基于蚁狮算法的元特征选择方法

doi:10.12305/j.issn.1001-506X.2023.09.22

系统工程与电子技术 ›› 2023, Vol. 45 ›› Issue (9): 2831-2842.doi: 10.12305/j.issn.1001-506X.2023.09.22

基于蚁狮算法的元特征选择方法

李庚松¹, 刘艺¹^,*, 郑奇斌², 秦伟¹, 李红梅², 任小广¹, 宋明武³

1. 国防科技创新研究院, 北京 100071
2. 军事科学院, 北京 100091
3. 天津(滨海)人工智能创新中心, 天津 300457

收稿日期:2022-05-06 出版日期:2023-08-30 发布日期:2023-09-05
通讯作者: 刘艺
作者简介:李庚松 (1999—), 男, 硕士, 主要研究方向为算法选择、大数据技术
刘艺 (1990—), 男, 助理研究员, 博士, 主要研究方向为机器人操作系统、大数据技术、演化算法
郑奇斌 (1990—), 男, 助理研究员, 博士, 主要研究方向为数据工程、数据挖掘、机器学习
秦伟 (1983—), 男, 助理研究员, 硕士, 主要研究方向为智能信息系统管理
李红梅 (1990—), 女, 助理研究员, 博士, 主要研究方向为个性化推荐
任小广 (1986—), 男, 副研究员, 博士, 主要研究方向为机器人操作系统、高性能计算、数值计算和模拟
宋明武 (1990—), 男, 工程师, 主要研究方向为人工智能
基金资助:
科技部科技创新2030-重大项目(2020AAA0104802);国家自然科学基金(91948303);国家自然科学青年基金(61802426)

Meta-feature selection method based on ant lion optimization algorithm

Gengsong LI¹, Yi LIU¹^,*, Qibin ZHENG², Wei QIN¹, Hongmei LI², Xiaoguang REN¹, Mingwu SONG³

1. Defense Innovation Institute, Beijing 100071, China
2. Academy of Military Science, Beijing 100091, China
3. Tianjin (Binhai) Artificial Intelligence Innovation Center, Tianjin 300450, China

Received:2022-05-06 Online:2023-08-30 Published:2023-09-05
Contact: Yi LIU

摘要/Abstract

摘要：

为了提升基于元学习算法选择的性能, 提出一种基于蚁狮算法的元特征选择方法。首先, 通过鲁棒初始化机制构建初始种群, 增强所选元特征子集的鲁棒性。其次, 在个体解的搜索过程中应用动态边界策略, 增加方法的种群多样性。然后, 采用混沌映射变异策略, 提升方法的寻优性能, 给出方法伪代码并分析时间复杂度。最后, 使用130个数据集、150种元特征、8种候选算法和5种性能指标构建分类算法选择问题进行测试实验, 分析方法的参数敏感性和机制策略效果, 通过准确率、查准率、查全率和F₁分数指标评估并对比方法性能, 验证了所提方法的有效性和优越性。

关键词: 元特征选择, 蚁狮优化算法, 算法选择, 元学习, 分类

Abstract:

To improve the performance of meta-learning algorithm selection, a meta-feature selection method based on ant lion algorithm is proposed. Firstly, an initial population is constructed through a robust initialization mechanism to enhance the robustness of the selected meta-feature subset. Secondly, dynamic boundary strategy is applied in the search process of individual solutions to increase the population diversity of the method. Then, the chaos map mutation strategy is used to improve the optimization performance of the method, give the method pseudocode and analyze the time complexity. Finally, classification algorithm selection problem are constructed using 130 datasets, 150 meta features, eight candidate algorithms, and five performance indicators for testing experiments. The parameter sensitivity and mechanism strategy effectiveness of the method are analyzed. The performance of the method is evaluated and compared through accuracy, precision, recall, and F₁ score indicators, verifying the effectiveness and superiority of the proposed method.

Key words: meta-feature selection, ant lion optimization (ALO) algorithm, algorithm selection, meta-learning, classification

中图分类号:

TP181

李庚松, 刘艺, 郑奇斌, 秦伟, 李红梅, 任小广, 宋明武. 基于蚁狮算法的元特征选择方法[J]. 系统工程与电子技术, 2023, 45(9): 2831-2842.

Gengsong LI, Yi LIU, Qibin ZHENG, Wei QIN, Hongmei LI, Xiaoguang REN, Mingwu SONG. Meta-feature selection method based on ant lion optimization algorithm[J]. Systems Engineering and Electronics, 2023, 45(9): 2831-2842.

图/表 14

图1

图2

图3

图4

表1

实验数据集信息"

序号	数据集名称	属性数	实例数	类数		序号	数据集名称	属性数	实例数	类数
1	abalone	8	4 177	29		66	kr_vs_kp	36	3 196	2
2	Absenteeism_at_work	20	740	18		67	led7digit	7	500	10
3	advertisement	1 558	3 279	2		68	lense	5	24	3
4	analcatdata_assessment	15	13	4		69	letter	16	20 000	26
5	analcatdata_authorship	70	841	4		70	lung_cancer	56	32	3
6	analcatdata_bankruptcy	6	50	2		71	lymphography	18	148	4
7	analcatdata_birthday	3	365	7		72	magic	10	19 020	2
8	analcatdata_bondrate	11	57	5		73	mfeat-fac	216	2 000	10
9	analcatdata_boxing1	3	120	2		74	mfeat-fou	76	2 000	10
10	analcatdata_boxing2	3	132	2		75	mfeat-kar	64	2 000	10
11	analcatdata_braziltourism	8	412	7		76	mfeat-mor	6	2 000	10
12	analcatdata_broadway	9	95	5		77	mfeat-pix	240	2 000	10
13	analcatdata_broadwaymult	7	285	7		78	monks_1_test	6	122	2
14	analcatdata_chall101	2	138	2		79	monks_1_train	6	124	2
15	analcatdata_creditscore	6	100	2		80	monks_2_test	6	432	2
16	analcatdata_currency	3	31	7		81	monks_2_train	6	169	2
17	analcatdata_cyyoung8092	10	97	2		82	monks_3_test	6	432	2
18	analcatdata_cyyoung9302	10	92	2		83	monks_3_train	6	122	2
19	analcatdata_dmf	4	797	6		84	movement_libras	90	360	15
20	analcatdata_draft	4	365	12		85	mushroom	22	8 124	2
21	analcatdata_esr	2	32	2		86	newthyroid	5	215	3
22	analcatdata_homerun	26	162	2		87	nursery	8	12 960	5
23	analcatdata_lawsuit	4	264	2		88	optdigits	64	3 823	10
24	analcatdata_mapleleafs	1	84	3		89	page_blocks	10	5 473	5
25	analcatdata_marketing	32	310	5		90	penbased	16	10 992	10
26	analcatdata_votesurvey	4	48	4		91	phoneme	5	5 404	2
27	anneal	38	798	6		92	pima	8	768	2
28	appendicitis	7	106	2		93	post_operative	8	90	3
29	arrhythmia	279	452	16		94	primary_tumor	17	339	22
30	audiology_standardized	69	226	24		95	ring	20	7 400	2
31	australian	14	690	2		96	risk_factors	35	858	26
32	Autism_Adult	20	704	2		97	saheart	9	462	2
33	automobile	25	205	7		98	satimage	36	6 435	7
34	balance_scale	4	625	3		99	segmentation_test	19	210	7
35	ballon	4	16	2		100	segmentation_train	19	2 100	7
36	banana	2	5 300	2		101	shuttle	9	58 000	7
37	breast_cancer	9	286	2		102	shuttle_landing_control	6	15	2
38	breast_cancer_wisconsin	9	699	2		103	sonar	60	208	2
39	bupa	6	345	2		104	soybean_large	35	307	19
40	car	6	1 728	4		105	soybean_small	35	47	4
41	chess	36	3 196	2		106	spambase	57	4 597	2
42	cleveland	13	297	5		107	spectf_test	44	269	2
43	cmc	9	1473	3		108	spectf_train	44	80	2
44	coil2000	85	9 822	2		109	spect_test	22	187	2
45	contraceptive	9	1 473	3		110	spect_train	22	80	2
46	crx	15	653	2		111	splice	60	3 190	3
47	cylinder-bands	19	539	2		112	student_mat	30	395	21
48	dermatology	34	366	6		113	student_por	30	649	21
49	divorce	54	170	2		114	Surveillance	7	15	3
50	echocardiogram	11	75	3		115	tae	5	151	3
51	ecoli	7	336	8		116	texture	40	5 000	11
52	flag	28	194	8		117	thyroid	21	7 200	3
53	flare	11	1 066	6		118	tic_tac_toe	9	958	2
54	german	20	1 000	2		119	titanic	3	2 201	2
55	glass	9	214	7		120	trains	32	10	2
56	haberman	3	306	2		121	twonorm	20	7 400	2
57	hayes_roth_test	4	28	4		122	vehicle	18	846	4
58	hayes_roth_train	4	132	4		123	vowel	13	990	11
59	heart_statlog	13	270	2		124	wdbc	30	569	2
60	hepatitis	19	155	2		125	wine	13	178	3
61	horse-colic-test	27	68	2		126	winequality_red	11	1 599	10
62	horse-colic-train	27	300	2		127	winequality_white	11	4 898	10
63	housevotes	16	232	2		128	wpbc	32	198	2
64	ionosphere	34	351	2		129	yeast	8	1 484	13
65	iris	4	150	3	130	zoo	16	101	7

表1

表2

元特征信息"

元特征类型	元特征名称
基于统计和信息论的元特征	attr_conc.mean、attr_conc.sd、attr_ent.mean、attr_ent.sd、attr_to_inst、can_cor.mean、can_cor.sd、cat_to_num、class_conc.mean、class_conc.sd、class_ent、cor.mean、cor.sd、cov.mean、cov.sd、eigenvalues.mean、eigenvalues.sd、eq_num_attr、freq_class.mean、freq_class.sd、g_mean.mean、g_mean.sd、gravity、h_mean.mean、h_mean.sd、inst_to_attr、iq_range.mean、iq_range.sd、joint_ent.mean、joint_ent.sd、kurtosis.mean、kurtosis.sd、lh_trace、mad.mean、mad.sd、max.mean、max.sd、mean.mean、mean.sd、median.mean、median.sd、min.mean、min.sd、mut_inf.mean、mut_inf.sd、nr_attr、nr_bin、nr_cat、nr_class、nr_cor_attr、nr_disc、nr_inst、nr_norm、nr_num、nr_outliers、ns_ratio、num_to_cat、one_itemset.mean、one_itemset.sd、p_trace、range.mean、range.sd、roy_root、sd.mean、sd.sd、sd_ratio、skewness.mean、skewness.sd、sparsity.mean、sparsity.sd、t_mean.mean、t_mean.sd、two_itemset.mean、two_itemset.sd、var.mean、var.sd、w_lambda
基于模型的元特征	leaves、leaves_branch.mean、leaves_branch.sd、leaves_corrob.mean、leaves_corrob.sd、leaves_homo.mean、leaves_homo.sd、leaves_per_class.mean、leaves_per_class.sd、nodes、nodes_per_attr、nodes_per_inst、nodes_per_level.mean、nodes_per_level.sd、nodes_repeated.mean、nodes_repeated.sd、tree_depth.mean、tree_depth.sd、tree_imbalance.mean、tree_imbalance.sd、tree_shape.mean、tree_shape.sd、var_importance.mean、var_importance.sd
基于基准的元特征	best_node.mean、best_node.sd、elite_nn.mean、elite_nn.sd、linear_discr.mean、linear_discr.sd、naive_bayes.mean、naive_bayes.sd、one_nn.mean、one_nn.sd、random_node.mean、random_node.sd、worst_node.mean、worst_node.sd
基于问题复杂度的元特征	c1、c2、cls_coef、density、f1.mean、f1.sd、f1v.mean、f1v.sd、f2.mean、f2.sd、f3.mean、f3.sd、f4.mean、f4.sd、hubs.mean、hubs.sd、l1.mean、l1.sd、l2.mean、l2.sd、l3.mean、l3.sd、lsc、n1、n2.mean、n2.sd、n3.mean、n3.sd、n4.mean、n4.sd、t1.mean、t1.sd、t2、t3、t4

表2

表3

表4

图5

表5

表6

表7

表8

表9

参考文献 31

1	ADAM S P, ALEXANDROPOULOS S-A N, PARDALOS P M, et al. No free lunch theorem: a review[M]//DEMETRIOU I C, PARDALOS P M. Approximation and optimization. Cham: Springer, 2019: 57-82.
2	KERSCHKE P , HOOS H H , NEUMANN F , et al. Automated algorithm selection: survey and perspectives[J]. Evolutionary Computation, 2019, 27 (1): 3- 45. doi: 10.1162/evco_a_00242
3	BRAZDIL P , GIRAUD-CARRIER C . Metalearning and algorithm selection: progress, state of the art and introduction to the 2018 Special Issue[J]. Machine Learning, 2018, 107 (1): 1- 14. doi: 10.1007/s10994-017-5692-y
4	YANG C, AKIMOTO Y, KIM D W, et al. OBOE: collaborative filtering for AutoML model selection[C]//Proc. of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019: 1173-1183.
5	李睿峰, 许爱强, 孙伟超, 等. 基于元学习的航空电子设备特征选择算法推荐方法[J]. 系统工程与电子技术, 2021, 43 (7): 2011- 2020.
	LI R F , XU A Q , SUN W C , et al. Recommendation method for avionics feature selection algorithm based on meta-learning[J]. Systems Engineering and Electronics, 2021, 43 (7): 2011- 2020.
6	DIAS L V , MIRANDA P B C , NASCIMENTO A C A , et al. ImageDataset2Vec: an image dataset embedding for algorithm selection[J]. Expert Systems with Applications, 2021, 180, 115053. doi: 10.1016/j.eswa.2021.115053
7	KOTLAR M , PUNT M , RADIVOJEVIC Z , et al. Novel meta-features for automated machine learning model selection in anomaly detection[J]. IEEE Access, 2021, 9, 89675- 89687. doi: 10.1109/ACCESS.2021.3090936
8	RIVOLLI A , GARCIA L P F , SOARES C , et al. Meta-features for meta-learning[J]. Knowledge-Based Systems, 2022, 240, 108101. doi: 10.1016/j.knosys.2021.108101
9	GARCIA-SAIZ D , ZORRILLA M . A meta-learning based framework for building algorithm recommenders: an application for educational arena[J]. Journal of Intelligent & Fuzzy Systems, 2017, 32 (2): 1449- 1459.
10	GARCIA L P F, LORENA A C, DE-SOUTO M C P, et al. Classifier recommendation using data complexity measures[C]//Proc. of the 24th International Conference on Pattern Recognition, 2018: 874-879.
11	CHALE M, BASTIAN N D, WEIR J. Algorithm selection framework for cyber attack detection[C]//Proc. of the 2nd ACM Workshop on Wireless Security and Machine Learning, 2020: 37-42.
12	MU T Y, WANG H Z, WANG C N, et al. Auto-CASH: autonomous classification algorithm selection with deep Q-network[EB/OL]. [2022-05-05]. https://arxiv.org/abs/2007.03254v1.
13	LI L , WANG Y , XU Y , et al. Meta-learning based industrial intelligence of feature nearest algorithm selection framework for classification problems[J]. Journal of Manufacturing Systems, 2022, 62, 767- 776. doi: 10.1016/j.jmsy.2021.03.007
14	MIRJALILI S . The ant lion optimizer[J]. Advances in Engineering Software, 2015, 83, 80- 98. doi: 10.1016/j.advengsoft.2015.01.010
15	ABUALIGAH L , SHEHAB M , ALSHINWAN M , et al. Ant lion optimizer: a comprehensive survey of its variants and applications[J]. Archives of Computational Methods in Engineering, 2021, 28 (3): 1397- 1416. doi: 10.1007/s11831-020-09420-6
16	IZADI S , AHMADI M , NIKBAZM R . Network traffic classification using convolutional neural network and ant-lion optimization[J]. Computers and Electrical Engineering, 2022, 101, 108024. doi: 10.1016/j.compeleceng.2022.108024
17	NIU G Q , LI X Y , WAN X , et al. Dynamic optimization of wastewater treatment process based on novel multi-objective ant lion optimization and deep learning algorithm[J]. Journal of Cleaner Production, 2022, 345, 131140. doi: 10.1016/j.jclepro.2022.131140
18	MAJJI R , NALINIPRIYA G , VIDYADHARI CH , et al. Jaya ant lion optimization-driven deep recurrent neural network for cancer classification using gene expression data[J]. Medical & Biological Engineering & Computing, 2021, 59, 1005- 1021.
19	曾子林, 张宏军, 张睿, 等. 基于元学习思想的算法选择问题综述[J]. 控制与决策, 2014, 29 (6): 961- 968. doi: 10.13195/j.kzyjc.2013.1297
	ZENG Z L , ZHANG H J , ZHANG R , et al. Summary of algorithm selection problem based on meta-learning[J]. Control and Decision, 2014, 29 (6): 961- 968. doi: 10.13195/j.kzyjc.2013.1297
20	KHAN I , ZHANG X , MOBASHAR R , et al. A literature survey and empirical study of meta-learning for classifier selection[J]. IEEE Access, 2020, 8, 10262- 10281. doi: 10.1109/ACCESS.2020.2964726
21	BALTE A , PISE N , KULKARNI P . Meta-learning with landmarking: a survey[J]. International Journal of Computer Applications, 2014, 105 (8): 47- 51.
22	LORENA A C, GARCIA L P F, LEHMANN J, et al. How complex is your classification problem? A survey on measuring classification complexity[EB/OL]. [2022-05-05]. https://arxiv.org/abs/1808.03591.
23	李郅琴, 杜建强, 聂斌, 等. 特征选择方法综述[J]. 计算机工程与应用, 2019, 55 (24): 10- 19.
	LI Z Q , DU J Q , NIE B , et al. Summary of feature selection methods[J]. Computer Engineering and Applications, 2019, 55 (24): 10- 19.
24	LIU Y , QIN W , ZHENG Q B , et al. An interpretable feature selection based on particle swarm optimization[J]. IEICE Transactions on Information and Systems, 2022, E105.D (8): 1495- 1500. doi: 10.1587/transinf.2021EDL8095
25	DUA D, GRAFF C. UCI machine learning repository[EB/OL]. [2022-03-19] http://archive.ics.uci.edu/ml.
26	ALCALA-FDEZ J , FERNANDEZ A , LUENGO J , et al. Keel data-mining software tool: data set repository, integration of algorithms and experimental analysis framework[J]. Journal of Multiple-Valued Logic & Soft Computing, 2011, 17, 255- 287.
27	KOOPERBERG C . StatLib: an archive for statistical software, datasets, and information[J]. The American Statistician, 1997, 51 (1): 98. doi: 10.2307/2684710
28	ALCOBACA E , SIQUEIRA F , RIVOLLI A , et al. MFE: towards reproducible meta-feature extraction[J]. Journal of Machine Learning Research, 2020, 21 (1): 4503- 4507.
29	PEDREGOSA F , VAROQUAUX G , GRAMFORT A , et al. Scikit-learn: machine learning in python[J]. Journal of Machine Learning Research, 2011, 12, 2825- 2830.
30	BRAZDIL P B , SOARES C . Ranking learning algorithms: using IBL and meta-learning on accuracy and time results[J]. Machine Learning, 2003, 50, 251- 277. doi: 10.1023/A:1021713901879
31	李洪奇, 徐青松, 朱丽萍, 等. 基于数据集相似性的分类算法推荐[J]. 计算机应用与软件, 2016, 33 (8): 62- 66.
	LI H Q , XU Q S , ZHU L P , et al. Classification algorithms recommendation based on dataset similarity[J]. Computer Applications and Software, 2016, 33 (8): 62- 66.

变异比例	元数据集
变异比例	D_Acc	D_Pre	D_Rec	D_F₁	D_A₁	D_A₂	D_A₃
5/6	43.4	42.0	36.8	44.4	42.2	33.1	37.6
4/5	41.5	41.1	35.5	43.3	42.0	33.7	37.1
3/4	43.9	43.4	36.8	44.4	42.1	34.2	36.7
2/3	43.5	42.7	37.2	44.9	42.3	33.5	37.8
1/2	43.6	43.4	36.7	44.9	42.6	33.6	37.1
1/3	42.9	43.1	37.2	44.7	42.2	34.0	37.5
1/4	43.5	43.0	37.0	44.3	42.0	33.3	37.7
1/5	42.5	42.4	35.7	44.1	42.1	33.9	37.3
1/6	42.9	43.2	36.9	44.0	41.9	33.6	37.3

元数据集	性能指标
元数据集	准确率	查准率	查全率	F₁分数
D_Acc	1.47	1.35	1.45	1.39
D_Pre	1.49	1.51	1.50	1.47
D_Rec	1.51	1.46	1.48	1.49
D_F₁	1.45	1.47	1.50	1.50
D_A₁	1.44	1.43	1.45	1.37
D_A₂	1.47	1.43	1.42	1.37
D_A₃	1.44	1.38	1.47	1.40

元数据集	RMA	kNN	RF	LR	LRW	SVR	RFR
D_Acc	43.6	31.4	35.7	30.3	25.7	32.3	31.7
D_Pre	43.4	29.0	36.8	29.8	19.7	31.5	28.6
D_Rec	36.7	20.3	30.9	30.2	23.4	30.2	27.7
D_F₁	44.9	28.6	36.6	33.4	23.1	35.2	31.1
D_A₁	42.6	25.4	33.8	27.7	27.4	27.7	32.2
D_A₂	33.6	14.0	32.5	20.3	23.7	20.8	28.0
D_A₃	37.1	24.2	32.3	28.6	22.5	31.5	33.7

元数据集	RMA	kNN	RF	LR	LRW	SVR	RFR
D_Acc	33.2	21.6	22.6	7.2	15.1	5.2	19.9
D_Pre	36.2	16.5	25.4	7.7	14.1	4.9	20.7
D_Rec	33.1	14.7	24.8	8.3	11.5	4.4	17.5
D_F₁	37.7	13.4	27.3	8.2	11.7	5.4	20.1
D_A₁	38.1	16.4	28.1	9.0	22.9	4.8	24.9
D_A₂	32.9	9.8	26.3	5.6	17.2	2.7	19.7
D_A₃	32.4	13.1	23.1	7.2	13.7	4.5	20.4

元数据集	RMA	kNN	RF	LR	LRW	SVR	RFR
D_Acc	30.0	21.2	22.6	16.0	16.4	15.2	20.5
D_Pre	32.6	17.1	23.7	15.7	13.1	14.3	21.8
D_Rec	29.5	16.0	22.9	16.8	14.8	14.1	19.2
D_F₁	32.7	14.9	23.1	15.8	16.9	14.2	22.4
D_A₁	38.2	20.2	28.3	18.5	22.7	17.4	24.8
D_A₂	31.6	12.6	26.8	13.2	18.0	13.1	20.5
D_A₃	29.5	16.3	22.0	14.3	13.2	14.2	21.1

基于蚁狮算法的元特征选择方法

Meta-feature selection method based on ant lion optimization algorithm

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 31

相关文章 15

编辑推荐

Metrics

本文评价

候选算法	D_Acc	D_Pre	D_Rec	D_F₁	D_A₁	D_A₂	D_A₃
kNN	0	3	3	3	19	9	2
RF	42	41	39	46	4	27	41
SVM	19	13	14	13	18	17	16
LoR	15	13	11	12	1	12	14
NB	6	10	14	8	21	11	9
LDA	14	19	17	15	31	20	13
ID3	15	15	15	13	36	24	19
MLP	19	16	17	20	0	10	16

元数据集	RMA	kNN	RF	LR	LRW	SVR	RFR
D_Acc	26.9	19.0	19.2	8.9	13.6	7.6	17.6
D_Pre	30.5	14.8	21.4	8.8	11.6	7.1	18.8
D_Rec	27.0	13.4	20.5	9.9	10.9	6.6	16.3
D_F₁	30.9	12.3	21.0	9.7	12.3	7.7	19.2
D_A₁	34.2	16.2	24.0	10.2	20.3	7.5	21.9
D_A₂	28.0	9.5	23.7	6.3	15.8	4.5	16.7
D_A₃	27.6	13.2	19.4	8.1	12.2	6.8	17.7

[1]	赵晓枫, 牛家辉, 刘春桐, 夏玉婷. 基于三维注意力与混合卷积的高光谱图像分类[J]. 系统工程与电子技术, 2023, 45(9): 2673-2680.
[2]	刘文波, 姚翼荣, 张弓, 胡文. 超维计算概念、应用及研究进展[J]. 系统工程与电子技术, 2023, 45(7): 1938-1956.
[3]	崔天舒, 王栋, 黄振. 面向空间认知通信的轻量化网络自动调制分类方法[J]. 系统工程与电子技术, 2023, 45(7): 2220-2226.
[4]	杨丽花, 任露露, 呼博, 邵永琪, 聂倩. 基于元学习的时变信道估计方法[J]. 系统工程与电子技术, 2023, 45(6): 1872-1879.
[5]	张晔, 侯毅, 欧阳克威, 周石琳. 单变量序列数据分类方法综述[J]. 系统工程与电子技术, 2023, 45(2): 313-335.
[6]	刘智星, 全英汇, 沙明辉, 方文, 高霞, 邢孟道. 载频-重频联合捷变雷达目标参数估计方法[J]. 系统工程与电子技术, 2023, 45(2): 401-406.
[7]	宋波涛, 许广亮. 基于LSTM与1DCNN的导弹轨迹预测方法[J]. 系统工程与电子技术, 2023, 45(2): 504-512.
[8]	龚佩, 李天昀, 章昕亮, 寸陈韬. 利用联合特征参数的卫星单-混信号调制识别[J]. 系统工程与电子技术, 2023, 45(2): 589-596.
[9]	王峻洲, 王华伟, 侯召国. 基于相似体系的民机结构超手册维修案例分析[J]. 系统工程与电子技术, 2022, 44(9): 2978-2985.
[10]	郭军成, 万刚, 胡欣杰, 严发宝, 王帅. 太阳射电频谱爆发识别的元学习方法[J]. 系统工程与电子技术, 2022, 44(8): 2410-2418.
[11]	童莹萍, 全英汇, 冯伟, 邢孟道. 基于空谱信息协同与Gram-Schmidt变换的多源遥感图像融合方法[J]. 系统工程与电子技术, 2022, 44(7): 2074-2083.
[12]	樊成, 王布宏, 田继伟. 基于多任务学习图卷积模型的航空网络节点分类[J]. 系统工程与电子技术, 2022, 44(7): 2341-2349.
[13]	曲志昱, 孙萌, 戴幻尧. 基于共形阵的角度和极化信息联合估计算法[J]. 系统工程与电子技术, 2022, 44(6): 1798-1804.
[14]	孙晶明, 虞盛康, 孙俊. 基于元学习的雷达小样本目标识别方法及改进[J]. 系统工程与电子技术, 2022, 44(6): 1839-1845.
[15]	李海, 白锦, 孙研, 任嘉伟. 基于修正小波变换插值-TAN的雷达降水粒子分类[J]. 系统工程与电子技术, 2022, 44(5): 1527-1535.