基于记忆细胞剪切和非线性资源分配的人工免疫识别系统

为减少人工免疫识别系统(AIRS)的记忆细胞数量并提高AIRS的分类准确率,提出一种基于记忆细胞剪切和非线性资源分配的人工免疫识别系统(PNAIRS).PNAIRS采用样本属性离散化来压缩训练空间,利用记忆细胞剪切来淘汰低适应度细胞,并使用非线性资源分配来优化分类器.PNAIRS对6个UCI数据集进行分类测试,测试结果与其它分类算法结果对比,显示PNAIRS具有较小规模的记忆细胞群体和较高的分类准确率,而且算法运行速度快.这表明PNAIRS算法是一个性能良好的分类算法,具有潜在的应用价值.     

基于不同核函数的支持向量机的分析与比较

本文首先介绍了SVM的原理及各种数据分类算法,然后描述三种不同的工具箱（LS SVMLAB、OSU SVM、SVM SteveGunn）,分析不同的核函数,在此基础上,对两个数据集（Iris、LiverDisorders）进行分类,记录其分类准确率及运行时间,通过比较分析,选出一个最佳的核函数以及工具箱.结果显示,OSU SVM工具箱的分类性能是最优的.     

基于改进高斯核函数的BGP异常检测方法

通过将边界网关协议(BGP)更新报文激增异常问题抽象为二分类问题,提出一种基于改进高斯核函数的BGP异常检测(IGKAD)方法。采用FMS特征选择算法,选择能同时最大化类间距离和最小化类内距离的特征,得到度量分类能力的特征权值。利用基于Manhattan距离与特征权值的改进高斯核函数构造支持向量机(SVM)分类模型,并结合基于网格搜索与交叉验证的参数寻优方法,提高SVM模型分类准确率。通过设计特征效率函数,给出最优特征子集构造方法,从而选取最优特征子集作为训练数据集。实验结果表明,当训练集包含TOP10和TOP8特征时,IGKAD方法的分类准确率分别为91.65%和90.37%,相比基于机器学习的BGP异常检测方法分类性能更优。     

FO-CA:一种基于距离差异度组合权重的多属性数据分类方法

为了解决多属性数据分类问题,提出了一种基于模糊优选模型与聚类分析的分类方法(FO-CA)。首先由模糊优选模型得到有序综合指标数据集,其中在权重阶段提出了距离差异度并以此为依据构建了一种组合主客观权重的赋权方法;然后采用聚类分析将有序综合指标数据集聚类为几个簇进而分类;最后选取UCI中的Iris、Wine和Ruspini 3个数据集进行仿真实验。实验结果表明,该分类方法相比模糊优选方法及K-Means算法能获得更好的分类结果,对决策者有一定的参考价值。     

有序规范实数对多相似度K最近邻分类算法

针对最近邻分类算法性能受到所采用的相似度或距离度量方法影响大，且难以选择最优的相似度或距离度量方法的问题，提出一种采用多相似度的基于有序规范实数对的K最近邻分类算法（OPNs-KNN）。首先，在机器学习领域中引入有序规范实数对（OPN）这一新的数学理论，利用多种相似度或距离度量方法将训练集和测试集中所有样本全部转换为OPN，使每个OPN均包含不同的相似度信息；然后再通过改进的最近邻算法对OPN进行分类，实现不同相似度或距离度量方法的结合与互补，从而提高分类性能。实验结果表明，在Iris、seeds等数据集上与距离加权K近邻规则（WKNN）等6种最近邻分类的改进算法相比，OPNs-KNN的分类准确率提高了0.29～15.28个百分点，验证了所提算法能大幅提升分类的性能。     

利用多群交叉变异人工鱼群算法生成分类规则

在基本人工鱼群算法的基础之上构建了用于解决连续变量空间分类规则提取的多群体人工鱼群算法,根据分类规则提取问题的特性设计了人工鱼的编码规则,并在此编码基础上定义了进行规则评价的适应值函数以及相关状态更新公式。为克服人工鱼群算法易陷入局部最优解的缺陷,引入了遗传算法中的交叉变异思想,设计了基于人工鱼的交叉及变异算子,提出了利用多种群交叉变异人工鱼群算法生成分类规则的算法思想。利用Iris和Wine数据集作为测试数据,结果表明：（1）该算法能够快速生成精度较高的分类规则;（2）在收敛效率及规则精度上全面优于基本多群体人工鱼群算法,并达到了多群体微粒群算法的性能水平。     

基于多群协同人工鱼群算法的分类规则提取算法

在对基本人工鱼群算法原理分析的基础上,提出了一种多群协同人工鱼群算法用于实现对连续空间变量的分类规则提取问题。定义了基于规则支持度与置信度的规则评价函数,构造了人工鱼在规则提取应用中的特定编码及相关概念的计算公式,给出了该算法的具体实现步骤,并用VC++软件编程实现。最后对Iris和Wine数据集进行测试实验,并与单群体鱼群算法及多种群微粒群算法进行比较。仿真结果表明,该算法能够快速提取分类精度较高的分类规则,因此利用该算法解决连续变量分类规则提取的相关问题是可行且有效的。     

一种人脸表情分类的新方法——Manhattan距离

提出了一种利用Manhattan距离进行人脸表情分类的新方法。Manhattan距离计算出具有不同模式的两个对象的距离更大。在实验中,比较了Manhattan距离、欧氏距离、余弦距离在人脸表情分类中的性能,得出Manhattan距离比另外两类距离有着更好的识别效果。     

基于分布估计算法的模糊分类方法

提出了基于分布估计算法的模糊分类建模方法,该方法基于Apriori原理生成初始模糊规则集,并且以匹茨堡型的二进制编码方式对模糊规则集编码,基于双变量相关的MIMIC (mutual information maximization for input clustering)分布估计算法从初始规则集中自动抽取模糊规则.通过在Iris,Pima,Wine这3个标准数据集的仿真实验表明,该方法比基于遗传算法的模糊分类器在准确率和解释性方面更有效.     

蚁群聚类算法中邻域变化规律的研究

为了提高蚁群聚类LF算法的聚类效果,在对基本LF算法改进的基础上,算法迭代过程中又进一步采用邻域线性增大和线性减小两种不同的方法,通过UCI数据集Iris和Wine数据的验证,使用FM作为聚类效果的评判标准,发现采用邻域线性递减的方法在两种数据集上运行的结果都优于邻域递增和邻域保持不变的情形.邻域递减策略使算法在运行初期能够对待聚类数据粗略的分类,随着邻域的减小,蚁群对数据分类的粒度逐渐细化,算法迭代结束,达到最佳的聚类结果.     

改进的加权t-SNE算法及在故障诊断中的应用

对随机邻域嵌入算法(stochastic neighbor embedding, SNE)中的距离进行改进,提出一种基于Manhattan距离的加权t-SNE(Mwt-SNE)算法。使用受空间维数影响较小的Manhattan距离作为度量方式,使用k均值聚类算法将高维空间数据样本点距离分为三类,基于表格法进行权重参数寻优与加权,以加权相对Manhattan距离代替欧式绝对距离计算相似度条件概率,从而增大数据对象之间的区分度,提升降维效果,增强分类显著性。提出基于Mwt-SNE算法的在线故障诊断模型,使用核密度估计(KDE)确定控制限并进行在线监控。TE化工过程实验表明Mwt-SNE算法能有效降低误报率和漏报率,从而提高故障诊断稳定性和准确性。     

一种基于混合核函数的SOM网络流量分类方法

由于传统的自组织映射SOM方法对高维、非线性的网络流量数据的分类性能效果不佳,本文引入核方法,提出一种基于混合核函数的SOM(MIX-KSOM)网络流量分类方法。该方法结合了全局性和局部性核函数的优点,采用径向基函数和多项式函数线性组合构成的混合核函数代替内积作为距离度量,使输入空间中复杂的流量样本在特征空间得以简化。实验结果表明,采用MIX-KSOM方法能较好地对网络流量进行分类,较传统的SOM、采用单一核函数的SOM(KSOM)分类方法性能更好,分类准确率也高于NB方法。     

Hepatitis disease diagnosis using a new hybrid system based on feature selection (FS) and artificial immune recognition system with fuzzy resource allocation

This paper presents a novel method for diagnosis of hepatitis disease. The proposed method is based on a hybrid method that uses feature selection (FS) and artificial immune recognition system (AIRS) with fuzzy resource allocation mechanism. AIRS has showed an effective performance on several problems such as machine learning benchmark problems and medical classification problems like breast cancer, diabets, liver disorders classification. By hybridizing FS and AIRS with fuzzy resource allocation mechanism, a method is obtained to solve this diagnosis problem via classifying. The robustness of this method with regard to sampling variations is examined using a cross-validation method. We used hepatitis disease dataset which is taken from UCI machine learning repository. We obtained a classification accuracy of 92.59%, which is the highest one reached so far. The classification accuracy was obtained via 10-fold cross validation. The obtained classification accuracy of our system was 92.59% and it was very promising with regard to the other classification applications in literature for this problem. Also, sensitivity, and specificity values for hepatitis disease dataset were obtained as 100 and 85%.     

Distance-based classification of handwritten symbols

We study online classification of isolated handwritten symbols using distance measures on spaces of curves. We compare three distance-based measures on a vector space representation of curves to elastic matching and ensembles of SVM. We consider the Euclidean and Manhattan distances and the distance to the convex hull of nearest neighbors. We show experimentally that of all these methods the distance to the convex hull of nearest neighbors yields the best classification accuracy of about 97.5%. Any of the above distance measures can be used to find the nearest neighbors and prune totally irrelevant classes, but the Manhattan distance is preferable for this because it admits a very efficient implementation. We use the first few Legendre-Sobolev coefficients of the coordinate functions to represent the symbol curves in a finite-dimensional vector space and choose the optimal dimension and number of bits per coefficient by cross-validation. We discuss an implementation of the proposed classification scheme that will allow classification of a sample among hundreds of classes in a setting with strict time and storage limitations.     

Breast cancer and liver disorders classification using artificial immune recognition system (AIRS) with performance evaluation by fuzzy resource allocation mechanism

Artificial Immune Recognition System (AIRS) classification algorithm, which has an important place among classification algorithms in the field of Artificial Immune Systems, has showed an effective and intriguing performance on the problems it was applied. AIRS was previously applied to some medical classification problems including Breast Cancer, Cleveland Heart Disease, Diabetes and it obtained very satisfactory results. So, AIRS proved to be an efficient artificial intelligence technique in medical field. In this study, the resource allocation mechanism of AIRS was changed with a new one determined by Fuzzy-Logic. This system, named as Fuzzy-AIRS was used as a classifier in the diagnosis of Breast Cancer and Liver Disorders, which are of great importance in medicine. The classifications of Breast Cancer and BUPA Liver Disorders datasets taken from University of California at Irvine (UCI) Machine Learning Repository were done using 10-fold cross-validation method. Reached classification accuracies were evaluated by comparing them with reported classifiers in UCI web site in addition to other systems that are applied to the related problems. Also, the obtained classification performances were compared with AIRS with regard to the classification accuracy, number of resources and classification time. Fuzzy-AIRS, which reached to classification accuracy of 98.51% for breast cancer, classified the Liver Disorders dataset with 83.36% accuracy. For both datasets, Fuzzy-AIRS obtained the highest classification accuracy according to the UCI web site. Beside of this success, Fuzzy-AIRS gained an important advantage over the AIRS by means of classification time. In the experiments, it was seen that the classification time in Fuzzy-AIRS was reduced about 70% of AIRS for both datasets. By reducing classification time as well as obtaining high classification accuracies in the applied datasets, Fuzzy-AIRS classifier proved that it could be used as an effective classifier for medical problems.     

A Hybrid Higher Order Neural Classifier for handling classification problems

In this paper, we propose a novel Hybrid Higher Order Neural Classifier (HHONC) which contains different high-order units. In contrast with conventional fully-connected higher order neural networks (HONN), our proposed method uses fewer learning parameters and allocates the best fitted model in dealing with different datasets by modifying the orders of different high-order units and updating the learning parameters. Structure, model selection and updating the learning parameters of HHONC is introduced and is applied in classification of the Iris data set, the breast cancer data set, the Wine recognition data set, the Glass identification data set, the Balance scale data set, and the Pima diabetes data set. Acquired results are compared with the methods presented in Chen and Shie (2009). It is observed that the fewer features the dataset contains, the more accurate the HHONC performs, however the accuracy of datasets with more features are acceptable. Experimental results show about 3.5% and 0.6% improvements compared to the best accuracy obtained in previously methods for classifying the Pima diabetes and Iris datasets, respectively. In addition, by using a same method for reducing the feature number, it’s shown the proposed method perform more accurate than methods presented in Shie and Chen (2008). In this case, improvements compared to the best acquired accuracy of mentioned methods are about 1.7%, 1.3% and 0.2% in classification of Pima, Iris and Breast cancer datasets, respectively.     

基于低密度分割几何距离的半监督KFDA算法

提出了一种基于低密度分割几何距离的半监督KFDA（kernel Fisher discriminant analysis）算法（semisupervised KFDA based on low density separation geometry distance，简称SemiGKFDA）.该算法以低密度分割几何距离作为相似性度量，通过大量无标签样本，提高KFDA算法的泛化能力.首先，利用核函数将原始空间样本数据映射到高维特征空间中；然后，通过有标签样本和无标签样本构建低密度分割几何距离测度上的内蕴结构一致性假设，使其作为正则化项整合到费舍尔判别分析的目标函数中；最后，通过求解最小化目标函数获得最优投影矩阵.人工数据集和UCI数据集上的实验表明，该算法与KFDA及其改进算法相比，在分类性能上有显著提高.此外，将该算法与其他算法应用到人脸识别问题中进行对比，实验结果表明，该算法具有更高的识别精度.     

中文语义角色标注的树核空间研究

使用基于树核函数的方法来进行语义角色标注,有效的树核空间的设计是影响系统性能的关键。探索树核空间在中文语义角色标注上的应用,考虑到同一谓词的各论元间的相互影响,提出多论元-谓词特征(AAPF)空间,并在此基础上提出了三种受平面特征启发的树核空间设计方法。基于中文PropBank语料的实验表明,加入一些重要平面特征信息的树核空间,性能有了明显的提高,分类精确率由90.96%提高到92.54%。最后使用复合核将特征启发的树核与特征向量结合起来,精确率达到95.21%,性能高于同类系统。