{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T03:57:25Z","timestamp":1777694245103,"version":"3.51.4"},"reference-count":63,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2023,3,15]],"date-time":"2023-03-15T00:00:00Z","timestamp":1678838400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["ICA"],"published-print":{"date-parts":[[2023,3,15]]},"abstract":"<jats:p>Various system identification (SI) techniques have been developed to ensure the sufficient structural performance of buildings. Recently, attempts have been made to solve the problem of the excessive computational time required for operational modal analysis (OMA), which is involved in SI, by using the deep learning (DL) algorithm and to overcome the limited applicability to structural problems of extended Kalman filter (EKF)-based SI technology through the development of a method enabling SI under unknown input conditions by adding a term for the input load to the algorithm. Although DL-based OMA methods and EKF-based SI techniques under unknown input conditions are being developed in various forms, they still produce incomplete identification processes when extracting the identification parameters. The neural network of the developed DL-based OMA method fails to extract all modal parameters perfectly, and EKF-based SI techniques has the limitations of a heavy algorithm and an increased computational burden with an input load term added to the algorithm. Therefore, this study proposes an EKF-based long short-term memory (EKF-LSTM) method that can identify modal parameters. The proposed EKF-LSTM method applies modal-expanded dynamic governing equations to the EKF to identify the modal parameters, where the input load used in the EKF algorithm is estimated using the LSTM method. The EKF-LSTM method can identify all modal parameters using the EKF, which is highly applicable to structural problems. Because the proposed method estimates the input load through an already trained LSTM network, there is no problem with computational burden when estimating the input load. The proposed EKF-LSTM method was verified using a numerical model with three degrees of freedom, and its effectiveness was confirmed by utilizing a steel frame structure model with three floors.<\/jats:p>","DOI":"10.3233\/ica-220696","type":"journal-article","created":{"date-parts":[[2022,11,15]],"date-time":"2022-11-15T11:39:55Z","timestamp":1668512395000},"page":"185-201","source":"Crossref","is-referenced-by-count":13,"title":["Modal identification of building structures under unknown input conditions using extended Kalman filter and long-short term memory"],"prefix":"10.1177","volume":"30","author":[{"given":"Da Yo","family":"Yun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyo Seon","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/ICA-220696_ref1","doi-asserted-by":"crossref","first-page":"106790","DOI":"10.1016\/j.compstruc.2022.106790","article-title":"SHM under varying environmental conditions: an approach based on model order reduction and deep learning","volume":"266","author":"Torzoni","year":"2022","journal-title":"Comput Struct"},{"key":"10.3233\/ICA-220696_ref2","doi-asserted-by":"crossref","first-page":"106741","DOI":"10.1016\/j.compstruc.2022.106741","article-title":"Frequency identification based on power spectral density transmissibility under unknown colored noise excitation","volume":"263","author":"Luo","year":"2022","journal-title":"Comput Struct"},{"issue":"8","key":"10.3233\/ICA-220696_ref3","doi-asserted-by":"crossref","first-page":"870","DOI":"10.1111\/mice.12552","article-title":"On-line system identification of structures using wavelet-Hilbert transform and sparse component analysis","volume":"35","author":"Karami","year":"2020","journal-title":"Comput Civ Infrastruct Eng"},{"key":"10.3233\/ICA-220696_ref4","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.autcon.2017.10.025","article-title":"Real-time structural health monitoring of a supertall building under construction based on visual modal identification strategy","volume":"85","author":"Park","year":"2018","journal-title":"Autom Constr"},{"issue":"1","key":"10.3233\/ICA-220696_ref5","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1111\/mice.12229","article-title":"Modal Response-Based Visual System Identification and Model Updating Methods for Building Structures","volume":"32","author":"Oh","year":"2017","journal-title":"Comput Civ Infrastruct Eng"},{"issue":"3","key":"10.3233\/ICA-220696_ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1002\/tal.1312","article-title":"New method for modal identification of super high-rise building structures using discretized synchrosqueezed wavelet and Hilbert transforms","volume":"26","author":"Li","year":"2017","journal-title":"Struct Des Tall Spec Build"},{"key":"10.3233\/ICA-220696_ref7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.engappai.2015.10.005","article-title":"New methodology for modal parameters identification of smart civil structures using ambient vibrations and synchrosqueezed wavelet transform","volume":"48","author":"Perez-Ramirez","year":"2016","journal-title":"Eng Appl Artif Intell"},{"key":"10.3233\/ICA-220696_ref8","doi-asserted-by":"crossref","unstructured":"Sirca GF, Adeli H. System identification in structural engineering. Vol. 19, Scientia Iranica, 2012.","DOI":"10.1016\/j.scient.2012.09.002"},{"issue":"1","key":"10.3233\/ICA-220696_ref9","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1061\/(ASCE)0733-9445(2006)132:1(102)","article-title":"Dynamic fuzzy wavelet neural network model for structural system identification","volume":"132","author":"Adeli","year":"2006","journal-title":"J Struct Eng"},{"key":"10.3233\/ICA-220696_ref10","doi-asserted-by":"crossref","unstructured":"Jiang X, Adeli H. Dynamic wavelet neural network for nonlinear identification of highrise buildings. Comput Civ Infrastruct Eng. 2005; 20(5).","DOI":"10.1111\/j.1467-8667.2005.00399.x"},{"key":"10.3233\/ICA-220696_ref11","doi-asserted-by":"crossref","first-page":"104373","DOI":"10.1016\/j.jobe.2022.104373","article-title":"Modal identification of high-rise buildings under earthquake excitations via an improved subspace methodology","volume":"52","author":"Zhou","year":"2022","journal-title":"J Build Eng"},{"key":"10.3233\/ICA-220696_ref12","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1016\/j.jobe.2018.08.017","article-title":"Modal analysis related safety-state evaluation of hidden frame supported glass curtain wall","volume":"20","author":"Huang","year":"2018","journal-title":"J Build Eng"},{"key":"10.3233\/ICA-220696_ref13","doi-asserted-by":"crossref","first-page":"104411","DOI":"10.1016\/j.jobe.2022.104411","article-title":"Statistical analysis of the modal properties of a seismically-damaged five-story RC building identified using ambient vibration data","volume":"52","author":"Astroza","year":"2022","journal-title":"J Build Eng"},{"key":"10.3233\/ICA-220696_ref14","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1016\/j.compstruct.2014.09.005","article-title":"A novel viscoelastic damping treatment for honeycomb sandwich structures","volume":"119","author":"Aumjaud","year":"2015","journal-title":"Compos Struct"},{"key":"10.3233\/ICA-220696_ref15","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1016\/j.compstruc.2018.10.013","article-title":"A parametric model order reduction technique for inverse viscoelastic material identification","volume":"212","author":"Xie","year":"2019","journal-title":"Comput Struct"},{"key":"10.3233\/ICA-220696_ref16","doi-asserted-by":"crossref","first-page":"106331","DOI":"10.1016\/j.compstruc.2020.106331","article-title":"Topology optimization of composite material with high broadband damping","volume":"239","author":"Zhang","year":"2020","journal-title":"Comput Struct"},{"key":"10.3233\/ICA-220696_ref17","doi-asserted-by":"crossref","first-page":"106651","DOI":"10.1016\/j.compstruc.2021.106651","article-title":"A reduced modal subspace approach for damped stochastic dynamic systems","volume":"257","author":"Kasinos","year":"2021","journal-title":"Comput Struct"},{"key":"10.3233\/ICA-220696_ref18","first-page":"5","article-title":"Damping estimation by frequency domain decomposition","author":"Brincker","year":"2001","journal-title":"Proceedings of the International Modal Analysis Conference \u2013 IMAC"},{"issue":"6","key":"10.3233\/ICA-220696_ref19","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1006\/mssp.1999.1249","article-title":"Reference-based stochastic subspace identification for output-only modal analysis","volume":"13","author":"Peeters","year":"1999","journal-title":"Mech Syst Signal Process"},{"issue":"4","key":"10.3233\/ICA-220696_ref20","doi-asserted-by":"crossref","first-page":"659","DOI":"10.1115\/1.1410370","article-title":"Stochastic System Identification for Operational Modal Analysis: A Review","volume":"123","author":"Peeters","year":"2001","journal-title":"J Dyn Syst Meas Control"},{"key":"10.3233\/ICA-220696_ref21","doi-asserted-by":"crossref","first-page":"103372","DOI":"10.1016\/j.jobe.2021.103372","article-title":"Maximum drift estimation based on only one accelerometer for damaged shear structures with unknown parameters","volume":"46","author":"Xu","year":"2022","journal-title":"J Build Eng"},{"key":"10.3233\/ICA-220696_ref22","doi-asserted-by":"crossref","first-page":"101639","DOI":"10.1016\/j.jobe.2020.101639","article-title":"Parameter estimation of resistor-capacitor models for building thermal dynamics using the unscented Kalman filter","volume":"34","author":"Chen","year":"2021","journal-title":"J Build Eng"},{"key":"10.3233\/ICA-220696_ref23","first-page":"1","article-title":"Sensor fault detection, localization, and reconstruction for online structural identification","author":"Huang","year":"2022","journal-title":"Struct Control Heal Monit"},{"key":"10.3233\/ICA-220696_ref24","doi-asserted-by":"crossref","unstructured":"Hu Z, Gallacher B. Extended Kalman filtering based parameter estimation and drift compensation for a MEMS rate integrating gyroscope. Sensors Actuators A Phys, 2016; 250.","DOI":"10.1016\/j.sna.2016.09.019"},{"key":"10.3233\/ICA-220696_ref25","doi-asserted-by":"crossref","unstructured":"Li H, Mao CX, Ou JP. Identification of Hysteretic Dynamic Systems by Using Hybrid Extended Kalman Filter and Wavelet Multiresolution Analysis with Limited Observation. J Eng Mech. 2013; 139(5).","DOI":"10.1061\/(ASCE)EM.1943-7889.0000510"},{"issue":"4","key":"10.3233\/ICA-220696_ref26","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1177\/1369433220963733","article-title":"A new physical parameter identification method for shear frame structures under limited inputs and outputs","volume":"24","author":"Liu","year":"2021","journal-title":"Adv Struct Eng"},{"key":"10.3233\/ICA-220696_ref27","doi-asserted-by":"crossref","unstructured":"Lei Y, Qiu H, Zhang F. Identification of structural element mass and stiffness changes using partial acceleration responses of chain-like systems under ambient excitations. J Sound Vib. 2020; 488.","DOI":"10.1016\/j.jsv.2020.115678"},{"issue":"12","key":"10.3233\/ICA-220696_ref28","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1061\/(ASCE)0733-9399(1984)110:12(1757)","article-title":"Structural identification by extended Kalman filter","volume":"110","author":"Hoshiya","year":"1984","journal-title":"J Eng Mech"},{"issue":"12","key":"10.3233\/ICA-220696_ref29","doi-asserted-by":"crossref","first-page":"966","DOI":"10.1111\/mice.12241","article-title":"Identification of Wind Loads and Estimation of Structural Responses of Super-Tall Buildings by an Inverse Method","volume":"31","author":"Zhi","year":"2016","journal-title":"Comput Civ Infrastruct Eng"},{"issue":"1","key":"10.3233\/ICA-220696_ref30","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1109\/TVT.2012.2222684","article-title":"Evaluation on State of Charge estimation of batteries with adaptive extended kalman filter by experiment approach","volume":"62","author":"Xiong","year":"2013","journal-title":"IEEE Trans Veh Technol"},{"issue":"4","key":"10.3233\/ICA-220696_ref31","doi-asserted-by":"crossref","first-page":"757","DOI":"10.1016\/0045-7949(94)90357-3","article-title":"Nonlinear structural identification using extended kalman filter","volume":"52","author":"Jeen-Shang","year":"1994","journal-title":"Comput Struct"},{"key":"10.3233\/ICA-220696_ref32","doi-asserted-by":"crossref","first-page":"106837","DOI":"10.1016\/j.ymssp.2020.106837","article-title":"Adaptive Kalman filters for nonlinear finite element model updating","volume":"143","author":"Song","year":"2020","journal-title":"Mech Syst Signal Process"},{"issue":"2","key":"10.3233\/ICA-220696_ref33","doi-asserted-by":"crossref","first-page":"154","DOI":"10.1504\/IJSTRUCTE.2018.093043","article-title":"Nonlinear system identification from noisy measurements","volume":"9","author":"Al-Hussein","year":"2018","journal-title":"Int J Struct Eng"},{"issue":"5","key":"10.3233\/ICA-220696_ref34","first-page":"774","article-title":"Identification of multistory shear buildings under unknown earthquake excitation using partial output measurements: Numerical and experimental studies","volume":"21","author":"Lei","year":"2014","journal-title":"Struct Control Heal Monit"},{"issue":"7","key":"10.3233\/ICA-220696_ref35","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1002\/stc.186","article-title":"Application of the unscented Kalman filter for real-time nonlinear structural system identification","volume":"14","author":"Meiliang","year":"2007","journal-title":"Struct Control Heal Monit"},{"key":"10.3233\/ICA-220696_ref36","doi-asserted-by":"crossref","unstructured":"Roveda L, Piga D. Sensorless environment stiffness and interaction force estimation for impedance control tuning in robotized interaction tasks. Auton Robots. 2021; 45(3).","DOI":"10.1007\/s10514-021-09970-z"},{"key":"10.3233\/ICA-220696_ref37","doi-asserted-by":"crossref","unstructured":"Zhang C, Gao YW, Huang JP, Huang JZ, Song GQ. Damage identification in bridge structures subject to moving vehicle based on extended Kalman filter with l1-norm regularization. Inverse Probl Sci Eng. 2020; 28(2).","DOI":"10.1080\/17415977.2019.1582650"},{"issue":"2","key":"10.3233\/ICA-220696_ref38","doi-asserted-by":"crossref","first-page":"594","DOI":"10.1109\/TAC.2017.2730480","article-title":"A Novel Adaptive Kalman Filter with Inaccurate Process and Measurement Noise Covariance Matrices","volume":"63","author":"Huang","year":"2018","journal-title":"IEEE Trans Automat Contr"},{"key":"10.3233\/ICA-220696_ref39","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.neucom.2016.10.026","article-title":"An adaptive Kalman filter estimating process noise covariance","volume":"223","author":"Wang","year":"2017","journal-title":"Neurocomputing"},{"issue":"1-2","key":"10.3233\/ICA-220696_ref40","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1016\/j.ymssp.2014.04.009","article-title":"An adaptive unscented Kalman filter for tracking sudden stiffness changes","volume":"49","author":"Bisht","year":"2014","journal-title":"Mech Syst Signal Process"},{"issue":"3","key":"10.3233\/ICA-220696_ref41","doi-asserted-by":"crossref","first-page":"391","DOI":"10.1080\/10168664.2020.1797614","article-title":"Structural Damage Identification with a Tuning-free Hybrid Extended Kalman Filter","volume":"31","author":"Yun","year":"2021","journal-title":"Struct Eng Int"},{"issue":"12","key":"10.3233\/ICA-220696_ref42","doi-asserted-by":"crossref","first-page":"1064","DOI":"10.1111\/mice.12310","article-title":"Modal Identification for High-Rise Building Structures Using Orthogonality of Filtered Response Vectors","volume":"32","author":"Kim","year":"2017","journal-title":"Comput Civ Infrastruct Eng"},{"issue":"3","key":"10.3233\/ICA-220696_ref43","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1002\/stc.171","article-title":"An adaptive extended Kalman filter for structural damage identifications II: Unknown inputs","volume":"14","author":"Yang","year":"2007","journal-title":"Struct Control Heal Monit"},{"issue":"7","key":"10.3233\/ICA-220696_ref44","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1111\/mice.12012","article-title":"A two-step model updating algorithm for parameter identification of linear elastic damped structures","volume":"28","author":"Garc\u00eda-Palencia","year":"2013","journal-title":"Comput Civ Infrastruct Eng"},{"key":"10.3233\/ICA-220696_ref45","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.engstruct.2015.11.014","article-title":"A general extended Kalman filter for simultaneous estimation of system and unknown inputs","volume":"109","author":"Pan","year":"2016","journal-title":"Eng Struct"},{"key":"10.3233\/ICA-220696_ref46","doi-asserted-by":"crossref","first-page":"103446","DOI":"10.1016\/j.autcon.2020.103446","article-title":"Field measurements for identification of modal parameters for high-rise buildings under construction or in use","volume":"121","author":"Yun","year":"2021","journal-title":"Autom Constr"},{"issue":"4","key":"10.3233\/ICA-220696_ref47","doi-asserted-by":"crossref","first-page":"849","DOI":"10.1002\/stc.84","article-title":"An adaptive extended Kalman filter for structural damage identification","volume":"13","author":"Yang","year":"2006","journal-title":"Struct Control Heal Monit"},{"issue":"1","key":"10.3233\/ICA-220696_ref48","doi-asserted-by":"crossref","first-page":"156","DOI":"10.1002\/stc.1764","article-title":"Unscented Kalman filter with unknown input and weighted global iteration for health assessment of large structural systems","volume":"23","author":"Al-Hussein","year":"2016","journal-title":"Struct Control Heal Monit"},{"issue":"11","key":"10.3233\/ICA-220696_ref49","first-page":"e2436","article-title":"Automated peak picking using region-based convolutional neural network for operational modal analysis","volume":"26","author":"Kim","year":"2019","journal-title":"Struct Control Heal Monit"},{"issue":"12","key":"10.3233\/ICA-220696_ref50","first-page":"e2843","article-title":"Machine-learning-based methods for output-only structural modal identification","volume":"28","author":"Liu","year":"2021","journal-title":"Struct Control Heal Monit"},{"issue":"4","key":"10.3233\/ICA-220696_ref51","first-page":"e2919","article-title":"Input-parameter-state estimation of limited information wind-excited systems using a sequential Kalman filter","volume":"29","author":"Impraimakis","year":"2022","journal-title":"Struct Control Heal Monit"},{"key":"10.3233\/ICA-220696_ref52","doi-asserted-by":"crossref","unstructured":"Xu Y, Lu X, Cetiner B, Taciroglu E. Real-time regional seismic damage assessment framework based on long short-term memory neural network. Comput Civ Infrastruct Eng. 2021; 36(4).","DOI":"10.1111\/mice.12628"},{"key":"10.3233\/ICA-220696_ref53","doi-asserted-by":"crossref","unstructured":"Qarib H, Adeli H. A new adaptive algorithm for automated feature extraction in exponentially damped signals for health monitoring of smart structures. Smart Mater Struct. 2015; 24(12).","DOI":"10.1088\/0964-1726\/24\/12\/125040"},{"key":"10.3233\/ICA-220696_ref54","doi-asserted-by":"crossref","unstructured":"Amezquita-Sanchez JP, Adeli H. A new music-empirical wavelet transform methodology for time-frequency analysis of noisy nonlinear and non-stationary signals. Digit Signal Process A Rev J. 2015; 45.","DOI":"10.1016\/j.dsp.2015.06.013"},{"key":"10.3233\/ICA-220696_ref55","doi-asserted-by":"crossref","unstructured":"Amezquita-Sanchez JP, Park HS, Adeli H. A novel methodology for modal parameters identification of large smart structures using MUSIC, empirical wavelet transform, and Hilbert transform. Eng Struct. 2017; 147.","DOI":"10.1016\/j.engstruct.2017.05.054"},{"key":"10.3233\/ICA-220696_ref56","doi-asserted-by":"crossref","unstructured":"Perez-Ramirez CA, Amezquita-Sanchez JP, Valtierra-Rodriguez M, Adeli H, Dominguez-Gonzalez A, Romero-Troncoso RJ. Recurrent neural network model with Bayesian training and mutual information for response prediction of large buildings. Eng Struct. 2019; 178.","DOI":"10.1016\/j.engstruct.2018.10.065"},{"key":"10.3233\/ICA-220696_ref57","doi-asserted-by":"crossref","unstructured":"Oh BK, Kim KJ, Kim Y, Park HS, Adeli H. Evolutionary learning based sustainable strain sensing model for structural health monitoring of high-rise buildings. Appl Soft Comput J. 2017; 58.","DOI":"10.1016\/j.asoc.2017.05.029"},{"key":"10.3233\/ICA-220696_ref58","doi-asserted-by":"crossref","first-page":"866","DOI":"10.1016\/j.ymssp.2015.02.001","article-title":"A dual Kalman filter approach for state estimation via output-only acceleration measurements","volume":"60","author":"Eftekhar Azam","year":"2015","journal-title":"Mech Syst Signal Process"},{"key":"10.3233\/ICA-220696_ref59","doi-asserted-by":"crossref","unstructured":"Kalman RE, Bucy RS. New results in linear filtering and prediction theory. J Fluids Eng Trans ASME. 1961; 83(1).","DOI":"10.1115\/1.3658902"},{"issue":"2","key":"10.3233\/ICA-220696_ref60","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1142\/S0218488598000094","article-title":"The vanishing gradient problem during learning recurrent neural nets and problem solutions","volume":"6","author":"Hochreiter","year":"1998","journal-title":"Int J Uncertainty, Fuzziness Knowlege-Based Syst"},{"issue":"8","key":"10.3233\/ICA-220696_ref61","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long Short Term Memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"key":"10.3233\/ICA-220696_ref62","unstructured":"Kingma DP, Ba J. Adam: A Method for Stochastic Optimization. BT \u2013 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. International Conference on Learning Representations (ICLR). 2015."},{"key":"10.3233\/ICA-220696_ref63","unstructured":"Ruder S. An overview of gradient descent optimization algorithms. 2016; 1-14. Available from: http:\/\/arxiv.org\/abs\/1609.04747."}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/ICA-220696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:14:44Z","timestamp":1777454084000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/ICA-220696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,15]]},"references-count":63,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.3233\/ica-220696","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"value":"1069-2509","type":"print"},{"value":"1875-8835","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,15]]}}}