Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings

•A new approach to nonlinear seismic response predictions of structures using multiple-component features.•Deep learning time-series predictions through hybrid ConvLSTM models.•Signal processing improved with DWT of acceleration time-history.•Hybrid model can predict nonlinear seismic response of in...

Full description

Saved in:

Bibliographic Details
Published in:	Computers & structures Vol. 252; p. 106570
Main Authors:	Torky, Ahmed A., Ohno, Susumu
Format:	Journal Article
Language:	English
Published:	New York Elsevier Ltd 01.08.2021 Elsevier BV
Subjects:	Artificial neural networks Butterworth filters Computer architecture Convolutional long short-term memory neural networks Data processing Deep learning Deep neural networks Discrete Wavelet Transform Discrete wavelet transforms Fast Fourier transformations Fourier transforms Machine learning Multi-component response Neural networks Nonlinear seismic response prediction Recurrent neural networks Seismic response Superstructures Wavelet transforms Deep neural networks Multi-component response Discrete wavelet transforms Convolutional long short-term memory neural networks Nonlinear seismic response prediction
ISSN:	0045-7949, 1879-2243
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	•A new approach to nonlinear seismic response predictions of structures using multiple-component features.•Deep learning time-series predictions through hybrid ConvLSTM models.•Signal processing improved with DWT of acceleration time-history.•Hybrid model can predict nonlinear seismic response of industrial-level building. This paper presents a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. Modern recurrent neural networks map the relationship between acceleration time-series of the base/ground of a building and the superstructure, as a form of nonlinear time-history analysis method. Seismic responses were measured in three components which enables multi-component seismic predictions with adequate deep learning architectures. While long short-term memory (LSTM) neural networks can obtain data from a single component per surrogate model, hybrid convolutional-LSTMs (ConvLSTM) neural networks are utilized for multi-component purposes. A guide for pre-processing data and structuring the architecture of deep neural networks are proposed. Also, two filtering methods are compared, Fast Fourier Transform (FFT) Butterworth filter and discrete wavelet transform (DWT) decomposition. Decimation is implemented to reduce the features to useful values, as a dimension reduction approach. With enhancements to the architecture of the network, training time can be reduced significantly, and accuracy could be further improved. A challenging case study is addressed that covers an industrial level practical building. Results show that proposed hybrid models can even predict the capacity curves of a structure indirectly, providing new prospects for engineers to evaluate the seismic performance of a building.
AbstractList	This paper presents a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. Modern recurrent neural networks map the relationship between acceleration time-series of the base/ground of a building and the superstructure, as a form of nonlinear time-history analysis method. Seismic responses were measured in three components which enables multi-component seismic predictions with adequate deep learning architectures. While long short-term memory (LSTM) neural networks can obtain data from a single component per surrogate model, hybrid convolutional-LSTMs (ConvLSTM) neural networks are utilized for multi-component purposes. A guide for pre-processing data and structuring the architecture of deep neural networks are proposed. Also, two filtering methods are compared, Fast Fourier Transform (FFT) Butterworth filter and discrete wavelet transform (DWT) decomposition. Decimation is implemented to reduce the features to useful values, as a dimension reduction approach. With enhancements to the architecture of the network, training time can be reduced significantly, and accuracy could be further improved. A challenging case study is addressed that covers an industrial level practical building. Results show that proposed hybrid models can even predict the capacity curves of a structure indirectly, providing new prospects for engineers to evaluate the seismic performance of a building. •A new approach to nonlinear seismic response predictions of structures using multiple-component features.•Deep learning time-series predictions through hybrid ConvLSTM models.•Signal processing improved with DWT of acceleration time-history.•Hybrid model can predict nonlinear seismic response of industrial-level building. This paper presents a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. Modern recurrent neural networks map the relationship between acceleration time-series of the base/ground of a building and the superstructure, as a form of nonlinear time-history analysis method. Seismic responses were measured in three components which enables multi-component seismic predictions with adequate deep learning architectures. While long short-term memory (LSTM) neural networks can obtain data from a single component per surrogate model, hybrid convolutional-LSTMs (ConvLSTM) neural networks are utilized for multi-component purposes. A guide for pre-processing data and structuring the architecture of deep neural networks are proposed. Also, two filtering methods are compared, Fast Fourier Transform (FFT) Butterworth filter and discrete wavelet transform (DWT) decomposition. Decimation is implemented to reduce the features to useful values, as a dimension reduction approach. With enhancements to the architecture of the network, training time can be reduced significantly, and accuracy could be further improved. A challenging case study is addressed that covers an industrial level practical building. Results show that proposed hybrid models can even predict the capacity curves of a structure indirectly, providing new prospects for engineers to evaluate the seismic performance of a building.
ArticleNumber	106570
Author	Ohno, Susumu Torky, Ahmed A.
Author_xml	– sequence: 1 givenname: Ahmed A. surname: Torky fullname: Torky, Ahmed A. email: ahmed.torky@dc.tohoku.ac.jp organization: Graduate School of Engineering, Tohoku University, Japan – sequence: 2 givenname: Susumu surname: Ohno fullname: Ohno, Susumu email: ohno@irides.tohoku.ac.jp organization: International Research Institute of Disaster Science, Tohoku University, Japan
BookMark	eNqNkMtOxCAUhonRxPHyDJK47njAtpSFC-M9MXGja0LpqTJ2oAI18e2ljnHhRheE5PBfDt8e2XbeISFHDJYMWH2yWhq_HmMKk1ly4CxP60rAFlmwRsiC8_J0mywAyqoQspS7ZC_GFQDUJcCCvF4ijnRAHZx1zzSheXH2bcJIex_oGLCzJs0vuXWwLuvoehqSLebSvIhLNKKNa2towJgnMVt9T7_2SVPQA20nO3Q5Ih6QnV4PEQ-_733ydH31eHFb3D_c3F2c3xemBJkKbKHSGjTKGhptRN1yzfvGVE3TtcA4yi4fyTljspWCQ9t3TV_3UrCqaUGc7pPjTe4Y_PyVpFZ-Ci5XKl6VdV2KildZJTYqE3yMAXs1BrvW4UMxUDNZtVI_ZNVMVm3IZufZL6exSSfrXQraDv_wn2_8mCG8WwwqGovOZNYBTVKdt39mfALJkp_o
CitedBy_id	crossref_primary_10_1016_j_engstruct_2025_120225 crossref_primary_10_1016_j_istruc_2025_110199 crossref_primary_10_1016_j_engstruct_2025_119710 crossref_primary_10_1016_j_engstruct_2025_119913 crossref_primary_10_1016_j_autcon_2022_104255 crossref_primary_10_1016_j_engstruct_2024_118702 crossref_primary_10_1016_j_engstruct_2025_121273 crossref_primary_10_1142_S0219455424501608 crossref_primary_10_1016_j_engstruct_2024_117733 crossref_primary_10_1007_s44379_024_00011_x crossref_primary_10_1080_13632469_2025_2469090 crossref_primary_10_1016_j_compstruc_2024_107443 crossref_primary_10_1016_j_engstruct_2023_117048 crossref_primary_10_1007_s42107_023_00915_8 crossref_primary_10_1016_j_jobe_2025_112643 crossref_primary_10_1142_S0219455425501986 crossref_primary_10_1177_14759217241241983 crossref_primary_10_3390_math12132084 crossref_primary_10_1088_1361_665X_ad742d crossref_primary_10_1007_s42107_025_01307_w crossref_primary_10_1016_j_compstruc_2023_107114 crossref_primary_10_1016_j_engappai_2024_109031 crossref_primary_10_1080_15732479_2024_2345853 crossref_primary_10_1016_j_compstruc_2023_107038 crossref_primary_10_1016_j_compstruc_2025_107719 crossref_primary_10_1016_j_soildyn_2023_108263 crossref_primary_10_1016_j_engappai_2025_110955 crossref_primary_10_1016_j_ress_2025_111006 crossref_primary_10_1007_s40430_023_04043_x crossref_primary_10_1002_eqe_4213 crossref_primary_10_1016_j_engstruct_2025_120247 crossref_primary_10_1080_17445302_2025_2472259 crossref_primary_10_1016_j_engstruct_2024_119132 crossref_primary_10_1016_j_compgeo_2025_107382 crossref_primary_10_1016_j_jii_2023_100470 crossref_primary_10_1016_j_measurement_2025_116820 crossref_primary_10_1016_j_ymssp_2023_110906 crossref_primary_10_1016_j_engappai_2024_108965 crossref_primary_10_1002_suco_70274 crossref_primary_10_1016_j_istruc_2025_109548 crossref_primary_10_1007_s00158_025_03969_1 crossref_primary_10_1016_j_aei_2025_103797 crossref_primary_10_1016_j_jobe_2025_112932 crossref_primary_10_1016_j_compstruc_2025_107902 crossref_primary_10_1016_j_soildyn_2024_108733 crossref_primary_10_1016_j_istruc_2024_106465 crossref_primary_10_1002_eqe_4264 crossref_primary_10_1016_j_engstruct_2025_120953 crossref_primary_10_1016_j_istruc_2025_109390 crossref_primary_10_1016_j_jobe_2024_110864 crossref_primary_10_1016_j_jobe_2024_108766 crossref_primary_10_3390_s22145186 crossref_primary_10_1016_j_cma_2024_117074 crossref_primary_10_1111_mice_12944 crossref_primary_10_1016_j_engstruct_2024_119227 crossref_primary_10_1007_s40430_025_05697_5 crossref_primary_10_1016_j_apor_2023_103514 crossref_primary_10_1016_j_engstruct_2022_114576 crossref_primary_10_1016_j_engstruct_2022_115503 crossref_primary_10_1016_j_aei_2023_102002 crossref_primary_10_1016_j_compstruc_2022_106742 crossref_primary_10_1016_j_jobe_2022_104837 crossref_primary_10_1002_eqe_4273 crossref_primary_10_1061_PPSCFX_SCENG_1292 crossref_primary_10_1016_j_engstruct_2022_115065 crossref_primary_10_1002_eqe_4236 crossref_primary_10_1016_j_compstruc_2025_107777 crossref_primary_10_1002_eqe_3863 crossref_primary_10_1007_s11069_024_06465_9 crossref_primary_10_1016_j_engstruct_2023_116094
Cites_doi	10.1038/nature14539 10.1785/0120050052 10.1016/j.compstruc.2019.05.006 10.1016/j.asoc.2018.05.018 10.1002/nme.1620090207 10.1002/2475-8876.1010 10.1177/8755293020919419 10.1371/journal.pone.0230114 10.1061/(ASCE)CP.1943-5487.0000820 10.1016/j.neunet.2018.12.005 10.1007/s00707-020-02878-2 10.3130/aijs.79.1107 10.1016/j.strusafe.2017.12.001 10.3130/aijs.78.1061 10.1016/j.strusafe.2019.101913 10.1007/s11831-017-9237-0
ContentType	Journal Article
Copyright	2021 Elsevier Ltd Copyright Elsevier BV Aug 2021
Copyright_xml	– notice: 2021 Elsevier Ltd – notice: Copyright Elsevier BV Aug 2021
DBID	AAYXX CITATION 7SC 8FD FR3 JQ2 KR7 L7M L~C L~D
DOI	10.1016/j.compstruc.2021.106570
DatabaseName	CrossRef Computer and Information Systems Abstracts Technology Research Database Engineering Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Civil Engineering Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Computer Science Collection Computer and Information Systems Abstracts Engineering Research Database Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional
DatabaseTitleList	Civil Engineering Abstracts
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering
EISSN	1879-2243
ExternalDocumentID	10_1016_j_compstruc_2021_106570 S0045794921000924
GroupedDBID	--K --M -~X .DC .~1 0R~ 1B1 1~. 1~5 29F 4.4 457 4G. 5GY 5VS 6TJ 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN AAYOK ABAOU ABBOA ABEFU ABFNM ABMAC ABTAH ABXDB ABYKQ ACAZW ACDAQ ACGFS ACIWK ACKIV ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADIYS ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AI. AIALX AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MHUIS MO0 N9A O-L O9- OAUVE OHT OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG RNS ROL RPZ RXW SBC SDF SDG SDP SES SET SEW SPC SPCBC SPD SST SSV SSW SSZ T5K T9H TAE TN5 UAO VH1 WUQ XPP ZMT ZY4 ~02 ~G- 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABJNI ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7SC 8FD AGCQF FR3 JQ2 KR7 L7M L~C L~D
ID	FETCH-LOGICAL-c409t-eb05aa0ae9608ac76b2a2f8c588db012e9d2e9922119b9720bfd8f6f97158b073
ISICitedReferencesCount	82
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000658896800007&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0045-7949
IngestDate	Sun Sep 07 03:46:14 EDT 2025 Sat Nov 29 07:26:30 EST 2025 Tue Nov 18 21:38:58 EST 2025 Fri Feb 23 02:44:41 EST 2024
IsPeerReviewed	true
IsScholarly	true
Keywords	Deep neural networks Multi-component response Discrete wavelet transforms Convolutional long short-term memory neural networks Nonlinear seismic response prediction
Language	English
LinkModel	OpenURL
MergedId	FETCHMERGED-LOGICAL-c409t-eb05aa0ae9608ac76b2a2f8c588db012e9d2e9922119b9720bfd8f6f97158b073
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
PQID	2546647525
PQPubID	2045492
ParticipantIDs	proquest_journals_2546647525 crossref_primary_10_1016_j_compstruc_2021_106570 crossref_citationtrail_10_1016_j_compstruc_2021_106570 elsevier_sciencedirect_doi_10_1016_j_compstruc_2021_106570
PublicationCentury	2000
PublicationDate	August 2021 2021-08-00 20210801
PublicationDateYYYYMMDD	2021-08-01
PublicationDate_xml	– month: 08 year: 2021 text: August 2021
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	Computers & structures
PublicationYear	2021
Publisher	Elsevier Ltd Elsevier BV
Publisher_xml	– name: Elsevier Ltd – name: Elsevier BV
References	Motosaka M, Ohno S, Mitsuji K, Wang X, Hatakeyama T. Development of Structural Health Monitoring System Combined with Earthquake Early Warning System for Real-time Earthquake Information Navigation. In: 16th World Conf. Earthq. Eng. Santiago, Chile, 9-13 January; 2017. Kumar, Islam, Sekimoto, Mattmann, Wilson (b0105) 2020; 15 Khodabandehlou, Pekcan, Fadali (b0090) 2019; 26 Kashima T. Dynamic Behavior of an Eight-Storey SRC Building Examined from Strong Motion Records. In: 13th World Conf. Earthq. Eng., Vancouver, Canada; 2004. Kashima T. Dynamic Behaviour of Src Buildings Damaged By the 2011 Great East Japan Earthquake Based on Strong Motion Records. In: Second Eur. Conf. Earthq. Eng. Seismol., Istanbul, Turkey, 2014: pp. 1–11. Zhang R, Liu Y, Sun H. Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling; 2019. p. 1–24. Wu, Jahanshahi (b0075) 2019 Lecun, Bengio, Hinton (b0045) 2015 Torky AA, Ohno S, Kashima T. Deep learning techniques for structural response prediction during strong ground motion. In: 17th World Conf Earthq Eng 17WCEE, Sendai, Japan, n.d. BRI Strong Motion Observation (English), (n.d.). B.R.I. (BRI) Kashima’s Office, International Institute of Seismology and Earthquake Engineering (IISEE), ViewWave Software; 2021. Kawamura, Kusunoki, Yamashita, Hattori, Hinata, Figueroa (b0145) 2013 Motosaka, Tsamba, Yoshida, Mitsuji (b0020) 2015; 15 Clinton, Bradford, Heaton, Favela (b0025) 2006 Bathe, Ramm, Wilson (b0015) 1975 Kashima T, Koyama S, Okawa I. Strong Motion Records in Buildings from the 2011 off the Pacific coast of Tohoku Earthquake, Building Research Data No.135, Building Research Institute, (n.d.). Rofooei FR, Kaveh A, Farahani FM. Estimating the vulnerability of the concrete moment resisting frame structures using artificial neural networks. Int. J. Optim. Civ. Eng. 2011. Ohno S, Tsuruta R. Ground-motion prediction by ANN using machine learning for the Tohoku region, Japan. In: 11th Natl. Conf. Earthq. Eng. 2018, NCEE 2018 Integr. Sci. Eng. Policy, Los Angeles, California; 2018. p. 5429–5437. Zhang, Chen, Chen, Zheng, Büyüköztürk, Sun (b0055) 2019; 220 Zhang, Burton, Sun, Shokrabadi (b0010) 2018; 72 Li, Nakamura, Kashima, Techigawara (b0140) 2014; 79 Xie, Ebad Sichani, Padgett, DesRoches (b0030) 2020 . Kim, Kwon, Song (b0100) 2019 Kim, Song, Kwon (b0085) 2020; 84 Lee, Ha, Zokhirova, Moon, Lee (b0120) 2018 Kusunoki, Hinata, Hattori, Tasai (b0115) 2018 Garcia-Garcia, Orts-Escolano, Oprea, Villena-Martinez, Martinez-Gonzalez, Garcia-Rodriguez (b0065) 2018; 70 Shi X, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In: Adv. Neural Inf. Process. Syst.; 2015. Kaveh, Dadras Eslamlou, Javadi, Geran Malek (b0040) 2021 Gulgec, Takáč, Pakzad (b0070) 2019; 33 Butterworth S. On the theory of filter amplifiers. Exp Wirel Wirel Eng; 1930. https://doi.org/citeulike-article-id:5322726. Kim (10.1016/j.compstruc.2021.106570_b0085) 2020; 84 10.1016/j.compstruc.2021.106570_b0135 Kaveh (10.1016/j.compstruc.2021.106570_b0040) 2021 Kim (10.1016/j.compstruc.2021.106570_b0100) 2019 Li (10.1016/j.compstruc.2021.106570_b0140) 2014; 79 Lee (10.1016/j.compstruc.2021.106570_b0120) 2018 Clinton (10.1016/j.compstruc.2021.106570_b0025) 2006 Zhang (10.1016/j.compstruc.2021.106570_b0055) 2019; 220 Lecun (10.1016/j.compstruc.2021.106570_b0045) 2015 Khodabandehlou (10.1016/j.compstruc.2021.106570_b0090) 2019; 26 10.1016/j.compstruc.2021.106570_b0110 10.1016/j.compstruc.2021.106570_b0155 10.1016/j.compstruc.2021.106570_b0035 10.1016/j.compstruc.2021.106570_b0050 10.1016/j.compstruc.2021.106570_b0095 10.1016/j.compstruc.2021.106570_b0150 Garcia-Garcia (10.1016/j.compstruc.2021.106570_b0065) 2018; 70 10.1016/j.compstruc.2021.106570_b0130 Xie (10.1016/j.compstruc.2021.106570_b0030) 2020 10.1016/j.compstruc.2021.106570_b0125 10.1016/j.compstruc.2021.106570_b0005 Kumar (10.1016/j.compstruc.2021.106570_b0105) 2020; 15 Motosaka (10.1016/j.compstruc.2021.106570_b0020) 2015; 15 10.1016/j.compstruc.2021.106570_b0080 10.1016/j.compstruc.2021.106570_b0060 Kawamura (10.1016/j.compstruc.2021.106570_b0145) 2013 Bathe (10.1016/j.compstruc.2021.106570_b0015) 1975 Gulgec (10.1016/j.compstruc.2021.106570_b0070) 2019; 33 Kusunoki (10.1016/j.compstruc.2021.106570_b0115) 2018 Wu (10.1016/j.compstruc.2021.106570_b0075) 2019 Zhang (10.1016/j.compstruc.2021.106570_b0010) 2018; 72
References_xml	– volume: 70 start-page: 41 year: 2018 end-page: 65 ident: b0065 article-title: A survey on deep learning techniques for image and video semantic segmentation publication-title: Appl Soft Comput J – reference: B.R.I. (BRI) Kashima’s Office, International Institute of Seismology and Earthquake Engineering (IISEE), ViewWave Software; 2021. – volume: 33 start-page: 04019005 year: 2019 ident: b0070 article-title: Convolutional neural network approach for robust structural damage detection and localization publication-title: J. Comput Civ Eng – reference: Shi X, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC. Convolutional LSTM network: A machine learning approach for precipitation nowcasting. In: Adv. Neural Inf. Process. Syst.; 2015. – year: 2018 ident: b0115 article-title: A new method for evaluating the real-time residual seismic capacity of existing structures using accelerometers: structures with multiple degrees of freedom publication-title: Japan Archit Rev – reference: Kashima T. Dynamic Behavior of an Eight-Storey SRC Building Examined from Strong Motion Records. In: 13th World Conf. Earthq. Eng., Vancouver, Canada; 2004. – year: 2018 ident: b0120 article-title: Background information of deep learning for structural engineering publication-title: Arch Comput Methods Eng – reference: Kashima T. Dynamic Behaviour of Src Buildings Damaged By the 2011 Great East Japan Earthquake Based on Strong Motion Records. In: Second Eur. Conf. Earthq. Eng. Seismol., Istanbul, Turkey, 2014: pp. 1–11. – volume: 26 start-page: 1 year: 2019 end-page: 12 ident: b0090 article-title: Vibration-based structural condition assessment using convolution neural networks publication-title: Struct Control Heal Monit – year: 1975 ident: b0015 article-title: Finite element formulations for large deformation dynamic analysis publication-title: Int J Numer Meth Eng – volume: 15 start-page: 3_1-3_16 year: 2015 ident: b0020 article-title: Long-term monitoring of amplitude dependent dynamic characteristics of a damaged building during the 2011 Tohoku Earthquake publication-title: J JAEEJournal Japan Assoc Earthq Eng – year: 2006 ident: b0025 article-title: The observed wander of the natural frequencies in a structure publication-title: Bull Seismol Soc Am – volume: 220 start-page: 55 year: 2019 end-page: 68 ident: b0055 article-title: Deep long short-term memory networks for nonlinear structural seismic response prediction publication-title: Comput Struct – reference: Motosaka M, Ohno S, Mitsuji K, Wang X, Hatakeyama T. Development of Structural Health Monitoring System Combined with Earthquake Early Warning System for Real-time Earthquake Information Navigation. In: 16th World Conf. Earthq. Eng. Santiago, Chile, 9-13 January; 2017. – volume: 79 start-page: 1107 year: 2014 end-page: 1115 ident: b0140 article-title: Earthquake damage evaluation of an 8-story steel-reinforced concrete building using Sa-Sd Curves publication-title: J Struct Constr Eng, AIJ. – volume: 72 start-page: 1 year: 2018 end-page: 16 ident: b0010 article-title: A machine learning framework for assessing post-earthquake structural safety publication-title: Struct Saf – year: 2021 ident: b0040 article-title: Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders publication-title: Acta Mech – year: 2019 ident: b0075 article-title: Deep convolutional neural network for structural dynamic response estimation and system identification publication-title: J Eng Mech – reference: Torky AA, Ohno S, Kashima T. Deep learning techniques for structural response prediction during strong ground motion. In: 17th World Conf Earthq Eng 17WCEE, Sendai, Japan, n.d. – year: 2015 ident: b0045 article-title: Deep learning publication-title: Nature – reference: Ohno S, Tsuruta R. Ground-motion prediction by ANN using machine learning for the Tohoku region, Japan. In: 11th Natl. Conf. Earthq. Eng. 2018, NCEE 2018 Integr. Sci. Eng. Policy, Los Angeles, California; 2018. p. 5429–5437. – year: 2020 ident: b0030 article-title: The promise of implementing machine learning in earthquake engineering: a state-of-the-art review publication-title: Earthq Spectra – year: 2013 ident: b0145 article-title: Study of a new method to compute the performance curve of real structures with acceleration sensors: in the case of SDOF system structures publication-title: J Struct Constr Eng – volume: 15 start-page: 1 year: 2020 end-page: 18 ident: b0105 article-title: ConvCast: An embedded convolutional LSTM based architecture for precipitation nowcasting using satellite data publication-title: PLoS ONE – reference: . – reference: BRI Strong Motion Observation (English), (n.d.). – reference: Butterworth S. On the theory of filter amplifiers. Exp Wirel Wirel Eng; 1930. https://doi.org/citeulike-article-id:5322726. – reference: Zhang R, Liu Y, Sun H. Physics-guided Convolutional Neural Network (PhyCNN) for Data-driven Seismic Response Modeling; 2019. p. 1–24. – year: 2019 ident: b0100 article-title: Response prediction of nonlinear hysteretic systems by deep neural networks publication-title: Neural Networks – reference: Rofooei FR, Kaveh A, Farahani FM. Estimating the vulnerability of the concrete moment resisting frame structures using artificial neural networks. Int. J. Optim. Civ. Eng. 2011. – volume: 84 start-page: 101913 year: 2020 ident: b0085 article-title: Probabilistic evaluation of seismic responses using deep learning method publication-title: Struct Saf – reference: Kashima T, Koyama S, Okawa I. Strong Motion Records in Buildings from the 2011 off the Pacific coast of Tohoku Earthquake, Building Research Data No.135, Building Research Institute, (n.d.). – year: 2015 ident: 10.1016/j.compstruc.2021.106570_b0045 article-title: Deep learning publication-title: Nature doi: 10.1038/nature14539 – year: 2006 ident: 10.1016/j.compstruc.2021.106570_b0025 article-title: The observed wander of the natural frequencies in a structure publication-title: Bull Seismol Soc Am doi: 10.1785/0120050052 – volume: 220 start-page: 55 year: 2019 ident: 10.1016/j.compstruc.2021.106570_b0055 article-title: Deep long short-term memory networks for nonlinear structural seismic response prediction publication-title: Comput Struct doi: 10.1016/j.compstruc.2019.05.006 – ident: 10.1016/j.compstruc.2021.106570_b0130 – volume: 70 start-page: 41 year: 2018 ident: 10.1016/j.compstruc.2021.106570_b0065 article-title: A survey on deep learning techniques for image and video semantic segmentation publication-title: Appl Soft Comput J doi: 10.1016/j.asoc.2018.05.018 – year: 1975 ident: 10.1016/j.compstruc.2021.106570_b0015 article-title: Finite element formulations for large deformation dynamic analysis publication-title: Int J Numer Meth Eng doi: 10.1002/nme.1620090207 – ident: 10.1016/j.compstruc.2021.106570_b0155 – year: 2018 ident: 10.1016/j.compstruc.2021.106570_b0115 article-title: A new method for evaluating the real-time residual seismic capacity of existing structures using accelerometers: structures with multiple degrees of freedom publication-title: Japan Archit Rev doi: 10.1002/2475-8876.1010 – year: 2020 ident: 10.1016/j.compstruc.2021.106570_b0030 article-title: The promise of implementing machine learning in earthquake engineering: a state-of-the-art review publication-title: Earthq Spectra doi: 10.1177/8755293020919419 – volume: 15 start-page: 1 year: 2020 ident: 10.1016/j.compstruc.2021.106570_b0105 article-title: ConvCast: An embedded convolutional LSTM based architecture for precipitation nowcasting using satellite data publication-title: PLoS ONE doi: 10.1371/journal.pone.0230114 – ident: 10.1016/j.compstruc.2021.106570_b0050 – ident: 10.1016/j.compstruc.2021.106570_b0035 – volume: 33 start-page: 04019005 year: 2019 ident: 10.1016/j.compstruc.2021.106570_b0070 article-title: Convolutional neural network approach for robust structural damage detection and localization publication-title: J. Comput Civ Eng doi: 10.1061/(ASCE)CP.1943-5487.0000820 – year: 2019 ident: 10.1016/j.compstruc.2021.106570_b0100 article-title: Response prediction of nonlinear hysteretic systems by deep neural networks publication-title: Neural Networks doi: 10.1016/j.neunet.2018.12.005 – year: 2021 ident: 10.1016/j.compstruc.2021.106570_b0040 article-title: Machine learning regression approaches for predicting the ultimate buckling load of variable-stiffness composite cylinders publication-title: Acta Mech doi: 10.1007/s00707-020-02878-2 – ident: 10.1016/j.compstruc.2021.106570_b0095 – ident: 10.1016/j.compstruc.2021.106570_b0125 – volume: 79 start-page: 1107 year: 2014 ident: 10.1016/j.compstruc.2021.106570_b0140 article-title: Earthquake damage evaluation of an 8-story steel-reinforced concrete building using Sa-Sd Curves publication-title: J Struct Constr Eng, AIJ. doi: 10.3130/aijs.79.1107 – ident: 10.1016/j.compstruc.2021.106570_b0150 – volume: 26 start-page: 1 year: 2019 ident: 10.1016/j.compstruc.2021.106570_b0090 article-title: Vibration-based structural condition assessment using convolution neural networks publication-title: Struct Control Heal Monit – ident: 10.1016/j.compstruc.2021.106570_b0135 – ident: 10.1016/j.compstruc.2021.106570_b0060 – volume: 72 start-page: 1 year: 2018 ident: 10.1016/j.compstruc.2021.106570_b0010 article-title: A machine learning framework for assessing post-earthquake structural safety publication-title: Struct Saf doi: 10.1016/j.strusafe.2017.12.001 – volume: 15 start-page: 3_1-3_16 year: 2015 ident: 10.1016/j.compstruc.2021.106570_b0020 article-title: Long-term monitoring of amplitude dependent dynamic characteristics of a damaged building during the 2011 Tohoku Earthquake publication-title: J JAEEJournal Japan Assoc Earthq Eng – ident: 10.1016/j.compstruc.2021.106570_b0080 – year: 2013 ident: 10.1016/j.compstruc.2021.106570_b0145 article-title: Study of a new method to compute the performance curve of real structures with acceleration sensors: in the case of SDOF system structures publication-title: J Struct Constr Eng doi: 10.3130/aijs.78.1061 – volume: 84 start-page: 101913 year: 2020 ident: 10.1016/j.compstruc.2021.106570_b0085 article-title: Probabilistic evaluation of seismic responses using deep learning method publication-title: Struct Saf doi: 10.1016/j.strusafe.2019.101913 – ident: 10.1016/j.compstruc.2021.106570_b0005 – ident: 10.1016/j.compstruc.2021.106570_b0110 – year: 2019 ident: 10.1016/j.compstruc.2021.106570_b0075 article-title: Deep convolutional neural network for structural dynamic response estimation and system identification publication-title: J Eng Mech – year: 2018 ident: 10.1016/j.compstruc.2021.106570_b0120 article-title: Background information of deep learning for structural engineering publication-title: Arch Comput Methods Eng doi: 10.1007/s11831-017-9237-0
SSID	ssj0006400
Score	2.5888147
Snippet	•A new approach to nonlinear seismic response predictions of structures using multiple-component features.•Deep learning time-series predictions through hybrid... This paper presents a new approach for nonlinear multi-component seismic response prediction of structures using hybrid deep learning techniques. Modern...
SourceID	proquest crossref elsevier
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	106570
SubjectTerms	Artificial neural networks Butterworth filters Computer architecture Convolutional long short-term memory neural networks Data processing Deep learning Deep neural networks Discrete Wavelet Transform Discrete wavelet transforms Fast Fourier transformations Fourier transforms Machine learning Multi-component response Neural networks Nonlinear seismic response prediction Recurrent neural networks Seismic response Superstructures Wavelet transforms
Title	Deep learning techniques for predicting nonlinear multi-component seismic responses of structural buildings
URI	https://dx.doi.org/10.1016/j.compstruc.2021.106570 https://www.proquest.com/docview/2546647525
Volume	252
WOSCitedRecordID	wos000658896800007&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: ScienceDirect database customDbUrl: eissn: 1879-2243 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0006400 issn: 0045-7949 databaseCode: AIEXJ dateStart: 19950103 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9QwELag5QAHxFO0lMoHekKp8o7DbdXuqqBqyyFFe7PsxKEtNJtuWtSf35n4kVAVCgcOG62cOOv1fJ4Z2-NvCHlfST8QaS28RAqYoDDle6JEIkgfrVsAIyrSySay-ZwtFvkXs13Q9ekEsqZh19d5-19FDWUgbDw6-w_idi-FAvgOQocriB2ufyX4faVamwzi2wfH0drzLiAlQIWHQOBOo0kyxEoHFXoYXL5sMDSgU6fdeU_t3MfPalpaTTTbk3RIk0q7G3u2Nj1E14PJPj1EKBbLlV6mnZyAAR6WUI9O-uTfGB50dX41XoQIAxcCZ1bG3OmYr2NlGyMbpmYk3VVav7Is98BriMYKONQctkaFBncqdr3GcIZyafu_sIvNgHIM3Rlsmd2_nx_x2fHhIS-mi2InmrUXHuYZw_34nWhfy_whWQ-zJAdNuD75NF18dvY7je3BJd38X6IC7_z93_k0t6x777IUz8hTM9egE42R5-SBal6QJyMGypfkO6KFWrTQAS0U0EIHtFCHFnoLLdSghTq00GVNB7RQh5ZX5Hg2LfYOPJN_wyth1n_pKeknQvhCwSyXiTJLZSjCmpUJYzjEQ5VX8MlDJAmUeRb6sq5YndZ5FiRMgu14TdagdeoNoXmcRjE8KxUDhxfsSBqj8pdlJWKRxckGSW0P8tKQ02OOlB_cRiGecdf1HLue667fIL6r2Gp-lvurfLQi4sbN1O4jB7DdX3nLCpWbQd9xzCmRxlkSJpt_vv2WPB5GzxZZg7erd-RR-fPytFttGyDeAJDIrjc
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=Deep+learning+techniques+for+predicting+nonlinear+multi-component+seismic+responses+of+structural+buildings&rft.jtitle=Computers+%26+structures&rft.au=Torky%2C+Ahmed+A&rft.au=Ohno%2C+Susumu&rft.date=2021-08-01&rft.pub=Elsevier+BV&rft.issn=0045-7949&rft.eissn=1879-2243&rft.volume=252&rft.spage=1&rft_id=info:doi/10.1016%2Fj.compstruc.2021.106570&rft.externalDBID=NO_FULL_TEXT
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0045-7949&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0045-7949&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0045-7949&client=summon