本文選題：數(shù)據(jù)流 + 概念漂移　； 參考：《北京郵電大學(xué)學(xué)報(bào)》2017年03期

【摘要】：為了更準(zhǔn)確快速地處理或適應(yīng)概念漂移,提出了基于原型學(xué)習(xí)的數(shù)據(jù)流分類算法,基于發(fā)掘并優(yōu)化現(xiàn)有方法存在的問題,提出了新的方法模型Sync Prototype,在預(yù)測(cè)方法、原型判定與更新方法等處理概念漂移問題的關(guān)鍵部分做出了新的嘗試與優(yōu)化.實(shí)驗(yàn)結(jié)果證明,相較于現(xiàn)有方法,Sync Prototype模型在分類性能、概念漂移的響應(yīng)速度以及時(shí)間性能等方面都有明顯提高,能夠更加有效處理并適應(yīng)數(shù)據(jù)流概念漂移問題.
[Abstract]:In order to deal with or adapt to the concept drift more accurately and quickly, a data stream classification algorithm based on prototype learning is proposed. Based on the problems of existing methods, a new method model, Sync prototype, is proposed. New attempts and optimizations have been made to deal with the key parts of concept drift problem such as prototype decision and update method. The experimental results show that compared with the existing methods, the Sync Prototype model can improve the classification performance, the response speed of concept drift and the performance of time obviously, and can deal with and adapt to the problem of conceptual drift of data flow more effectively.
【作者單位】： 北京郵電大學(xué)網(wǎng)絡(luò)體系構(gòu)建與融合北京市重點(diǎn)實(shí)驗(yàn)室;中國(guó)電力科學(xué)研究院;
【基金】：國(guó)家電網(wǎng)公司科技項(xiàng)目(XT71-15-056)
【分類號(hào)】：TP311.13

【相似文獻(xiàn)】

相關(guān)碩士學(xué)位論文 前1條

1 談海宇;面向大數(shù)據(jù)的流分類挖掘算法及其概念漂移應(yīng)用研究[D];南京郵電大學(xué);2016年

，

本文編號(hào)：1810196