An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data

Lane change intention prediction is an essential component for motion planning of Autonomous Vehicles (AVs). In this work, we aim to achieve this task by using Long-Short Term Memory (LSTM) network. One critical challenge on this task is that the dataset used for training such a network is usually h...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Transportation research. Part C, Emerging technologies Jg. 133; S. 103414
Hauptverfasser: Shi, Qian, Zhang, Hui
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Elsevier Ltd 01.12.2021
Schlagworte:
ISSN:0968-090X, 1879-2359
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Abstract Lane change intention prediction is an essential component for motion planning of Autonomous Vehicles (AVs). In this work, we aim to achieve this task by using Long-Short Term Memory (LSTM) network. One critical challenge on this task is that the dataset used for training such a network is usually highly imbalanced due to the fact that the size of left/right lane change data is much smaller than that of the lane keeping data. The imbalanced dateset would lead to trivial output of LSTM model. To deal with this problem, we propose a hierarchical over-sampling bagging method based on Grey Wolf Optimizer (GWO) algorithm and Synthetic Minority Over-sampling Technique (SMOTE). With the proposed method, more diverse and informative instances of minority classes can be generated for training LSTM model. Furthermore, we also propose a sampling technique to keep the temporal information and make the proposed method applicable to sequential data. Moreover, to further improve the prediction performance, we also take the interactions between neighboring vehicles into account by concatenating their trajectories when constructing features. We evaluate our method against several baseline algorithms over two benchmark datasets and the empirical results validate the effectiveness and efficiency of our method in terms of the indexes of prediction time, F1, and G-mean. •Taking the data imbalance into consideration when training the lane change intention predictor and modify the SMOTE method by GWO algorithm.•A modified oversampling method which can generate imbalanced trajectory sequence and keep the temporal information in the newly formed sequence.•Taking the influence of surrounding vehicles into consideration by mathematically integrating the features of surrounding vehicles and subject vehicle for training the prediction classifier of lane change intention.
AbstractList Lane change intention prediction is an essential component for motion planning of Autonomous Vehicles (AVs). In this work, we aim to achieve this task by using Long-Short Term Memory (LSTM) network. One critical challenge on this task is that the dataset used for training such a network is usually highly imbalanced due to the fact that the size of left/right lane change data is much smaller than that of the lane keeping data. The imbalanced dateset would lead to trivial output of LSTM model. To deal with this problem, we propose a hierarchical over-sampling bagging method based on Grey Wolf Optimizer (GWO) algorithm and Synthetic Minority Over-sampling Technique (SMOTE). With the proposed method, more diverse and informative instances of minority classes can be generated for training LSTM model. Furthermore, we also propose a sampling technique to keep the temporal information and make the proposed method applicable to sequential data. Moreover, to further improve the prediction performance, we also take the interactions between neighboring vehicles into account by concatenating their trajectories when constructing features. We evaluate our method against several baseline algorithms over two benchmark datasets and the empirical results validate the effectiveness and efficiency of our method in terms of the indexes of prediction time, F1, and G-mean. •Taking the data imbalance into consideration when training the lane change intention predictor and modify the SMOTE method by GWO algorithm.•A modified oversampling method which can generate imbalanced trajectory sequence and keep the temporal information in the newly formed sequence.•Taking the influence of surrounding vehicles into consideration by mathematically integrating the features of surrounding vehicles and subject vehicle for training the prediction classifier of lane change intention.
ArticleNumber 103414
Author Zhang, Hui
Shi, Qian
Author_xml – sequence: 1
  givenname: Qian
  surname: Shi
  fullname: Shi, Qian
  organization: School of Transportation Science and Engineering, Beihang University, Beijing 100191, China
– sequence: 2
  givenname: Hui
  orcidid: 0000-0002-2501-712X
  surname: Zhang
  fullname: Zhang, Hui
  email: huizhang285@gmail.com
  organization: School of Transportation Science and Engineering, Beihang University, Beijing 100191, China
BookMark eNp9kMtOwzAQRS1UJNrCB7DzD6TYTuKHWFUVL6mIBUViZ00cp3WUOpVjKvH3OJQVi65mRva50j0zNPG9twjdUrKghPK7dhGDWTDCaLrzghYXaEqlUBnLSzVBU6K4zIgin1doNgwtIYSqUkzRbumx2x9Cf7Q17iwE7_w2q2BI5_p984rhkB7B7HDTB9yBt9jswG8tdj5aH13v8SHY2pnfdfiqWmsijn1KrSD9NymohgjX6LKBbrA3f3OOPh4fNqvnbP329LJarjPDlIgZM0WtBGnyWkqRC16VUhAquQChSs55wQugwGmeK1FxUjLJCTNW1YYUVSVZPkf0lGtCPwzBNvoQ3B7Ct6ZEj6p0q5MqParSJ1WJEf8Y4yKMhWIA150l70-kTZWOzgY9GGfH0i4kD7ru3Rn6B4X7hTo
CitedBy_id crossref_primary_10_1080_19439962_2023_2201181
crossref_primary_10_1080_21680566_2024_2326018
crossref_primary_10_1016_j_advengsoft_2022_103283
crossref_primary_10_1109_TIV_2024_3360417
crossref_primary_10_1080_15325008_2024_2329326
crossref_primary_10_1109_TITS_2025_3542517
crossref_primary_10_3390_infrastructures8110156
crossref_primary_10_1080_19439962_2024_2372292
crossref_primary_10_1109_TITS_2022_3207182
crossref_primary_10_3390_su16041639
crossref_primary_10_1016_j_mechatronics_2024_103143
crossref_primary_10_1016_j_tre_2024_103748
crossref_primary_10_1371_journal_pone_0320578
crossref_primary_10_1016_j_trc_2022_103874
crossref_primary_10_1109_TITS_2025_3552417
crossref_primary_10_1049_cit2_12313
crossref_primary_10_1016_j_measurement_2025_116670
crossref_primary_10_1016_j_engappai_2024_108171
crossref_primary_10_1109_TITS_2023_3248842
crossref_primary_10_1109_TITS_2023_3330941
crossref_primary_10_1016_j_tbs_2023_100595
crossref_primary_10_1177_03611981251335883
crossref_primary_10_1109_TKDE_2023_3348550
crossref_primary_10_3390_info14050257
crossref_primary_10_1109_TITS_2023_3320583
crossref_primary_10_3390_electronics13091625
crossref_primary_10_1109_TVT_2024_3441759
crossref_primary_10_1016_j_commtr_2025_100164
crossref_primary_10_1109_TITS_2023_3344647
crossref_primary_10_1016_j_multra_2025_100222
crossref_primary_10_1109_ACCESS_2023_3327815
crossref_primary_10_1016_j_physa_2022_128290
crossref_primary_10_1177_16878132221108491
crossref_primary_10_3390_systems11040196
Cites_doi 10.1016/j.ins.2019.07.070
10.1613/jair.953
10.1109/IVS.2011.5940538
10.1109/TITS.2013.2285337
10.1162/neco.1997.9.8.1735
10.1109/TVT.2021.3064680
10.1109/IVS.2013.6629564
10.1109/TKDE.2016.2609424
10.1109/IVS.2017.7995919
10.1109/TIE.2020.2994868
10.1002/rob.20135
10.1109/ITSC45102.2020.9294326
10.1006/jcss.1997.1504
10.1109/34.3899
10.1016/j.trc.2020.102615
10.1016/S0893-6080(99)00073-8
10.1016/j.advengsoft.2013.12.007
10.1109/ICRA.2019.8794146
10.1177/154193120504902217
10.1109/TIV.2017.2708600
10.1142/S0218001401000836
10.1109/ITSC.2017.8317874
10.1177/0361198120922210
10.1016/j.bspc.2020.102194
10.1109/TSMCB.2008.2002909
10.1109/ACCESS.2020.2982170
10.1109/TVT.2020.2996954
10.1016/j.apergo.2015.03.017
10.1109/TKDE.2008.239
10.1016/j.patcog.2007.04.009
10.1109/TNNLS.2019.2920246
10.1023/A:1018054314350
10.1109/TASE.2015.2498192
10.1162/089976699300016890
10.1109/CIDM.2009.4938667
10.1016/j.neucom.2018.04.088
10.1016/j.eswa.2007.01.009
10.1109/TIT.1967.1053964
10.1109/TCST.2007.894653
10.3390/s18041096
10.1109/TITS.2019.2932802
10.3141/2645-18
ContentType Journal Article
Copyright 2021 Elsevier Ltd
Copyright_xml – notice: 2021 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.trc.2021.103414
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Economics
Engineering
EISSN 1879-2359
ExternalDocumentID 10_1016_j_trc_2021_103414
S0968090X21004083
GrantInformation_xml – fundername: National Natural Science Foundation of China
  grantid: U1864201
  funderid: http://dx.doi.org/10.13039/501100001809
GroupedDBID --K
--M
-~X
.DC
.~1
0R~
123
1B1
1RT
1~.
1~5
29Q
4.4
457
4G.
5VS
7-5
71M
8P~
9JN
9JO
AAAKF
AAAKG
AACTN
AAEDT
AAEDW
AAFJI
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AARIN
AAXUO
AAYFN
ABBOA
ABLJU
ABMAC
ABMMH
ABUCO
ABXDB
ABYKQ
ACDAQ
ACGFS
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
ADTZH
AEBSH
AECPX
AEKER
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHJVU
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
AKYCK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOMHK
AOUOD
APLSM
ASPBG
AVARZ
AVWKF
AXJTR
AZFZN
BJAXD
BKOJK
BLXMC
CS3
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HAMUX
HMY
HVGLF
HZ~
H~9
IHE
J1W
JJJVA
KOM
LY1
LY7
M3Y
M41
MO0
MS~
N9A
O-L
O9-
OAUVE
OZT
P-8
P-9
P2P
PC.
PRBVW
Q38
R2-
RIG
ROL
RPZ
SDF
SDG
SDS
SES
SET
SEW
SPC
SPCBC
SSB
SSD
SSO
SSS
SST
SSV
SSZ
T5K
TN5
WUQ
XPP
~G-
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ADNMO
AEIPS
AFJKZ
AGQPQ
AIIUN
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c297t-2c4d970f3d887376b58701867a795666464a1a613397b60528602ce9dc04bb823
ISICitedReferencesCount 42
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000771458500004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0968-090X
IngestDate Sat Nov 29 07:09:43 EST 2025
Tue Nov 18 22:35:44 EST 2025
Fri Feb 23 02:43:40 EST 2024
IsPeerReviewed true
IsScholarly true
Keywords Autonomous Vehicles
Ensemble learning
Lane change intention prediction
Long Short Term Memory (LSTM) network
Over-sampling method
Data imbalance
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-2c4d970f3d887376b58701867a795666464a1a613397b60528602ce9dc04bb823
ORCID 0000-0002-2501-712X
ParticipantIDs crossref_primary_10_1016_j_trc_2021_103414
crossref_citationtrail_10_1016_j_trc_2021_103414
elsevier_sciencedirect_doi_10_1016_j_trc_2021_103414
PublicationCentury 2000
PublicationDate December 2021
2021-12-00
PublicationDateYYYYMMDD 2021-12-01
PublicationDate_xml – month: 12
  year: 2021
  text: December 2021
PublicationDecade 2020
PublicationTitle Transportation research. Part C, Emerging technologies
PublicationYear 2021
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References Hou, Jin, Niu, Sun, Lu (b18) 2011
Ju, Zhang, Tan (b19) 2021
Morris, B., Doshi, A., Trivedi, M., 2011. Lane change intent prediction for driver assistance: On-road design and evaluation. In: 2011 IEEE Intelligent Vehicles Symposium, IV. pp. 895–901.
Mandalia, Salvucci (b27) 2005; 49
Luo, Nguyen, Fleming, Zhang (b25) 2021; 70
Wu, Guo, Lin, Yu, Ji (b43) 2018; 18
Pentland, Liu (b32) 1999; 11
Bakhit, Osman, Ishak (b1) 2017
Sun, Kamel, Wong, Wang (b35) 2007; 40
Mahajan, Katrakazas, Antoniou (b26) 2020; 2674
Talebpour, Mahmassani, Mete, Hamdar (b36) 2018
Falcone, Borrelli, Asgari, Tseng, Hrovat (b11) 2007; 15
Benterki, Boukhnifer, Judalet, Maaoui (b2) 2020; 8
Hou, Edara, Sun (b17) 2014; 15
Tang, Zhang, Chawla, Krasser (b37) 2009; 39
Turk, Morgenthaler, Gremban, Marra (b38) 1988; 10
Wang, Huang, Khajepour, Cao, Lv (b39) 2020; 69
Mirjalili, Mirjalili, Lewis (b28) 2014; 69
Chawla, Bowyer, Hall, Kegelmeyer (b5) 2002; 16
De Morais, Vasconcelos (b8) 2019; 343
Yang, Yu, Wen, Cao, Chen, Wong, You (b45) 2020; 31
Peng, Guo, Fu, Yuan, Wang (b31) 2015; 50
Graves (b14) 2012
Haibo, Edwardo (b15) 2009; 21
Zyner, A., Worrall, S., Ward, J., Nebot, E., 2017. Long short term memory for driver intent prediction. In: 2017 IEEE Intelligent Vehicles Symposium, IV. pp. 1484–1489.
Breiman (b4) 1996; 24
Yu, Wang, Lai (b46) 2008; 34
Hochreiter, Schmidhuber (b16) 1997; 9
Ojala, Vepsäläinen, Hanhirova, Hirvisalo, Tammi (b30) 2020; 21
Petmezas, Haris, Stefanopoulos, Kilintzis, Maglaveras (b33) 2021; 63
Liu, Yao (b24) 1999; 12
Xing, Lv, Cao (b44) 2020; 115
Freund, Schapire (b13) 1995; 55
Cover, Hart (b6) 1953; 13
Wozniak, Krawczyk, Schaefer (b42) 2013; 14
Zheng, Hansen (b47) 2017; 2
Bhahramani (b3) 2001; 15
Fernández-Llorca, D., Biparva, M., Izquierdo-Gonzalo, R., Tsotsos, J.K., 2020. Two-stream networks for lane-change prediction of surrounding vehicles. In: 2020 International Conference on Intelligent Transportation Systems, ITSC. pp. 1–6.
Elreedy, Atiya (b10) 2019; 505
Cremean, Foote, Gillula, Hines, Kogan, Kriechbaum, Lamb, Leibs, Lindzey, Rasmussen (b7) 2006; 23
Wang, S., Yao, X., 2009. Diversity analysis on imbalanced data sets by using ensemble models. In: IEEE Symposium on Computational Intelligence & Data Mining. pp. 1–8.
Kingma, D.P., Ba, J.L., 2015. Adam: A method for stochastic optimization. In: 2015 International Conference on Learning Representations, ICLR. pp. 1–15.
Kumar, P., Perrollaz, M., Lefèvre, S., Laugier, C., 2013. Learning-based approach for online lane change intention prediction. In: Intelligent Vehicles Symposium. pp. 797–802.
Wang, Pineau (b40) 2016; 28
Shi, Zhang (b34) 2020; 68
Lee, D., Kwon, Y.P., McMains, S., Hedrick, J.K., 2017. Convolution neural network-based lane change intention prediction of surrounding vehicles for ACC. In: 2017 International Conference on Intelligent Transportation Systems, ITSC. pp. 1–6.
Ding, W., Chen, J., Shen, S., 2019. Predicting vehicle behaviors over an extended horizon using behavior interaction network. In: 2019 International Conference on Robotics and Automation, ICRA. pp. 8634–8640.
Lefevre, Carvalho, Borrelli (b23) 2016; 13
Talebpour (10.1016/j.trc.2021.103414_b36) 2018
Tang (10.1016/j.trc.2021.103414_b37) 2009; 39
Turk (10.1016/j.trc.2021.103414_b38) 1988; 10
Wang (10.1016/j.trc.2021.103414_b39) 2020; 69
Bhahramani (10.1016/j.trc.2021.103414_b3) 2001; 15
10.1016/j.trc.2021.103414_b12
Bakhit (10.1016/j.trc.2021.103414_b1) 2017
10.1016/j.trc.2021.103414_b9
De Morais (10.1016/j.trc.2021.103414_b8) 2019; 343
Lefevre (10.1016/j.trc.2021.103414_b23) 2016; 13
Cremean (10.1016/j.trc.2021.103414_b7) 2006; 23
Yu (10.1016/j.trc.2021.103414_b46) 2008; 34
Benterki (10.1016/j.trc.2021.103414_b2) 2020; 8
Wang (10.1016/j.trc.2021.103414_b40) 2016; 28
Breiman (10.1016/j.trc.2021.103414_b4) 1996; 24
Chawla (10.1016/j.trc.2021.103414_b5) 2002; 16
Petmezas (10.1016/j.trc.2021.103414_b33) 2021; 63
Wozniak (10.1016/j.trc.2021.103414_b42) 2013; 14
Peng (10.1016/j.trc.2021.103414_b31) 2015; 50
Shi (10.1016/j.trc.2021.103414_b34) 2020; 68
Xing (10.1016/j.trc.2021.103414_b44) 2020; 115
Falcone (10.1016/j.trc.2021.103414_b11) 2007; 15
Hochreiter (10.1016/j.trc.2021.103414_b16) 1997; 9
Yang (10.1016/j.trc.2021.103414_b45) 2020; 31
Ju (10.1016/j.trc.2021.103414_b19) 2021
10.1016/j.trc.2021.103414_b41
Cover (10.1016/j.trc.2021.103414_b6) 1953; 13
Hou (10.1016/j.trc.2021.103414_b18) 2011
10.1016/j.trc.2021.103414_b22
Mirjalili (10.1016/j.trc.2021.103414_b28) 2014; 69
Pentland (10.1016/j.trc.2021.103414_b32) 1999; 11
10.1016/j.trc.2021.103414_b21
10.1016/j.trc.2021.103414_b20
Liu (10.1016/j.trc.2021.103414_b24) 1999; 12
Mandalia (10.1016/j.trc.2021.103414_b27) 2005; 49
Wu (10.1016/j.trc.2021.103414_b43) 2018; 18
Graves (10.1016/j.trc.2021.103414_b14) 2012
Haibo (10.1016/j.trc.2021.103414_b15) 2009; 21
Zheng (10.1016/j.trc.2021.103414_b47) 2017; 2
Elreedy (10.1016/j.trc.2021.103414_b10) 2019; 505
Luo (10.1016/j.trc.2021.103414_b25) 2021; 70
Mahajan (10.1016/j.trc.2021.103414_b26) 2020; 2674
Sun (10.1016/j.trc.2021.103414_b35) 2007; 40
Hou (10.1016/j.trc.2021.103414_b17) 2014; 15
Ojala (10.1016/j.trc.2021.103414_b30) 2020; 21
10.1016/j.trc.2021.103414_b48
Freund (10.1016/j.trc.2021.103414_b13) 1995; 55
10.1016/j.trc.2021.103414_b29
References_xml – reference: Morris, B., Doshi, A., Trivedi, M., 2011. Lane change intent prediction for driver assistance: On-road design and evaluation. In: 2011 IEEE Intelligent Vehicles Symposium, IV. pp. 895–901.
– volume: 70
  start-page: 2930
  year: 2021
  end-page: 2944
  ident: b25
  article-title: Unknown input observer based approach for distributed tube-based model predictive control of heterogeneous vehicle platoons
  publication-title: IEEE Trans. Veh. Technol.
– volume: 34
  start-page: 1434
  year: 2008
  end-page: 1444
  ident: b46
  article-title: Credit risk assessment with a multistage neural network ensemble learning approach
  publication-title: Expert Syst. Appl.
– volume: 40
  start-page: 3358
  year: 2007
  end-page: 3378
  ident: b35
  article-title: Cost-sensitive boosting for classification of imbalanced data
  publication-title: Pattern Recognit.
– volume: 10
  start-page: 342
  year: 1988
  end-page: 361
  ident: b38
  article-title: VITS-a vision system for autonomous land vehicle navigation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
– volume: 31
  start-page: 1387
  year: 2020
  end-page: 1400
  ident: b45
  article-title: Hybrid classifier ensemble for imbalanced data
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
– volume: 39
  start-page: 281
  year: 2009
  end-page: 288
  ident: b37
  article-title: SVMs modeling for highly imbalanced classification
  publication-title: IEEE Trans. Syst. Man Cybern. B
– start-page: 168
  year: 2017
  end-page: 175
  ident: b1
  article-title: Detecting imminent lane change maneuvers in connected vehicle environments
  publication-title: Transp. Res. Rec. J. Transp. Res. Board
– volume: 12
  start-page: 1399
  year: 1999
  end-page: 1404
  ident: b24
  article-title: Ensemble learning via negative correlation
  publication-title: Neural Netw.
– volume: 18
  start-page: 1096
  year: 2018
  end-page: 1110
  ident: b43
  article-title: A weighted deep representation learning model for imbalanced fault diagnosis in cyber-physical systems
  publication-title: Sensors
– volume: 115
  start-page: 1
  year: 2020
  end-page: 19
  ident: b44
  article-title: An ensemble deep learning approach for driver lane change intention inference
  publication-title: Transp. Res. C
– volume: 343
  start-page: 3
  year: 2019
  end-page: 18
  ident: b8
  article-title: Boosting the performance of over-sampling algorithms through under-sampling the minority class
  publication-title: Neurocomputing
– volume: 505
  start-page: 32
  year: 2019
  end-page: 64
  ident: b10
  article-title: A comprehensive analysis of synthetic minority oversampling technique (SMOTE) for handling class imbalance
  publication-title: Inform. Sci.
– reference: Lee, D., Kwon, Y.P., McMains, S., Hedrick, J.K., 2017. Convolution neural network-based lane change intention prediction of surrounding vehicles for ACC. In: 2017 International Conference on Intelligent Transportation Systems, ITSC. pp. 1–6.
– volume: 50
  start-page: 207
  year: 2015
  end-page: 217
  ident: b31
  article-title: Multi-parameter prediction of drivers’ lane-changing behaviour with neural network model
  publication-title: Applied Ergon.
– volume: 15
  start-page: 566
  year: 2007
  end-page: 580
  ident: b11
  article-title: Predictive active steering control for autonomous vehicle systems
  publication-title: IEEE Trans. Control Syst. Technol.
– volume: 23
  start-page: 777
  year: 2006
  end-page: 810
  ident: b7
  article-title: Alice: An information-rich autonomous vehicle for high-speed desert navigation
  publication-title: J. Field Robotics
– year: 2012
  ident: b14
  article-title: Long Short-Term Memory
– reference: Fernández-Llorca, D., Biparva, M., Izquierdo-Gonzalo, R., Tsotsos, J.K., 2020. Two-stream networks for lane-change prediction of surrounding vehicles. In: 2020 International Conference on Intelligent Transportation Systems, ITSC. pp. 1–6.
– volume: 16
  start-page: 321
  year: 2002
  end-page: 357
  ident: b5
  article-title: SMOTE: Synthetic minority over-sampling technique
  publication-title: J. Artificial Intelligence Res.
– volume: 55
  start-page: 119
  year: 1995
  end-page: 139
  ident: b13
  article-title: A decision-thoretic generalization of on-line learning and an application to boosting
  publication-title: J. Comput. Syst. Sci.
– volume: 69
  start-page: 8164
  year: 2020
  end-page: 8175
  ident: b39
  article-title: Ethical decision-making platform in autonomous vehicles with lexicographic optimization based model predictive controller
  publication-title: IEEE Trans. Veh. Technol.
– volume: 15
  start-page: 647
  year: 2014
  end-page: 655
  ident: b17
  article-title: Modeling mandatory lane changing using Bayes classifier and decision trees
  publication-title: IEEE Trans. Intell. Transp. Syst.
– year: 2021
  ident: b19
  article-title: Distributed stochastic model predictive control for heterogeneous vehicle platoons subject to modeling uncertainties
  publication-title: IEEE Intell. Transp. Syst. Mag.
– volume: 2674
  start-page: 336
  year: 2020
  end-page: 347
  ident: b26
  article-title: Prediction of lane-changing maneuvers with automatic labeling and deep learning
  publication-title: Transp. Res. Rec. J. Transp. Res. Board
– reference: Ding, W., Chen, J., Shen, S., 2019. Predicting vehicle behaviors over an extended horizon using behavior interaction network. In: 2019 International Conference on Robotics and Automation, ICRA. pp. 8634–8640.
– volume: 68
  start-page: 6248
  year: 2020
  end-page: 6256
  ident: b34
  article-title: Fault diagnosis of an autonomous vehicle with an improved SVM algorithm subject to unbalanced datasets
  publication-title: IEEE Trans. Ind. Electron.
– reference: Wang, S., Yao, X., 2009. Diversity analysis on imbalanced data sets by using ensemble models. In: IEEE Symposium on Computational Intelligence & Data Mining. pp. 1–8.
– volume: 13
  start-page: 21
  year: 1953
  end-page: 27
  ident: b6
  article-title: Nearest neighbor pattern classification
  publication-title: IEEE Trans. Inform. Theory
– volume: 13
  start-page: 32
  year: 2016
  end-page: 42
  ident: b23
  article-title: A learning-based framework for velocity control in autonomous driving
  publication-title: IEEE Trans. Autom. Sci. Eng.
– volume: 14
  start-page: 554
  year: 2013
  end-page: 562
  ident: b42
  article-title: Cost-sensitive decision tree ensembles for effective imbalanced classification
  publication-title: Appl. Soft Comput.
– volume: 21
  start-page: 1263
  year: 2009
  end-page: 1284
  ident: b15
  article-title: Learning from imbalanced data
  publication-title: IEEE Trans. Knowl. Data Eng.
– volume: 2
  start-page: 14
  year: 2017
  end-page: 24
  ident: b47
  article-title: Lane-change detection from steering signal using spectral segmentation and learning-based classification
  publication-title: IEEE Trans. Intell. Veh.
– start-page: 386
  year: 2011
  end-page: 393
  ident: b18
  article-title: Driver intention recognition method using continuous hidden Markov model
  publication-title: Int. J. Comput. Intell. Syst.
– reference: Kingma, D.P., Ba, J.L., 2015. Adam: A method for stochastic optimization. In: 2015 International Conference on Learning Representations, ICLR. pp. 1–15.
– volume: 11
  start-page: 229
  year: 1999
  end-page: 242
  ident: b32
  article-title: Modeling and prediction of human behavior
  publication-title: Neural Comput.
– volume: 15
  start-page: 9
  year: 2001
  end-page: 42
  ident: b3
  article-title: An introduction to hidden Markov models and Bayesian networks
  publication-title: Int. J. Pattern Recognit. Artif. Intell.
– volume: 69
  start-page: 46
  year: 2014
  end-page: 61
  ident: b28
  article-title: Grey wolf optimizer
  publication-title: Adv. Eng. Softw.
– volume: 28
  start-page: 3353
  year: 2016
  end-page: 3366
  ident: b40
  article-title: Online bagging and boosting for imbalanced data streams
  publication-title: IEEE Trans. Knowl. Data Eng.
– reference: Kumar, P., Perrollaz, M., Lefèvre, S., Laugier, C., 2013. Learning-based approach for online lane change intention prediction. In: Intelligent Vehicles Symposium. pp. 797–802.
– volume: 9
  start-page: 1735
  year: 1997
  end-page: 1780
  ident: b16
  article-title: Long short-term memory
  publication-title: Neural Comput.
– volume: 24
  start-page: 123
  year: 1996
  end-page: 140
  ident: b4
  article-title: Bagging predictors
  publication-title: Mach. Learn.
– volume: 63
  start-page: 1
  year: 2021
  end-page: 9
  ident: b33
  article-title: Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets
  publication-title: Biomed. Signal Process. Control
– start-page: 20
  year: 2018
  end-page: 28
  ident: b36
  article-title: Near-crash identification in a connected vehicle environment
  publication-title: Transp. Res. Rec. J. Transp. Res. Board
– reference: Zyner, A., Worrall, S., Ward, J., Nebot, E., 2017. Long short term memory for driver intent prediction. In: 2017 IEEE Intelligent Vehicles Symposium, IV. pp. 1484–1489.
– volume: 8
  start-page: 56992
  year: 2020
  end-page: 57002
  ident: b2
  article-title: Artificial intelligence for vehicle behavior anticipation: Hybrid approach based on maneuver classification and trajectory prediction
  publication-title: IEEE Access
– volume: 21
  start-page: 3756
  year: 2020
  end-page: 3765
  ident: b30
  article-title: Novel convolutional neural network-based roadside unit for accurate pedestrian localisation
  publication-title: IEEE Trans. Intell. Transp. Syst.
– volume: 49
  start-page: 1965
  year: 2005
  end-page: 1969
  ident: b27
  article-title: Using Support Vector Machines for Lane-change detection
  publication-title: Proc. Hum. Factors Ergon. Soc. Annu. Meet.
– volume: 505
  start-page: 32
  year: 2019
  ident: 10.1016/j.trc.2021.103414_b10
  article-title: A comprehensive analysis of synthetic minority oversampling technique (SMOTE) for handling class imbalance
  publication-title: Inform. Sci.
  doi: 10.1016/j.ins.2019.07.070
– year: 2021
  ident: 10.1016/j.trc.2021.103414_b19
  article-title: Distributed stochastic model predictive control for heterogeneous vehicle platoons subject to modeling uncertainties
  publication-title: IEEE Intell. Transp. Syst. Mag.
– volume: 16
  start-page: 321
  issue: 1
  year: 2002
  ident: 10.1016/j.trc.2021.103414_b5
  article-title: SMOTE: Synthetic minority over-sampling technique
  publication-title: J. Artificial Intelligence Res.
  doi: 10.1613/jair.953
– ident: 10.1016/j.trc.2021.103414_b29
  doi: 10.1109/IVS.2011.5940538
– volume: 15
  start-page: 647
  issue: 2
  year: 2014
  ident: 10.1016/j.trc.2021.103414_b17
  article-title: Modeling mandatory lane changing using Bayes classifier and decision trees
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2013.2285337
– start-page: 386
  year: 2011
  ident: 10.1016/j.trc.2021.103414_b18
  article-title: Driver intention recognition method using continuous hidden Markov model
  publication-title: Int. J. Comput. Intell. Syst.
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  ident: 10.1016/j.trc.2021.103414_b16
  article-title: Long short-term memory
  publication-title: Neural Comput.
  doi: 10.1162/neco.1997.9.8.1735
– volume: 70
  start-page: 2930
  issue: 4
  year: 2021
  ident: 10.1016/j.trc.2021.103414_b25
  article-title: Unknown input observer based approach for distributed tube-based model predictive control of heterogeneous vehicle platoons
  publication-title: IEEE Trans. Veh. Technol.
  doi: 10.1109/TVT.2021.3064680
– ident: 10.1016/j.trc.2021.103414_b21
  doi: 10.1109/IVS.2013.6629564
– volume: 28
  start-page: 3353
  issue: 12
  year: 2016
  ident: 10.1016/j.trc.2021.103414_b40
  article-title: Online bagging and boosting for imbalanced data streams
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2016.2609424
– ident: 10.1016/j.trc.2021.103414_b48
  doi: 10.1109/IVS.2017.7995919
– volume: 68
  start-page: 6248
  issue: 7
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b34
  article-title: Fault diagnosis of an autonomous vehicle with an improved SVM algorithm subject to unbalanced datasets
  publication-title: IEEE Trans. Ind. Electron.
  doi: 10.1109/TIE.2020.2994868
– volume: 23
  start-page: 777
  issue: 9
  year: 2006
  ident: 10.1016/j.trc.2021.103414_b7
  article-title: Alice: An information-rich autonomous vehicle for high-speed desert navigation
  publication-title: J. Field Robotics
  doi: 10.1002/rob.20135
– ident: 10.1016/j.trc.2021.103414_b12
  doi: 10.1109/ITSC45102.2020.9294326
– volume: 55
  start-page: 119
  issue: 1
  year: 1995
  ident: 10.1016/j.trc.2021.103414_b13
  article-title: A decision-thoretic generalization of on-line learning and an application to boosting
  publication-title: J. Comput. Syst. Sci.
  doi: 10.1006/jcss.1997.1504
– volume: 14
  start-page: 554
  issue: 1
  year: 2013
  ident: 10.1016/j.trc.2021.103414_b42
  article-title: Cost-sensitive decision tree ensembles for effective imbalanced classification
  publication-title: Appl. Soft Comput.
– year: 2012
  ident: 10.1016/j.trc.2021.103414_b14
– ident: 10.1016/j.trc.2021.103414_b20
– volume: 10
  start-page: 342
  issue: 3
  year: 1988
  ident: 10.1016/j.trc.2021.103414_b38
  article-title: VITS-a vision system for autonomous land vehicle navigation
  publication-title: IEEE Trans. Pattern Anal. Mach. Intell.
  doi: 10.1109/34.3899
– volume: 115
  start-page: 1
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b44
  article-title: An ensemble deep learning approach for driver lane change intention inference
  publication-title: Transp. Res. C
  doi: 10.1016/j.trc.2020.102615
– volume: 12
  start-page: 1399
  issue: 10
  year: 1999
  ident: 10.1016/j.trc.2021.103414_b24
  article-title: Ensemble learning via negative correlation
  publication-title: Neural Netw.
  doi: 10.1016/S0893-6080(99)00073-8
– volume: 69
  start-page: 46
  year: 2014
  ident: 10.1016/j.trc.2021.103414_b28
  article-title: Grey wolf optimizer
  publication-title: Adv. Eng. Softw.
  doi: 10.1016/j.advengsoft.2013.12.007
– ident: 10.1016/j.trc.2021.103414_b9
  doi: 10.1109/ICRA.2019.8794146
– volume: 49
  start-page: 1965
  issue: 22
  year: 2005
  ident: 10.1016/j.trc.2021.103414_b27
  article-title: Using Support Vector Machines for Lane-change detection
  publication-title: Proc. Hum. Factors Ergon. Soc. Annu. Meet.
  doi: 10.1177/154193120504902217
– start-page: 20
  issue: 2424
  year: 2018
  ident: 10.1016/j.trc.2021.103414_b36
  article-title: Near-crash identification in a connected vehicle environment
  publication-title: Transp. Res. Rec. J. Transp. Res. Board
– volume: 2
  start-page: 14
  issue: 1
  year: 2017
  ident: 10.1016/j.trc.2021.103414_b47
  article-title: Lane-change detection from steering signal using spectral segmentation and learning-based classification
  publication-title: IEEE Trans. Intell. Veh.
  doi: 10.1109/TIV.2017.2708600
– volume: 15
  start-page: 9
  issue: 1
  year: 2001
  ident: 10.1016/j.trc.2021.103414_b3
  article-title: An introduction to hidden Markov models and Bayesian networks
  publication-title: Int. J. Pattern Recognit. Artif. Intell.
  doi: 10.1142/S0218001401000836
– ident: 10.1016/j.trc.2021.103414_b22
  doi: 10.1109/ITSC.2017.8317874
– volume: 2674
  start-page: 336
  issue: 7
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b26
  article-title: Prediction of lane-changing maneuvers with automatic labeling and deep learning
  publication-title: Transp. Res. Rec. J. Transp. Res. Board
  doi: 10.1177/0361198120922210
– volume: 63
  start-page: 1
  year: 2021
  ident: 10.1016/j.trc.2021.103414_b33
  article-title: Automated atrial fibrillation detection using a hybrid CNN-LSTM network on imbalanced ECG datasets
  publication-title: Biomed. Signal Process. Control
  doi: 10.1016/j.bspc.2020.102194
– volume: 39
  start-page: 281
  issue: 1
  year: 2009
  ident: 10.1016/j.trc.2021.103414_b37
  article-title: SVMs modeling for highly imbalanced classification
  publication-title: IEEE Trans. Syst. Man Cybern. B
  doi: 10.1109/TSMCB.2008.2002909
– volume: 8
  start-page: 56992
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b2
  article-title: Artificial intelligence for vehicle behavior anticipation: Hybrid approach based on maneuver classification and trajectory prediction
  publication-title: IEEE Access
  doi: 10.1109/ACCESS.2020.2982170
– volume: 69
  start-page: 8164
  issue: 8
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b39
  article-title: Ethical decision-making platform in autonomous vehicles with lexicographic optimization based model predictive controller
  publication-title: IEEE Trans. Veh. Technol.
  doi: 10.1109/TVT.2020.2996954
– volume: 50
  start-page: 207
  year: 2015
  ident: 10.1016/j.trc.2021.103414_b31
  article-title: Multi-parameter prediction of drivers’ lane-changing behaviour with neural network model
  publication-title: Applied Ergon.
  doi: 10.1016/j.apergo.2015.03.017
– volume: 21
  start-page: 1263
  issue: 9
  year: 2009
  ident: 10.1016/j.trc.2021.103414_b15
  article-title: Learning from imbalanced data
  publication-title: IEEE Trans. Knowl. Data Eng.
  doi: 10.1109/TKDE.2008.239
– volume: 40
  start-page: 3358
  issue: 12
  year: 2007
  ident: 10.1016/j.trc.2021.103414_b35
  article-title: Cost-sensitive boosting for classification of imbalanced data
  publication-title: Pattern Recognit.
  doi: 10.1016/j.patcog.2007.04.009
– volume: 31
  start-page: 1387
  issue: 4
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b45
  article-title: Hybrid classifier ensemble for imbalanced data
  publication-title: IEEE Trans. Neural Netw. Learn. Syst.
  doi: 10.1109/TNNLS.2019.2920246
– volume: 24
  start-page: 123
  issue: 2
  year: 1996
  ident: 10.1016/j.trc.2021.103414_b4
  article-title: Bagging predictors
  publication-title: Mach. Learn.
  doi: 10.1023/A:1018054314350
– volume: 13
  start-page: 32
  issue: 1
  year: 2016
  ident: 10.1016/j.trc.2021.103414_b23
  article-title: A learning-based framework for velocity control in autonomous driving
  publication-title: IEEE Trans. Autom. Sci. Eng.
  doi: 10.1109/TASE.2015.2498192
– volume: 11
  start-page: 229
  year: 1999
  ident: 10.1016/j.trc.2021.103414_b32
  article-title: Modeling and prediction of human behavior
  publication-title: Neural Comput.
  doi: 10.1162/089976699300016890
– ident: 10.1016/j.trc.2021.103414_b41
  doi: 10.1109/CIDM.2009.4938667
– volume: 343
  start-page: 3
  year: 2019
  ident: 10.1016/j.trc.2021.103414_b8
  article-title: Boosting the performance of over-sampling algorithms through under-sampling the minority class
  publication-title: Neurocomputing
  doi: 10.1016/j.neucom.2018.04.088
– volume: 34
  start-page: 1434
  issue: 2
  year: 2008
  ident: 10.1016/j.trc.2021.103414_b46
  article-title: Credit risk assessment with a multistage neural network ensemble learning approach
  publication-title: Expert Syst. Appl.
  doi: 10.1016/j.eswa.2007.01.009
– volume: 13
  start-page: 21
  issue: 1
  year: 1953
  ident: 10.1016/j.trc.2021.103414_b6
  article-title: Nearest neighbor pattern classification
  publication-title: IEEE Trans. Inform. Theory
  doi: 10.1109/TIT.1967.1053964
– volume: 15
  start-page: 566
  issue: 3
  year: 2007
  ident: 10.1016/j.trc.2021.103414_b11
  article-title: Predictive active steering control for autonomous vehicle systems
  publication-title: IEEE Trans. Control Syst. Technol.
  doi: 10.1109/TCST.2007.894653
– volume: 18
  start-page: 1096
  issue: 4
  year: 2018
  ident: 10.1016/j.trc.2021.103414_b43
  article-title: A weighted deep representation learning model for imbalanced fault diagnosis in cyber-physical systems
  publication-title: Sensors
  doi: 10.3390/s18041096
– volume: 21
  start-page: 3756
  issue: 9
  year: 2020
  ident: 10.1016/j.trc.2021.103414_b30
  article-title: Novel convolutional neural network-based roadside unit for accurate pedestrian localisation
  publication-title: IEEE Trans. Intell. Transp. Syst.
  doi: 10.1109/TITS.2019.2932802
– start-page: 168
  issue: 2645
  year: 2017
  ident: 10.1016/j.trc.2021.103414_b1
  article-title: Detecting imminent lane change maneuvers in connected vehicle environments
  publication-title: Transp. Res. Rec. J. Transp. Res. Board
  doi: 10.3141/2645-18
SSID ssj0001957
Score 2.5420802
Snippet Lane change intention prediction is an essential component for motion planning of Autonomous Vehicles (AVs). In this work, we aim to achieve this task by using...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 103414
SubjectTerms Autonomous Vehicles
Data imbalance
Ensemble learning
Lane change intention prediction
Long Short Term Memory (LSTM) network
Over-sampling method
Title An improved learning-based LSTM approach for lane change intention prediction subject to imbalanced data
URI https://dx.doi.org/10.1016/j.trc.2021.103414
Volume 133
WOSCitedRecordID wos000771458500004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1879-2359
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0001957
  issn: 0968-090X
  databaseCode: AIEXJ
  dateStart: 19950201
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3da9swEBdZO1j3MLZupd0XetjTgootO7b1GEpHO7aykQzyZixZWVNaJzhO6J_fO-sjbvbBNtiLMSaKgu4X3U_nu98R8i7QfKoGSrFBlkYs5jpgolCcFQmXopQ8KoVpNpFeXGSTifjS601dLcz6Oq2q7PZWLP6rqeEZGBtLZ__C3P5L4QHcg9HhCmaH6x8Zflhh6WM9XwOVtD0hvjN0VmX_02j82auItwmGmOpqi39b5QiT-7io8fVNe7tcSYzUIEWd3UjMg8SEAVvR5mmtl0g3cLIKQpfHQFDrpn_SbrhY59nWZrlgfid9cdS2Fu5_7WDVR7LPVrNuaIKHW2kevmZmk6DUBh4TTLgIJsYDmW03SwXjkdUGd_uyUcj4YY834Yar46ZGCUoeom5AbCpRt6SzRzgXTsVRFw_I5gOyy9OBgN1vd3h-OvnofXYojCas-23u_XebCbg10c8ZTIeVjJ-SJ_Y4QYcGBs9IT1f75JGrNl_uk8cdwcnn5HJYUQcOeh8cFMFBHTgogIMiOKgBB_XgoBtwUAsO2szpBhwUwfGCfPtwOj45Y7bXBlNcpA3jKi5FGkyjErwOOB0J_90AxQ6LFE7QSRIncREWwP2Av0o4AnPsXaa0KFUQS5nx6IDsVPNKHxKqdajKApUcyygelFqCCwVWPFWJBhNHxREJ3PrlygrRYz-U69xlHF7lsOQ5LnlulvyIvPdDFkaF5Xcfjp1RcksjDT3MAUG_Hvby34a9Insb6L8mO0290m_IQ7VuZsv6rcXZHeXblxw
linkProvider Elsevier
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=An+improved+learning-based+LSTM+approach+for+lane+change+intention+prediction+subject+to+imbalanced+data&rft.jtitle=Transportation+research.+Part+C%2C+Emerging+technologies&rft.au=Shi%2C+Qian&rft.au=Zhang%2C+Hui&rft.date=2021-12-01&rft.pub=Elsevier+Ltd&rft.issn=0968-090X&rft.eissn=1879-2359&rft.volume=133&rft_id=info:doi/10.1016%2Fj.trc.2021.103414&rft.externalDocID=S0968090X21004083
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0968-090X&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0968-090X&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0968-090X&client=summon