Frequency enhanced vector quantized variational autoencoder for structural vibration response compression
•The frequency enhanced vector quantized variational autoencoder (FEVQVAE) is proposed for structural vibration response compression.•The proposed dual-branch block in both time and frequency domains enhances feature extraction, to some extent mitigating the challenge for neural networks to extract...
Uloženo v:
| Vydáno v: | Mechanical systems and signal processing Ročník 224; s. 112136 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.02.2025
|
| Témata: | |
| ISSN: | 0888-3270 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | •The frequency enhanced vector quantized variational autoencoder (FEVQVAE) is proposed for structural vibration response compression.•The proposed dual-branch block in both time and frequency domains enhances feature extraction, to some extent mitigating the challenge for neural networks to extract high-frequency features.•The proposed frequency block separates the extraction of features for a single resonant band and multiple resonant bands, enabling the FEVQVAE to more effectively extract frequency-domain features of vibration responses.
The structural health monitoring system has been widely installed on large civil structures, generating a significant amount of structural vibration response data over their long-term service life, which poses challenges for data transmission and storage. The compression method for structural vibration responses based on the traditional deep autoencoder (AE) can only compress the original data into low-dimensional floating-point features and not into low-dimensional integer features, which limits its compression capability. To address this issue, this paper proposes a frequency enhanced vector quantized variational autoencoder (FEVQVAE) method for compressing structural vibration responses with higher compression ratios. The proposed method has three key innovations. Firstly, the proposed time-domain and frequency-domain dual-branch block enhances the feature extraction capability of both the encoder and decoder, to some extent mitigating the challenge for neural networks to extract high-frequency features. Secondly, the proposed frequency block separates the extraction of features for a single resonant band and multiple resonant bands, enabling the encoder and decoder to more effectively extract frequency-domain features of the vibration responses. Thirdly, by introducing sensor position encoding, compression of multiple sensor data can be achieved with only one model. The effectiveness of the proposed method is validated using acceleration responses from a Dowling Hall Footbridge under normal operating conditions and a long-span suspension bridge subjected to non-stationary excitations such as wind and vehicle loads. Experimental results demonstrate that the compression performance of the proposed FEVQVAE method is significantly improved compared to the AE method and the vector quantized variational autoencoder method. Modal parameter identification results of the original and reconstructed responses show excellent consistency at a compression ratio of 19.2, with a maximum relative frequency error of only 0.952% for the first six mode frequencies and a minimum modal confidence criterion of 0.9614 for the first six mode shapes. Overall, the proposed method exhibits high precision in the compression of structural vibration response, effectively alleviating the storage and transmission challenges of monitoring big data. |
|---|---|
| AbstractList | •The frequency enhanced vector quantized variational autoencoder (FEVQVAE) is proposed for structural vibration response compression.•The proposed dual-branch block in both time and frequency domains enhances feature extraction, to some extent mitigating the challenge for neural networks to extract high-frequency features.•The proposed frequency block separates the extraction of features for a single resonant band and multiple resonant bands, enabling the FEVQVAE to more effectively extract frequency-domain features of vibration responses.
The structural health monitoring system has been widely installed on large civil structures, generating a significant amount of structural vibration response data over their long-term service life, which poses challenges for data transmission and storage. The compression method for structural vibration responses based on the traditional deep autoencoder (AE) can only compress the original data into low-dimensional floating-point features and not into low-dimensional integer features, which limits its compression capability. To address this issue, this paper proposes a frequency enhanced vector quantized variational autoencoder (FEVQVAE) method for compressing structural vibration responses with higher compression ratios. The proposed method has three key innovations. Firstly, the proposed time-domain and frequency-domain dual-branch block enhances the feature extraction capability of both the encoder and decoder, to some extent mitigating the challenge for neural networks to extract high-frequency features. Secondly, the proposed frequency block separates the extraction of features for a single resonant band and multiple resonant bands, enabling the encoder and decoder to more effectively extract frequency-domain features of the vibration responses. Thirdly, by introducing sensor position encoding, compression of multiple sensor data can be achieved with only one model. The effectiveness of the proposed method is validated using acceleration responses from a Dowling Hall Footbridge under normal operating conditions and a long-span suspension bridge subjected to non-stationary excitations such as wind and vehicle loads. Experimental results demonstrate that the compression performance of the proposed FEVQVAE method is significantly improved compared to the AE method and the vector quantized variational autoencoder method. Modal parameter identification results of the original and reconstructed responses show excellent consistency at a compression ratio of 19.2, with a maximum relative frequency error of only 0.952% for the first six mode frequencies and a minimum modal confidence criterion of 0.9614 for the first six mode shapes. Overall, the proposed method exhibits high precision in the compression of structural vibration response, effectively alleviating the storage and transmission challenges of monitoring big data. |
| ArticleNumber | 112136 |
| Author | Xue, Zhilin Ou, Jinping An, Yonghui |
| Author_xml | – sequence: 1 givenname: Zhilin surname: Xue fullname: Xue, Zhilin organization: Department of Civil Engineering, Dalian University of Technology, Dalian 116023, PR China – sequence: 2 givenname: Yonghui surname: An fullname: An, Yonghui email: anyh@dlut.edu.cn organization: Department of Civil Engineering, Dalian University of Technology, Dalian 116023, PR China – sequence: 3 givenname: Jinping surname: Ou fullname: Ou, Jinping organization: Department of Civil Engineering, Dalian University of Technology, Dalian 116023, PR China |
| BookMark | eNqFkM9OwzAMh3MYEtvgCbj0BVqcdv134IAmBkiTuMA5clNHZNqSLUknjacn3ThxgJNl-_dZ8jdjE2MNMXbHIePAq_tNdtp5v89yyBcZ5zkvqgmbQtM0aZHXcM1m3m8AoF1ANWV65egwkJGnhMwnGkl9ciQZrEsOA5qgv8YBOo1BW4PbBIdgY9z25BIVUz64QYbBxdVRd-4cSxz5vTWeEml3-9j4OLxhVwq3nm5_6px9rJ7ely_p-u35dfm4TmUBRUiVRN5RzZWS1MoeSPWqa2qoco5lSxyrppCtrFugFktSCyg5NgRYdw2WORZzVlzuSme9d6TE3ukdupPgIEZDYiPOhsRoSFwMRar9RUkdzs8Eh3r7D_twYSm-ddTkhJeaRpXaRZWit_pP_htFIIzB |
| CitedBy_id | crossref_primary_10_1016_j_jisa_2025_104204 crossref_primary_10_3390_electronics14132602 |
| Cites_doi | 10.1111/j.1747-1567.2011.00751.x 10.1109/TIT.2006.871582 10.1061/(ASCE)CP.1943-5487.0001027 10.1016/j.ymssp.2019.06.036 10.1061/(ASCE)ST.1943-541X.0000946 10.1177/1475921719844039 10.1061/(ASCE)CP.1943-5487.0000855 10.1016/j.ymssp.2022.109937 10.1109/TBME.2012.2226175 10.1111/mice.12528 10.1061/(ASCE)ST.1943-541X.0002997 10.1061/(ASCE)ST.1943-541X.0002535 10.1109/TIT.2016.2556683 10.1109/TPAMI.2023.3322904 10.1061/(ASCE)CP.1943-5487.0001051 10.1002/stc.1737 10.1061/(ASCE)0887-3801(2006)20:6(390) 10.1002/stc.2979 10.1177/1475921718757405 10.1007/s11831-012-9069-x 10.1002/eqe.3960 10.1061/(ASCE)BE.1943-5592.0001668 10.1177/1475921720935585 10.12989/sss.2015.15.3.555 10.1016/j.ymssp.2023.110790 10.1016/j.ymssp.2022.109585 10.1002/stc.1681 10.1061/(ASCE)CF.1943-5509.0001694 10.1061/(ASCE)CP.1943-5487.0001023 10.1109/ICASSP.2019.8683277 10.1016/j.ymssp.2024.111168 10.1109/MSP.2018.2880837 |
| ContentType | Journal Article |
| Copyright | 2024 |
| Copyright_xml | – notice: 2024 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ymssp.2024.112136 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| ExternalDocumentID | 10_1016_j_ymssp_2024_112136 S0888327024010343 |
| GroupedDBID | --K --M .~1 0R~ 1B1 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AATTM AAXKI AAXUO AAYFN ABBOA ABJNI ABMAC ACDAQ ACGFS ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEIPS AEKER AENEX AFJKZ AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD AXJTR BJAXD BKOJK BLXMC CS3 DM4 DU5 EBS EFBJH EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ IHE J1W JJJVA KOM LG5 LG9 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 ROL RPZ SDF SDG SDP SES SEW SPC SPCBC SPD SST SSV SSZ T5K XPP ZMT ZU3 ~G- 29M 9DU AAQXK AAYWO AAYXX ABDPE ABEFU ABFNM ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADFGL ADJOM ADMUD ADNMO AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP APXCP ASPBG AVWKF AZFZN CAG CITATION COF EFKBS EFLBG EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET WUQ ~HD |
| ID | FETCH-LOGICAL-c303t-fca1be71ffce9cd0efdfb870621a59e1a683c9c790e9a5ef4051a8e0a7b8a52a3 |
| ISICitedReferencesCount | 2 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001367741500001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0888-3270 |
| IngestDate | Sat Nov 29 08:08:41 EST 2025 Tue Nov 18 21:09:43 EST 2025 Sat Mar 29 16:09:30 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Deep learning Vector quantized variational autoencoder Vibration response compression Structural health monitoring |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c303t-fca1be71ffce9cd0efdfb870621a59e1a683c9c790e9a5ef4051a8e0a7b8a52a3 |
| ParticipantIDs | crossref_primary_10_1016_j_ymssp_2024_112136 crossref_citationtrail_10_1016_j_ymssp_2024_112136 elsevier_sciencedirect_doi_10_1016_j_ymssp_2024_112136 |
| PublicationCentury | 2000 |
| PublicationDate | 2025-02-01 2025-02-00 |
| PublicationDateYYYYMMDD | 2025-02-01 |
| PublicationDate_xml | – month: 02 year: 2025 text: 2025-02-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationTitle | Mechanical systems and signal processing |
| PublicationYear | 2025 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Chen, Ni, Zhou (b0115) 2022; 29 Barker, Puckett (b0005) 2021 Metzler, Maleki, Baraniuk (b0090) 2016; 62 Zheng, Li, Li, Hao (b0245) 2023; 52 Ni, Zhang, Noori (b0150) 2020; 35 Almasri, Sadhu, Chaudhuri (b0080) 2020; 34 A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, PyTorch: an imperative style, high-performance deep learning library, Proceedings of the 33rd International Conference on Neural Information Processing Systems, Curran Associates Inc., 2019, pp. Article 721. Łańcucki, Chorowski, Sanchez, Marxer, Chen, Dolfing, Khurana, Alumäe, Laurent (b0210) 2020 Hosny, Nik-Bakht, Moselhi (b0010) 2022; 36 Hagedorn, Liu, König, Hajdin, Blumenfeld, Stöckner, Billmaier, Grossauer, Gavin (b0015) 2023; 37 Sun, Shang, Xia, Bhowmick, Nagarajaiah (b0035) 2020; 146 Donoho (b0085) 2006; 52 Yazicigil, Haque, Kinget, Wright (b0110) 2019; 36 Prechelt (b0230) 2002 Ma, Dai, Bai, Wang, Fu (b0205) 2024 Reynders (b0260) 2012; 19 J.-P. Xiang, K. Tian, J. Zhang, MIMT: Masked Image Modeling Transformer for Video Compression, International Conference on Learning Representations, 2023. Bao, Yu, Li, Mao, Jiao, Zou, Ou (b0105) 2015; 22 An, Xue, Ou (b0120) 2024; 211 Kang, Qiu, Zhang, Li, Xia (b0170) 2022 Duan, Lu, Ma, Huang, Ma, Zhu (b0160) 2024; 46 Oord, Vinyals (b0155) 2017; 30 I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, International Conference on Learning Representations, 2018. Y. Takida, T. Shibuya, W. Liao, C.-H. Lai, J. Ohmura, T. Uesaka, N. Murata, S. Takahashi, T. Kumakura, Y. Mitsufuji, SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization, International Conference on Machine Learning, PMLR, 2022, pp. 20987-21012. Kingma (b0185) 2013 Fenerci, Kvåle, Petersen, Rønnquist, Øiseth (b0060) 2021; 147 Moser, Moaveni (b0240) 2013; 37 Bao, Tang, Li, Zhang (b0190) 2019; 18 Maes, Lombaert (b0055) 2021; 26 Zhang, Li (b0075) 2006; 20 Dong, Wan, Luo, Todd (b0125) 2023; 188 Li, Au (b0045) 2019; 132 Yang, Nagarajaiah (b0135) 2014; 140 Huh, Cheung, Agrawal, Isola (b0220) 2023 Kang, Ren, Xie, Zhao, Wang (b0065) 2023; 183 Ho, Jain, Abbeel (b0200) 2020; 33 Zhang, Yi, Qu, Li (b0050) 2022; 36 Duan, Lu, Ma, Zhu (b0165) 2023 Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez, Kaiser (b0195) 2017; 30 Li, Ou, Zhang, Pei, Li (b0070) 2015; 15 D'efossez, Copet, Synnaeve, Adi (b0145) 2022; abs/2210.13438 Zhang, Jung, Makeig, Rao (b0095) 2013; 60 Balageas, Fritzen, Güemes (b0040) 2010 Bao, Tang, Li (b0100) 2020; 19 Dong, Catbas (b0030) 2021; 20 Yang, Nagarajaiah, Ni (b0130) 2015; 22 Hu, Chen, Zhang, Yin, Yu, Liu, Ding (b0020) 2023; 204 Quqa, Antolini, Scarselli, Gnudi, Lico, Carissimi, Pasotti, Canegallo, Landi, Diotallevi (b0025) 2022; 36 C. Gârbacea, A.v.d. Oord, Y. Li, F.S.C. Lim, A. Luebs, O. Vinyals, T.C. Walters, Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 735-739. F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, ArXiv, 1511.07122 (2015). Dong (10.1016/j.ymssp.2024.112136_b0030) 2021; 20 10.1016/j.ymssp.2024.112136_b0140 Chen (10.1016/j.ymssp.2024.112136_b0115) 2022; 29 Bao (10.1016/j.ymssp.2024.112136_b0105) 2015; 22 Zheng (10.1016/j.ymssp.2024.112136_b0245) 2023; 52 Hu (10.1016/j.ymssp.2024.112136_b0020) 2023; 204 Bao (10.1016/j.ymssp.2024.112136_b0190) 2019; 18 10.1016/j.ymssp.2024.112136_b0180 Vaswani (10.1016/j.ymssp.2024.112136_b0195) 2017; 30 Yang (10.1016/j.ymssp.2024.112136_b0130) 2015; 22 Łańcucki (10.1016/j.ymssp.2024.112136_b0210) 2020 Yang (10.1016/j.ymssp.2024.112136_b0135) 2014; 140 Prechelt (10.1016/j.ymssp.2024.112136_b0230) 2002 10.1016/j.ymssp.2024.112136_b0215 10.1016/j.ymssp.2024.112136_b0175 Reynders (10.1016/j.ymssp.2024.112136_b0260) 2012; 19 Zhang (10.1016/j.ymssp.2024.112136_b0050) 2022; 36 Li (10.1016/j.ymssp.2024.112136_b0045) 2019; 132 Duan (10.1016/j.ymssp.2024.112136_b0160) 2024; 46 Fenerci (10.1016/j.ymssp.2024.112136_b0060) 2021; 147 Oord (10.1016/j.ymssp.2024.112136_b0155) 2017; 30 Moser (10.1016/j.ymssp.2024.112136_b0240) 2013; 37 Ni (10.1016/j.ymssp.2024.112136_b0150) 2020; 35 D'efossez (10.1016/j.ymssp.2024.112136_b0145) 2022; abs/2210.13438 Metzler (10.1016/j.ymssp.2024.112136_b0090) 2016; 62 Barker (10.1016/j.ymssp.2024.112136_b0005) 2021 Zhang (10.1016/j.ymssp.2024.112136_b0095) 2013; 60 Kingma (10.1016/j.ymssp.2024.112136_b0185) 2013 Balageas (10.1016/j.ymssp.2024.112136_b0040) 2010 Hagedorn (10.1016/j.ymssp.2024.112136_b0015) 2023; 37 An (10.1016/j.ymssp.2024.112136_b0120) 2024; 211 Bao (10.1016/j.ymssp.2024.112136_b0100) 2020; 19 Huh (10.1016/j.ymssp.2024.112136_b0220) 2023 Sun (10.1016/j.ymssp.2024.112136_b0035) 2020; 146 10.1016/j.ymssp.2024.112136_b0235 Quqa (10.1016/j.ymssp.2024.112136_b0025) 2022; 36 Maes (10.1016/j.ymssp.2024.112136_b0055) 2021; 26 Duan (10.1016/j.ymssp.2024.112136_b0165) 2023 Yazicigil (10.1016/j.ymssp.2024.112136_b0110) 2019; 36 Zhang (10.1016/j.ymssp.2024.112136_b0075) 2006; 20 Hosny (10.1016/j.ymssp.2024.112136_b0010) 2022; 36 Li (10.1016/j.ymssp.2024.112136_b0070) 2015; 15 Almasri (10.1016/j.ymssp.2024.112136_b0080) 2020; 34 Donoho (10.1016/j.ymssp.2024.112136_b0085) 2006; 52 Ma (10.1016/j.ymssp.2024.112136_b0205) 2024 Ho (10.1016/j.ymssp.2024.112136_b0200) 2020; 33 Dong (10.1016/j.ymssp.2024.112136_b0125) 2023; 188 Kang (10.1016/j.ymssp.2024.112136_b0170) 2022 10.1016/j.ymssp.2024.112136_b0225 Kang (10.1016/j.ymssp.2024.112136_b0065) 2023; 183 |
| References_xml | – volume: 36 start-page: 04022013 year: 2022 ident: b0025 article-title: Phase Change Memories in Smart Sensing Solutions for Structural Health Monitoring publication-title: J. Comput. Civ. Eng. – volume: 26 start-page: 04721001 year: 2021 ident: b0055 article-title: Monitoring Railway Bridge KW51 Before, During, and After Retrofitting publication-title: J. Bridg. Eng. – volume: 204 year: 2023 ident: b0020 article-title: Vision-based multi-point real-time monitoring of dynamic displacement of large-span cable-stayed bridges publication-title: Mech. Syst. Sig. Process. – volume: abs/2210.13438 year: 2022 ident: b0145 publication-title: High Fidelity Neural Audio Compression, ArXiv – volume: 211 year: 2024 ident: b0120 article-title: Deep learning-based sparsity-free compressive sensing method for high accuracy structural vibration response reconstruction publication-title: Mech. Syst. Sig. Process. – start-page: 14096 year: 2023 end-page: 14113 ident: b0220 article-title: Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks publication-title: International Conference on Machine Learning, PMLR – volume: 52 start-page: 1289 year: 2006 end-page: 1306 ident: b0085 article-title: Compressed sensing publication-title: IEEE Trans. Inf. Theory – volume: 188 year: 2023 ident: b0125 article-title: A fast sparsity-free compressive sensing approach for vibration data reconstruction using deep convolutional GAN publication-title: Mech. Syst. Sig. Process. – volume: 36 start-page: 04021109 year: 2022 ident: b0050 article-title: Detecting Hinge Joint Damage in Hollow Slab Bridges Using Mode Shapes Extracted from Vehicle Response publication-title: J. Perform. Constr. Facil – start-page: 3739 year: 2022 end-page: 3748 ident: b0170 article-title: Pilc: Practical image lossless compression with an end-to-end gpu oriented neural framework publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 33 start-page: 6840 year: 2020 end-page: 6851 ident: b0200 article-title: Denoising diffusion probabilistic models publication-title: Advances in Neural Information Processing Systems – start-page: 1 year: 2020 end-page: 7 ident: b0210 article-title: Robust training of vector quantized bottleneck models publication-title: 2020 International Joint Conference on Neural Networks (IJCNN) – volume: 37 start-page: 15 year: 2013 end-page: 26 ident: b0240 article-title: Design and deployment of a continuous monitoring system for the dowling hall footbridges publication-title: Exp. Tech. – volume: 30 year: 2017 ident: b0195 article-title: I.J.A.i.n.i.p.s. Polosukhin, Attention is all you need publication-title: Adv. Neural Inf. Proces. Syst. – volume: 34 start-page: 04019041 year: 2020 ident: b0080 article-title: Toward Compressed Sensing of Structural Monitoring Data Using Discrete Cosine Transform publication-title: J. Comput. Civ. Eng. – reference: A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Köpf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, PyTorch: an imperative style, high-performance deep learning library, Proceedings of the 33rd International Conference on Neural Information Processing Systems, Curran Associates Inc., 2019, pp. Article 721. – reference: Y. Takida, T. Shibuya, W. Liao, C.-H. Lai, J. Ohmura, T. Uesaka, N. Murata, S. Takahashi, T. Kumakura, Y. Mitsufuji, SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization, International Conference on Machine Learning, PMLR, 2022, pp. 20987-21012. – year: 2010 ident: b0040 article-title: Structural health monitoring – volume: 29 start-page: e2979 year: 2022 ident: b0115 article-title: A deep learning framework for adaptive compressive sensing of high-speed train vibration responses publication-title: Struct. Control Health Monit. – volume: 60 start-page: 300 year: 2013 end-page: 309 ident: b0095 article-title: Compressed Sensing for Energy-Efficient Wireless Telemonitoring of Noninvasive Fetal ECG Via Block Sparse Bayesian Learning publication-title: IEEE Trans. Biomed. Eng. – volume: 22 start-page: 433 year: 2015 end-page: 448 ident: b0105 article-title: Compressive sensing-based lost data recovery of fast-moving wireless sensing for structural health monitoring publication-title: Struct. Control Health Monit. – volume: 37 start-page: 04022041 year: 2023 ident: b0015 article-title: BIM-Enabled Infrastructure Asset Management Using Information Containers and Semantic Web publication-title: J. Comput. Civ. Eng. – volume: 20 start-page: 692 year: 2021 end-page: 743 ident: b0030 article-title: A review of computer vision–based structural health monitoring at local and global levels publication-title: Struct. Health Monit. – volume: 140 start-page: 04014032 year: 2014 ident: b0135 article-title: Data Compression of Structural Seismic Responses via Principled Independent Component Analysis publication-title: J. Struct. Eng. – start-page: 5694 year: 2024 end-page: 5703 ident: b0205 article-title: Rewrite the Stars publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – reference: C. Gârbacea, A.v.d. Oord, Y. Li, F.S.C. Lim, A. Luebs, O. Vinyals, T.C. Walters, Low Bit-rate Speech Coding with VQ-VAE and a WaveNet Decoder, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, pp. 735-739. – volume: 62 start-page: 5117 year: 2016 end-page: 5144 ident: b0090 article-title: From Denoising to Compressed Sensing publication-title: IEEE Trans. Inf. Theory – volume: 15 start-page: 555 year: 2015 end-page: 576 ident: b0070 article-title: Research and practice of health monitoring for long-span bridges in the mainland of China publication-title: Smart Struct. Syst. – volume: 147 start-page: 04721003 year: 2021 ident: b0060 article-title: Data Set from Long-Term Wind and Acceleration Monitoring of the Hardanger Bridge publication-title: J. Struct. Eng. – volume: 183 year: 2023 ident: b0065 article-title: An enhanced method to reduce reconstruction error of compressed sensing for structure vibration signals publication-title: Mech. Syst. Sig. Process. – volume: 20 start-page: 390 year: 2006 end-page: 399 ident: b0075 article-title: Wavelet-Based Vibration Sensor Data Compression Technique for Civil Infrastructure Condition Monitoring publication-title: J. Comput. Civ. Eng. – volume: 19 start-page: 293 year: 2020 end-page: 304 ident: b0100 article-title: Compressive-sensing data reconstruction for structural health monitoring: a machine-learning approach publication-title: Struct. Health Monit. – volume: 19 start-page: 51 year: 2012 end-page: 124 ident: b0260 article-title: System Identification Methods for (Operational) Modal Analysis: Review and Comparison publication-title: Arch. Comput. Meth. Eng. – volume: 132 start-page: 490 year: 2019 end-page: 511 ident: b0045 article-title: An expectation-maximization algorithm for Bayesian operational modal analysis with multiple (possibly close) modes publication-title: Mech. Syst. Sig. Process. – volume: 46 start-page: 436 year: 2024 end-page: 450 ident: b0160 article-title: QARV: Quantization-Aware ResNet VAE for Lossy Image Compression publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1312.6114 year: 2013 ident: b0185 publication-title: Auto-encoding variational bayes, ArXiv – reference: I. Loshchilov, F. Hutter, Decoupled Weight Decay Regularization, International Conference on Learning Representations, 2018. – volume: 35 start-page: 685 year: 2020 end-page: 700 ident: b0150 article-title: Deep learning for data anomaly detection and data compression of a long-span suspension bridge publication-title: Comput. Aided Civ. Inf. Eng. – start-page: 198 year: 2023 end-page: 207 ident: b0165 article-title: Lossy image compression with quantized hierarchical vaes publication-title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision – volume: 22 start-page: 1119 year: 2015 end-page: 1131 ident: b0130 article-title: Data compression of very large-scale structural seismic and typhoon responses by low-rank representation with matrix reshape publication-title: Struct. Control Health Monit. – volume: 30 start-page: 6306 year: 2017 end-page: 6315 ident: b0155 article-title: Neural discrete representation learning publication-title: Advances in neural information processing systems – volume: 52 start-page: 3369 year: 2023 end-page: 3391 ident: b0245 article-title: Multi-channel response reconstruction using transformer based generative adversarial network publication-title: Earthq. Eng. Struct. Dyn. – volume: 18 start-page: 401 year: 2019 end-page: 421 ident: b0190 article-title: Computer vision and deep learning–based data anomaly detection method for structural health monitoring publication-title: Struct. Health Monit. – volume: 36 start-page: 04022012 year: 2022 ident: b0010 article-title: Physical Distancing Analytics for Construction Planning Using 4D BIM publication-title: J. Comput. Civ. Eng. – reference: F. Yu, V. Koltun, Multi-scale context aggregation by dilated convolutions, ArXiv, 1511.07122 (2015). – start-page: 55 year: 2002 end-page: 69 ident: b0230 article-title: Early stopping-but when?, Neural Networks: Tricks of the trade publication-title: Springer – reference: J.-P. Xiang, K. Tian, J. Zhang, MIMT: Masked Image Modeling Transformer for Video Compression, International Conference on Learning Representations, 2023. – volume: 36 start-page: 81 year: 2019 end-page: 100 ident: b0110 article-title: Taking Compressive Sensing to the Hardware Level: Breaking Fundamental Radio-Frequency Hardware Performance Tradeoffs publication-title: IEEE Signal Process Mag. – year: 2021 ident: b0005 article-title: Design of highway bridges: An LRFD approach publication-title: John Wiley & Sons – volume: 146 start-page: 04020073 year: 2020 ident: b0035 article-title: Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection publication-title: J. Struct. Eng. – volume: abs/2210.13438 year: 2022 ident: 10.1016/j.ymssp.2024.112136_b0145 publication-title: High Fidelity Neural Audio Compression, ArXiv – volume: 37 start-page: 15 year: 2013 ident: 10.1016/j.ymssp.2024.112136_b0240 article-title: Design and deployment of a continuous monitoring system for the dowling hall footbridges publication-title: Exp. Tech. doi: 10.1111/j.1747-1567.2011.00751.x – volume: 52 start-page: 1289 year: 2006 ident: 10.1016/j.ymssp.2024.112136_b0085 article-title: Compressed sensing publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2006.871582 – volume: 36 start-page: 04022013 year: 2022 ident: 10.1016/j.ymssp.2024.112136_b0025 article-title: Phase Change Memories in Smart Sensing Solutions for Structural Health Monitoring publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0001027 – volume: 132 start-page: 490 year: 2019 ident: 10.1016/j.ymssp.2024.112136_b0045 article-title: An expectation-maximization algorithm for Bayesian operational modal analysis with multiple (possibly close) modes publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2019.06.036 – volume: 140 start-page: 04014032 year: 2014 ident: 10.1016/j.ymssp.2024.112136_b0135 article-title: Data Compression of Structural Seismic Responses via Principled Independent Component Analysis publication-title: J. Struct. Eng. doi: 10.1061/(ASCE)ST.1943-541X.0000946 – volume: 19 start-page: 293 year: 2020 ident: 10.1016/j.ymssp.2024.112136_b0100 article-title: Compressive-sensing data reconstruction for structural health monitoring: a machine-learning approach publication-title: Struct. Health Monit. doi: 10.1177/1475921719844039 – volume: 30 start-page: 6306 year: 2017 ident: 10.1016/j.ymssp.2024.112136_b0155 article-title: Neural discrete representation learning publication-title: Advances in neural information processing systems – volume: 34 start-page: 04019041 year: 2020 ident: 10.1016/j.ymssp.2024.112136_b0080 article-title: Toward Compressed Sensing of Structural Monitoring Data Using Discrete Cosine Transform publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0000855 – volume: 188 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0125 article-title: A fast sparsity-free compressive sensing approach for vibration data reconstruction using deep convolutional GAN publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2022.109937 – volume: 60 start-page: 300 year: 2013 ident: 10.1016/j.ymssp.2024.112136_b0095 article-title: Compressed Sensing for Energy-Efficient Wireless Telemonitoring of Noninvasive Fetal ECG Via Block Sparse Bayesian Learning publication-title: IEEE Trans. Biomed. Eng. doi: 10.1109/TBME.2012.2226175 – volume: 33 start-page: 6840 year: 2020 ident: 10.1016/j.ymssp.2024.112136_b0200 article-title: Denoising diffusion probabilistic models publication-title: Advances in Neural Information Processing Systems – volume: 35 start-page: 685 year: 2020 ident: 10.1016/j.ymssp.2024.112136_b0150 article-title: Deep learning for data anomaly detection and data compression of a long-span suspension bridge publication-title: Comput. Aided Civ. Inf. Eng. doi: 10.1111/mice.12528 – volume: 147 start-page: 04721003 year: 2021 ident: 10.1016/j.ymssp.2024.112136_b0060 article-title: Data Set from Long-Term Wind and Acceleration Monitoring of the Hardanger Bridge publication-title: J. Struct. Eng. doi: 10.1061/(ASCE)ST.1943-541X.0002997 – ident: 10.1016/j.ymssp.2024.112136_b0180 – volume: 146 start-page: 04020073 year: 2020 ident: 10.1016/j.ymssp.2024.112136_b0035 article-title: Review of Bridge Structural Health Monitoring Aided by Big Data and Artificial Intelligence: From Condition Assessment to Damage Detection publication-title: J. Struct. Eng. doi: 10.1061/(ASCE)ST.1943-541X.0002535 – year: 2010 ident: 10.1016/j.ymssp.2024.112136_b0040 – volume: 30 year: 2017 ident: 10.1016/j.ymssp.2024.112136_b0195 article-title: I.J.A.i.n.i.p.s. Polosukhin, Attention is all you need publication-title: Adv. Neural Inf. Proces. Syst. – volume: 62 start-page: 5117 year: 2016 ident: 10.1016/j.ymssp.2024.112136_b0090 article-title: From Denoising to Compressed Sensing publication-title: IEEE Trans. Inf. Theory doi: 10.1109/TIT.2016.2556683 – volume: 46 start-page: 436 year: 2024 ident: 10.1016/j.ymssp.2024.112136_b0160 article-title: QARV: Quantization-Aware ResNet VAE for Lossy Image Compression publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2023.3322904 – ident: 10.1016/j.ymssp.2024.112136_b0225 – volume: 37 start-page: 04022041 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0015 article-title: BIM-Enabled Infrastructure Asset Management Using Information Containers and Semantic Web publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0001051 – volume: 22 start-page: 1119 year: 2015 ident: 10.1016/j.ymssp.2024.112136_b0130 article-title: Data compression of very large-scale structural seismic and typhoon responses by low-rank representation with matrix reshape publication-title: Struct. Control Health Monit. doi: 10.1002/stc.1737 – volume: 20 start-page: 390 year: 2006 ident: 10.1016/j.ymssp.2024.112136_b0075 article-title: Wavelet-Based Vibration Sensor Data Compression Technique for Civil Infrastructure Condition Monitoring publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)0887-3801(2006)20:6(390) – volume: 29 start-page: e2979 year: 2022 ident: 10.1016/j.ymssp.2024.112136_b0115 article-title: A deep learning framework for adaptive compressive sensing of high-speed train vibration responses publication-title: Struct. Control Health Monit. doi: 10.1002/stc.2979 – volume: 18 start-page: 401 year: 2019 ident: 10.1016/j.ymssp.2024.112136_b0190 article-title: Computer vision and deep learning–based data anomaly detection method for structural health monitoring publication-title: Struct. Health Monit. doi: 10.1177/1475921718757405 – ident: 10.1016/j.ymssp.2024.112136_b0235 – volume: 19 start-page: 51 year: 2012 ident: 10.1016/j.ymssp.2024.112136_b0260 article-title: System Identification Methods for (Operational) Modal Analysis: Review and Comparison publication-title: Arch. Comput. Meth. Eng. doi: 10.1007/s11831-012-9069-x – year: 2021 ident: 10.1016/j.ymssp.2024.112136_b0005 article-title: Design of highway bridges: An LRFD approach publication-title: John Wiley & Sons – volume: 52 start-page: 3369 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0245 article-title: Multi-channel response reconstruction using transformer based generative adversarial network publication-title: Earthq. Eng. Struct. Dyn. doi: 10.1002/eqe.3960 – start-page: 5694 year: 2024 ident: 10.1016/j.ymssp.2024.112136_b0205 article-title: Rewrite the Stars publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 26 start-page: 04721001 year: 2021 ident: 10.1016/j.ymssp.2024.112136_b0055 article-title: Monitoring Railway Bridge KW51 Before, During, and After Retrofitting publication-title: J. Bridg. Eng. doi: 10.1061/(ASCE)BE.1943-5592.0001668 – volume: 20 start-page: 692 year: 2021 ident: 10.1016/j.ymssp.2024.112136_b0030 article-title: A review of computer vision–based structural health monitoring at local and global levels publication-title: Struct. Health Monit. doi: 10.1177/1475921720935585 – ident: 10.1016/j.ymssp.2024.112136_b0140 – start-page: 1 year: 2020 ident: 10.1016/j.ymssp.2024.112136_b0210 article-title: Robust training of vector quantized bottleneck models – volume: 15 start-page: 555 year: 2015 ident: 10.1016/j.ymssp.2024.112136_b0070 article-title: Research and practice of health monitoring for long-span bridges in the mainland of China publication-title: Smart Struct. Syst. doi: 10.12989/sss.2015.15.3.555 – volume: 204 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0020 article-title: Vision-based multi-point real-time monitoring of dynamic displacement of large-span cable-stayed bridges publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2023.110790 – volume: 183 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0065 article-title: An enhanced method to reduce reconstruction error of compressed sensing for structure vibration signals publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2022.109585 – start-page: 55 year: 2002 ident: 10.1016/j.ymssp.2024.112136_b0230 article-title: Early stopping-but when?, Neural Networks: Tricks of the trade publication-title: Springer – ident: 10.1016/j.ymssp.2024.112136_b0215 – start-page: 3739 year: 2022 ident: 10.1016/j.ymssp.2024.112136_b0170 article-title: Pilc: Practical image lossless compression with an end-to-end gpu oriented neural framework – volume: 22 start-page: 433 year: 2015 ident: 10.1016/j.ymssp.2024.112136_b0105 article-title: Compressive sensing-based lost data recovery of fast-moving wireless sensing for structural health monitoring publication-title: Struct. Control Health Monit. doi: 10.1002/stc.1681 – volume: 36 start-page: 04021109 year: 2022 ident: 10.1016/j.ymssp.2024.112136_b0050 article-title: Detecting Hinge Joint Damage in Hollow Slab Bridges Using Mode Shapes Extracted from Vehicle Response publication-title: J. Perform. Constr. Facil doi: 10.1061/(ASCE)CF.1943-5509.0001694 – start-page: 1312.6114 year: 2013 ident: 10.1016/j.ymssp.2024.112136_b0185 – volume: 36 start-page: 04022012 year: 2022 ident: 10.1016/j.ymssp.2024.112136_b0010 article-title: Physical Distancing Analytics for Construction Planning Using 4D BIM publication-title: J. Comput. Civ. Eng. doi: 10.1061/(ASCE)CP.1943-5487.0001023 – ident: 10.1016/j.ymssp.2024.112136_b0175 doi: 10.1109/ICASSP.2019.8683277 – volume: 211 year: 2024 ident: 10.1016/j.ymssp.2024.112136_b0120 article-title: Deep learning-based sparsity-free compressive sensing method for high accuracy structural vibration response reconstruction publication-title: Mech. Syst. Sig. Process. doi: 10.1016/j.ymssp.2024.111168 – volume: 36 start-page: 81 year: 2019 ident: 10.1016/j.ymssp.2024.112136_b0110 article-title: Taking Compressive Sensing to the Hardware Level: Breaking Fundamental Radio-Frequency Hardware Performance Tradeoffs publication-title: IEEE Signal Process Mag. doi: 10.1109/MSP.2018.2880837 – start-page: 198 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0165 article-title: Lossy image compression with quantized hierarchical vaes – start-page: 14096 year: 2023 ident: 10.1016/j.ymssp.2024.112136_b0220 article-title: Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks publication-title: International Conference on Machine Learning, PMLR |
| SSID | ssj0009406 |
| Score | 2.459187 |
| Snippet | •The frequency enhanced vector quantized variational autoencoder (FEVQVAE) is proposed for structural vibration response compression.•The proposed dual-branch... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 112136 |
| SubjectTerms | Deep learning Structural health monitoring Vector quantized variational autoencoder Vibration response compression |
| Title | Frequency enhanced vector quantized variational autoencoder for structural vibration response compression |
| URI | https://dx.doi.org/10.1016/j.ymssp.2024.112136 |
| Volume | 224 |
| WOSCitedRecordID | wos001367741500001&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 issn: 0888-3270 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0009406 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3LbtQwFLWGKQu6QDzV8qi8YAepJs7LXo5QK6igYlGkYRXZjk1TtZ7RvNT267m2Y0-AakQXbKKRFXuinCPn-vrcY4TeyawQOWCdENE0tiRHJlwKnZC8EaUkmmaZKxT-Up2e0smEfRsMbkMtzPqyMoZeX7PZf4Ua2gBsWzp7D7jjoNAAvwF0uALscP0n4I_nXh19816Zc7-_v3apeVtAaZbtrW2AFXLIAvLVcmrdLK2phNUcekdZ58axtmtpR5C5l9IqJ0H30lnTj2u_KltB7EssvQe625Ww6hBb6uWrEcJXEvCdrPy2iE3nRHqO3Qz4Y2p-nq_amP1dOaK1Zha6dzkKUgRZc28qo0lG_BEhYd4lJO_NnKn1livvnNR9fuHi8OZqsbAWoyQ_3Nz9u4X2H5-2KDgMWraL2g1S20FqP8gDtEMqWFYN0c7489HkZGPZnLuTWeOzB88qpw7861nujmt6scrZE_S4W2TgsSfHUzRQ5hna7VlPPkdtpAkONMGeJjjSBPdogns0wUATvKEJjjTBgSa4R5MX6Pvx0dnHT0l37EYiIZ5ZJlryVKgq1VoqJpuR0o0WdjucpLxgKuUlzSSTFRspxgulIeRPOVUjXgnKC8Kzl2hopkbtIZxSRWlWKqVYmqdacKFZkWmZq5GEsKjYRyS8tFp2nvT2aJTLegtg--hD7DTzlizbby8DGnUXVfposQZ-bev46n7_8xo92lD_DRoCCuoteijXy3YxP-jI9Qvj8qOu |
| 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=Frequency+enhanced+vector+quantized+variational+autoencoder+for+structural+vibration+response+compression&rft.jtitle=Mechanical+systems+and+signal+processing&rft.au=Xue%2C+Zhilin&rft.au=An%2C+Yonghui&rft.au=Ou%2C+Jinping&rft.date=2025-02-01&rft.issn=0888-3270&rft.volume=224&rft.spage=112136&rft_id=info:doi/10.1016%2Fj.ymssp.2024.112136&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ymssp_2024_112136 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0888-3270&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0888-3270&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0888-3270&client=summon |