Fusion imaging-based recurrent capsule classification network for time series

doi:10.11772/j.issn.1001-9081.2022010089

Journal of Computer Applications ›› 2023, Vol. 43 ›› Issue (3): 692-699.DOI: 10.11772/j.issn.1001-9081.2022010089

• Artificial intelligence • Previous Articles

Fusion imaging-based recurrent capsule classification network for time series

Rongjun CHEN¹^,², Xuanhui YAN¹^,²(), Chaocheng YANG¹^,²

^1.College of Computer and Cyberspace Security，Fujian Normal University，Fuzhou Fujian 350117，China
^2.Digital Fujian Internet-of-Things Laboratory of Environmental Monitoring （Fujian Normal University），Fuzhou Fujian 350117，China

Received:2022-01-25 Revised:2022-04-19 Accepted:2022-04-20 Online:2022-04-26 Published:2023-03-10
Contact: Xuanhui YAN
About author:CHEN Rongjun， born in 1996， M. S. candidate. His research interests include deep learning， time series analysis.
YANG Chaocheng， born in 1996， M. S. candidate. His research interests include time series analysis， machine learning.
Supported by:
Guiding Project of Fujian Provincial Science and Technology Department(2020H0011)

面向时间序列的混合图像化循环胶囊分类网络

陈容均¹^,², 严宣辉¹^,²(), 杨超城¹^,²

^1.福建师范大学计算机与网络空间安全学院，福州 350117
^2.数字福建环境监测物联网实验室（福建师范大学），福州 350117

通讯作者: 严宣辉
作者简介:陈容均（1996—），男，福建三明人，硕士研究生，主要研究方向：深度学习、时间序列分析
严宣辉（1968—），男，福建福州人，副教授，博士，主要研究方向：人工智能、深度学习
杨超城（1996—），男，河南周口人，硕士研究生，主要研究方向：时间序列分析、机器学习。
基金资助:
福建省科技厅引导性项目(2020H0011)

Abstract

Abstract:

To address the problem of lack of temporal correlations and spatial location relationships in imaging time series， Fusion-Imaing Recurrent Capsule Neural Network （FIR-Capsnet） for time series was proposed to fuse and extract spatial-temporal information from time series images. Firstly， the multi-level spatial-temporal features of time series images were captured by using Gramian Angular Field （GAF）， Markov Transition Field （MTF） and Recurrence Plot （RP）. Then， the spatial relationships of time series images were learnt by the rotation invariance of capsule neural network and iterative routing algorithm. Finally， the temporal correlations hidden in the time series data were learnt by the gate mechanism of Long-Short Term Memory （LSTM） network. Experimental results show that FIR-Capsnet achieves 15 wins on 30 UCR public datasets and outperforms Fusion-CNN by 7.2 percentage points in classification accuracy on Human Activity Recognition （HAR） dataset， illustrating the advantages of FIR-Capsnet in processing time series data.

Key words: pattern recognition, time series classification, deep learning, imaging time series, recurrent capsule neural network

摘要：

针对时间序列图像化缺少时间关联关系与空间位置关系的问题，提出面向时间序列的混合图像化循环胶囊神经网络（FIR-Capsnet）以融合并提取时间序列图像的时空信息。首先通过格拉姆角场（GAF）、马尔可夫跃迁场（MTF）与重现图（RP）方法捕获时间序列图像的多水平时空特征；然后利用胶囊神经网络的旋转不变性与路由迭代算法学习时间序列图像的空间关系；最后引入长短时记忆（LSTM）网络的门机制学习时间序列数据隐含的时间关联性。实验结果表明，FIR-Capsnet在30个UCR公开数据集上取得15次胜利；并且在人体活动识别（HAR）数据集上相较于Fusion-CNN、FIR-Capsnet的分类准确率提高7.2个百分点，说明了FIR-Capsnet处理时序数据的优势。

关键词: 模式识别, 时间序列分类, 深度学习, 时间序列图像化, 循环胶囊神经网络

CLC Number:

TP391.4

Rongjun CHEN, Xuanhui YAN, Chaocheng YANG. Fusion imaging-based recurrent capsule classification network for time series[J]. Journal of Computer Applications, 2023, 43(3): 692-699.

陈容均, 严宣辉, 杨超城. 面向时间序列的混合图像化循环胶囊分类网络[J]. 《计算机应用》唯一官方网站, 2023, 43(3): 692-699.

Figures/Tables 14

References 40

1	QIANG Y， XINDONG W. 10 Challenging problems in data mining research［J］. International Journal of Information Technology and Decision Making， 2006， 5（4）： 597-604.
2	ESLING P， AGON C. Time-series data mining［J］. ACM Computing Surveys， 2012， 45（1）： 1-34. 10.1145/2379776.2379788
3	王鑫，吴际，刘超，等. 基于LSTM循环神经网络的故障时间序列预测［J］. 北京航空航天大学学报， 2018， 44（4）： 772-784. 10.13700/j.bh.1001-5965.2017.0285
	WANG X， WU J， LIU C， et al. Exploring LSTM based recurrent neural network for failure time series prediction［J］. Journal of Beijing University of Aeronautics and Astronautics， 2018， 44（4）： 772-784. 10.13700/j.bh.1001-5965.2017.0285
4	BÖSE J H， FLUNKERT V， GASTHAUS J， et al. Probabilistic demand forecasting at scale［J］. Proceedings of the VLDB Endowment， 2017， 10（12）： 1694-1705. 10.14778/3137765.3137775
5	CAI L， JANOWICZ K， MAI G C， et al. Traffic transformer： capturing the continuity and periodicity of time series for traffic forecasting［J］. Transactions in GIS， 2020， 24（3）： 736-755. 10.1111/tgis.12644
6	李浩，张杉，曹斌，等. 基于城市道路卡口数据的交通流量预测［J］. 重庆大学学报， 2020， 43（11）：29-40. 10.11835/j.issn.1000-582X.2020.11.004
	LI H， ZHANG S， CAO B， et al. Prediction traffic flow based on traffic data of urban road check points［J］. Journal of Chongqing University， 2020， 43（11）： 29-40. 10.11835/j.issn.1000-582X.2020.11.004
7	CARVALHAIS N， FORKEL M， KHOMIK M， et al. Global covariation of carbon turnover times with climate in terrestrial ecosystems［J］. Nature， 2014， 514（7521）： 213-217. 10.1038/nature13731
8	高世乐，王滢，李海林，等. 基于矩阵画像的金融时序数据预测方法［J］. 计算机应用， 2021， 41（1）：199-207. 10.11772/j.issn.1001-9081.2020060877
	GAO S L， WANG Y， LI H L， et al. Prediction method on financial time series data based on matrix profile［J］. Journal of Computer Applications， 2021， 41（1）： 199-207. 10.11772/j.issn.1001-9081.2020060877
9	RAJAN D， THIAGARAJAN J J. A generative modeling approach to limited channel ECG classification［C］// Proceedings of the 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway： IEEE， 2018： 2571-2574. 10.1109/embc.2018.8512757
10	朱兆坤，李金宝. 多特征信息融合LSTM-RNN检测OSA方法［J］. 计算机研究与发展， 2020， 57（12）：2547-2555. 10.7544/issn1000-1239.2020.20190583
	ZHU Z K， LI J B. Multi-feature information fusion LSTM-RNN detection for OSA［J］. Journal of Computer Research and Development， 2020， 57（12）： 2547-2555. 10.7544/issn1000-1239.2020.20190583
11	NWEKE H F， TEH Y W， AL-GARADI M A， et al. Deep learning algorithms for human activity recognition using mobile and wearable sensor networks： state of the art and research challenges［J］. Expert Systems with Applications， 2018， 105： 233-261. 10.1016/j.eswa.2018.03.056
12	吴海涛，陆志平，胡晨骏. 混合神经网络模型在人体活动识别中的研究［J］. 计算机应用与软件， 2021， 38（8）：187-193， 219. 10.3969/j.issn.1000-386x.2021.08.029
	WU H T， LU Z P， HU C J. Human activity recognition based on hybrid neural network models［J］. Computer Applications and Software， 2021， 38（8）： 187-193， 219. 10.3969/j.issn.1000-386x.2021.08.029
13	SUSTO G A， CENEDESE A， TERZI M. Time-series classification methods： review and applications to power systems data［M］// ARGHANDEHR， ZHOU Y X. Big Data Application in Power Systems. Amsterdam： Elsevier Science， 2018： 179-220. 10.1016/b978-0-12-811968-6.00009-7
14	SHOKOOHI-YEKTA M， HU B， JIN H X， et al. Generalizing DTW to the multi-dimensional case requires an adaptive approach［J］. Data Mining and Knowledge Discovery， 2017， 31（1）： 1-31. 10.1007/s10618-016-0455-0
15	HILLS J， LINES J， BARANAUSKAS E， et al. Classification of time series by shapelet transformation［J］. Data Mining and Knowledge Discovery， 2014， 28（4）： 851-881. 10.1007/s10618-013-0322-1
16	YE L X， KEOGH E. Time series shapelets： a new primitive for data mining［C］// Proceedings of the 2009 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2009： 947-956. 10.1145/1557019.1557122
17	DENG H T， RUNGER G， TUV E， et al. A time series forest for classification and feature extraction［J］. Information Sciences， 2013， 239： 142-153. 10.1016/j.ins.2013.02.030
18	LINES J， TAYLOR S， BAGNALL A. Time series classification with HIVE-COTE： the hierarchical vote collective of transformation-based ensembles［J］. ACM Transactions on Knowledge Discovery from Data， 2018， 12（5）： No.52. 10.1145/3182382
19	SCHÄFER P. The BOSS is concerned with time series classification in the presence of noise［J］. Data Mining and Knowledge Discovery， 2015， 29（6）： 1505-1530. 10.1007/s10618-014-0377-7
20	SCHÄFER P， LESER U. Fast and accurate time series classification with WEASEL［C］// Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York： ACM， 2017： 637-646. 10.1145/3132847.3132980
21	SCHÄFER P， HÖGQVIST M. SFA： a symbolic Fourier approximation and index for similarity search in high dimensional datasets［C］// Proceedings of the 15th International Conference on Extending Database Technology. New York： ACM， 2012： 516-527. 10.1145/2247596.2247656
22	WANG J Y， WANG Z， LI J F， et al. Multilevel wavelet decomposition network for interpretable time series analysis［C］// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York： ACM， 2018： 2437-2446. 10.1145/3219819.3220060
23	ZHENG Y， LIU Q， CHEN E H， et al. Exploiting multi-channels deep convolutional neural networks for multivariate time series classification［J］. Frontiers of Computer Science， 2016， 10（1）： 96-112. 10.1007/s11704-015-4478-2
24	ZHAO B D， LU H Z， CHEN S F， et al. Convolutional neural networks for time series classification［J］. Journal of Systems Engineering and Electronics， 2017， 28（1）：162-169. 10.21629/jsee.2017.01.18
25	ZHANG X C， GAO Y F， LIN J， et al. TapNet： multivariate time series classification with attentional prototypical network［C］// Proceedings of the 24th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2020： 6845-6852. 10.1609/aaai.v34i04.6165
26	ZHANG Y， HOU Y， OUYANG K W， et al. Multi-scale signed recurrence plot based time series classification using inception architectural networks［J］. Pattern Recognition， 2022， 123： No.108385. 10.1016/j.patcog.2021.108385
27	CHAN K P， FU A W C. Efficient time series matching by wavelets［C］// Proceedings of the 15th International Conference on Data Engineering. Piscataway： IEEE， 1999： 126-133. 10.1109/icde.1999.754915
28	WANG Z G， OATES T. Imaging time-series to improve classification and imputation［C］// Proceedings of the 24th International Joint Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2015： 3939-3945.
29	HATAMI N， GAVET Y， DEBAYLE J. Classification of time-series images using deep convolutional neural networks［C］// Proceedings of the SPIE 10696， 10th International Conference on Machine Vision. Bellingham， WA： SPIE， 2018： No.106960Y. 10.1117/12.2309486
30	RODRIGUES N M， BATISTA J E， MARIANO P， et al. Artificial intelligence meets marine ecotoxicology： applying deep learning to bio-optical data from marine diatoms exposed to legacy and emerging contaminants［J］. Biology， 2021， 10（9）： No.932. 10.3390/biology10090932
31	ISMAIL FAWAZ H， FORESTIER G， WEBER J， et al. Deep learning for time series classification： a review［J］. Data Mining and Knowledge Discovery， 2019， 33（4）： 917-963. 10.1007/s10618-019-00619-1
32	LUO Y， MESGARANI N. Conv-TasNet： surpassing ideal time-frequency magnitude masking for speech separation［J］. IEEE/ACM Transactions on Audio Speech and Language Processing， 2019， 27（8）： 1256-1266. 10.1109/taslp.2019.2915167
33	SABOUR S， FROSST N， HINTON G E. Dynamic routing between capsules［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 3859-3869.
34	王飞龙，刘萍，张玲，等. 改进胶囊网络的小样本图像分类算法［J］. 计算机科学与探索， 2022， 16（10）：2387-2394. 10.3778/j.issn.1673-9418.2102026
	WANG F L， LIU P， ZHANG L， et.al. Modified algorithm of capsule network for classifying small sample image［J］. Journal of Frontiers of Computer Science and Technology， 2022， 16（10）：2387-2394. 10.3778/j.issn.1673-9418.2102026
35	胡春涛，夏玲玲，张亮，等. 基于胶囊网络和卷积网络的文本分类对比［J］. 计算机技术与发展， 2020， 30（10）：86-91. 10.3969/j.issn.1673-629X.2020.10.016
	HU C T， XIA L L， ZHANG L， et al. Comparative study of news text classification based on capsule network and convolution network［J］. Computer Technology and Development， 2020， 30（10）：86-91. 10.3969/j.issn.1673-629X.2020.10.016
36	RAJASEGARAN J， JAYASUNDARA V， JAYASEKARA S， et al. DeepCaps： going deeper with capsule networks［C］// Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2019： 10717-10725. 10.1109/cvpr.2019.01098
37	陈解元. 基于LSTM 的卷积神经网络异常流量检测方法［J］. 网络与信息安全， 2021， 40（7）：42-46. 10.19358/j.issn.2096-5133.2021.07.007
	CHEN X Y. Network intrusion detection based on convolutional neural networks with LSTM［J］. Network and Information Security， 2021， 40（7）： 42-46. 10.19358/j.issn.2096-5133.2021.07.007
38	DAU H A， BAGNALL A， KAMGAR K， et al. The UCR time series archive［J］. IEEE/CAA Journal of Automatica Sinica， 2019， 6（6）： 1293-1305. 10.1109/jas.2019.1911747
39	马超红. 基于PAA的时间序列早期分类［J］. 计算机科学，2018， 45（2）：148-162. 10.11896/j.issn.1002-137X.2018.02.050
	MA C H. Early classification of time series based on piecewise aggregate approximation［J］. Computer Science， 2018， 45（2）： 148-162. 10.11896/j.issn.1002-137X.2018.02.050
40	WANG Z G， YAN W Z， OATES T. Time series classification from scratch with deep neural networks： a strong baseline［C］// Proceedings of the 2017 International Joint Conference on Neural Networks. Piscataway： IEEE， 2017： 1578-1585. 10.1109/ijcnn.2017.7966039

数据集	类型	训练样本数	测试样本数	时间序列长度	类别数
Computers	Device	250	250	720	2
DistalPhalanxOutline Correct	Image	600	276	80	2
Earthquakes	Sensor	322	139	512	2
ECG5000	ECG	500	4 500	140	5
ElectricDevices	Device	8 926	7 711	96	7
FaceFour	Image	24	88	350	4
FiftyWords	Image	450	455	270	50
InsectWingbeatSound	Sensor	220	1 980	256	11
LargeKitchenAppliances	Device	375	375	720	3
Lightning2	Sensor	60	61	637	2
Mallat	Simulated	55	2 345	1 024	8
Meat	Spectro	60	60	448	3
MiddlePhalanxOutline AgeGroup	Image	400	154	80	3
MiddlePhalanxTW	Image	399	154	80	6
MoteStrain	Sensor	20	1 252	84	2
PhalangesOutlinesCorrect	Image	1 800	858	80	2
ProximalPhalanxOutline Correct	Image	600	291	80	2
ShapeletSim	Simulated	20	180	500	2
ShapesAll	Image	600	600	512	60
SmallKitchenAppliances	Device	375	375	720	3
SonyAIBORobotSurface1	Sensor	20	601	70	2
SonyAIBORobotSurface2	Sensor	27	953	65	2
StarlightCurves	Sensor	1 000	8 236	1 024	3
Strawberry	Spectro	613	370	235	2
Symbols	Image	25	995	398	6
ToeSegmentation1	Motion	40	228	277	2
TwoLeadECG	ECG	23	1 139	82	2
Wine	Spectro	57	54	234	2
WordSynonyms	Image	267	638	270	25
Worms	Motion	181	77	900	5

数据集	类型	训练样本数	测试样本数	时间序列长度	类别数
Computers	Device	250	250	720	2
DistalPhalanxOutline Correct	Image	600	276	80	2
Earthquakes	Sensor	322	139	512	2
ECG5000	ECG	500	4 500	140	5
ElectricDevices	Device	8 926	7 711	96	7
FaceFour	Image	24	88	350	4
FiftyWords	Image	450	455	270	50
InsectWingbeatSound	Sensor	220	1 980	256	11
LargeKitchenAppliances	Device	375	375	720	3
Lightning2	Sensor	60	61	637	2
Mallat	Simulated	55	2 345	1 024	8
Meat	Spectro	60	60	448	3
MiddlePhalanxOutline AgeGroup	Image	400	154	80	3
MiddlePhalanxTW	Image	399	154	80	6
MoteStrain	Sensor	20	1 252	84	2
PhalangesOutlinesCorrect	Image	1 800	858	80	2
ProximalPhalanxOutline Correct	Image	600	291	80	2
ShapeletSim	Simulated	20	180	500	2
ShapesAll	Image	600	600	512	60
SmallKitchenAppliances	Device	375	375	720	3
SonyAIBORobotSurface1	Sensor	20	601	70	2
SonyAIBORobotSurface2	Sensor	27	953	65	2
StarlightCurves	Sensor	1 000	8 236	1 024	3
Strawberry	Spectro	613	370	235	2
Symbols	Image	25	995	398	6
ToeSegmentation1	Motion	40	228	277	2
TwoLeadECG	ECG	23	1 139	82	2
Wine	Spectro	57	54	234	2
WordSynonyms	Image	267	638	270	25
Worms	Motion	181	77	900	5

动作类型	训练样本数	测试样本数
共计	7 352	2 947
走路	1 374	532
上楼	1 286	491
下楼	1 407	537
坐下	1 226	496
站直	986	420
躺下	1 073	471

动作类型	训练样本数	测试样本数
共计	7 352	2 947
走路	1 374	532
上楼	1 286	491
下楼	1 407	537
坐下	1 226	496
站直	986	420
躺下	1 073	471

数据集	Fusion-CNN	GAF-Capsnet	RP-Capsnet	MTF-Capsnet	FIR-Capsnet
Computers	0.630	0.710	0.730	0.720	0.760
DistalPhalanxOutlineCorrect	0.772	0.790	0.772	0.784	0.858
Earthquakes	0.895	0.753	0.828	0.753	0.785
ECG5000	0.823	0.930	0.945	0.946	0.945
ElectricDevices	0.719	0.770	0.809	0.776	0.849
FaceFour	0.826	1.000	1.000	0.957	0.957
FiftyWords	0.470	0.630	0.586	0.646	0.680
InsectWingbeatSound	0.616	0.654	0.666	0.693	0.691
LargeKitchenAppliances	0.507	0.610	0.633	0.640	0.627
Lightning2	0.720	0.800	0.800	0.800	0.800
Mallat	0.960	0.996	1.000	1.000	1.000
Meat	0.833	0.958	0.958	1.000	0.958
MiddlePhalanxOutlineAgeGroup	0.604	0.658	0.667	0.720	0.730
MiddlePhalanxTW	0.559	0.559	0.631	0.523	0.559
MoteStrain	0.914	0.933	0.914	0.965	0.929
PhalangesOutlinesCorrect	0.724	0.780	0.803	0.780	0.800
ProximalPhalanxOutlineCorrect	0.777	0.810	0.804	0.872	0.849
ShapeletSim	0.825	0.650	0.625	0.625	0.700
ShapesAll	0.608	0.713	0.771	0.742	0.833
SmallKitchenAppliances	0.573	0.653	0.726	0.693	0.720
SonyAIBORobotSurface1	0.872	0.952	0.952	0.960	0.968
SonyAIBORobotSurface2	0.948	0.969	0.913	0.949	0.969
StarlightCurves	0.975	0.971	0.962	0.984	0.905
Strawberry	0.954	0.959	0.970	0.975	0.964
Symbols	0.980	0.975	0.956	0.971	0.961
ToeSegmentation1	0.815	0.796	0.796	0.833	0.870
TwoLeadECG	0.991	1.000	0.991	0.991	1.000
Wine	0.869	1.000	1.000	0.826	1.000
WordSynonyms	0.541	0.678	0.552	0.707	0.729
Worms	0.774	0.742	0.871	0.871	0.871
平均准确率	0.748	0.792	0.802	0.802	0.821
方差	0.192	0.182	0.173	0.176	0.156
获胜次数	3	5	8	11	15
平均序值	4.129	3.064	2.645	2.322	1.903
MPCE	0.067	0.056	0.054	0.054	0.050

Fusion imaging-based recurrent capsule classification network for time series

面向时间序列的混合图像化循环胶囊分类网络

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 14

References 40

Related Articles 15

Recommended Articles

Metrics

网络	各个动作类型准确率						总体准确率
网络	走路	上楼	下楼	坐下	站直	躺下	总体准确率
Fusion-CNN	0.878	0.856	0.865	0.926	0.873	0.918	0.878
GAF-Capsnet	0.933	0.904	0.929	0.953	0.943	0.896	0.933
RP-Capsnet	0.866	0.923	0.946	0.966	0.989	0.921	0.866
MTF-Capsnet	0.909	0.900	0.831	0.994	1.000	0.935	0.929
FIR-Capsnet	0.963	0.942	0.871	1.000	0.998	0.922	0.950

[1]	Boyi FU, Yuncong PENG, Xin LAN, Xiaolin QIN. Survey of label noise learning algorithms based on deep learning [J]. Journal of Computer Applications, 2023, 43(3): 674-684.
[2]	Qi WANG, Hang LEI, Xupeng WANG. Deep face verification under pose interference [J]. Journal of Computer Applications, 2023, 43(2): 595-600.
[3]	Ping WANG, Nan CHEN, Lei LU. Fall detection algorithm based on scene prior and attention guidance [J]. Journal of Computer Applications, 2023, 43(2): 529-535.
[4]	Li’an ZHU, Hong ZHANG. Nonhomogeneous image dehazing based on dual-branch conditional generative adversarial network [J]. Journal of Computer Applications, 2023, 43(2): 567-574.
[5]	Yangping LIN, Jia LIU, Pei CHEN, Mingshu ZHANG, Xiaoyuan YANG. Semi-generative video steganography scheme based on deep convolutional generative adversarial net [J]. Journal of Computer Applications, 2023, 43(1): 169-175.
[6]	Jun ZHANG, Pengli WU, Lukui SHI, Jin SHI, Bin PAN. Deep learning model for multi-station temperature prediction combined with MOD11A1 and surface meteorological station data [J]. Journal of Computer Applications, 2023, 43(1): 321-328.
[7]	Keyou GUO, Xue LI, Min YANG. Real‑time detection method of traffic information based on lightweight YOLOv4 [J]. Journal of Computer Applications, 2023, 43(1): 74-80.
[8]	Zhijun SHEN, Lina MU, Jing GAO, Yuanhang SHI, Zhiqiang LIU. Review of fine-grained image categorization [J]. Journal of Computer Applications, 2023, 43(1): 51-60.
[9]	Youxin WANG, Bin CHEN. Print defect detection method based on deep comparison network [J]. Journal of Computer Applications, 2023, 43(1): 250-258.
[10]	Jinghu LI, Qianguo XING, Xiangyang ZHENG, Lin LI, Lili WANG. Noctiluca scintillans red tide extraction method from UAV images based on deep learning [J]. Journal of Computer Applications, 2022, 42(9): 2969-2974.
[11]	Jinghan YIN, Shaojun QU, Zekai YAO, Xuanye HU, Xiaoyu QIN, Pujing HUA. Traffic sign recognition model in haze weather based on YOLOv5 [J]. Journal of Computer Applications, 2022, 42(9): 2876-2884.
[12]	Jiaxuan WEI, Shikang DU, Zhixuan YU, Ruisheng ZHANG. Review of white-box adversarial attack technologies in image classification [J]. Journal of Computer Applications, 2022, 42(9): 2732-2741.
[13]	Yajiao LIU, Haitao YU, Jiang WANG, Lifeng YU, Chunhui ZHANG. Surface detection algorithm of multi-shape small defects for section steel based on deep learning [J]. Journal of Computer Applications, 2022, 42(8): 2601-2608.
[14]	Yinglü XUAN, Yuan WAN, Jiahui CHEN. Time series classification by LSTM based on multi-scale convolution and attention mechanism [J]. Journal of Computer Applications, 2022, 42(8): 2343-2352.
[15]	Xianjie ZHANG, Zhiming ZHANG. Handwritten English text recognition based on convolutional neural network and Transformer [J]. Journal of Computer Applications, 2022, 42(8): 2394-2400.