²é¿´: 407  |  »Ø¸´: 2
±¾Ìû²úÉú 1 ¸ö LS-EPI £¬µã»÷ÕâÀï½øÐв鿴

baroshi

ľ³æ (ÕýʽдÊÖ)

[ÇóÖú] °ïæ²éһƪÎÄÕµÄSCIºÅ£¬Ð»Ð»¡£

A compressed sensing approach for efficient ensemble learning 

[ ·¢×ÔÊÖ»ú°æ http://muchong.com/3g ]
»Ø¸´´ËÂ¥

» ²ÂÄãϲ»¶

KeepFighting
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû

muse

¾èÖú¹ó±ö (ÖªÃû×÷¼Ò)

¡¾´ð°¸¡¿Ó¦Öú»ØÌû

¡ï ¡ï ¡ï ¡ï ¡ï
¸Ðл²ÎÓ룬ӦÖúÖ¸Êý +1
baroshi: ½ð±Ò+5, ¡ï¡ï¡ï¡ï¡ï×î¼Ñ´ð°¸ 2014-09-21 19:06:41
sunshan4379: LS-EPI+1, ¸ÐлӦÖú£¡ 2014-09-21 19:36:07
A compressed sensing approach for efficient ensemble learning

×÷Õß:Li, L (Li, Lin)[ 1 ] ; Stolkin, R (Stolkin, Rustam)[ 2 ] ; Jiao, LC (Jiao, Licheng)[ 1 ] ; Liu, F (Liu, Fang)[ 1 ] ; Wang, S (Wang, Shuang)[ 1 ]

PATTERN RECOGNITION

¾í: 47

ÆÚ: 10

Ò³: 3451-3465

DOI: 10.1016/j.patcog.2014.04.015

³ö°æÄê: OCT 2014

²é¿´ÆÚ¿¯ÐÅÏ¢
ÕªÒª

This paper presents a method for improved ensemble learning, by treating the optimization of an ensemble of classifiers as a compressed sensing problem. Ensemble learning methods improve the performance of a learned predictor by integrating a weighted combination of multiple predictive models. Ideally, the number of models needed in the ensemble should be minimized, while optimizing the weights associated with each included model. We solve this problem by treating it as an example of the compressed sensing problem, in which a sparse solution must be reconstructed from an under-determined linear system. Compressed sensing techniques are then employed to find an ensemble which is both small and effective. An additional contribution of this paper, is to present a new performance evaluation method (a new pairwise diversity measurement) called the roulette-wheel kappa-error. This method takes into account the different weightings of the classifiers, and also reduces the total number of pairs of classifiers needed in the kappa-error diagram, by selecting pairs through a roulette-wheel selection method according to the weightings of the classifiers. This approach can greatly improve the clarity and informativeness of the kappa-error diagram, especially when the number of classifiers in the ensemble is large. We use 25 different public data sets to evaluate and compare the performance of compressed sensing ensembles using four different sparse reconstruction algorithms, combined with two different classifier learning algorithms and two different training data manipulation techniques. We also give the comparison experiments of our method against another five state-of-the-art pruning methods. These experiments show that our method produces comparable or better accuracy, while being significantly faster than the compared methods. (C) 2014 Elsevier Ltd. All rights reserved.
¹Ø¼ü´Ê

×÷Õ߹ؼü´Ê:Ensemble learning; Classification; Classifier ensemble; Sparse reconstruction; Compressed sensing; Roulette-wheel selection; Kappa-error

KeyWords Plus:RANDOM SUBSPACE METHOD; CLASSIFIER ENSEMBLES; NEURAL-NETWORKS; ALGORITHMS; REGRESSION; DIVERSITY
×÷ÕßÐÅÏ¢

ͨѶ×÷ÕßµØÖ·: Li, L (ͨѶ×÷Õß)
[ÏÔʾÔöÇ¿×éÖ¯ÐÅÏ¢µÄÃû³Æ]         Xidian Univ, Int Res Ctr Intelligent Percept & Computat, Minist Educ, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Peoples R China.

µØÖ·:
[ÏÔʾÔöÇ¿×éÖ¯ÐÅÏ¢µÄÃû³Æ]         [ 1 ] Xidian Univ, Int Res Ctr Intelligent Percept & Computat, Minist Educ, Key Lab Intelligent Percept & Image Understanding, Xian 710071, Peoples R China
[ÏÔʾÔöÇ¿×éÖ¯ÐÅÏ¢µÄÃû³Æ]         [ 2 ] Univ Birmingham, Sch Mech Engn, Birmingham B15 2TT, W Midlands, England

µç×ÓÓʼþµØÖ·:xdlinli86@163.com; lchjiao@mail.xidian.edu.cn
»ù½ð×ÊÖúÖÂл
»ù½ð×ÊÖú»ú¹¹        ÊÚȨºÅ
National Natural Science Foundation of China        
61371201
61001202
61272279
61273317
National Top Youth Talents Support Program of China          
²é¿´»ù½ð×ÊÖúÐÅÏ¢   
³ö°æÉÌ

ELSEVIER SCI LTD, THE BOULEVARD, LANGFORD LANE, KIDLINGTON, OXFORD OX5 1GB, OXON, ENGLAND
Àà±ð / ·ÖÀà

Ñо¿·½Ïò:Computer Science; Engineering

Web of Science Àà±ð:Computer Science, Artificial Intelligence; Engineering, Electrical & Electronic
ÎÄÏ×ÐÅÏ¢

ÎÄÏ×ÀàÐÍ:Article

ÓïÖÖ:English

Èë²ØºÅ: WOS:000338392400020

ISSN: 0031-3203

µç×Ó ISSN: 1873-5142
ÆÚ¿¯ÐÅÏ¢

    Ŀ¼£º Current Contents Connect®

    Impact Factor (Ó°ÏìÒò×Ó): Journal Citation Reports®

ÆäËûÐÅÏ¢

IDS ºÅ: AK4KA

Web of Science ºËÐĺϼ¯ÖÐµÄ "ÒýÓõIJο¼ÎÄÏ×": 47

Web of Science ºËÐĺϼ¯ÖÐµÄ "±»ÒýƵ´Î": 0
µã»÷ÎÒ»ØÌûÏÂÃæµÄ¡°ËÍTAºì»¨¡±£¬ËÍÎÒÒ»¶äºì»¨°É£¡
2Â¥2014-09-21 18:42:43
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû

muse

¾èÖú¹ó±ö (ÖªÃû×÷¼Ò)

¡¾´ð°¸¡¿Ó¦Öú»ØÌû

Èë²ØºÅ: WOS:000338392400020
µã»÷ÎÒ»ØÌûÏÂÃæµÄ¡°ËÍTAºì»¨¡±£¬ËÍÎÒÒ»¶äºì»¨°É£¡
3Â¥2014-09-21 18:42:51
ÒÑÔÄ   »Ø¸´´ËÂ¥   ¹Ø×¢TA ¸øTA·¢ÏûÏ¢ ËÍTAºì»¨ TAµÄ»ØÌû
Ïà¹Ø°æ¿éÌø×ª ÎÒÒª¶©ÔÄÂ¥Ö÷ baroshi µÄÖ÷Ìâ¸üÐÂ
×î¾ßÈËÆøÈÈÌûÍÆ¼ö [²é¿´È«²¿] ×÷Õß »Ø/¿´ ×îºó·¢±í
[¿¼ÑÐ] Ò»Ö¾Ô¸»ª¶«Àí¹¤´óѧ081700£¬³õÊÔ·ÖÊý271 +5 kotoko_ik 2026-03-23 6/300 2026-03-24 10:29 by ѧÊõ°áשer
[¿¼ÑÐ] 081700 µ÷¼Á 267·Ö +8 ÃÔÈ˵Ĺþ¹þ 2026-03-23 8/400 2026-03-24 08:23 by sunyuanna
[¿¼ÑÐ] Ò»Ö¾Ô¸ÄϺ½²ÄÁÏר317·ÖÇóµ÷¼Á +4 ըѽըѽըÊíÌõ 2026-03-23 4/200 2026-03-24 07:32 by wangy0907
[¿¼ÑÐ] ²ÄÁÏ/ũҵרҵ£¬07/08¿ªÍ·¾ù¿É£¬¹ýÏß¾ÍÐÐ +3 ºÇßíŶ»í 2026-03-23 4/200 2026-03-23 22:30 by Íô£¡£¿£¡
[¿¼ÑÐ] 291 Çóµ÷¼Á +4 »¯¹¤2026½ì±ÏÒµÉ 2026-03-21 5/250 2026-03-23 16:46 by »¯¹¤2026½ì±ÏÒµÉ
[¿¼ÑÐ] ²ÄÁÏÓ뻯¹¤¿¼Ñе÷¼Á +4 ‹üÈA 2026-03-22 4/200 2026-03-23 16:13 by Ò»ÐݸçFU
[¿¼ÑÐ] 307Çóµ÷¼Á +11 ÀäóÏ123 2026-03-17 11/550 2026-03-22 20:16 by edmund7
[¿¼ÑÐ] 298Çóµ÷¼ÁÒ»Ö¾Ô¸211 +3 Éϰ¶6666@ 2026-03-20 3/150 2026-03-22 15:50 by ColorlessPI
[¿¼ÑÐ] Çóµ÷¼ÁԺУÐÅÏ¢ +6 CX 330 2026-03-21 6/300 2026-03-22 15:25 by ÎÞи¿É»÷111
[¿¼ÑÐ] 0805 316Çóµ÷¼Á +3 ´óÑ©Éî²Ø 2026-03-18 3/150 2026-03-21 18:55 by ѧԱ8dgXkO
[¿¼ÑÐ] 0703»¯Ñ§µ÷¼Á +4 ÄÝÄÝninicgb 2026-03-21 4/200 2026-03-21 18:39 by ѧԱ8dgXkO
[»ù½ðÉêÇë] ѧУÒѾ­Ìá½»µ½NSFC£¬»¹ÄÜÐÞ¸ÄÂ𣿠40+4 babangida 2026-03-19 9/450 2026-03-21 16:12 by babangida
[¿¼ÑÐ] 0805²ÄÁÏ320Çóµ÷¼Á +3 ÉÎïÓï 2026-03-20 3/150 2026-03-21 15:46 by Î޼ʵIJÝÔ­
[¿¼ÑÐ] 301Çóµ÷¼Á +10 yyÒªÉϰ¶Ñ½ 2026-03-17 10/500 2026-03-21 03:14 by JourneyLucky
[¿¼ÑÐ] Çóµ÷¼Á +3 Ma_xt 2026-03-17 3/150 2026-03-21 02:05 by JourneyLucky
[¿¼ÑÐ] ²ÄÁÏ 336 Çóµ÷¼Á +3 An@. 2026-03-18 4/200 2026-03-21 01:39 by JourneyLucky
[¿¼ÑÐ] Ò»Ö¾Ô¸»ªÖпƼ¼´óѧ£¬080502£¬354·ÖÇóµ÷¼Á +5 ÊØºòϦÑôCF 2026-03-18 5/250 2026-03-21 01:06 by JourneyLucky
[¿¼ÑÐ] 317Çóµ÷¼Á +5 Éê×ÓÉêÉê 2026-03-19 9/450 2026-03-20 22:26 by JourneyLucky
[¿¼ÑÐ] 0856µ÷¼Á£¬ÊÇѧУ¾ÍÈ¥ +8 sllhht 2026-03-19 9/450 2026-03-20 14:25 by ÎÞи¿É»÷111
[¿¼ÑÐ] 085600²ÄÁÏÓ뻯¹¤µ÷¼Á 324·Ö +10 llllkkkhh 2026-03-18 12/600 2026-03-19 14:33 by llllkkkhh
ÐÅÏ¢Ìáʾ
ÇëÌî´¦ÀíÒâ¼û