融入灰狼优化的多隐层极限学习机以及支持向量机(Support vector machine, SVM)相比,所提方...     

BiLSTM在JavaScript恶意代码检测中的应用

传统的机器学习方法在检测JavaScript恶意代码时,存在提取特征过程复杂、计算量大、代码被恶意混淆导致难以检测的问题,不利于当前JavaScript恶意代码检测准确性和实时性的要求.基于此,提出一种基于双向长短时神经网络(BiLSTM)的JavaScript恶意代码检测方法.首先,将得到的样本数据经过代码反混淆,数据分词,代码向量化后得到适应于神经网络输入的标准化数据.其次,利用BiLSTM算法对向量化数据进行训练,学习JavaScript恶意代码的抽象特征.最后,利用学习到的特征对代码进行分类.将本文方法与深度学习方法和主流机器学习方法进行比较,结果表明该方法具有较高的准确率和较低的误报率.     

基于Relief和SVM-RFE的组合式SNP特征选择

针对SNP的全基因组关联分析面临SNP数据的高维小样本特性和遗传疾病病理的复杂性两大难点,将特征选择引入SNP全基因组关联分析中,提出基于Relief和SVM-RFE的组合式SNP特征选择方法。该方法包括两个阶段:Filter阶段,使用Relief算法剔除无关SNPs;Wrapper阶段,使用基于支持向量机的特征递归消减方法(SVM-RFE)筛选出与遗传疾病相关的关键SNPs。实验表明,该方法具有明显优于单独使用SVM-RFE算法的性能,优于单独使用Relief-SVM算法的分类准确率,为SNP全基因组关联分析提供了一种有效途径。     

GA-based method for feature selection and parameters optimization for machine learning regression applied to software effort estimation

ContextIn software industry, project managers usually rely on their previous experience to estimate the number men/hours required for each software project. The accuracy of such estimates is a key factor for the efficient application of human resources. Machine learning techniques such as radial basis function (RBF) neural networks, multi-layer perceptron (MLP) neural networks, support vector regression (SVR), bagging predictors and regression-based trees have recently been applied for estimating software development effort. Some works have demonstrated that the level of accuracy in software effort estimates strongly depends on the values of the parameters of these methods. In addition, it has been shown that the selection of the input features may also have an important influence on estimation accuracy.ObjectiveThis paper proposes and investigates the use of a genetic algorithm method for simultaneously (1) select an optimal input feature subset and (2) optimize the parameters of machine learning methods, aiming at a higher accuracy level for the software effort estimates.MethodSimulations are carried out using six benchmark data sets of software projects, namely, Desharnais, NASA, COCOMO, Albrecht, Kemerer and Koten and Gray. The results are compared to those obtained by methods proposed in the literature using neural networks, support vector machines, multiple additive regression trees, bagging, and Bayesian statistical models.ResultsIn all data sets, the simulations have shown that the proposed GA-based method was able to improve the performance of the machine learning methods. The simulations have also demonstrated that the proposed method outperforms some recent methods reported in the recent literature for software effort estimation. Furthermore, the use of GA for feature selection considerably reduced the number of input features for five of the data sets used in our analysis.ConclusionsThe combination of input features selection and parameters optimization of machine learning methods improves the accuracy of software development effort. In addition, this reduces model complexity, which may help understanding the relevance of each input feature. Therefore, some input parameters can be ignored without loss of accuracy in the estimations.     

Feature selection in single and ensemble learning‐based bankruptcy prediction models

Feature selection is an important data preprocessing step for the construction of an effective bankruptcy prediction model. The prediction performance can be affected by the employed feature selection and classification techniques. However, there have been very few studies of bankruptcy prediction that identify the best combination of feature selection and classification techniques. In this study, two types of feature selection methods, including filter‐ and wrapper‐based methods, are considered, and two types of classification techniques, including statistical and machine learning techniques, are employed in the development of the prediction methods. In addition, bagging and boosting ensemble classifiers are also constructed for comparison. The experimental results based on three related datasets that contain different numbers of input features show that the genetic algorithm as the wrapper‐based feature selection method performs better than the filter‐based one by information gain. It is also shown that the lowest prediction error rates for the three datasets are provided by combining the genetic algorithm with the naïve Bayes and support vector machine classifiers without bagging and boosting.     

Decision tree based light weight intrusion detection using a wrapper approach

The objective of this paper is to construct a lightweight Intrusion Detection System (IDS) aimed at detecting anomalies in networks. The crucial part of building lightweight IDS depends on preprocessing of network data, identifying important features and in the design of efficient learning algorithm that classify normal and anomalous patterns. Therefore in this work, the design of IDS is investigated from these three perspectives. The goals of this paper are (i) removing redundant instances that causes the learning algorithm to be unbiased (ii) identifying suitable subset of features by employing a wrapper based feature selection algorithm (iii) realizing proposed IDS with neurotree to achieve better detection accuracy. The lightweight IDS has been developed by using a wrapper based feature selection algorithm that maximizes the specificity and sensitivity of the IDS as well as by employing a neural ensemble decision tree iterative procedure to evolve optimal features. An extensive experimental evaluation of the proposed approach with a family of six decision tree classifiers namely Decision Stump, C4.5, Naive Baye’s Tree, Random Forest, Random Tree and Representative Tree model to perform the detection of anomalous network pattern has been introduced.     

基于深度学习的虹膜人脸多特征融合识别

传统多生物特征融合识别方法中人工设计特征提取存在盲目性和差异性,特征融合存在空间不匹配或维度过高等问题,为此提出一种基于深度学习的多生物特征融合识别方法。通过卷积神经网络(convolutional neural networks,CNN)提取人脸和虹膜特征、参数化t-SNE算法特征降维和支持向量机(support vector machine,SVM)分类组合进行融合识别。实验结果表明,该融合识别方法与单一生物特征识别以及其它融合识别方法相比,鲁棒性增强,识别性能提升明显。     

基于ResNet的稳健语音DOA估计算法

针对传统波达方向（Direction of arrival, DOA）估计算法在阵列模型误差条件下估计性能下降的问题,提出了一种基于残差网络（Residual network, ResNet）的DOA估计算法。该算法根据神经网络数据驱动不依赖阵列流型的特点,从广义互相关（Generalized cross-correlation, GCC）中提取特征,将提取的特征作为神经网络深层分类器的输入,对信号分类;根据分类结果选取对应子区间数据进行训练,建立ResNet学习特征与DOA估计之间的非线性映射关系,形成一个数据驱动的稳健DOA估计系统。仿真与实验验证结果表明,该算法有效地解决了传统DOA算法在阵列模型误差条件下无法准确得到DOA结果的问题。     

A new approach for manufacturing forecast problems with insufficient data: the case of TFT–LCDs

Manufacturing forecast problems have been widely discussed in recent years, where more accurate predictions could reduce the overall manufacturing costs. This study uses the case of ensuring the heights of thin film transistor–liquid crystal display photo-spacers. It is a small sample size prediction problem, because the data available for analysis is limited on the manufacturing lines. A new approach is developed to deal with this problem, which involves three steps. The first step is using K-means clustering to separate data into K clusters, while the second step is to compute the possibility through the fuzzy membership function in each cluster for attribute extension. The last step is to put the data with new generate attributes into a backpropagation neural network (BPNN) machine learning algorithm. Two performance evaluation methods, cross-validation and data specification testing, are selected to compare the proposed method with three popular prediction models: linear regression, support vector machine for regression (SVR), and BPNN. The results show that the proposed method outperforms the others with regard to the total errors, mean square error, and standard deviation.     

混合式的K-匿名特征选择算法

K-匿名算法通过对数据的泛化、隐藏等手段使得数据达到K-匿名条件,在隐藏特征的同时考虑数据的隐私性与分类性能,可以视为一种特殊的特征选择方法,即K-匿名特征选择。K-匿名特征选择方法结合K-匿名与特征选择的特点使用多个评价准则选出K-匿名特征子集。过滤式K-匿名特征选择方法难以搜索到所有满足K-匿名条件的候选特征子集,不能保证得到的特征子集的分类性能最优,而封装式特征选择方法计算成本很大,因此,结合过滤式特征排序与封装式特征选择的特点,改进已有方法中的前向搜索策略,设计了一种混合式K-匿名特征选择算法,使用分类性能作为评价准则选出分类性能最好的K-匿名特征子集。在多个公开数据集上进行实验,结果表明,所提算法在分类性能上可以超过现有算法并且信息损失更小。     

机器学习在工业网络入侵检测中的研究应用

在工业化和信息化两化深度融合的背景下,工业控制网络面临着高强度、持续性的恶意渗透和网络攻击,对国家安全和工业生产构成了巨大威胁.检测工业控制网络遭受恶意攻击,高效区分正常数据和攻击数据的研究已成为热点问题.以密西西比州立大学SCADA实验室的能源系统攻击数据集作为工业控制网络入侵检测的主要研究对象,对比不同机器学习算法的准确率、漏警率、虚警率等重要指标,得出综合性能最优的XGBoost算法.为进一步提高入侵检测效率,提出了一种针对XGBoost算法的包裹式特征选择方法,在简化数据集的同时突出不同特征在入侵检测中的重要性.研究结果表明,结合包裹式特征选择的XGBoost算法能有效解决入侵检测问题并提高入侵检测效率,验证了此方法的有效性和科学性.     

FP-CNNH:一种基于深度卷积神经网络的快速图像哈希算法

在大数据时代,图像检索技术在大规模数据上的应用是一个热门的研究领域。近年来,大规模图像检索系统中, 图像哈希算法 由于具备提高图像的检索效率同时减少储存空间的优点而受到广泛的关注。现有的有监督学习哈希算法存在一些问题,主流的有监督的哈希算法需要通过图像特征提取器获取人为构造的图像特征表示,这种做法带来的图像特征损失影响了哈希算法的效果,也不能较好地处理图像数据集中语义的相似性问题。随着深度学习在大规模数据上研究的兴起,一些相关研究尝试通过深度神经网络进行有监督的哈希函数学习,提升了哈希函数的效果,但这类方法需要针对数据集人为设计复杂的深度神经网络,增大了哈希函数设计的难度,而且深度神经网络的训练需要较多的数据和较长的时间,这些问题影响了基于深度学习的哈希算法在大规模数据集上的应用。针对这些问题,提出了一种基于深度卷积神经网络的快速图像哈希算法,该算法通过设计优化问题的求解方法以及使用预训练的大规模深度神经网络,提高了哈希算法的效果,同时明显地缩短了复杂神经网络的训练时间。根据在不同图像数据集上的实验结果分析可知, 与现有的基准算法相比,提出的算法在哈希函数训练效果和训练时间上都具有较大的提高。     

基于卷积神经网络的发动机气路故障诊断方法

深度学习是一种新的基于特征表示的机器学习方法。深度学习模型包含多个隐藏层,可以通过对输入数据进行自动学习来获取隐藏的功能层中的特征信息。与传统的诊断方法相比,深度学习具备从原始信息中提取更丰富的特征的能力,因此已经成为基于机器学习的故障诊断研究的新方向,为发动机气路等复杂系统故障诊断带来了新思路。结合发动机气路试验数据的特点与深度学习的优势,提出基于卷积神经网络的故障诊断方法,包括预处理、模型训练及优化等过程,并实现了复杂系统故障诊断预测算法平台。经某发动机气路试验仿真数据实例验证,提出的方法具有较好的可行性和效果,能够充分利用深度学习的优点,更准确地识别发动机气路的健康状况。     

Calibration-free and model-independent method for high-DOF image-based visual servoing

This paper presents a novel method to improve the performance of high-DOF image base visual servoing (IBVS) with an uncalibrated camera. Firstly, analysis and comparison between point-based and moment-based features are carried out with respect to a 4-DOF positioning task. Then, an extended interaction matrix (IM) related to the digital image, and a Kalman filter (KF)-based estimation algorithm of the extended IM without calibration and IM model are proposed. Finally, the KF-based algorithm is extended to realize an approximation to decoupled control scheme. Experimental results conducted on an industrial robot show that our proposed methods can provide accurate estimation of IM, and achieve similar performance compared with traditional calibration-based method. Therefore, the proposed methods can be applied to any robot control system in variational environments, and can realize instant operation to planar object with complex and unknown shape at large displacement.     

面部表情的深度卷积级联森林识别

面部表情识别广泛应用于各种研究领域,针对面部表情识别使用深度神经网络方法结构复杂、可解释性差和传统机器学习方法特征提取缺乏多样性、识别率低的问题.提出了一种新的深度卷积级联森林(Deep Convolution Cascade Forest,DCCF)方法用于人脸面部表情识别,该方法通过卷积神经网络深度学习人脸面部显著特征,并采用基于随机森林的级联结构森林逐层学习识别出不同的面部表情特征,提高了人脸表情的识别准确率.DCCF在JAFFE、CK+和Fer2013 3个公开面部表情数据集进行了实验,并对面部表情提取的5种特征和7种分类方法进行了比较分析,结果显示DCCF在对比的算法中人脸表情识别性能最好,3个数据集的准确率分别达到91.4%,98.7%,71.6%.     

Convolutional Neural Network for RemoteSensing Plant Cover Extracting

The key point of the state-of-the-art machine learning method to extract land information is to construct the features-vector.The existing methods mainly use the spectral features,texture features of remote sensing images to construct the features-vector,however,this method can only get limited features and requires too much human intervention.In the face of the above problems,this paper builds a convolutional neural network model for mining the deep-level features of multi-band remote sensing images and then extract the greenbelt in the Kubuqi Desert.The model was trained and hyperparameter selection was performed.The performance of the model was evaluated by cross validation and comparative analysis between methods.The experimental results show that the model is of high accuracy and good generalization ability.Finally,the test data set was input into the model to predict land cover classes and to do visualization.The importance of this study is to inspire new thinking of better performance of the green land and even more complex information extraction from remote sensing images.     

基于HI-DD-AdaBoost.RT的锂离子动力电池SOH预测

锂离子电池是一个复杂的电化学动态系统,实时准确的健康状态(SOH)估计对电动汽车动力锂电池的维护至关重要,传统建模方法难以实现SOH的在线估算.基于此,从实时评估电池的SOH出发,在增量学习的基础上,选取与电池健康状态相关的指标建立SOH预测模型.考虑到增量学习中的耗时性问题,提出融合滑动窗口技术的HI-DD算法,该算法可以检测概念漂移是否发生,从而指导和确定模型更新位置;设计出HI-DD与AdaBoost.RT结合的模型更新策略,进而提高模型的在线学习性能和预测精度,最后使用CALCE提供的电池老化实验数据对所提出的方法进行验证.结果表明,基于增量学习的HI-DD-AdaBoost.RT预测算法具有较强的在线更新能力和较高的预测精度,能够满足SOH在线预测的实际需求.     

Selective ensemble extreme learning machine modeling of effluent quality in wastewater treatment plants

Real-time and reliable measurements of the effluent quality are essential to improve operating efficiency and reduce energy consumption for the wastewater treatment process.Due to the low accuracy and unstable performance of the traditional effluent quality measurements,we propose a selective ensemble extreme learning machine modeling method to enhance the effluent quality predictions.Extreme learning machine algorithm is inserted into a selective ensemble frame as the component model since it runs much faster and provides better generalization performance than other popular learning algorithms.Ensemble extreme learning machine models overcome variations in different trials of simulations for single model.Selective ensemble based on genetic algorithm is used to further exclude some bad components from all the available ensembles in order to reduce the computation complexity and improve the generalization performance.The proposed method is verified with the data from an industrial wastewater treatment plant,located in Shenyang,China.Experimental results show that the proposed method has relatively stronger generalization and higher accuracy than partial least square,neural network partial least square,single extreme learning machine and ensemble extreme learning machine model.     

基于- 范数约束的LSSVR 多核学习算法

针对核函数选择对最小二乘支持向量机回归模型泛化性的影响, 提出一种新的基于????- 范数约束的最小二乘支持向量机多核学习算法. 该算法提供了两种求解方法, 均通过两重循环进行求解, 外循环用于更新核函数的权值, 内循环用于求解最小二乘支持向量机的拉格朗日乘数, 充分利用该多核学习算法, 有效提高了最小二乘支持向量机的泛化能力, 而且对惩罚参数的选择具有较强的鲁棒性. 基于单变量和多变量函数的仿真实验表明了所提出算法的有效性.