基于贝叶斯分类器的垃圾邮件过滤的研究与改进

介绍了一个改进的基于贝叶斯分类技术的垃圾邮件过滤器的系统结构,完成了系统的整体设计和实现。提出了一种改进的邮件信息增益方法,选取多个样本进行实验比较分析,提高了贝叶斯分类器的性能。     

基于贝叶斯网络的垃圾邮件自动识别

在分析反垃圾邮件技术发展现状的基础上,提出一种基于贝叶斯智能分析的垃圾邮件识别方法,利用邮件中的词串作为构建贝叶斯网络的特征参数对网络进行训练,并用训练好的贝叶斯网络对邮件进行识别.实验结果表明文中提出的方法有良好的自学习能力及自适应性,具有较强的实用性.     

垃圾邮件分类技术对比研究

文章主要进行了接收端的垃圾邮件处理技术的对比研究,包括预处理、特征选择和分类3大步骤。其中特征选择技术包括文档频率（DF）、信息增益（IG）、优势率（ODD）等方法。文章详细介绍了其中基于粗糙集理论的特征选择方法--信息增益（knowledge gain）,并用实验验证了该方法在正确率等指标中的突出表现。主流分类器算法包括k近邻、贝叶斯、SVM等,其中详细展示了线性分类器在垃圾邮件分类算法实验中的突出表现。     

基于概率神经网络的垃圾邮件分类

概率神经网络是由Specht博士在1989年提出的一种径向基神经网络的重要变形。本文提出了把概率神经网络用于垃圾邮件分类,并通过Matlab仿真试验与贝叶斯分类器进行比较,得到了比较理想的结果。     

基于不完全朴素贝叶斯分类模型的垃圾邮件分类模型

由于朴素贝叶斯分类模型的简单高效,在垃圾邮件分类时可以达到较好的效果;但朴素贝叶斯的条件独立假设割裂了属性之间的关系,影响了分类的准确性。放松朴素贝叶斯分类模型关于属性之间条件独立假设,介绍一种新的基于不完全朴素贝叶斯分类模型的垃圾邮件分类模型,N平均1 依赖邮件过滤模型。使用N个1 依赖分类模型的平均概率作为分类的预测概率。实验证明,该模型在简单、高效的同时降低了对垃圾邮件分类的错误率。     

基于云计算的贝叶斯分类算法在过滤垃圾邮件中的研究

为了抵制垃圾邮件对互联网及其用户造成的严重不良影响,本文采用高效的贝叶斯分类算法,基于hadoop平台实现垃圾邮件的过滤系统,克服了传统并行系统在编程实现和系统扩展上的不足,充分利用云计算环境优势,使系统实现简单,扩展容易,性能提高;并做了相关的试验,验证了设计理论。     

应用特征词分类贡献的垃圾邮件过滤研究

在垃圾邮件过滤中,考虑到特征词对合法邮件和垃圾邮件分类贡献的不同,通过定义分类贡献比系数,将特征词分类贡献的思想应用到特征选择和朴素贝叶斯过滤器的设计中,在英文语料库上进行实验,实验结果表明,应用特征词分类贡献的垃圾邮件过滤方法可以有效提高过滤器对合法邮件和垃圾邮件的识别能力,降低过滤器对合法邮件和垃圾邮件的误判率。     

基于贝叶斯算法的垃圾邮件过滤研究

大量垃圾邮件的出现给用户收发电子邮件带来极大困扰。贝叶斯算法由于在垃圾邮件处理上表现出很高的准确度,因此受到了广泛关注。本文介绍了贝叶斯算法的理论依据,分析了贝叶斯算法的优缺点,总结了贝叶斯的相关改进算法,最后对贝叶斯算法进行了总结和展望。     

朴素贝叶斯算法在垃圾邮件过滤中的分析和应用

朴素贝叶斯方法(Naive Bayes)以其运行快速、易于实现的特点,被广泛应用于各种文本分类和邮件过滤的应用系统中,但现有以NB为基础的过滤系统在分类性能、准确率等方面还存在一些问题,深入研究需要了解相关的背景知识.本文首先分析和比较了现存的各种NB版本,总结各个NB的优点和不足,进而又介绍和比较了具有代表性的各种NB改进算法,目的是便于研究者在进行改进和深入研究时能有一个明确的方向.     

垃圾邮件研究与防范

随着电子邮件的广泛应用,垃圾邮件作为商业广告、恶意程序或敏感内容的载体,也越来越对系统的安全和人们的生活造成了严重的威胁,垃圾邮件的处理和防范已经成为全球性的具有重要现实意义的课题。本文首先对垃圾邮件进行了概述,然后主要对垃圾邮件的两种防范技术验证法和过滤法进行了综合介绍。     

支持向量机在反垃圾邮件过滤中的应用

垃圾邮件对计算机系统的安全和人们的生活造成了严重的威胁,反垃圾邮件问题已经成为的具有重要现实意义的研究课题.针对垃圾邮件过滤本质是分类问题,提出了一种基于服务器前端的反垃圾邮件过滤方法,它采用了改进的v支持向量机算法对邮件内容进行分类,过滤垃圾邮件.研究结果表明该方法与直接的支持向量机增量算法相比,提高了过滤的准确率,具有一定的应用价值.     

一种针对同音词伪装的反垃圾短信系统设计

近年来随着垃圾短信过滤技术的进步,垃圾短信的特征也在发生变化,其中利用同音词伪装的垃圾短信,就能轻松逃避很多过滤系统的拦截。针对这个问题,利用同音词伪装其拼音不变的特点,提出了以拼音串作为提取垃圾短信特征的关键字,从短信中提取出普通向量和伪装向量,并分别作为输入量,进行相互独立的贝叶斯过滤的方法,最后综合两次过滤的结果,判断是否为垃圾短信。实验结果表明,该方法能有效地识利用同音字伪装的垃圾短信。     

一种复合的双引擎智能垃圾邮件过滤方法

研究了几种常用的垃圾邮件过滤算法,分析了这几种方法在邮件过滤应用中各自的优缺点.根据这几种算法的优缺点,对它们进行改良与结合,并增加了通过查看发出的邮件内容进行自动学习的机制;同时针对中英文垃圾邮件采用不同的学习算法,从而建立一个适用中英文环境的垃圾邮件过滤方法.实验表明,该方法的效率和性能达到了较好的水平.     

Development and performance evaluation of neural network classifiers for Indian internet shoppers

The rapid growth of usage of internet has paved the way towards the use of online shopping. Consumers’ behavior is one of the significant aspects that is considered by the service providers for the improvement of various services. Consumers are generally satisfied if their needs are fulfilled. In this paper an in depth investigation is made on the behavior of Indian consumers towards online shopping. Factor analysis is carried out to extract significant factors that affect online shopping of Indian consumers and these consumers are clustered based on their behavior, towards online shopping using hierarchical clustering. Employing the results of clustering in training of multilayer perceptron (MLP), functional link artificial neural network (FLANN) and radial basis function (RBF) networks efficient classifier models are developed. The performance of these classifiers are evaluated and compared with those obtained by conventional statistical based discriminant analysis. The simulation study demonstrates that the RBF network provides best classification performance of internet shoppers compared to those given by the FLANN, MLP and discriminant analysis based methods. The simulation study on the impact of different combination of inputs demonstrates that demographic input has least effect on classification performance. On the other hand the combination of psychological and cultural inputs play the most significant role in classification followed by psychological and then cultural inputs alone.     

An empirical study of supervised email classification in Internet of Things: Practical performance and key influencing factors

Internet of Things (IoT) is gradually adopted by many organizations to facilitate the information collection and sharing. In an organization, an IoT node usually can receive and send an email for event notification and reminder. However, unwanted and malicious emails are a big security challenge to IoT systems. For example, attackers may intrude a network by sending emails with phishing links. To mitigate this issue, email classification is an important solution with the aim of distinguishing legitimate and spam emails. Artificial intelligence especially machine learning is a major tool for helping detect malicious emails, but the performance might be fluctuant according to specific datasets. The previous research figured out that supervised learning could be acceptable in practice, and that practical evaluation and users' feedback are important. Motivated by these observations, we conduct an empirical study to validate the performance of common learning algorithms under three different environments for email classification. With over 900 users, our study results validate prior observations and indicate that LibSVM and SMO-SVM can achieve better performance than other selected algorithms.     

Dialectic decision support systems: System design and empirical evaluation

Many complex and unstructured decisions are hindered by a lack of clear understanding of various underlying assumptions and perspectives involved in the decision process. At present, the traditional decision support systems (DSS) pay little attention to the elicitation of underlying assumptions and perspectives in dealing with complex issues. We argue that the Socratic dialectic inquiry is an effective method for dealing with unstructured problems that are complex and require the involvement of different perspectives in DSS. In this paper, we propose a design for Dialectic Decision Support Systems (DDSS), in which dialectical processes are integrated with traditional DSS in order to provide support for individual decision makers. We then formulate a conceptual model for identifying factors that contribute to the efficacy of DDSS in comparison to traditional DSS. The empirical test of the model supports the superior efficacy of the DDSS and identifies factors that contribute to it. The contributions of this research are in generating support for stimulating critical thinking, dealing with complex decision issues and identifying creative solutions.     

A survey of document image classification: problem statement,classifier architecture and performance evaluation

Document image classification is an important step in Office Automation, Digital Libraries, and other document image analysis applications. There is great diversity in document image classifiers: they differ in the problems they solve, in the use of training data to construct class models, and in the choice of document features and classification algorithms. We survey this diverse literature using three components: the problem statement, the classifier architecture, and performance evaluation. This brings to light important issues in designing a document classifier, including the definition of document classes, the choice of document features and feature representation, and the choice of classification algorithm and learning mechanism. We emphasize techniques that classify single-page typeset document images without using OCR results. Developing a general, adaptable, high-performance classifier is challenging due to the great variety of documents, the diverse criteria used to define document classes, and the ambiguity that arises due to ill-defined or fuzzy document classes.     

Conceptual design evaluation considering the ambiguity semantic variables fusion with conflict beliefs: An integrated Dempster-Shafer evidence theory and intuitionistic fuzzy -VIKOR

Quantifying the uncertain linguistic evaluation from decision-makers (DMs) is one of the most challenging parts in the conceptual design decision. Although fuzzy decision models have been widely used to capture potential uncertainty by assigning a fuzzy term with the certain belief, the ambiguity subjective evaluation of semantic variables with conflict beliefs derived from DMs have not been well addressed. To solve this drawback, a concept decision model based on Dempster-Shafer (DS) evidence theory and intuitionistic fuzzy -Vlsekriterijumska Optimizacija I Kompromisno Resenje (VIKOR) considering the ambiguity semantic variables fusion is proposed. Firstly, by incorporating semantic variables of intuitionistic fuzzy sets (IFSs), the diversified semantic judgments and its belief will be taken into account to form an ambiguity semantic initial decision matrix; secondly, the DS combination rule will be used to fuse the different semantic variables of multi-DMs in each scheme, update the belief of each semantic variable, and then the semantic fusion value matrix of the scheme will be constructed; finally, the weight of each evaluation objective will be calculated based on the value matrix and information entropy model, IFS-VIKOR model will be constructed to rank the concepts. A case study of the tree climbing and trimming machine will be employed to verify the proposed decision model. This decision model considering diversifying semantic variables and the conflict belief is proven to be effective compared with the IFS-SAW and ISF-TOPSIS.