Dynamic weighted ensemble classification algorithm based on accuracy climbing

doi:10.11772/j.issn.1001-9081.2021071234

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (1): 123-131.DOI: 10.11772/j.issn.1001-9081.2021071234

• Data science and technology • Previous Articles

Dynamic weighted ensemble classification algorithm based on accuracy climbing

Xiaojuan LI, Meng HAN(), Le WANG, Ni ZHENG, Haodong CHENG

School of Computer Science and Engineering，North Minzu University，Yinchuan Ningxia 750021，China

Received:2021-07-15 Revised:2021-08-30 Accepted:2021-09-15 Online:2021-08-30 Published:2022-01-10
Contact: Meng HAN
About author:LI Xiaojuan， born in 1994， M. S. candidate. Her research interests include data stream classification.
HAN Meng， born in 1982， Ph. D.， associate professor. Her research interests include data mining.
WANG Le， born in 1994， M. S. candidate. Her research interests include data stream classification.
CHENG Haodong， born in 1996， M. S. candidate. His research interests include pattern mining.
First author contact:ZHANG Ni， born in 1996， M. S. candidate. Her research interests include pattern mining.
Supported by:
National Natural Science Foundation of China(62062004);Ningxia Natural Science Foundation(2020AAC03216)

基于准确率爬坡的动态加权集成分类算法

李小娟, 韩萌(), 王乐, 张妮, 程浩东

北方民族大学计算机科学与工程学院，银川 750021

通讯作者: 韩萌
作者简介:李小娟（1994—），女，宁夏吴忠人，硕士研究生，CCF会员，主要研究方向：数据流分类
韩萌（1982—），女，河南商丘人，副教授，博士，CCF会员，主要研究方向：数据挖掘
王乐（1994—），女，吉林白城人，硕士研究生，CCF会员，主要研究方向：数据流分类
张妮（1996—），女，山西长治人，硕士研究生，CCF会员，主要研究方向：模式挖掘
程浩东（1996—），男，山东泰安人，硕士研究生，CCF会员，主要研究方向：模式挖掘。
基金资助:
国家自然科学基金资助项目(62062004);宁夏自然科学基金资助项目(2020AAC03216)

Abstract

Abstract:

In the traditional ensemble classification algorithm， the ensemble number is generally set to a fixed value， which may lead to a low classification accuracy. Aiming at this problem， an accuracy Climbing Ensemble Classification Algorithm （C-ECA） was proposed. Firstly， the base classifiers was no longer replaced the same number of base classifiers with the worst performance， but updated based on the accuracy in this algorithm， and then the optimal ensemble number was determined. Secondly， on the basis of C-ECA， a Dynamic Weighted Ensemble Classification Algorithm based on Climbing （C-DWECA） was proposed. When the base classifier was trained on the data stream with different features， the best weight of the base classifier was able to be obtained by a weighting function proposed in this algorithm， thereby improving the performance of the ensemble classifier. Finally， in order to detect the concept drift earlier and improve the final accuracy， Fast Hoffding Drift Detection Method （FHDDM） was adopted. Experimental results show that the accuracy of C-DWECA can reach up to 97.44%， and the average accuracy of the proposed algorithm is about 40% higher than that of Adaptable Diversity-based Online Boosting （ADOB） algorithm， and is also better than those of other comparison algorithms such as Leveraging Bagging （LevBag） and Adaptive Random Forest （ARF）.

Key words: ensemble learning, classification, data stream, dynamic weighting, ensemble number, accuracy, climbing

摘要：

传统集成分类算法中，一般将集成数目设置为固定值，这可能会导致较低分类准确率。针对这一问题，提出了准确率爬坡集成分类算法（C-ECA）。首先，该算法不再用一些基分类器去替换相同数量的表现最差的基分类器，而是基于准确率对基分类器进行更新，然后确定最佳集成数目。其次，在C-ECA的基础上提出了基于爬坡的动态加权集成分类算法（C-DWECA）。该算法提出了一个加权函数，其在具有不同特征的数据流上训练基分类器时，可以获得基分类器的最佳权值，从而提升集成分类器的性能。最后，为了能更早地检测到概念漂移并提高最终精度，采用了快速霍夫丁漂移检测方法（FHDDM）。实验结果表明C-DWECA的准确率最高可达到97.44%，并且该算法的平均准确率比自适应多样性的在线增强（ADOB）算法提升了40%左右，也优于杠杆装袋（LevBag）、自适应随机森林（ARF）等其他对比算法。

关键词: 集成学习, 分类, 数据流, 动态加权, 集成数目, 准确率, 爬坡

CLC Number:

TP391.1

Xiaojuan LI, Meng HAN, Le WANG, Ni ZHENG, Haodong CHENG. Dynamic weighted ensemble classification algorithm based on accuracy climbing[J]. Journal of Computer Applications, 2022, 42(1): 123-131.

李小娟, 韩萌, 王乐, 张妮, 程浩东. 基于准确率爬坡的动态加权集成分类算法[J]. 《计算机应用》唯一官方网站, 2022, 42(1): 123-131.

Figures/Tables 12

Fig.1 Distribution types of real concept drift and virtual concept drift

Fig.2 Types of concep drift based on speed of change

Fig.3 Base classifier update methods

Fig.4 Schematic diagram of C-ECA algorithm

Tab.1 Parameters of Agrawal data streams

数据流	实例数	function	InstanceRandomSeed	peturbFraction
Agrawal	1 000 000	1	1	0.05
Agrawal-1	500 000	1	1	0.05
Agrawal-2	500 000	1	1	0.10
Agrawal-3	500 000	2	2	0.05

Tab.2 Parameters of Hyperplane data streams

数据流

实例数

Instance-

RandomSeed

numAtts

Num-

DriftAtts

Noise-

Percentage

Fig.5 Influence of ensemble number on accuracy

Tab.3 Accuracy comparison among C-ECA， C-DWECA and different comparison algorithms

算法	数据流
算法	Agrawal	Agrawal-1	Agrawal-2	Agrawal-3	Hyperplane-1	Hyperplane-2	Hyperplane-3	Wave	SEA	LED	RandomRBF
C-ECA	94.16 $±$ 0.10	94.64 $±$ 0.10	88.41 $±$ 0.10	90.63 $±$ 0.10	91.72 $±$ 0.01	86.14 $±$ 0.01	91.72 $±$ 0.01	85.38 $±$ 0.01	89.65 $±$ 0.01	74.09 $±$ 0.01	95.69 $±$ 0.01
C-DWECA	97.24 $±$ 0.10	97.29 $±$ 0.10	93.88 $±$ 0.10	94.07 $±$ 0.10	93.27 $±$ 0.01	89.67 $±$ 0.01	92.52 $±$ 0.01	91.73 $±$ 0.01	91.07 $±$ 0.01	80.42 $±$ 0.01	97.44 $±$ 0.01
ADOB	87.54 $±$ 0.10	93.57 $±$ 0.10	87.78 $±$ 0.10	80.82 $±$ 0.10	49.92 $±$ 0.01	50.00 $±$ 0.01	49.92 $±$ 0.01	33.35 $±$ 0.01	86.98 $±$ 0.01	9.98 $±$ 0.01	93.73 $±$ 0.01
BOLE	87.69 $±$ 0.10	92.79 $±$ 0.10	87.12 $±$ 0.10	77.63 $±$ 0.10	88.87 $±$ 0.01	83.17 $±$ 0.01	88.87 $±$ 0.01	82.78 $±$ 0.01	89.54 $±$ 0.01	74.05 $±$ 0.01	93.93 $±$ 0.01
OzaBoost	89.42 $±$ 0.30	93.42 $±$ 0.30	89.83 $±$ 0.10	82.92 $±$ 0.10	90.93 $±$ 0.01	85.51 $±$ 0.01	90.67 $±$ 0.01	85.15 $±$ 0.01	89.55 $±$ 0.01	74.06 $±$ 0.01	92.71 $±$ 0.01
AUE2	90.19 $±$ 0.10	95.08 $±$ 0.10	90.13 $±$ 0.10	93.10 $±$ 0.10	91.32 $±$ 0.01	86.70 $±$ 0.01	91.31 $±$ 0.01	84.17 $±$ 0.01	89.86 $±$ 0.20	74.09 $±$ 0.01	95.41 $±$ 0.01
OAUE	90.22 $±$ 0.01	95.09 $±$ 0.01	90.26 $±$ 0.10	92.11 $±$ 0.10	91.25 $±$ 0.01	86.70 $±$ 0.01	91.25 $±$ 0.01	84.30 $±$ 0.01	89.88 $±$ 0.01	71.12 $±$ 0.01	95.38 $±$ 0.01
LevBag	90.21 $±$ 0.01	95.25 $±$ 0.01	90.35 $±$ 0.10	87.29 $±$ 0.10	91.44 $±$ 0.01	86.51 $±$ 0.01	91.44 $±$ 0.01	86.58 $±$ 0.01	89.90 $±$ 0.01	74.03 $±$ 0.01	96.01 $±$ 0.01
OCBoost	88.52 $±$ 0.01	93.84 $±$ 0.01	88.34 $±$ 0.10	74.18 $±$ 0.10	89.62 $±$ 0.01	84.75 $±$ 0.01	89.62 $±$ 0.01	55.05 $±$ 0.01	89.43 $±$ 0.01	16.99 $±$ 0.01	92.71 $±$ 0.01
OzaBag	90.06 $±$ 0.01	95.04 $±$ 0.01	90.11 $±$ 0.10	90.70 $±$ 0.10	90.93 $±$ 0.01	86.35 $±$ 0.01	90.93 $±$ 0.01	85.87 $±$ 0.01	89.78 $±$ 0.01	74.17 $±$ 0.01	95.06 $±$ 0.01
ARF	91.95 $±$ 0.01	96.43 $±$ 0.01	92.19 $±$ 0.10	93.66 $±$ 0.10	90.71 $±$ 0.01	86.25 $±$ 0.01	90.71 $±$ 0.01	86.85 $±$ 0.01	89.96 $±$ 0.01	74.21 $±$ 0.01	96.40 $±$ 0.01
ADACC	80.78 $±$ 0.01	85.31 $±$ 0.01	86.09 $±$ 0.10	63.07 $±$ 0.10	92.39 $±$ 0.01	77.90 $±$ 0.01	92.39 $±$ 0.01	77.96 $±$ 0.01	86.49 $±$ 0.01	57.75 $±$ 0.01	62.97 $±$ 0.01
LimAtt-Classifier	94.33 $±$ 0.01	94.37 $±$ 0.01	88.95 $±$ 0.10	72.18 $±$ 0.10	78.40 $±$ 0.01	74.03 $±$ 0.01	78.40 $±$ 0.01	82.80 $±$ 0.01	78.92 $±$ 0.01	74.04 $±$ 0.01	72.72 $±$ 0.01

Tab.3 Accuracy comparison among C-ECA， C-DWECA and different comparison algorithms

算法	数据流
算法	Agrawal	Agrawal-1	Agrawal-2	Agrawal-3	Hyperplane-1	Hyperplane-2	Hyperplane-3	Wave	SEA	LED	RandomRBF
C-ECA	94.16 $±$ 0.10	94.64 $±$ 0.10	88.41 $±$ 0.10	90.63 $±$ 0.10	91.72 $±$ 0.01	86.14 $±$ 0.01	91.72 $±$ 0.01	85.38 $±$ 0.01	89.65 $±$ 0.01	74.09 $±$ 0.01	95.69 $±$ 0.01
C-DWECA	97.24 $±$ 0.10	97.29 $±$ 0.10	93.88 $±$ 0.10	94.07 $±$ 0.10	93.27 $±$ 0.01	89.67 $±$ 0.01	92.52 $±$ 0.01	91.73 $±$ 0.01	91.07 $±$ 0.01	80.42 $±$ 0.01	97.44 $±$ 0.01
ADOB	87.54 $±$ 0.10	93.57 $±$ 0.10	87.78 $±$ 0.10	80.82 $±$ 0.10	49.92 $±$ 0.01	50.00 $±$ 0.01	49.92 $±$ 0.01	33.35 $±$ 0.01	86.98 $±$ 0.01	9.98 $±$ 0.01	93.73 $±$ 0.01
BOLE	87.69 $±$ 0.10	92.79 $±$ 0.10	87.12 $±$ 0.10	77.63 $±$ 0.10	88.87 $±$ 0.01	83.17 $±$ 0.01	88.87 $±$ 0.01	82.78 $±$ 0.01	89.54 $±$ 0.01	74.05 $±$ 0.01	93.93 $±$ 0.01
OzaBoost	89.42 $±$ 0.30	93.42 $±$ 0.30	89.83 $±$ 0.10	82.92 $±$ 0.10	90.93 $±$ 0.01	85.51 $±$ 0.01	90.67 $±$ 0.01	85.15 $±$ 0.01	89.55 $±$ 0.01	74.06 $±$ 0.01	92.71 $±$ 0.01
AUE2	90.19 $±$ 0.10	95.08 $±$ 0.10	90.13 $±$ 0.10	93.10 $±$ 0.10	91.32 $±$ 0.01	86.70 $±$ 0.01	91.31 $±$ 0.01	84.17 $±$ 0.01	89.86 $±$ 0.20	74.09 $±$ 0.01	95.41 $±$ 0.01
OAUE	90.22 $±$ 0.01	95.09 $±$ 0.01	90.26 $±$ 0.10	92.11 $±$ 0.10	91.25 $±$ 0.01	86.70 $±$ 0.01	91.25 $±$ 0.01	84.30 $±$ 0.01	89.88 $±$ 0.01	71.12 $±$ 0.01	95.38 $±$ 0.01
LevBag	90.21 $±$ 0.01	95.25 $±$ 0.01	90.35 $±$ 0.10	87.29 $±$ 0.10	91.44 $±$ 0.01	86.51 $±$ 0.01	91.44 $±$ 0.01	86.58 $±$ 0.01	89.90 $±$ 0.01	74.03 $±$ 0.01	96.01 $±$ 0.01
OCBoost	88.52 $±$ 0.01	93.84 $±$ 0.01	88.34 $±$ 0.10	74.18 $±$ 0.10	89.62 $±$ 0.01	84.75 $±$ 0.01	89.62 $±$ 0.01	55.05 $±$ 0.01	89.43 $±$ 0.01	16.99 $±$ 0.01	92.71 $±$ 0.01
OzaBag	90.06 $±$ 0.01	95.04 $±$ 0.01	90.11 $±$ 0.10	90.70 $±$ 0.10	90.93 $±$ 0.01	86.35 $±$ 0.01	90.93 $±$ 0.01	85.87 $±$ 0.01	89.78 $±$ 0.01	74.17 $±$ 0.01	95.06 $±$ 0.01
ARF	91.95 $±$ 0.01	96.43 $±$ 0.01	92.19 $±$ 0.10	93.66 $±$ 0.10	90.71 $±$ 0.01	86.25 $±$ 0.01	90.71 $±$ 0.01	86.85 $±$ 0.01	89.96 $±$ 0.01	74.21 $±$ 0.01	96.40 $±$ 0.01
ADACC	80.78 $±$ 0.01	85.31 $±$ 0.01	86.09 $±$ 0.10	63.07 $±$ 0.10	92.39 $±$ 0.01	77.90 $±$ 0.01	92.39 $±$ 0.01	77.96 $±$ 0.01	86.49 $±$ 0.01	57.75 $±$ 0.01	62.97 $±$ 0.01
LimAtt-Classifier	94.33 $±$ 0.01	94.37 $±$ 0.01	88.95 $±$ 0.10	72.18 $±$ 0.10	78.40 $±$ 0.01	74.03 $±$ 0.01	78.40 $±$ 0.01	82.80 $±$ 0.01	78.92 $±$ 0.01	74.04 $±$ 0.01	72.72 $±$ 0.01

Tab. 4 Average accuracies of different algorithms

算法	平均准确率/%
C-ECA	88.55
C-DWECA	92.60
ADOB	65.78
BOLE	86.04
OzaBoost	87.65
AUE2	89.21
OAUE	88.86
LevBag	89.00
OCBoost	78.45
OzaBag	89.00
ARF	89.93
ADACC	78.46
LimAttClassifier	80.83

Fig. 6 Accuracy comparison of different algorithms

Fig. 7 Spanning tree depth comparison of different algorithms

Tab.5 Comparison of time efficiency between C-ECA， C-DWECA algorithms and different comparison algorithms

算法	数据流
算法	Agrawal	Agrawal-1	Agrawal-2	Agrawal-3	Hyperplane-1	Hyperplane-2	Wave	SEA	LED	RandomRBF
C-ECA	243.00	107.00	95.00	103.00	96.00	180.00	189	50.67	148.00	89.00
C-DWECA	834.00	310.00	296.00	464.00	1 573.00	1 295.00	1 955	540.00	568.00	461.00
ADOB	802.00	886.00	933.00	390.00	1 656.00	1 597.00	2 362	280.00	2 756.00	508.00
BOLE	86.00	46.24	47.94	53.16	51.23	52.36	153	15.35	85.00	43.11
OzaBoost	57.39	23.19	22.85	24.75	35.34	36.56	75	14.77	35.09	41.60
AUE2	62.00	23.88	30.44	42.89	61.00	61.00	111	19.76	59.39	55.03
OAUE	74.00	27.97	35.31	57.80	62.00	62.00	111	22.84	55.71	59.55
LevBag	113.00	45.74	56.07	69.00	102.00	100.00	141	36.18	70.00	82.00
OCBoost	60.00	27.06	28.20	32.86	40.93	40.83	88	18.79	49.31	42.31
OzaBag	34.11	15.38	17.56	22.50	34.50	34.73	66	11.97	31.35	33.52
ARF	185.00	96.00	104.00	109.00	109.00	106.00	123	73.00	65.00	83.00
ADACC	60.00	31.34	23.29	20.39	51.12	50.60	90	13.65	51.19	29.62
LimAttClassifier	48.78	19.06	18.74	21.77	35.60	36.54	92	9.61	51.49	36.85

References 22

1	李小娟，韩萌，王乐，等. 监督与半监督学习下的数据流集成分类综述［J］. 计算机应用研究， 2021， 38（7）：1921-1929.
	LI X J， HAN M， WANG L， et al. Overview of data stream ensemble classification under supervised and semi-supervised learning［J］. Application Research of Computers， 2021， 38（7）：1921-1929.
2	杨剑锋，乔佩蕊，李永梅，等. 机器学习分类问题及算法研究综述［J］. 统计与决策， 2019， 35（6）： 36-40. 10.13546/j.cnki.tjyjc.2019.06.008
	YANG J F， QIAO P R， LI Y M， et al. A review of machine learning classification problems and algorithms［J］. Statistics and Decision， 2019， 35（6）： 36-40. 10.13546/j.cnki.tjyjc.2019.06.008
3	GOMES H M， BARDDAL J P， ENEMBRECK F， et al. A survey on ensemble learning for data stream classification［J］. ACM Computing Surveys， 2017， 50（2）： No.23. 10.1145/3054925
4	DONG X B， YU Z W， CAO W M， et al. A survey on ensemble learning［J］. Frontiers of Computer Science， 2020， 14（2）：241-258. 10.1007/s11704-019-8208-z
5	BIFET A， HOLMES G， PFAHRINGER B. Leveraging bagging for evolving data streams ［C］// Proceeding of the 2010 Joint European Conference on Machine Learning and Knowledge Discovery in Databases， LNCS6321. Berlin： Springer， 2010：135-150.
6	KHAN A J， RAZA B， SHAHID A R， et al. Handling incomplete data classification using Imputed Feature selected Bagging （IFBag） method ［J］. Intelligent Data Analysis， 2021， 25（4）： 825-846. 10.3233/ida-205331
7	SARNOVSKY M， MARCINKO J. Adaptive bagging methods for classification of data streams with concept drift［J］. Acta Polytechnica Hungarica， 2021， 18（3）：47-63. 10.12700/aph.18.3.2021.3.3
8	章恒，鞠时光.基于概念漂移检测的网络数据流分类［J］.计算机与现代化，2021（7）：107-114. 10.3969/j.issn.1006-2475.2021.07.019
	ZHANG H， JU S-G. Network data stream classification based on concept drift detection［J］. Computer and Modernization， 2021（7）： 107-114. 10.3969/j.issn.1006-2475.2021.07.019
9	SHASTRI S， MANSOTRA V， KOUR P， et al. Voting-Boosting： a novel machine learning ensemble for the prediction of Infants' Data［J］. Indian Journal of Science and Technology， 2020， 13（22）： 2189-2202. 10.17485/ijst/v13i22.468
10	KHINE A A， KHIN H W. Credit card fraud detection using online boosting with extremely fast decision tree［C］// Proceedings of 2020 IEEE Conference on Computer Applications. Piscataway： IEEE， 2020： 1-4. 10.1109/icca49400.2020.9022843
11	MASTELINI S M， SANTANA E J， CERRI R， et al. DSTARS： a multi-target deep structure for tracking asynchronous regressor stacking ［J］. Applied Soft Computing， 2020， 91： No.106215. 10.1016/j.asoc.2020.106215
12	ORTIZ-DÍAZ A A， BALDO F， MARIÑO L M P， et al. FASE-AL — adaptation of fast adaptive stacking of ensembles for supporting active learning［EB/OL］. （2020-01-30）［2021-05-22］..
13	JIANG W L， CHEN Z H， XIANG Y， et al. SSEM： a novel self-adaptive stacking ensemble model for classification［J］. IEEE Access， 2019， 7： 120337-120349. 10.1109/access.2019.2933262
14	EFENDI E， DULEK B. Online EM-based ensemble classification with correlated agents ［J］. IEEE Signal Processing Letters， 2021， 28： 294-298. 10.1109/lsp.2021.3052135
15	AGUSTIN， ORTIZ， DIAZ， et al. Fast adapting ensemble： a new algorithm for mining data streams with concept drift［J］. The Scientific World Journal， 2015， 2015： No.235810. 10.1155/2015/235810
16	BRZEZINSKI D， STEFANOWSKI J. Combining block-based and online methods in learning ensembles from concept drifting data streams ［J］. Information Sciences， 2014， 265：50-67. 10.1016/j.ins.2013.12.011
17	SHAO J M， HUANG F， YANG Q L， et al. Robust prototype-based learning on data streams［J］. IEEE Transactions on Knowledge and Data Engineering， 2018， 30（5）： 978-991. 10.1109/tkde.2017.2772239
18	SONG G， YE Y M， ZHANG H J， et al. Dynamic clustering forest： an ensemble framework to efficiently classify textual data stream with concept drift ［J］. Information Sciences， 2016， 357： 125-143. 10.1016/j.ins.2016.03.043
19	SANTOS S G T C ， GONÇALVES JÚNIOR P M， SILVA G D S， et al. Speeding up recovery from concept drifts ［C］// Proceedings of the 2014 Joint European Conference on Machine Learning and Knowledge Discovery in Databases， LNCS8726. Berlin： Springer， 2014：179-194.
20	BERTINI J R， NICOLETTI M D C. An iterative boosting-based ensemble for streaming data classification ［J］. Information Fusion， 2019， 45： 66-78. 10.1016/j.inffus.2018.01.003
21	BAIDARI I， HONNIKOLL N. Accuracy weighted diversity-based online boosting［J］. Expert Systems with Applications， 2020， 160： No.113723. 10.1016/j.eswa.2020.113723
22	BIFET A， HOLMES G， PFAHRINGER B， et al. MOA： massive online analysis， a framework for stream classification and clustering ［C］// Proceedings of the 2010 1st Workshop on Applications of Pattern Analysis. New York： JMLR.org， 2010： 44-50. 10.1109/icdmw.2010.17

[1]	Yang LI, Anbiao WU, Ye YUAN, Linlin ZHAO, Guoren WANG. Unsupervised attributed graph embedding model based on node similarity [J]. Journal of Computer Applications, 2022, 42(1): 1-8.
[2]	MAO Mingze, CAO Ruihao, YAN Chungang. Semi-supervised classification algorithm based on weight diversity [J]. Journal of Computer Applications, 2021, 41(9): 2473-2480.
[3]	SONG Zhongshan, LIANG Jiarui, ZHENG Lu, LIU Zhenyu, TIE Jun. Remote sensing scene classification based on bidirectional gated scale feature fusion [J]. Journal of Computer Applications, 2021, 41(9): 2726-2735.
[4]	SHI Xuesong, LI Xianhua, SUN Qing, SONG Tao. Noise image segmentation by adaptive wavelet transform based on artificial bee swarm and fuzzy C-means [J]. Journal of Computer Applications, 2021, 41(8): 2312-2317.
[5]	HU Tianjie, HU Wenjun, WANG Shitong. Distribution entropy penalized support vector data description [J]. Journal of Computer Applications, 2021, 41(8): 2212-2218.
[6]	LI Mengmeng, QIN Wei, LIU Yi, DIAO Xingchun. Hybrid ant colony optimization algorithm with brain storm optimization [J]. Journal of Computer Applications, 2021, 41(8): 2412-2417.
[7]	ZHU Liang, XU Hua, CUI Xin. Improved AdaBoost algorithm based on base classifier coefficients and diversity [J]. Journal of Computer Applications, 2021, 41(8): 2225-2231.
[8]	ZHANG Yang, JIANG Minghu. Authorship identification of text based on attention mechanism [J]. Journal of Computer Applications, 2021, 41(7): 1897-1901.
[9]	XIAO Zhenyuan, WANG Yihan, LUO Jianqiao, XIONG Ying, LI Bailin. RefineDet based on subsection weighted loss function [J]. Journal of Computer Applications, 2021, 41(7): 1928-1932.
[10]	YIN Chunyong, ZHANG Guojie. Ensemble classification model for distributed drifted data streams [J]. Journal of Computer Applications, 2021, 41(7): 1947-1955.
[11]	ZHANG Hui, ZHANG Nana, HUANG Jun. Multi-angle head pose estimation method based on optimized LeNet-5 network [J]. Journal of Computer Applications, 2021, 41(6): 1667-1672.
[12]	SHI Yangxiao, ZHANG Jun, CHEN Peng, WANG Bing. Classification of steel surface defects based on lightweight network [J]. Journal of Computer Applications, 2021, 41(6): 1836-1841.
[13]	JIA Heming, LANG Chunbo, JIANG Zichao. Plant leaf disease recognition method based on lightweight convolutional neural network [J]. Journal of Computer Applications, 2021, 41(6): 1812-1819.
[14]	LU Xinwei, YU Pengfei, LI Haiyan, LI Hongsong, DING Wenqian. Weakly supervised fine-grained image classification algorithm based on attention-attention bilinear pooling [J]. Journal of Computer Applications, 2021, 41(5): 1319-1325.
[15]	GUO Shuai, SU Yang. Encrypted traffic classification method based on data stream [J]. Journal of Computer Applications, 2021, 41(5): 1386-1391.

Dynamic weighted ensemble classification algorithm based on accuracy climbing

基于准确率爬坡的动态加权集成分类算法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 22

Related Articles 15

Recommended Articles

Metrics