EA-LSTM: Evolutionary attention-based LSTM for time series prediction

Time series prediction with deep learning methods, especially Long Short-term Memory Neural Network (LSTM), have scored significant achievements in recent years. Despite the fact that LSTM can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feat...

Full description

Saved in:
Bibliographic Details
Published inKnowledge-based systems Vol. 181; p. 104785
Main Authors Li, Youru, Zhu, Zhenfeng, Kong, Deqiang, Han, Hua, Zhao, Yao
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 01.10.2019
Elsevier Science Ltd
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Time series prediction with deep learning methods, especially Long Short-term Memory Neural Network (LSTM), have scored significant achievements in recent years. Despite the fact that LSTM can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within multiple time-steps is insufficient. To address this issue, an evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction. By transferring shared parameters, an evolutionary attention learning approach is introduced to LSTM. Thus, like that for biological evolution, the pattern for importance-based attention sampling can be confirmed during temporal relationship mining. To refrain from being trapped into partial optimization like traditional gradient-based methods, an evolutionary computation inspired competitive random search method is proposed, which can well configure the parameters in the attention layer. Experimental results have illustrated that the proposed model can achieve competetive prediction performance compared with other baseline methods.
AbstractList Time series prediction with deep learning methods, especially Long Short-term Memory Neural Network (LSTM), have scored significant achievements in recent years. Despite the fact that LSTM can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within multiple time-steps is insufficient. To address this issue, an evolutionary attention-based LSTM training with competitive random search is proposed for multivariate time series prediction. By transferring shared parameters, an evolutionary attention learning approach is introduced to LSTM. Thus, like that for biological evolution, the pattern for importance-based attention sampling can be confirmed during temporal relationship mining. To refrain from being trapped into partial optimization like traditional gradient-based methods, an evolutionary computation inspired competitive random search method is proposed, which can well configure the parameters in the attention layer. Experimental results have illustrated that the proposed model can achieve competetive prediction performance compared with other baseline methods.
ArticleNumber 104785
Author Han, Hua
Zhao, Yao
Li, Youru
Zhu, Zhenfeng
Kong, Deqiang
Author_xml – sequence: 1
  givenname: Youru
  surname: Li
  fullname: Li, Youru
  organization: Institute of Information Science, Beijing Jiaotong University, Beijing, 100044, China
– sequence: 2
  givenname: Zhenfeng
  surname: Zhu
  fullname: Zhu, Zhenfeng
  email: zhfzhu@bjtu.edu.cn
  organization: Institute of Information Science, Beijing Jiaotong University, Beijing, 100044, China
– sequence: 3
  givenname: Deqiang
  surname: Kong
  fullname: Kong, Deqiang
  organization: Microsoft Multimedia, Beijing, 100080, China
– sequence: 4
  givenname: Hua
  surname: Han
  fullname: Han, Hua
  organization: National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China
– sequence: 5
  givenname: Yao
  surname: Zhao
  fullname: Zhao, Yao
  organization: Institute of Information Science, Beijing Jiaotong University, Beijing, 100044, China
BookMark eNp9kM1qwzAQhEVJoUnaN-jB0LPdlWRZVg-FENIfSOmh6VnY8hrkJlYqOYG-fWXcc0_LwjezO7Mgs971SMgthYwCLe677Kt34SdkDKjKQGTAygsyp6VkqcxBzcgclIBUgqBXZBFCBwCM0XJONptVuv3YvT0km7Pbnwbr-sr_JNUwYD8uaV0FbJIRSVrnk8EeMAnoLYbk6LGxZqSuyWVb7QPe_M0l-Xza7NYv6fb9-XW92qaGlzCkCkUlq7bmtQJVy6LgUAsujKilYhUrGAeMXzHV5FyqWhSFrCPQGMoNb3jOl-Ru8j16933CMOjOnXwfT2rGFANR8lxFKp8o410IHlt99PYQY2kKeixMd3oqTI-FaRA6FhZlj5MMY4KzRa-DsdibGNKjGXTj7P8Gv4kmdjg
CitedBy_id crossref_primary_10_1080_23249935_2020_1845250
crossref_primary_10_1029_2023GL104464
crossref_primary_10_3390_info15030124
crossref_primary_10_1016_j_engfailanal_2022_106790
crossref_primary_10_1016_j_jenvman_2023_118006
crossref_primary_10_1287_ijds_2022_0015
crossref_primary_10_3390_su132111596
crossref_primary_10_1016_j_bdr_2023_100377
crossref_primary_10_1021_acsomega_1c00617
crossref_primary_10_1016_j_desal_2021_115107
crossref_primary_10_1109_ACCESS_2023_3339500
crossref_primary_10_1016_j_jag_2022_102828
crossref_primary_10_1016_j_knosys_2023_111230
crossref_primary_10_3390_agriculture12020256
crossref_primary_10_3390_ijerph192013555
crossref_primary_10_1103_PhysRevResearch_6_013182
crossref_primary_10_1016_j_asoc_2022_109714
crossref_primary_10_3390_electronics11182935
crossref_primary_10_1016_j_neunet_2022_10_009
crossref_primary_10_1016_j_inffus_2023_102180
crossref_primary_10_1016_j_measen_2024_101179
crossref_primary_10_1063_5_0137792
crossref_primary_10_3390_s22155742
crossref_primary_10_1016_j_eswa_2022_117600
crossref_primary_10_1108_IJCHM_12_2021_1474
crossref_primary_10_1109_ACCESS_2020_2995044
crossref_primary_10_3390_electronics13071254
crossref_primary_10_1007_s11356_022_18914_8
crossref_primary_10_1016_j_energy_2021_120996
crossref_primary_10_3390_atmos14050869
crossref_primary_10_4081_gh_2023_1176
crossref_primary_10_1016_j_asoc_2020_106574
crossref_primary_10_1016_j_scs_2023_104679
crossref_primary_10_1007_s10278_021_00526_2
crossref_primary_10_1002_er_6093
crossref_primary_10_1016_j_asoc_2023_110582
crossref_primary_10_3390_su12062451
crossref_primary_10_1016_j_matt_2024_04_030
crossref_primary_10_1155_2021_9940232
crossref_primary_10_1016_j_eswa_2023_120843
crossref_primary_10_1016_j_asoc_2023_110335
crossref_primary_10_1016_j_sysarc_2024_103181
crossref_primary_10_1016_j_bspc_2021_102829
crossref_primary_10_1016_j_energy_2021_121756
crossref_primary_10_1016_j_optlastec_2024_111170
crossref_primary_10_1111_coin_12554
crossref_primary_10_1142_S2196888823500033
crossref_primary_10_1016_j_rser_2022_112473
crossref_primary_10_32604_jiot_2022_036066
crossref_primary_10_1145_3447394
crossref_primary_10_1109_ACCESS_2022_3192430
crossref_primary_10_1109_JSTARS_2022_3223423
crossref_primary_10_3390_electronics12010107
crossref_primary_10_1016_j_eswa_2022_119329
crossref_primary_10_1016_j_apenergy_2021_116660
crossref_primary_10_1080_13675567_2021_1945018
crossref_primary_10_3233_JIFS_237250
crossref_primary_10_3390_en16196767
crossref_primary_10_1038_s41597_024_03483_x
crossref_primary_10_1109_ACCESS_2020_3020801
crossref_primary_10_1007_s10489_021_02824_2
crossref_primary_10_1016_j_energy_2021_120682
crossref_primary_10_1007_s11227_022_04506_3
crossref_primary_10_3390_agriculture11040359
crossref_primary_10_1109_ACCESS_2020_2995656
crossref_primary_10_3390_s21144826
crossref_primary_10_1016_j_compstruc_2022_106915
crossref_primary_10_1109_TII_2022_3229837
crossref_primary_10_1007_s00034_021_01691_z
crossref_primary_10_1016_j_est_2024_110906
crossref_primary_10_1016_j_neucom_2021_03_111
crossref_primary_10_1109_JIOT_2023_3297843
crossref_primary_10_1016_j_aei_2022_101759
crossref_primary_10_1049_itr2_12007
crossref_primary_10_1016_j_isatra_2021_08_030
crossref_primary_10_1029_2022SW003326
crossref_primary_10_1007_s12559_021_09854_5
crossref_primary_10_1016_j_energy_2022_125746
crossref_primary_10_1016_j_jhydrol_2021_126815
crossref_primary_10_1109_TNNLS_2021_3137178
crossref_primary_10_1108_DTA_07_2022_0281
crossref_primary_10_1016_j_egyr_2024_06_010
crossref_primary_10_1007_s10489_022_03833_5
crossref_primary_10_1063_5_0081858
crossref_primary_10_1016_j_chaos_2022_112183
crossref_primary_10_1016_j_najef_2021_101421
crossref_primary_10_1016_j_jpowsour_2023_233788
crossref_primary_10_1016_j_fuel_2024_131826
crossref_primary_10_1109_TII_2024_3383018
crossref_primary_10_5194_essd_14_5605_2022
crossref_primary_10_2514_1_I011269
crossref_primary_10_1002_int_22725
crossref_primary_10_1016_j_measurement_2021_110074
crossref_primary_10_7717_peerj_cs_1292
crossref_primary_10_1145_3526087
crossref_primary_10_1049_stg2_12173
crossref_primary_10_3390_electronics12143084
crossref_primary_10_1109_TEC_2023_3294540
crossref_primary_10_1016_j_eswa_2021_115715
crossref_primary_10_3390_s22114062
crossref_primary_10_1016_j_eswa_2023_119545
crossref_primary_10_1016_j_aej_2022_07_029
crossref_primary_10_1061__ASCE_ME_1943_5479_0000995
crossref_primary_10_1155_2022_6111030
crossref_primary_10_3390_ani13081322
crossref_primary_10_1631_FITEE_2300005
crossref_primary_10_1016_j_energy_2022_126179
crossref_primary_10_1007_s11760_022_02426_6
crossref_primary_10_1145_3604616
crossref_primary_10_1016_j_neucom_2022_06_014
crossref_primary_10_1155_2021_1766743
crossref_primary_10_1109_TII_2022_3163137
crossref_primary_10_1051_ro_2023029
crossref_primary_10_3390_su152115558
crossref_primary_10_1016_j_vehcom_2020_100291
crossref_primary_10_1007_s10479_022_04528_3
crossref_primary_10_1109_TII_2022_3221219
crossref_primary_10_1016_j_oceaneng_2021_109066
crossref_primary_10_3390_ijgi11050294
crossref_primary_10_1007_s11356_023_25606_4
crossref_primary_10_1016_j_engappai_2021_104354
crossref_primary_10_3390_pr11030776
crossref_primary_10_1007_s00521_021_06212_2
crossref_primary_10_1016_j_eswa_2019_113082
crossref_primary_10_1007_s11042_023_14388_z
crossref_primary_10_1016_j_wroa_2023_100207
crossref_primary_10_3390_agriculture10120612
crossref_primary_10_1088_1755_1315_1285_1_012014
crossref_primary_10_1016_j_aei_2023_101898
crossref_primary_10_3390_app11209373
crossref_primary_10_3390_en15218128
crossref_primary_10_1007_s10614_023_10432_0
crossref_primary_10_1109_ACCESS_2024_3400588
crossref_primary_10_1016_j_compeleceng_2022_108530
crossref_primary_10_1016_j_snb_2024_136085
crossref_primary_10_1016_j_inffus_2020_10_014
crossref_primary_10_1109_TCBB_2021_3131136
crossref_primary_10_1007_s10462_023_10554_9
crossref_primary_10_1016_j_engappai_2023_107072
crossref_primary_10_3390_s22218450
crossref_primary_10_1007_s00170_023_11352_x
crossref_primary_10_1007_s10489_021_02416_0
crossref_primary_10_1016_j_ecoinf_2024_102477
crossref_primary_10_3390_su12041390
crossref_primary_10_1002_int_22370
crossref_primary_10_1088_1742_6596_1550_3_032121
crossref_primary_10_1016_j_egyai_2023_100241
crossref_primary_10_3390_s23156778
crossref_primary_10_1016_j_dt_2022_05_011
crossref_primary_10_1002_we_2762
crossref_primary_10_1109_JIOT_2022_3185010
crossref_primary_10_1016_j_advwatres_2023_104569
crossref_primary_10_1016_j_cmpb_2021_106487
crossref_primary_10_1016_j_measurement_2021_109685
crossref_primary_10_1016_j_egyr_2022_08_195
crossref_primary_10_3390_electronics11040652
crossref_primary_10_1016_j_asoc_2022_109460
crossref_primary_10_1016_j_ecolmodel_2022_110250
crossref_primary_10_1080_17445302_2024_2312749
crossref_primary_10_1155_2023_8962283
crossref_primary_10_1016_j_ijhydene_2022_09_238
crossref_primary_10_1007_s10489_021_02899_x
crossref_primary_10_3390_e25091326
crossref_primary_10_3934_mbe_2023739
crossref_primary_10_1016_j_measurement_2023_113053
crossref_primary_10_3390_make3040047
crossref_primary_10_1038_s41598_023_31737_y
crossref_primary_10_3390_e26030215
crossref_primary_10_1109_TFUZZ_2024_3355000
crossref_primary_10_1007_s11063_022_11046_7
crossref_primary_10_1108_ECAM_05_2022_0450
crossref_primary_10_1109_TEVC_2021_3079985
crossref_primary_10_1007_s00521_021_05958_z
crossref_primary_10_1109_TSM_2023_3324057
crossref_primary_10_1016_j_eswa_2022_117483
crossref_primary_10_1016_j_ins_2020_08_017
crossref_primary_10_1016_j_knosys_2021_106921
crossref_primary_10_3390_w15132380
crossref_primary_10_53433_yyufbed_1335866
crossref_primary_10_1145_3603704
crossref_primary_10_7717_peerj_16192
crossref_primary_10_1016_j_egyr_2023_01_109
crossref_primary_10_1016_j_knosys_2022_109608
crossref_primary_10_1007_s12065_020_00365_0
crossref_primary_10_3390_su14042068
crossref_primary_10_1007_s00500_023_08467_4
crossref_primary_10_3389_fpsyg_2022_980778
crossref_primary_10_1155_2022_6811401
crossref_primary_10_3390_s21041171
crossref_primary_10_1016_j_jhydrol_2022_128463
crossref_primary_10_54525_tbbmd_1031017
crossref_primary_10_1007_s13131_021_1763_9
crossref_primary_10_3390_s22072683
crossref_primary_10_1016_j_enbuild_2021_111718
crossref_primary_10_1016_j_comnet_2023_109865
crossref_primary_10_3390_fractalfract5020038
crossref_primary_10_1016_j_asoc_2022_109275
crossref_primary_10_1142_S2424786322500311
crossref_primary_10_1007_s11269_022_03207_z
crossref_primary_10_1016_j_energy_2023_128701
crossref_primary_10_1016_j_asoc_2023_110412
crossref_primary_10_1016_j_eswa_2022_116944
crossref_primary_10_1155_2023_9523230
crossref_primary_10_1016_j_ymssp_2024_111599
crossref_primary_10_3390_s22239043
crossref_primary_10_1186_s12864_023_09866_5
crossref_primary_10_3390_electronics11162555
crossref_primary_10_1007_s11517_024_03120_0
crossref_primary_10_1007_s42979_022_01248_0
crossref_primary_10_1109_ACCESS_2020_2995478
crossref_primary_10_1109_ACCESS_2021_3135261
crossref_primary_10_1155_2023_3815063
crossref_primary_10_1016_j_engappai_2022_105440
crossref_primary_10_3390_data9010013
crossref_primary_10_1016_j_aei_2021_101510
crossref_primary_10_3390_w15173118
crossref_primary_10_1016_j_dcan_2022_06_019
crossref_primary_10_3389_fenrg_2021_730640
crossref_primary_10_3390_e22101134
crossref_primary_10_2166_hydro_2023_001
crossref_primary_10_1016_j_apenergy_2022_119754
Cites_doi 10.1109/ICMLA.2016.0182
10.1109/CVPR.2014.82
10.1007/978-3-642-24797-2_2
10.1137/0202009
10.24963/ijcai.2017/366
10.24963/ijcai.2018/476
10.1109/TNNLS.2016.2582924
10.1016/j.enbuild.2014.04.034
10.1162/neco.1997.9.8.1735
10.1109/ICASSP.2017.7953075
10.1609/aaai.v29i1.9559
10.1080/01621459.1970.10481180
10.1109/CVPR.2015.7298714
10.1145/3219819.3219873
10.1038/323533a0
ContentType Journal Article
Copyright 2019 Elsevier B.V.
Copyright Elsevier Science Ltd. Oct 1, 2019
Copyright_xml – notice: 2019 Elsevier B.V.
– notice: Copyright Elsevier Science Ltd. Oct 1, 2019
DBID AAYXX
CITATION
7SC
8FD
E3H
F2A
JQ2
L7M
L~C
L~D
DOI 10.1016/j.knosys.2019.05.028
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Library & Information Sciences Abstracts (LISA)
Library & Information Science Abstracts (LISA)
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Technology Research Database
Computer and Information Systems Abstracts – Academic
Library and Information Science Abstracts (LISA)
ProQuest Computer Science Collection
Computer and Information Systems Abstracts
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts Professional
DatabaseTitleList Technology Research Database

DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 1872-7409
ExternalDocumentID 10_1016_j_knosys_2019_05_028
S0950705119302400
GroupedDBID --K
--M
.DC
.~1
0R~
1B1
1~.
1~5
4.4
457
4G.
5VS
7-5
71M
77K
8P~
9JN
AACTN
AAEDT
AAEDW
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAXUO
AAYFN
ABAOU
ABBOA
ABIVO
ABJNI
ABMAC
ABYKQ
ACAZW
ACDAQ
ACGFS
ACRLP
ACZNC
ADBBV
ADEZE
ADGUI
ADTZH
AEBSH
AECPX
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJOXV
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOUOD
ARUGR
AXJTR
BJAXD
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FIRID
FNPLU
FYGXN
G-Q
GBLVA
GBOLZ
IHE
J1W
JJJVA
KOM
LG9
LY7
M41
MHUIS
MO0
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PQQKQ
Q38
RIG
ROL
RPZ
SDF
SDG
SDP
SES
SPC
SPCBC
SST
SSV
SSW
SSZ
T5K
WH7
XPP
ZMT
~02
~G-
29L
AAQXK
AAXKI
AAYXX
ABDPE
ABXDB
ACNNM
ACRPL
ADJOM
ADMUD
ADNMO
AFJKZ
AKRWK
ASPBG
AVWKF
AZFZN
CITATION
FEDTE
FGOYB
G-2
HLZ
HVGLF
HZ~
R2-
SBC
SET
SEW
UHS
WUQ
7SC
8FD
E3H
F2A
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c380t-9e5a7afb3b909b76630b535c5b792a26230e21829d4379b5667bb53dc13c3d343
IEDL.DBID AIKHN
ISSN 0950-7051
IngestDate Thu Oct 10 19:42:07 EDT 2024
Fri Dec 06 01:37:21 EST 2024
Fri Feb 23 02:18:39 EST 2024
IsDoiOpenAccess false
IsOpenAccess true
IsPeerReviewed true
IsScholarly true
Keywords Deep neural network
Time series prediction
Evolutionary computation
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c380t-9e5a7afb3b909b76630b535c5b792a26230e21829d4379b5667bb53dc13c3d343
OpenAccessLink http://arxiv.org/pdf/1811.03760
PQID 2292058349
PQPubID 2035257
ParticipantIDs proquest_journals_2292058349
crossref_primary_10_1016_j_knosys_2019_05_028
elsevier_sciencedirect_doi_10_1016_j_knosys_2019_05_028
PublicationCentury 2000
PublicationDate 2019-10-01
2019-10-00
20191001
PublicationDateYYYYMMDD 2019-10-01
PublicationDate_xml – month: 10
  year: 2019
  text: 2019-10-01
  day: 01
PublicationDecade 2010
PublicationPlace Amsterdam
PublicationPlace_xml – name: Amsterdam
PublicationTitle Knowledge-based systems
PublicationYear 2019
Publisher Elsevier B.V
Elsevier Science Ltd
Publisher_xml – name: Elsevier B.V
– name: Elsevier Science Ltd
References Kyunghyun Cho, Bart van Merrienboer, Çaglar Gülçehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, Yoshua Bengio, Learning phrase representations using RNN encoder–decoder for statistical machine translation, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014, pp. 1724–1734.
Zhou Yu, Jun Yu, Jianping Fan, Dacheng Tao, Multi-modal factorized bilinear pooling with co-attention learning for visual question answering, in: Proceedings of the 2015 IEEE International Conference on Computer Vision, 2017, pp. 1839–1848.
Pierre Hulot, Daniel Aloise, Sanjay Dominik Jena, Towards station-level demand prediction for effective rebalancing in bike-sharing systems, in: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018, pp. 378–386.
Mohammad Abdelaziz Gowayyed, Marwan Torki, Mohamed Elsayed Hussein, Motaz El-Saban, Histogram of oriented displacements (HOD): describing trajectories of human joints for action recognition, in: Proceedings of the 23rd International Joint Conference on Artificial Intelligence, 2013, pp. 1351–1357.
Xia Li, Ruibin Bai, Freight vehicle travel time prediction using gradient boosting regression tree, in: Proceedings of the 2016 IEEE International Conference on Machine Learning and Applications, 2016, pp. 1010–1015.
Raviteja Vemulapalli, Felipe Arrate, Rama Chellappa, Human action recognition by representing 3d skeletons as points in a lie group, in: Proceedings of the 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 588–595.
Udny Yule (b5) 1927; 226
Plutowski, Cottrell, White (b30) 1996; 9
Kyunghyun Cho, Bart van Merrienboer, Dzmitry Bahdanau, Yoshua Bengio, On the properties of neural machine translation: Encoder–decoder approaches, in: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014, pp. 103–111.
Harris Drucker, Christopher J.C. Burges, Linda Kaufman, Alexander J. Smola, Vladimir Vapnik, Support vector regression machines, in: Proceedings of Conference on Neural Information Processing Systems 1996, 1996, pp. 155–161.
Yao Qin, Dongjin Song, Haifeng Chen, Wei Cheng, Guofei Jiang, Garrison W. Cottrell, A dual-stage attention-based recurrent neural network for time series prediction, in: Proceedings of the twenty-sixth International Joint Conference on Artificial Intelligence, 2017, pp. 2627–2633.
Rumelhart, Hinton, Williams (b12) 1986; 323
Jiasen Lu, Caiming Xiong, Devi Parikh, Richard Socher, Knowing when to look: Adaptive attention via a visual sentinel for image captioning, in: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 3242–3250.
Hochreiter, Schmidhuber (b13) 1997; 9
Yong Du, Wei Wang, Liang Wang, Hierarchical recurrent neural network for skeleton based action recognition, in: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 1110–1118.
Luchen Liu, Jianhao Shen, Ming Zhang, Zichang Wang, Jian Tang, Learning the joint representation of heterogeneous temporal events for clinical endpoint prediction, in: Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018, pp. 109–116.
Guolin Ke, Qi Meng, Thomas Finley, Taifeng Wang, Wei Chen, Weidong Ma, Qiwei Ye, Tie-Yan Liu, Lightgbm: A highly efficient gradient boosting decision tree, in: Proceedings of Conference on Neural Information Processing Systems 2017, 2017, pp. 3149–3157.
Suyoun Kim, Takaaki Hori, Shinji Watanabe, Joint ctc-attention based end-to-end speech recognition using multi-task learning, in: Proceedings of the 2017 IEEE International Conference on Acoustics, Speech and Signal Processing, 2017, pp. 4835–4839.
Zhang, Clune, Stanley (b22) 2017
Graves (b26) 2012
Huang, Zou, Guo, Li, Zhang, Zhang, Huang, Song (b28) 2015; 471
Kristina Davoian, Wolfram-Manfred Lippe, Time series prediction with parallel evolutionary artificial neural multi-order, in: Proceedings of the 2007 IEEE International Conference on Data Mining, 2007, pp. 10–15.
Holland (b21) 1973; 2
Wei Cao, Liang Hu, Longbing Cao, Deep modeling complex couplings within financial markets, in: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015, pp. 2518–2524.
Yuxuan Liang, Songyu Ke, Junbo Zhang, Xiuwen Yi, Yu Zheng, Geoman: Multi-level attention multi-order for geo-sensory time series prediction, in: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018, pp. 3428–3434.
Kingma, Adam (b27) 2014
Zamora-Martínez, Romeu, Botella-Rocamora, Pardo (b29) 2014; 83
Box, Pierce (b6) 1968; 65
Bahdanau, Cho, Bengio (b16) 2014
Lehman, Chen, Clune, Stanley (b24) 2017
Conti, Madhavan, Petroski Such, Lehman, Stanley, Clune (b23) 2017
Greff, Srivastava, Koutník, Steunebrink, Schmidhuber (b25) 2017; 28
10.1016/j.knosys.2019.05.028_b20
Hochreiter (10.1016/j.knosys.2019.05.028_b13) 1997; 9
Box (10.1016/j.knosys.2019.05.028_b6) 1968; 65
Kingma (10.1016/j.knosys.2019.05.028_b27) 2014
10.1016/j.knosys.2019.05.028_b4
10.1016/j.knosys.2019.05.028_b3
Zamora-Martínez (10.1016/j.knosys.2019.05.028_b29) 2014; 83
10.1016/j.knosys.2019.05.028_b8
10.1016/j.knosys.2019.05.028_b7
Greff (10.1016/j.knosys.2019.05.028_b25) 2017; 28
10.1016/j.knosys.2019.05.028_b9
Huang (10.1016/j.knosys.2019.05.028_b28) 2015; 471
Plutowski (10.1016/j.knosys.2019.05.028_b30) 1996; 9
10.1016/j.knosys.2019.05.028_b2
10.1016/j.knosys.2019.05.028_b1
Graves (10.1016/j.knosys.2019.05.028_b26) 2012
10.1016/j.knosys.2019.05.028_b10
10.1016/j.knosys.2019.05.028_b32
10.1016/j.knosys.2019.05.028_b11
Lehman (10.1016/j.knosys.2019.05.028_b24) 2017
10.1016/j.knosys.2019.05.028_b31
10.1016/j.knosys.2019.05.028_b14
Bahdanau (10.1016/j.knosys.2019.05.028_b16) 2014
10.1016/j.knosys.2019.05.028_b15
Zhang (10.1016/j.knosys.2019.05.028_b22) 2017
Conti (10.1016/j.knosys.2019.05.028_b23) 2017
Rumelhart (10.1016/j.knosys.2019.05.028_b12) 1986; 323
10.1016/j.knosys.2019.05.028_b18
Holland (10.1016/j.knosys.2019.05.028_b21) 1973; 2
Udny Yule (10.1016/j.knosys.2019.05.028_b5) 1927; 226
10.1016/j.knosys.2019.05.028_b19
10.1016/j.knosys.2019.05.028_b17
References_xml – volume: 83
  start-page: 162
  year: 2014
  end-page: 172
  ident: b29
  article-title: On-line learning of indoor temperature forecasting models towards energy efficiency
  publication-title: Energy Build.
  contributor:
    fullname: Pardo
– volume: 2
  start-page: 88
  year: 1973
  end-page: 105
  ident: b21
  article-title: Genetic algorithms and the optimal allocation of trials
  publication-title: SIAM J. Comput.
  contributor:
    fullname: Holland
– volume: 226
  start-page: 267
  year: 1927
  end-page: 298
  ident: b5
  article-title: On a method of investigating periodicities in disturbed series, with special reference to Wolfer’s sunspot numbers
  publication-title: Phil. Trans. R. Soc. Lond.
  contributor:
    fullname: Udny Yule
– year: 2014
  ident: b16
  article-title: Neural machine translation by jointly learning to align and translate
  contributor:
    fullname: Bengio
– year: 2014
  ident: b27
  article-title: A method for stochastic optimization
  contributor:
    fullname: Adam
– volume: 65
  start-page: 1509
  year: 1968
  end-page: 1526
  ident: b6
  article-title: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models
  publication-title: Publ. Am. Stat. Assoc.
  contributor:
    fullname: Pierce
– year: 2017
  ident: b23
  article-title: Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents
  contributor:
    fullname: Clune
– volume: 323
  start-page: 533
  year: 1986
  end-page: 536
  ident: b12
  article-title: Learning representations by back-propagating errors
  publication-title: Nature
  contributor:
    fullname: Williams
– year: 2017
  ident: b24
  article-title: Safe mutations for deep and recurrent neural multi-order through output gradients
  contributor:
    fullname: Stanley
– volume: 9
  start-page: 273
  year: 1996
  end-page: 294
  ident: b30
  article-title: Experience with selecting exemplars from clean data
  publication-title: Neural Multi-order
  contributor:
    fullname: White
– year: 2012
  ident: b26
  article-title: Supervised sequence labelling with recurrent neural multi-order
  publication-title: Studies in Computational Intelligence, Vol. 385
  contributor:
    fullname: Graves
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: b13
  article-title: Long short-term memory
  publication-title: Neural Computation
  contributor:
    fullname: Schmidhuber
– year: 2017
  ident: b22
  article-title: On the relationship between the OpenAI evolution strategy and stochastic gradient descent
  contributor:
    fullname: Stanley
– volume: 28
  start-page: 2222
  year: 2017
  end-page: 2232
  ident: b25
  article-title: LSTM: A search space odyssey
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  contributor:
    fullname: Schmidhuber
– volume: 471
  year: 2015
  ident: b28
  article-title: Assessing Beijing’s PM2.5 pollution: severity, weather impact, APEC winter heating
  publication-title: Proc. R. Soc. A Math. Phys. Eng. Sci.
  contributor:
    fullname: Song
– ident: 10.1016/j.knosys.2019.05.028_b9
  doi: 10.1109/ICMLA.2016.0182
– ident: 10.1016/j.knosys.2019.05.028_b32
  doi: 10.1109/CVPR.2014.82
– ident: 10.1016/j.knosys.2019.05.028_b7
– ident: 10.1016/j.knosys.2019.05.028_b1
– ident: 10.1016/j.knosys.2019.05.028_b31
– year: 2012
  ident: 10.1016/j.knosys.2019.05.028_b26
  article-title: Supervised sequence labelling with recurrent neural multi-order
  doi: 10.1007/978-3-642-24797-2_2
  contributor:
    fullname: Graves
– ident: 10.1016/j.knosys.2019.05.028_b10
– ident: 10.1016/j.knosys.2019.05.028_b17
– volume: 2
  start-page: 88
  issue: 2
  year: 1973
  ident: 10.1016/j.knosys.2019.05.028_b21
  article-title: Genetic algorithms and the optimal allocation of trials
  publication-title: SIAM J. Comput.
  doi: 10.1137/0202009
  contributor:
    fullname: Holland
– ident: 10.1016/j.knosys.2019.05.028_b15
– ident: 10.1016/j.knosys.2019.05.028_b11
  doi: 10.24963/ijcai.2017/366
– ident: 10.1016/j.knosys.2019.05.028_b20
  doi: 10.24963/ijcai.2018/476
– volume: 28
  start-page: 2222
  issue: 10
  year: 2017
  ident: 10.1016/j.knosys.2019.05.028_b25
  article-title: LSTM: A search space odyssey
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2016.2582924
  contributor:
    fullname: Greff
– volume: 83
  start-page: 162
  year: 2014
  ident: 10.1016/j.knosys.2019.05.028_b29
  article-title: On-line learning of indoor temperature forecasting models towards energy efficiency
  publication-title: Energy Build.
  doi: 10.1016/j.enbuild.2014.04.034
  contributor:
    fullname: Zamora-Martínez
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 10.1016/j.knosys.2019.05.028_b13
  article-title: Long short-term memory
  publication-title: Neural Computation
  doi: 10.1162/neco.1997.9.8.1735
  contributor:
    fullname: Hochreiter
– ident: 10.1016/j.knosys.2019.05.028_b19
  doi: 10.1109/ICASSP.2017.7953075
– year: 2017
  ident: 10.1016/j.knosys.2019.05.028_b22
  contributor:
    fullname: Zhang
– ident: 10.1016/j.knosys.2019.05.028_b8
– ident: 10.1016/j.knosys.2019.05.028_b18
– year: 2014
  ident: 10.1016/j.knosys.2019.05.028_b16
  contributor:
    fullname: Bahdanau
– year: 2017
  ident: 10.1016/j.knosys.2019.05.028_b23
  contributor:
    fullname: Conti
– ident: 10.1016/j.knosys.2019.05.028_b14
– year: 2014
  ident: 10.1016/j.knosys.2019.05.028_b27
  contributor:
    fullname: Kingma
– ident: 10.1016/j.knosys.2019.05.028_b2
  doi: 10.1609/aaai.v29i1.9559
– volume: 226
  start-page: 267
  issue: 226
  year: 1927
  ident: 10.1016/j.knosys.2019.05.028_b5
  article-title: On a method of investigating periodicities in disturbed series, with special reference to Wolfer’s sunspot numbers
  publication-title: Phil. Trans. R. Soc. Lond.
  contributor:
    fullname: Udny Yule
– volume: 65
  start-page: 1509
  issue: 332
  year: 1968
  ident: 10.1016/j.knosys.2019.05.028_b6
  article-title: Distribution of residual autocorrelations in autoregressive-integrated moving average time series models
  publication-title: Publ. Am. Stat. Assoc.
  doi: 10.1080/01621459.1970.10481180
  contributor:
    fullname: Box
– year: 2017
  ident: 10.1016/j.knosys.2019.05.028_b24
  contributor:
    fullname: Lehman
– volume: 9
  start-page: 273
  issue: 2
  year: 1996
  ident: 10.1016/j.knosys.2019.05.028_b30
  article-title: Experience with selecting exemplars from clean data
  publication-title: Neural Multi-order
  contributor:
    fullname: Plutowski
– ident: 10.1016/j.knosys.2019.05.028_b4
  doi: 10.1109/CVPR.2015.7298714
– ident: 10.1016/j.knosys.2019.05.028_b3
  doi: 10.1145/3219819.3219873
– volume: 323
  start-page: 533
  issue: 6088
  year: 1986
  ident: 10.1016/j.knosys.2019.05.028_b12
  article-title: Learning representations by back-propagating errors
  publication-title: Nature
  doi: 10.1038/323533a0
  contributor:
    fullname: Rumelhart
– volume: 471
  issue: 2182
  year: 2015
  ident: 10.1016/j.knosys.2019.05.028_b28
  article-title: Assessing Beijing’s PM2.5 pollution: severity, weather impact, APEC winter heating
  publication-title: Proc. R. Soc. A Math. Phys. Eng. Sci.
  contributor:
    fullname: Huang
SSID ssj0002218
Score 2.68734
Snippet Time series prediction with deep learning methods, especially Long Short-term Memory Neural Network (LSTM), have scored significant achievements in recent...
SourceID proquest
crossref
elsevier
SourceType Aggregation Database
Publisher
StartPage 104785
SubjectTerms Deep neural network
Evolutionary computation
Machine learning
Neural networks
Optimization
Parameters
Random search method
Time series
Time series prediction
Title EA-LSTM: Evolutionary attention-based LSTM for time series prediction
URI https://dx.doi.org/10.1016/j.knosys.2019.05.028
https://www.proquest.com/docview/2292058349
Volume 181
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PT8IwFG4QLl78bUSR9OC10q0bXb0RMoM_4AIk3Jp16xI0AQJowsW_3fe2zkRjYuJx29uyfH1979v6-j1CblLwAenDCGR-FrBApJKZPFdMAneQPEq6Oce9w8NRdzANHmfhrEb61V4YLKt0sb-M6UW0dmc6Ds3Oaj7vjIEcgL_iOphAoS74bm9AOsK12kbv4Wkw-grIvl_85kN7hjdUO-iKMq_XxXKzQ91uTxUSntiW_fcM9SNWFwno_ogcOOZIe-XLHZOaXZyQw6orA3WT9JTEcY89jyfDOxq_O79K1juKOppFZSPDxJVRNKHAWCl2l6foiHZDV2tct0GrMzK9jyf9AXPNElgqIr5lyoaJTHIjjOLKSCAS3IQiTEMjlZ_4wHK4RbV2laECoQEWJw0YZKknUpGJQJyT-mK5sBeEmghl4Hkkk8wE1nCV5VYJz-YoRgjWTcIqgPSq1MTQVbHYiy4B1Qio5qEGQJtEVijqb2OrIWz_cWerAl27uQXXscFWGIlAXf77wVdkH4_KqrwWqW_Xb_Ya2MXWtMne7YfXdj70CWKEzSE
link.rule.ids 314,780,784,4502,24116,27924,27925,45585,45679
linkProvider Elsevier
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PS8MwFA5jHvTib3E6NQevcVnTLo23IR1Tt122wW6haVOYQje2Kezi3-57bYooguC1eS3ly8vL1-a97xFym4APSA9mIPVSn_kikcxkmWISuIPkYdzJONYOD0ed_tR_mgWzGnmoamEwrdLF_jKmF9HaXWk5NFvL-bw1BnIA_ornYAKFuuC7fccPgP2CU999fOV5eF7xkw-tGZpX9XNFktdrvlhvUbW7rQoBT2zK_vv-9CNSF9tP75DsO95Iu-WrHZGazY_JQdWTgbolekKiqMsG48nwnkbvzqvi1ZaiimaR18hw20opmlDgqxR7y1N0Q7umyxWe2qDVKZn2oslDn7lWCSwRId8wZYNYxpkRRnFlJNAIbgIRJIGRyos94Djcola7SlF_0ACHkwYM0qQtEpEKX5yRer7I7TmhJkQReB7KODW-NVylmVWibTOUIgTrBmEVQHpZKmLoKlXsRZeAagRU80ADoA0iKxT1t5nVELT_uLNZga7dyoJxbK8VhMJXF_9-8A3Z7U-GAz14HD1fkj0cKfPzmqS-Wb3ZK-AZG3Nd-NEnOALN-g
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=EA-LSTM%3A+Evolutionary+attention-based+LSTM+for+time+series+prediction&rft.jtitle=Knowledge-based+systems&rft.au=Li%2C+Youru&rft.au=Zhu%2C+Zhenfeng&rft.au=Kong%2C+Deqiang&rft.au=Han%2C+Hua&rft.date=2019-10-01&rft.pub=Elsevier+Science+Ltd&rft.issn=0950-7051&rft.eissn=1872-7409&rft.volume=181&rft.spage=1&rft_id=info:doi/10.1016%2Fj.knosys.2019.05.028&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon