Optimizing LSTM with multi-strategy improved WOA for robust prediction of high-speed machine tests data
LSTM networks are popular for predicting data with nonlinear and temporal properties. However, it is difficult to select optimal hyperparameters using empirical methods, which can significantly affect their performance and modeling time. To address this, we propose a novel hybrid model called CMAL-W...
Uloženo v:
| Vydáno v: | Chaos, solitons and fractals Ročník 178; s. 114394 |
|---|---|
| Hlavní autoři: | , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Ltd
01.01.2024
|
| Témata: | |
| ISSN: | 0960-0779 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | LSTM networks are popular for predicting data with nonlinear and temporal properties. However, it is difficult to select optimal hyperparameters using empirical methods, which can significantly affect their performance and modeling time. To address this, we propose a novel hybrid model called CMAL-WOA-LSTM (CWLM), which utilizes the multi-strategy improved whale optimization algorithm (WOA) to optimize three key hyperparameters of LSTM. Four modifications are introduced to improve the performance of WOA. Circle chaotic map is used for population initialization, and a modified dynamic backward learning strategy improves population diversity. A nonlinear function optimizes iterations to allow global exploration and faster convergence. Lévy Flight updates of feasible solutions using random walks are carried out near the optimal value for each iteration. By conducting benchmarks and comparative analysis, we illustrate the effectiveness and rationale behind the four improvements. Subsequently, we explain our optimization ideas for constructing hybrid models, highlighting their distinctions from traditional deep learning approaches. Moreover, we provide detailed modeling steps for CWLM and elaborate on the relationships of each part within the model. CWLM is compared with five other models using milling force data and wear data from high-speed machine tests. Root Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, R-Squared, and computational time are used as error metrics. The results show that CWLM outperforms other models in terms of prediction performance and robustness. CWLM demonstrates improved prediction performance and robustness, making it applicable in a wide range of applications that use LSTM for data prediction.
•Improve WOA population diversity with chaotic map and modified backward learning•Optimize iterations and search ability with a new nonlinear function and Lévy Flight•Utilize hybrid multi-strategy enhanced WOA to optimize LSTM hyperparameters•Develop a novel prediction model to efficiently predict milling force and tool wear•Novel proposed model outperforms the other five popular models in three tests |
|---|---|
| AbstractList | LSTM networks are popular for predicting data with nonlinear and temporal properties. However, it is difficult to select optimal hyperparameters using empirical methods, which can significantly affect their performance and modeling time. To address this, we propose a novel hybrid model called CMAL-WOA-LSTM (CWLM), which utilizes the multi-strategy improved whale optimization algorithm (WOA) to optimize three key hyperparameters of LSTM. Four modifications are introduced to improve the performance of WOA. Circle chaotic map is used for population initialization, and a modified dynamic backward learning strategy improves population diversity. A nonlinear function optimizes iterations to allow global exploration and faster convergence. Lévy Flight updates of feasible solutions using random walks are carried out near the optimal value for each iteration. By conducting benchmarks and comparative analysis, we illustrate the effectiveness and rationale behind the four improvements. Subsequently, we explain our optimization ideas for constructing hybrid models, highlighting their distinctions from traditional deep learning approaches. Moreover, we provide detailed modeling steps for CWLM and elaborate on the relationships of each part within the model. CWLM is compared with five other models using milling force data and wear data from high-speed machine tests. Root Mean Square Error, Mean Absolute Error, Mean Absolute Percentage Error, R-Squared, and computational time are used as error metrics. The results show that CWLM outperforms other models in terms of prediction performance and robustness. CWLM demonstrates improved prediction performance and robustness, making it applicable in a wide range of applications that use LSTM for data prediction.
•Improve WOA population diversity with chaotic map and modified backward learning•Optimize iterations and search ability with a new nonlinear function and Lévy Flight•Utilize hybrid multi-strategy enhanced WOA to optimize LSTM hyperparameters•Develop a novel prediction model to efficiently predict milling force and tool wear•Novel proposed model outperforms the other five popular models in three tests |
| ArticleNumber | 114394 |
| Author | Che, Zhongyuan Peng, Chong Yue, Chenxiao |
| Author_xml | – sequence: 1 givenname: Zhongyuan orcidid: 0000-0002-8188-8050 surname: Che fullname: Che, Zhongyuan organization: School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China – sequence: 2 givenname: Chong orcidid: 0000-0003-4219-3827 surname: Peng fullname: Peng, Chong email: pch@buaa.edu.cn organization: School of Mechanical Engineering and Automation, Beihang University, Beijing 100191, China – sequence: 3 givenname: Chenxiao orcidid: 0009-0005-5048-6736 surname: Yue fullname: Yue, Chenxiao organization: School of Electronic Information Engineering, Beihang University, Beijing 100191, China |
| BookMark | eNqFkL1OwzAURj0UiRZ4Aha_QMp1nDpkYKgq_qSiDhQxWo59k7hq4sh2i8rTk1ImBpjucs8nnTMho851SMg1gykDJm42U90oF6YppHzKWMaLbETGUAhIIM-LczIJYQMADEQ6JvWqj7a1n7ar6fJ1_UI_bGxou9tGm4ToVcT6QG3be7dHQ99Xc1o5T70rdyHS3qOxOlrXUVfRxtZNEnoc_lqlG9shjRhioEZFdUnOKrUNePVzL8jbw_168ZQsV4_Pi_ky0Rx4THipU4NVCgxZmSPXWaZ1URk2y4W-RRikUhAZapiVqhKm4iLjQpmZgoIpzfgF4add7V0IHivZe9sqf5AM5LGP3MjvPvLYR576DFTxi9I2qqPYkMBu_2HvTiwOWnuLXgZtsdNDGo86SuPsn_wX39GILg |
| CitedBy_id | crossref_primary_10_1038_s41598_025_96941_4 crossref_primary_10_1016_j_eswa_2024_124556 crossref_primary_10_3390_s24227359 crossref_primary_10_3390_sym17081369 crossref_primary_10_1016_j_renene_2024_121992 crossref_primary_10_1016_j_aei_2025_103654 crossref_primary_10_1016_j_marpolbul_2025_118606 crossref_primary_10_1016_j_chaos_2025_116981 crossref_primary_10_1016_j_ijhydene_2024_09_229 crossref_primary_10_1016_j_rineng_2025_105984 crossref_primary_10_1016_j_ijepes_2025_110630 crossref_primary_10_1371_journal_pone_0316836 crossref_primary_10_1038_s41598_024_79059_x crossref_primary_10_3390_toxics13050327 crossref_primary_10_1149_2162_8777_ad6637 |
| Cites_doi | 10.1016/j.ejor.2012.02.042 10.1109/ACCESS.2021.3111408 10.1016/j.camwa.2017.10.022 10.1162/neco_a_01199 10.1038/nature11098 10.1016/j.apenergy.2019.113541 10.1016/j.swevo.2016.12.005 10.1103/PhysRevLett.58.1100 10.1109/TNNLS.2016.2582924 10.1007/s11269-022-03133-0 10.1109/TEVC.2012.2227145 10.1016/j.asoc.2019.105550 10.1109/TSG.2017.2753802 10.3390/app11052387 10.1155/2022/7498025 10.1016/j.eswa.2018.07.019 10.1007/s00170-021-07560-y 10.1155/2019/1934796 10.1002/for.2839 10.3390/en11113227 10.1890/06-1916.1 10.1016/j.apenergy.2019.04.047 10.1007/s00357-018-9261-2 10.3390/s22207900 10.1016/j.chaos.2020.110336 10.1109/ACCESS.2021.3083593 10.1073/pnas.1121201109 10.1109/ACCESS.2020.3006499 10.1016/j.advengsoft.2016.01.008 10.1016/j.energy.2021.120069 10.1016/j.chemosphere.2019.01.121 10.1162/neco.1997.9.8.1735 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.chaos.2023.114394 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Sciences (General) Mathematics |
| ExternalDocumentID | 10_1016_j_chaos_2023_114394 S0960077923012961 |
| GroupedDBID | --K --M -~X .~1 0R~ 1B1 1RT 1~. 1~5 29B 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN AABNK AACTN AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXKI AAXUO ABJNI ABMAC ABNEU ABTAH ABWVN ABXDB ACDAQ ACFVG ACGFS ACNNM ACRLP ACRPL ADBBV ADEZE ADMUD ADNMO AEBSH AEIPS AEKER AENEX AFFNX AFJKZ AFTJW AGHFR AGUBO AGYEJ AHHHB AIEXJ AIKHN AITUG AIVDX AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ASPBG AVWKF AXJTR AZFZN BBWZM BKOJK BLXMC CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA HLZ HMV HVGLF HZ~ IHE J1W KOM LG9 M38 M41 MO0 N9A NDZJH O-L O9- OAUVE OGIMB OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SBC SDF SDG SDP SES SEW SPC SPCBC SPD SPG SSQ SSZ T5K WUQ XPP ZY4 ~G- 9DU AATTM AAYWO AAYXX ACLOT ACVFH ADCNI AEUPX AFPUW AGQPQ AIGII AIIUN AKBMS AKYEP APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c303t-3bc2def201e1b7e3c44cc9fd1576c8e02022064ec05baf6df36436ad5a091ac13 |
| ISICitedReferencesCount | 22 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001146684700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0960-0779 |
| IngestDate | Tue Nov 18 22:25:32 EST 2025 Sat Nov 29 08:16:14 EST 2025 Sat Mar 08 15:49:02 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Long short-term memory Hyperparameter optimization Multi-strategy improved whale optimization algorithm Milling force prediction Tool wear prediction |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c303t-3bc2def201e1b7e3c44cc9fd1576c8e02022064ec05baf6df36436ad5a091ac13 |
| ORCID | 0009-0005-5048-6736 0000-0003-4219-3827 0000-0002-8188-8050 |
| ParticipantIDs | crossref_primary_10_1016_j_chaos_2023_114394 crossref_citationtrail_10_1016_j_chaos_2023_114394 elsevier_sciencedirect_doi_10_1016_j_chaos_2023_114394 |
| PublicationCentury | 2000 |
| PublicationDate | January 2024 2024-01-00 |
| PublicationDateYYYYMMDD | 2024-01-01 |
| PublicationDate_xml | – month: 01 year: 2024 text: January 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Chaos, solitons and fractals |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Humphries, Weimerskirch, Queiroz, Southall, Sims (bb0170) 2012; 109 Li, Chai, Zhang, Wang, Ma (bb0125) 2022; 2022 Ibrahim, Mirjalili, El-Said, Ghoneim, Al-Harthi, Ibrahim (bb0130) 2021; 9 Leccardi (bb0190) 2005; vol. ID Tizhoosh (bb0155) 2005; vol. 1 Greff, Srivastava, Koutnik, Steunebrink, Schmidhuber (bb0020) 2017; 28 Mockus, Tiesis, Zilinskas (bb0115) 2014 Mirjalili, Lewis (bb0140) 2016; 95 Bai, Zeng, Li, Zhang (bb0045) 2019; 222 Elsaraiti, Merabet (bb0010) 2021; 11 Goldberger, Hinton, Roweis, Salakhutdinov (bb0205) 2004 Reynolds, Smith, Menzel, Greggers, Reynolds, Riley (bb0165) 2007; 88 Li, Sun, Liu, Wang, Huang (bb0085) 2022; 36 Bergstra, Bengio (bb0110) 2012; 13 Baek, Kim (bb0040) 2018; 113 Harris, Banigan, Christian, Konradt, Tait Wojno, Norose (bb0185) 2012; 486 Sun, Qin, Przystupa, Majka, Kochan (bb0055) 2022; 22 Shahid, Zameer, Muneeb (bb0120) 2021; 223 Zhang, Ye, Qin, Liu, Wang, Yu (bb0035) 2019; 247 Schmidhuber, Cummins (bb0070) 1999 Shi, Lei, Huang, Huang, Ren, Hu (bb0015) 2018; 11 Pan, Zheng, Liu, Liu, Lin, Chen (bb0175) 2018; 75 Yu, Si, Hu, Zhang (bb0050) 2019; 31 Gao, Guo, Hanson, Liu, Wang, Zan (bb0075) 2021; 116 Sayed, Darwish, Hassanien (bb0150) 2018; 35 Ghimire, Deo, Raj, Mi (bb0030) 2019; 253 Yang, Li, Liu, Zheng (bb0105) 2013; 17 . 2010 PHM Society Conference Data Challenge Dataset. The Prognostics and Health Management Society (PHM Society). Ghoneim, Farrag, Rashed, El-Kenawy, Ibrahim (bb0135) 2021; 9 Pan, Jing, Jiao, Wang (bb0100) 2020; 8 Haupt, Haupt (bb0145) 2003 Cao, Ewing, Thompson (bb0005) 2012; 221 Mavrovouniotis, Li, Yang (bb0060) 2017; 33 Yuan, Chen, Jiang, Yuan (bb0195) 2019; 82 Shao, Li, Zhao, Bian (bb0080) 2019; 2019 Kong, Dong, Jia, Hill, Xu, Zhang (bb0025) 2019; 10 Hochreiter, Schmidhuber (bb0065) 1997; 9 Shlesinger, West, Klafter (bb0180) 1987; 58 Yang (bb0160) 2010 Jiao, Song, Kong, Tang (bb0095) 2022; 41 Prasanth, Singh, Kumar, Tikkiwal, Chong (bb0090) 2021; 142 Haupt (10.1016/j.chaos.2023.114394_bb0145) 2003 Li (10.1016/j.chaos.2023.114394_bb0085) 2022; 36 Jiao (10.1016/j.chaos.2023.114394_bb0095) 2022; 41 Yu (10.1016/j.chaos.2023.114394_bb0050) 2019; 31 Leccardi (10.1016/j.chaos.2023.114394_bb0190) 2005; vol. ID Ghoneim (10.1016/j.chaos.2023.114394_bb0135) 2021; 9 Yang (10.1016/j.chaos.2023.114394_bb0160) 2010 Sun (10.1016/j.chaos.2023.114394_bb0055) 2022; 22 Shi (10.1016/j.chaos.2023.114394_bb0015) 2018; 11 Gao (10.1016/j.chaos.2023.114394_bb0075) 2021; 116 Pan (10.1016/j.chaos.2023.114394_bb0100) 2020; 8 Hochreiter (10.1016/j.chaos.2023.114394_bb0065) 1997; 9 Pan (10.1016/j.chaos.2023.114394_bb0175) 2018; 75 Li (10.1016/j.chaos.2023.114394_bb0125) 2022; 2022 Harris (10.1016/j.chaos.2023.114394_bb0185) 2012; 486 10.1016/j.chaos.2023.114394_bb0200 Yang (10.1016/j.chaos.2023.114394_bb0105) 2013; 17 Ghimire (10.1016/j.chaos.2023.114394_bb0030) 2019; 253 Kong (10.1016/j.chaos.2023.114394_bb0025) 2019; 10 Reynolds (10.1016/j.chaos.2023.114394_bb0165) 2007; 88 Humphries (10.1016/j.chaos.2023.114394_bb0170) 2012; 109 Shahid (10.1016/j.chaos.2023.114394_bb0120) 2021; 223 Mockus (10.1016/j.chaos.2023.114394_bb0115) 2014 Prasanth (10.1016/j.chaos.2023.114394_bb0090) 2021; 142 Elsaraiti (10.1016/j.chaos.2023.114394_bb0010) 2021; 11 Mirjalili (10.1016/j.chaos.2023.114394_bb0140) 2016; 95 Shao (10.1016/j.chaos.2023.114394_bb0080) 2019; 2019 Zhang (10.1016/j.chaos.2023.114394_bb0035) 2019; 247 Greff (10.1016/j.chaos.2023.114394_bb0020) 2017; 28 Baek (10.1016/j.chaos.2023.114394_bb0040) 2018; 113 Bergstra (10.1016/j.chaos.2023.114394_bb0110) 2012; 13 Yuan (10.1016/j.chaos.2023.114394_bb0195) 2019; 82 Mavrovouniotis (10.1016/j.chaos.2023.114394_bb0060) 2017; 33 Shlesinger (10.1016/j.chaos.2023.114394_bb0180) 1987; 58 Goldberger (10.1016/j.chaos.2023.114394_bb0205) 2004 Bai (10.1016/j.chaos.2023.114394_bb0045) 2019; 222 Ibrahim (10.1016/j.chaos.2023.114394_bb0130) 2021; 9 Cao (10.1016/j.chaos.2023.114394_bb0005) 2012; 221 Tizhoosh (10.1016/j.chaos.2023.114394_bb0155) 2005; vol. 1 Schmidhuber (10.1016/j.chaos.2023.114394_bb0070) 1999 Sayed (10.1016/j.chaos.2023.114394_bb0150) 2018; 35 |
| References_xml | – volume: 223 year: 2021 ident: bb0120 article-title: A novel genetic LSTM model for wind power forecast publication-title: Energy – volume: 35 start-page: 300 year: 2018 end-page: 344 ident: bb0150 article-title: A new chaotic whale optimization algorithm for features selection publication-title: J Classif – start-page: 850 year: 1999 end-page: 855 ident: bb0070 article-title: Learning to forget: continual prediction with LSTM publication-title: International conference on artificial neural networks (ICANN) – volume: 109 start-page: 7169 year: 2012 end-page: 7174 ident: bb0170 article-title: Foraging success of biological Lévy flights recorded in situ publication-title: Proc Natl Acad Sci U S A – volume: 58 start-page: 1100 year: 1987 end-page: 1103 ident: bb0180 article-title: Lévy dynamics of enhanced diffusion: application to turbulence publication-title: Phys Rev Lett – volume: 221 start-page: 148 year: 2012 end-page: 154 ident: bb0005 article-title: Forecasting wind speed with recurrent neural networks publication-title: Eur J Oper Res – volume: 247 start-page: 270 year: 2019 end-page: 284 ident: bb0035 article-title: Wind speed prediction method using shared weight long short-term memory network and gaussian process regression publication-title: Appl Energy – volume: vol. ID start-page: 11 year: 2005 end-page: 091 ident: bb0190 article-title: Comparison of three algorithms for Lévy noise generation publication-title: 5th EUROMECH nonlinear oscillations conference (ENOC5) – volume: 9 start-page: 1735 year: 1997 end-page: 1780 ident: bb0065 article-title: Long short-term memory publication-title: Neural Comput – volume: 11 start-page: 3227 year: 2018 ident: bb0015 article-title: Hourly day-ahead wind power prediction using the hybrid model of variational model decomposition and long short-term memory publication-title: Energies – volume: 222 start-page: 286 year: 2019 end-page: 294 ident: bb0045 article-title: An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting publication-title: Chemosphere – volume: 82 year: 2019 ident: bb0195 article-title: Prediction interval of wind power using parameter optimized Beta distribution based LSTM model publication-title: Appl Soft Comput – volume: 11 start-page: 2387 year: 2021 ident: bb0010 article-title: Application of long-short-term-memory recurrent neural networks to forecast wind speed publication-title: Appl Sci – volume: 31 start-page: 1235 year: 2019 end-page: 1270 ident: bb0050 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Comput – volume: 9 start-page: 125787 year: 2021 end-page: 125804 ident: bb0130 article-title: Wind speed ensemble forecasting based on deep learning using adaptive dynamic optimization algorithm publication-title: IEEE Access – volume: 28 start-page: 2222 year: 2017 end-page: 2232 ident: bb0020 article-title: LSTM: a search space odyssey publication-title: IEEE Trans Neural Netw Learning Syst – year: 2010 ident: bb0160 article-title: Nature-inspired metaheuristic algorithms – volume: 253 year: 2019 ident: bb0030 article-title: Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms publication-title: Appl Energy – volume: 17 start-page: 721 year: 2013 end-page: 736 ident: bb0105 article-title: A grid-based evolutionary algorithm for many-objective optimization publication-title: IEEE Trans Evol Computat – volume: 88 start-page: 1955 year: 2007 end-page: 1961 ident: bb0165 article-title: Displaced honey bees perform optimal scale-free search flights publication-title: Ecology – volume: 33 start-page: 1 year: 2017 end-page: 17 ident: bb0060 article-title: A survey of swarm intelligence for dynamic optimization: algorithms and applications publication-title: Swarm Evol – volume: 9 start-page: 78324 year: 2021 end-page: 78340 ident: bb0135 article-title: Adaptive dynamic meta-heuristics for feature selection and classification in diagnostic accuracy of transformer faults publication-title: IEEE Access – volume: 10 start-page: 841 year: 2019 end-page: 851 ident: bb0025 article-title: Short-term residential load forecasting based on LSTM recurrent neural network publication-title: IEEE Trans Smart Grid – volume: 2022 start-page: 1 year: 2022 end-page: 10 ident: bb0125 article-title: Prediction model of ischemic stroke recurrence using PSO-LSTM in mobile medical monitoring system publication-title: Comput Intell Neurosci – volume: vol. 1 start-page: 695 year: 2005 end-page: 701 ident: bb0155 article-title: Opposition-based learning: a new scheme for machine intelligence publication-title: International conference on computational intelligence for modelling, control and automation and international conference on intelligent agents, web technologies and internet commerce (CIMCA-IAWTIC’06) – volume: 95 start-page: 51 year: 2016 end-page: 67 ident: bb0140 article-title: The whale optimization algorithm publication-title: Adv Eng Softw – volume: 116 start-page: 1721 year: 2021 end-page: 1735 ident: bb0075 article-title: Thermal error prediction of ball screws based on PSO-LSTM publication-title: Int J Adv Manuf Technol – reference: . – volume: 8 start-page: 121460 year: 2020 end-page: 121468 ident: bb0100 article-title: Analysis and application of grey wolf optimizer-long short-term memory publication-title: IEEE Access – volume: 2019 start-page: 1 year: 2019 end-page: 15 ident: bb0080 article-title: Nickel price forecast based on the LSTM neural network optimized by the improved PSO algorithm publication-title: Math Probl Eng – year: 2003 ident: bb0145 article-title: Practical genetic algorithms – volume: 75 start-page: 1226 year: 2018 end-page: 1236 ident: bb0175 article-title: A stochastic model for thermal transport of nanofluid in porous media: derivation and applications publication-title: Comput Math Appl – start-page: 513 year: 2004 end-page: 520 ident: bb0205 article-title: Neighbourhood components analysis publication-title: 17th international conference on neural information processing systems (ICNIPS) – volume: 142 year: 2021 ident: bb0090 article-title: Forecasting spread of COVID-19 using google trends: a hybrid GWO-deep learning approach publication-title: Chaos Solitons Fractals – volume: 41 start-page: 933 year: 2022 end-page: 944 ident: bb0095 article-title: Volatility forecasting for crude oil based on text information and deep learning PSO-LSTM model publication-title: J Forecast – volume: 486 start-page: 545 year: 2012 end-page: 548 ident: bb0185 article-title: Generalized Lévy walks and the role of chemokines in migration of effector CD8+ T cells publication-title: Nature – volume: 22 start-page: 7900 year: 2022 ident: bb0055 article-title: Individualized short-term electric load forecasting using data-driven meta-heuristic method based on LSTM network publication-title: Sensors – volume: 113 start-page: 457 year: 2018 end-page: 480 ident: bb0040 article-title: ModAugNet: a new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module publication-title: Expert Syst Appl – start-page: 117 year: 2014 end-page: 129 ident: bb0115 article-title: The application of Bayesian methods for seeking the extremum publication-title: In book: towards global optimisation 2, North-Holand – reference: 2010 PHM Society Conference Data Challenge Dataset. The Prognostics and Health Management Society (PHM Society). – volume: 13 start-page: 281 year: 2012 end-page: 305 ident: bb0110 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res – volume: 36 start-page: 2095 year: 2022 end-page: 2115 ident: bb0085 article-title: Monthly runoff forecasting using variational mode decomposition coupled with gray wolf optimizer-based long short-term memory neural networks publication-title: Water Resour Manage – volume: 221 start-page: 148 year: 2012 ident: 10.1016/j.chaos.2023.114394_bb0005 article-title: Forecasting wind speed with recurrent neural networks publication-title: Eur J Oper Res doi: 10.1016/j.ejor.2012.02.042 – volume: 9 start-page: 125787 year: 2021 ident: 10.1016/j.chaos.2023.114394_bb0130 article-title: Wind speed ensemble forecasting based on deep learning using adaptive dynamic optimization algorithm publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3111408 – volume: 75 start-page: 1226 year: 2018 ident: 10.1016/j.chaos.2023.114394_bb0175 article-title: A stochastic model for thermal transport of nanofluid in porous media: derivation and applications publication-title: Comput Math Appl doi: 10.1016/j.camwa.2017.10.022 – ident: 10.1016/j.chaos.2023.114394_bb0200 – volume: 31 start-page: 1235 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0050 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Comput doi: 10.1162/neco_a_01199 – volume: vol. ID start-page: 11 year: 2005 ident: 10.1016/j.chaos.2023.114394_bb0190 article-title: Comparison of three algorithms for Lévy noise generation – volume: 486 start-page: 545 year: 2012 ident: 10.1016/j.chaos.2023.114394_bb0185 article-title: Generalized Lévy walks and the role of chemokines in migration of effector CD8+ T cells publication-title: Nature doi: 10.1038/nature11098 – volume: 253 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0030 article-title: Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms publication-title: Appl Energy doi: 10.1016/j.apenergy.2019.113541 – volume: 33 start-page: 1 year: 2017 ident: 10.1016/j.chaos.2023.114394_bb0060 article-title: A survey of swarm intelligence for dynamic optimization: algorithms and applications publication-title: Swarm Evol doi: 10.1016/j.swevo.2016.12.005 – volume: 58 start-page: 1100 year: 1987 ident: 10.1016/j.chaos.2023.114394_bb0180 article-title: Lévy dynamics of enhanced diffusion: application to turbulence publication-title: Phys Rev Lett doi: 10.1103/PhysRevLett.58.1100 – volume: 28 start-page: 2222 year: 2017 ident: 10.1016/j.chaos.2023.114394_bb0020 article-title: LSTM: a search space odyssey publication-title: IEEE Trans Neural Netw Learning Syst doi: 10.1109/TNNLS.2016.2582924 – year: 2003 ident: 10.1016/j.chaos.2023.114394_bb0145 – volume: 36 start-page: 2095 year: 2022 ident: 10.1016/j.chaos.2023.114394_bb0085 article-title: Monthly runoff forecasting using variational mode decomposition coupled with gray wolf optimizer-based long short-term memory neural networks publication-title: Water Resour Manage doi: 10.1007/s11269-022-03133-0 – volume: 17 start-page: 721 year: 2013 ident: 10.1016/j.chaos.2023.114394_bb0105 article-title: A grid-based evolutionary algorithm for many-objective optimization publication-title: IEEE Trans Evol Computat doi: 10.1109/TEVC.2012.2227145 – volume: 82 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0195 article-title: Prediction interval of wind power using parameter optimized Beta distribution based LSTM model publication-title: Appl Soft Comput doi: 10.1016/j.asoc.2019.105550 – volume: 10 start-page: 841 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0025 article-title: Short-term residential load forecasting based on LSTM recurrent neural network publication-title: IEEE Trans Smart Grid doi: 10.1109/TSG.2017.2753802 – volume: 11 start-page: 2387 year: 2021 ident: 10.1016/j.chaos.2023.114394_bb0010 article-title: Application of long-short-term-memory recurrent neural networks to forecast wind speed publication-title: Appl Sci doi: 10.3390/app11052387 – volume: 2022 start-page: 1 year: 2022 ident: 10.1016/j.chaos.2023.114394_bb0125 article-title: Prediction model of ischemic stroke recurrence using PSO-LSTM in mobile medical monitoring system publication-title: Comput Intell Neurosci doi: 10.1155/2022/7498025 – start-page: 850 year: 1999 ident: 10.1016/j.chaos.2023.114394_bb0070 article-title: Learning to forget: continual prediction with LSTM – volume: 113 start-page: 457 year: 2018 ident: 10.1016/j.chaos.2023.114394_bb0040 article-title: ModAugNet: a new forecasting framework for stock market index value with an overfitting prevention LSTM module and a prediction LSTM module publication-title: Expert Syst Appl doi: 10.1016/j.eswa.2018.07.019 – volume: 116 start-page: 1721 year: 2021 ident: 10.1016/j.chaos.2023.114394_bb0075 article-title: Thermal error prediction of ball screws based on PSO-LSTM publication-title: Int J Adv Manuf Technol doi: 10.1007/s00170-021-07560-y – volume: 2019 start-page: 1 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0080 article-title: Nickel price forecast based on the LSTM neural network optimized by the improved PSO algorithm publication-title: Math Probl Eng doi: 10.1155/2019/1934796 – volume: 41 start-page: 933 year: 2022 ident: 10.1016/j.chaos.2023.114394_bb0095 article-title: Volatility forecasting for crude oil based on text information and deep learning PSO-LSTM model publication-title: J Forecast doi: 10.1002/for.2839 – volume: 11 start-page: 3227 year: 2018 ident: 10.1016/j.chaos.2023.114394_bb0015 article-title: Hourly day-ahead wind power prediction using the hybrid model of variational model decomposition and long short-term memory publication-title: Energies doi: 10.3390/en11113227 – volume: 88 start-page: 1955 year: 2007 ident: 10.1016/j.chaos.2023.114394_bb0165 article-title: Displaced honey bees perform optimal scale-free search flights publication-title: Ecology doi: 10.1890/06-1916.1 – volume: 247 start-page: 270 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0035 article-title: Wind speed prediction method using shared weight long short-term memory network and gaussian process regression publication-title: Appl Energy doi: 10.1016/j.apenergy.2019.04.047 – volume: 35 start-page: 300 year: 2018 ident: 10.1016/j.chaos.2023.114394_bb0150 article-title: A new chaotic whale optimization algorithm for features selection publication-title: J Classif doi: 10.1007/s00357-018-9261-2 – volume: 22 start-page: 7900 year: 2022 ident: 10.1016/j.chaos.2023.114394_bb0055 article-title: Individualized short-term electric load forecasting using data-driven meta-heuristic method based on LSTM network publication-title: Sensors doi: 10.3390/s22207900 – volume: 142 year: 2021 ident: 10.1016/j.chaos.2023.114394_bb0090 article-title: Forecasting spread of COVID-19 using google trends: a hybrid GWO-deep learning approach publication-title: Chaos Solitons Fractals doi: 10.1016/j.chaos.2020.110336 – volume: vol. 1 start-page: 695 year: 2005 ident: 10.1016/j.chaos.2023.114394_bb0155 article-title: Opposition-based learning: a new scheme for machine intelligence – volume: 9 start-page: 78324 year: 2021 ident: 10.1016/j.chaos.2023.114394_bb0135 article-title: Adaptive dynamic meta-heuristics for feature selection and classification in diagnostic accuracy of transformer faults publication-title: IEEE Access doi: 10.1109/ACCESS.2021.3083593 – volume: 109 start-page: 7169 year: 2012 ident: 10.1016/j.chaos.2023.114394_bb0170 article-title: Foraging success of biological Lévy flights recorded in situ publication-title: Proc Natl Acad Sci U S A doi: 10.1073/pnas.1121201109 – start-page: 513 year: 2004 ident: 10.1016/j.chaos.2023.114394_bb0205 article-title: Neighbourhood components analysis – volume: 8 start-page: 121460 year: 2020 ident: 10.1016/j.chaos.2023.114394_bb0100 article-title: Analysis and application of grey wolf optimizer-long short-term memory publication-title: IEEE Access doi: 10.1109/ACCESS.2020.3006499 – volume: 95 start-page: 51 year: 2016 ident: 10.1016/j.chaos.2023.114394_bb0140 article-title: The whale optimization algorithm publication-title: Adv Eng Softw doi: 10.1016/j.advengsoft.2016.01.008 – start-page: 117 year: 2014 ident: 10.1016/j.chaos.2023.114394_bb0115 article-title: The application of Bayesian methods for seeking the extremum – year: 2010 ident: 10.1016/j.chaos.2023.114394_bb0160 – volume: 13 start-page: 281 year: 2012 ident: 10.1016/j.chaos.2023.114394_bb0110 article-title: Random search for hyper-parameter optimization publication-title: J Mach Learn Res – volume: 223 year: 2021 ident: 10.1016/j.chaos.2023.114394_bb0120 article-title: A novel genetic LSTM model for wind power forecast publication-title: Energy doi: 10.1016/j.energy.2021.120069 – volume: 222 start-page: 286 year: 2019 ident: 10.1016/j.chaos.2023.114394_bb0045 article-title: An ensemble long short-term memory neural network for hourly PM2.5 concentration forecasting publication-title: Chemosphere doi: 10.1016/j.chemosphere.2019.01.121 – volume: 9 start-page: 1735 year: 1997 ident: 10.1016/j.chaos.2023.114394_bb0065 article-title: Long short-term memory publication-title: Neural Comput doi: 10.1162/neco.1997.9.8.1735 |
| SSID | ssj0001062 |
| Score | 2.5175385 |
| Snippet | LSTM networks are popular for predicting data with nonlinear and temporal properties. However, it is difficult to select optimal hyperparameters using... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 114394 |
| SubjectTerms | Hyperparameter optimization Long short-term memory Milling force prediction Multi-strategy improved whale optimization algorithm Tool wear prediction |
| Title | Optimizing LSTM with multi-strategy improved WOA for robust prediction of high-speed machine tests data |
| URI | https://dx.doi.org/10.1016/j.chaos.2023.114394 |
| Volume | 178 |
| WOSCitedRecordID | wos001146684700001&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: 0960-0779 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0001062 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwELfQxgM8IDZAbMDkBx5AxVObOF-PVTW0TexDWoG-RYntrJ22pGrSqeOv5852nLGhCZB4iaq0dlvfT3e_u9wHIe_B5oPh4YpFWZAznnk-i6WKGM99FQcyLqTOJvz2JTo-jieT5NRWXNd6nEBUlvFqlcz_q6jhHggbS2f_QtxuU7gBr0HocAWxw_WPBH8CSuBq9kNXL52Nj0ykVecNstq0or3B2shFdQ1c8_vJUCcaLqp8WTfYMUDOhCOR4Lizeg72rXelcy5VD4hpU_dsQVvX4mCamWy9GrPpMPkGw_EFFmBll460j6bmUci0Ks9vlh0qT5XRNyN8w2mhpUlRnKpyNcuq28EJj98JTriqmS5FSYcewz7rR2aIjNPCZpLPPY1uggsXuwL_yS4Oe8f2xr6ZjHynVfYZ7owbg18FPAa94nUvChLQduvDg73JobPR4Ajr50vtL2n7UenMv3tf9XvOcouHjJ-TZ9aBoEMj-A3ySJWb5OmR675bb5INq7Br-sF2Ff_4gpx3uKCIC4q4oL_igra4oIALCrigBhe0wwWtCtrhglpcUI0Lirh4Sb5-3huP9pmdssEE0JeG-bnwpCqACKpBHilfcC5EUsgBeKIiVuBOeB7wViX6QZ4VoSx8ILFhJoMMqGYmBv4rslZWpXpNKBjOBNiPVAmPOfdUnIQ85AJ89iDnkS-3iNeeYypsC3qchHKZtrmGF6k-_BQPPzWHv0U-uUVz04Hl4Y-HrYBSSyINOUwBUQ8t3P7XhW_Ikw76b8las1iqd-SxuG5m9WLHIu8nr9uYdQ |
| 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=Optimizing+LSTM+with+multi-strategy+improved+WOA+for+robust+prediction+of+high-speed+machine+tests+data&rft.jtitle=Chaos%2C+solitons+and+fractals&rft.au=Che%2C+Zhongyuan&rft.au=Peng%2C+Chong&rft.au=Yue%2C+Chenxiao&rft.date=2024-01-01&rft.pub=Elsevier+Ltd&rft.issn=0960-0779&rft.volume=178&rft_id=info:doi/10.1016%2Fj.chaos.2023.114394&rft.externalDocID=S0960077923012961 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0960-0779&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0960-0779&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0960-0779&client=summon |