Evolutionary ensemble of diverse artificial neural networks using speciation

Recently, many researchers have designed neural network architectures with evolutionary algorithms but most of them have used only the fittest solution of the last generation. To better exploit information, an ensemble of individuals is a more promising choice because information that is derived from combining a set of classifiers might produce higher accuracy than merely using the information from the best classifier among them. One of the major factors for optimum accuracy is the diversity of the classifier set. In this paper, we present a method of generating diverse evolutionary neural networks through fitness sharing and then combining these networks by the behavior knowledge space method. Fitness sharing that shares resources if the distance between the individuals is smaller than the sharing radius is a representative speciation method, which produces diverse results than standard evolutionary algorithms that converge to only one solution. Especially, the proposed method calculates the distance between the individuals using average output, Pearson correlation and modified Kullback–Leibler entropy to enhance fitness sharing performance. In experiments with Australian credit card assessment, breast cancer, and diabetes in the UCI database, the proposed method performed better than not only the non-speciation method but also better than previously published methods.     

基于FCM与KKT条件的增量学习方法

增量学习方法的思想是仅利用部分相关的样本集参与训练,即能够保留历史样本知识,又能够不断地吸收新的知识,提高机器学习效率和精度,解决了大量样本训练时间长和存储空间不足的问题。因此,如何有效地丢弃大量无效的样本点是增量学习算法研究的重点。文中提出了一种FCM(Fuzzy C-Means)和KKT(Karush-KuhnTucker)条件结合的增量学习方法,分别从历史样本集和新增样本集两个阶段对无效样本进行过滤,利用余下的样本进行训练。最后,利用UCI数据库中的4组数据进行实验分析,结果证明训练精度与全数据样本的训练精度几乎完全拟合。     

LTE系统PUSCH的研究

PUSCH(Physical Uplink Shared Channel)是LTE物理层上行共享信道,是LTE物理层各个信道中最为复杂和重要的信道之一,承载的信息种类很多,如承载上行业务数据UL-SCH、参考信号和多种上行控制信息(UCI:Uplink Control Infor-mation)。UCI包括CQI、PMI、RI、HARQ-ACK/NAK。PUSCH发送端与接收端处理流程模块众多且复杂。文章介绍了PUSCH承载的各类信息及其用途,以及PUSCH发送与接收各个模块的大致处理流程。     

不同的距离测量方法对人工免疫识别系统的性能影响*

人工免疫识别系统AIRS（Artificial Immune Recognition System）是著名的免疫网络分类器,被成功地应用到大量的分类问题,表现出了良好的性能。为了分析不同的距离测量方法对AIRS的性能影响, 采用三种距离测量方法实现AIRS,这三种方法分别是Euclidean距离、Manhattan距离和RBF核空间距离,并将三种用不同距离测量方法实现的AIRS算法应用于Iris,Heart和Wine数据集的分类测试。所获得的三组数据集分类的准确率和抗体规模进行了相互比较,结果表明采用Manhattan距离AIRS算法获得了对Iris和Heart的最高分类准确率,而采用核空间距离,算法获得了对Wine的最高分类准确率。从抗体群体规模来看,采用核空间距离则能获得最小的抗体群体。从性能比较可知,不同的距离测量方法对AIRS算法的分类性能较大的影响。     

Ensemble classification based on generalized additive models

Generalized additive models (GAMs) are a generalization of generalized linear models (GLMs) and constitute a powerful technique which has successfully proven its ability to capture nonlinear relationships between explanatory variables and a response variable in many domains. In this paper, GAMs are proposed as base classifiers for ensemble learning. Three alternative ensemble strategies for binary classification using GAMs as base classifiers are proposed: (i) GAMbag based on Bagging, (ii) GAMrsm based on the Random Subspace Method (RSM), and (iii) GAMens as a combination of both. In an experimental validation performed on 12 data sets from the UCI repository, the proposed algorithms are benchmarked to a single GAM and to decision tree based ensemble classifiers (i.e. RSM, Bagging, Random Forest, and the recently proposed Rotation Forest). From the results a number of conclusions can be drawn. Firstly, the use of an ensemble of GAMs instead of a single GAM always leads to improved prediction performance. Secondly, GAMrsm and GAMens perform comparably, while both versions outperform GAMbag. Finally, the value of using GAMs as base classifiers in an ensemble instead of standard decision trees is demonstrated. GAMbag demonstrates performance comparable to ordinary Bagging. Moreover, GAMrsm and GAMens outperform RSM and Bagging, while these two GAM ensemble variations perform comparably to Random Forest and Rotation Forest. Sensitivity analyses are included for the number of member classifiers in the ensemble, the number of variables included in a random feature subspace and the number of degrees of freedom for GAM spline estimation.     

一种改进的LTE上行信道估计方法研究

信道质量指示与混合自动重传请求应答是3GPP LTE系统中重要的反馈信息,在物理上行控制信道PUCCH中的传输采用联合编码和单独编码方式。当上行控制信息UCI单独编码时,CQI参考信号中嵌入ACK比特,减少了用于信道估计的参考信号并且降低了信道估计性能。针对此问题提出一种改进的上行信道估计解决方案,仿真结果表明了该算法在高速多普勒频移环境下依然具有较好的性能,该算法已应用于TD-LTE无线综合测试仪表的开发中。     

基于混合身份搜索黏菌优化的模糊C-均值聚类算法

针对模糊C-均值聚类算法(fuzzy C-means clustering, FCM)对于初始化聚类中心敏感、收敛速度慢,聚类效果不稳定且容易陷入局部最优等问题,提出了一种将黏菌(SMA)与青少年身份搜索(AISA)相融合的自适应优化模糊C-均值算法(AISA-SMA-FCM)。该算法首先通过引入AISA算法中的青少年社会机制,改善SMA算法中的全局搜索和局部开发性能。克服了SMA对于高维数据及部分混峰数据不敏感的缺陷,通过标准测试函数验证改进后的混合AISA-SMA算法寻优求解性能更为优秀;其次此算法用于FCM聚类算法的迭代机制中,通过将AISA-SMA聚类环节加入FCM算法聚类中心迭代过程中,使FCM算法获得自适应优化算法相同的特性,即算法在每次迭代中都将具有探索和开发两个过程,并依据循环迭代次数调节比重,求解聚类结果;最后通过UCI标准数据集仿真测试,利用适应度平均值与聚类正确率评价所提算法的稳定性与有效性,结果表明,AISA-SMA算法用于FCM聚类问题效果较好,AISA-SMA-FCM算法较其他聚类方式和相应的优化技术具有收敛速度快、求解精度高的优点。     

A new efficient SIF-based FCIL (SIF–FCIL) mining algorithm in predicting the crime locations

In our innovative crime location forecast method, at the outset, the crime features are mined from the crime database and used for performing the adaptive mutation-based artificial bee colony (AMABC) algorithm, in which the database attributes and crime values are bunched together. Subsequently, the frequent closed itemsets lattice (FCIL) is built by the rules support factor values, and from this the frequent rules are extracted. In the course of the FCIL creation, the clustered attributes values are processed like a sliding window. In accordance with the frequent rules, the related crime locations are created. Thus, our proposed sliding with itemsets factor-based FCIL proposed technique is endowed with the superb skill of fruitfully forecasting the locations by means of AMABC and FCIL methods. In our innovative approach, we apply an UCI Machine Learning Repository-Communities and Crime Data Set for the offence investigation. The novel method is analysed and contrasted with the modern mining algorithms such as Apriori, Eclat and conservative FCIL.     

基于属性差异与相似关系的知识约简方法

在数据挖掘系统的研究设计中，知识的获取和表示是一个备受关注的问题。提出的知识约简方法——差异相似矩阵算法，根据信息系统中各个样本的属性取值的差异性和相似性，构建矩阵模型，求取各决策类的最佳约简属性集，得出用于指导分类的规则知识。基于该算法开发的知识约简系统，能够有效地应用于大规模数据集的分析处理中。     

基于矩阵的模糊决策系统的属性约简算法

通过矩阵刻画粗糙集理论,用模糊矩阵定义了模糊粗糙集的上（下）近似、重要度等概念,给出模糊决策系统的属性约简算法。将其运用到信息系统的属性约简算法和模糊信息系统的属性约简算法中,用UCI数据集说明算法的可行性。