A cost-sensitive classification algorithm: BEE-Miner
A cost-sensitive classification algorithm: BEE-Miner
复制标题
DOI：
10.1016/j.knosys.2015.12.010
复制
发表时间：
2016-03
期刊：
影响因子：
--
通讯作者：
Pinar Tapkan;Lale Özbakır;S. Kulluk;A. Baykasoğlu
中科院分区：
文献类型：
--
作者：
Pinar Tapkan;Lale Özbakır;S. Kulluk;A. Baykasoğlu
分类是一种数据挖掘技术，用于通过使用可用数据来预测未来，旨在发现变量和类别之间的隐藏关系。由于成本成分在大多数现实生活中的分类问题中至关重要，并且大多数传统的分类方法都是为了正确分类的目的，因此开发成本敏感的分类器以最小化总错误分类成本仍然是一个备受关注的主题。本研究的目的是提出一种有效的解决方法，根据以前的经验配置和评估学习系统，从而获得决策和预测。由于大多数现实生活中的问题都是成本敏感的，并且开发有效的直接方法来进行成本敏感的多类分类仍然是一个有吸引力的领域，因此利用最近开发的蜜蜂算法（BA）提出了一种成本敏感的分类方法，即 BEE-Miner 算法。 BEE-Miner 的主要优点是它能够处理二元和多类问题，并通过生成邻居解决方案和评估解决方案的质量将误分类成本纳入算法中。对所提出的 BEE-Miner 算法的成本不敏感和成本敏感版本进行了广泛的计算研究，并以高测试精度和低误分类成本获得了针对不同类型问题的有效结果。
Classification is a data mining technique which is utilized to predict the future by using available data and aims to discover hidden relationships between variables and classes. Since the cost component is crucial in most real life classification problems and most traditional classification methods work for the purpose of correct classification, developing cost-sensitive classifiers which minimize the total misclassification cost remains a subject of much interest. The purpose of this study is to present an effective solution method that configurates and evaluates learning systems from previous experiences, thus aiming to obtain decisions and predictions. Since most real life problems are cost-sensitive and developing effective direct methods for cost-sensitive multi-class classification is still an attractive area, a cost-sensitive classification method, the BEE-Miner algorithm, is proposed by utilizing the recently developed Bees Algorithm (BA). The main advantages of BEE-Miner are its capability to handle both binary and multi-class problems and to incorporate misclassification cost into the algorithm via generating neighbor solutions and evaluating the quality of the solutions. An extensive computational study is also performed on cost-insensitive and cost-sensitive versions of the proposed BEE-Miner algorithm and effective results on different types of problems are obtained with high test accuracy and low misclassification cost.