一种新的模糊规则权重方法的非平衡数据分类问题的研究-控制与决策.PDF

绗?7 鍗 绗? 鏈 鎺 鍒 涓 鍐 绛 2012 骞 1 鏈 Vol. 27 No. 1 Control and Decision Jan. 2011 鏂囩珷缂栧彿: 1001-0920 (2012) 01-0104-05 涓€绉嶆柊鐨勬ā绯婅鍒欐潈閲嶆柟娉曠殑闈炲钩琛 鏁版嵁鍒嗙被闂鐨勭爺绌 闄 鍒? 鍐 涓 (澶ц繛娴蜂簨澶у鏁板绯伙紝杈藉畞澶ц繛116026) 鎽 瑕? 閽堝浼犵粺鍒嗙被绠楁硶鍦ㄥ鐞嗛潪骞宠　鏁版嵁闆嗘墍鍑虹幇鐨勫皯鏁扮被鍒嗙被鍑嗙‘鐜囪緝浣庣殑闂, 閫氳繃寮曞叆鍔犳潈绯绘暟鍜屾牱鏈 鍒嗗竷鍑芥暟缁欏嚭浜嗕竴绉嶆柊鐨勬ā绯婅鍒欐潈閲嶇殑璁＄畻鏂规硶. 璇ユ柟娉曞姞寮轰簡绫婚棿鐨勫姣斿害鍜屽樊寮傛€? 鍓婂急浜嗙被鍐呭樊璺? 灏嗚鏉 閲嶆柟娉曚笌Chi et al 瑙勫垯鐢熸垚绠楁硶鍜屾ā绯婂垎绫绘帹鐞嗘ā鍨嬬粨鍚堝舰鎴愭柊鐨勫垎绫荤畻娉? 瀵瑰叿鏈変笉鍚岄潪骞宠　搴︾殑UCI 鏁版嵁闆嗚繘 琛孧atlab 瀵规瘮鐮旂┒, 鎵€寰楃粨鏋滈獙璇佷簡璇ョ畻娉曠殑鍙潬鎬т笌鏈夋晥鎬? 鍏抽敭璇岤 闈炲钩琛℃暟鎹紱鏁版嵁鍒嗙被锛涙ā绯婅鍒欐潈閲嶏紱鏁版嵁棰勫鐞 涓浘鍒嗙被鍙耳 TP273 鏂囩尞鏍囪瘑鐮? A Research on a new method for fuzzy rule weights in imbalanced data classi铿乧ation problem CHEN Gang, FENG Dan (Department of Mathematics锛孌alian Maritime University 锛孌alian 116026 锛孋hina 锛嶤orrespondent 锛欳HEN Gang, E-mail 锛歝hengang@dlmu.edu.cn) Abstract: For the problem that the traditional classi铿乧ation methods often tend to the majority class and lead a lower classi铿乧ation accuracy to the minority class in imbalanced data, a new calculation method of fuzzy rule weights is proposed. This algorithm not only keeps the pattern matching degree within class in uniform distribution, but also enhances the contrast of inter-class. Then a classi铿乧ation algorithm is designed, which includes the new calculation method of fuzzy rule weights, Chi et al algorithm and fuzzy reasoning model. Finally numerical simulation about the imbalanced data of UCI data sets shows the reliability of the classi铿乧ation algorithm. Key words: imbalanced data 锛沝ata classi铿乧ation 锛沠uzzy rules weights 锛沝ata processing 1 寮曞紩寮 瑷€瑷€瑷€ 瓒婂瀛