本文選題：關(guān)聯(lián)分類方法 + 不平衡數(shù)據(jù)��； 參考：《系統(tǒng)工程理論與實(shí)踐》2017年04期

【摘要】：不平衡數(shù)據(jù)的出現(xiàn)給傳統(tǒng)關(guān)聯(lián)分類算法帶來(lái)了巨大的挑戰(zhàn).為了提高關(guān)聯(lián)分類方法對(duì)不平衡數(shù)據(jù)集的分類精度,本文分別從數(shù)據(jù)和規(guī)則層次著手,提出了關(guān)鍵值抽樣法(key value sampling,KVS)和規(guī)則驗(yàn)證法(rule validation,RV).關(guān)鍵值抽樣法通過(guò)增加與少數(shù)類相關(guān)性強(qiáng)的數(shù)據(jù),減少與多數(shù)類相關(guān)性弱的數(shù)據(jù)來(lái)達(dá)到數(shù)據(jù)類分布平衡.避免了大量有效信息的流失,并且增強(qiáng)了與少數(shù)類相關(guān)性強(qiáng)的數(shù)據(jù)信息.規(guī)則驗(yàn)證法對(duì)初步生成的分類器進(jìn)行了規(guī)則驗(yàn)證,并對(duì)分類性能不好的規(guī)則進(jìn)行調(diào)整,從而保證了分類器中規(guī)則的質(zhì)量.實(shí)驗(yàn)表明,本文中的研究方法能夠有效提高關(guān)聯(lián)分類方法處理不平衡數(shù)據(jù)的精度.
[Abstract]:The appearance of unbalanced data brings a great challenge to the traditional association classification algorithm. In order to improve the classification accuracy of association classification for unbalanced datasets, the key value sampling method (KVS) and rule validation method (RVS) are proposed in this paper from the level of data and rules, respectively. By increasing the data with strong correlation with a few classes and reducing the data with weak correlation with most classes, the key value sampling method achieves the equilibrium of data class distribution. It avoids the loss of a large amount of effective information and enhances the data information which has strong correlation with a few classes. The rule verification method verifies the rule of the initial generated classifier and adjusts the rules with poor classification performance to ensure the quality of the rules in the classifier. The experimental results show that the proposed method can effectively improve the accuracy of the association classification method in dealing with unbalanced data.
【作者單位】： 大連理工大學(xué)系統(tǒng)工程研究所;
【基金】：國(guó)家自然科學(xué)基金(71671024,71421001) 教育部人文社科基金(15YJCZH198) 遼寧經(jīng)濟(jì)社會(huì)發(fā)展立項(xiàng)課題(20161s lktzizzx-01)~~
【分類號(hào)】：TP311.13
，

本文編號(hào)：1827299