{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:21:15Z","timestamp":1740108075393,"version":"3.37.3"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["GXWD20201230155427003-20200821171505003"],"award-info":[{"award-number":["GXWD20201230155427003-20200821171505003"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1913213"],"award-info":[{"award-number":["U1913213"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2022,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we propose a hybrid offline\/online neural networks learning method, which combines complementary advantages of two types of neural networks (NNs): deep NN (DNN) and single-layer radial basis function NN (RBFNN). Firstly, after analyzing the mechatronic system\u2019s model, we select reasonable features as the input of the DNN to learn the inverse dynamic characteristics of the closed-loop system offline, so as to establish the mapping between the desired trajectory and the reference trajectory of the system. The trained DNN is used to generate a new reference trajectory and compensate for the tracking error in advance, which can speed up the convergence of online learning control based on RBFNN. This reference trajectory is further modified iteratively when the tracking task is repeated. For this purpose, a single-layer RBFNN model is established, and an online learning algorithm is developed to update the RBFNN parameters. The proposed hybrid offline\/online NN method can improve the tracking performance of mechatronic systems by modifying the reference trajectory on top of the baseline controller without affecting the\u00a0system stability. To verify the effectiveness of this method, we conduct experiments on a piezoelectric drive platform.<\/jats:p>","DOI":"10.1007\/s00521-022-07062-2","type":"journal-article","created":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T20:54:42Z","timestamp":1646686482000},"page":"11707-11719","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Reference modification for trajectory tracking using hybrid offline and online neural networks learning"],"prefix":"10.1007","volume":"34","author":[{"given":"Jiangang","family":"Li","sequence":"first","affiliation":[]},{"given":"Youhua","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Ganggang","family":"Zhong","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1443-2547","authenticated-orcid":false,"given":"Yanan","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,7]]},"reference":[{"issue":"1","key":"7062_CR1","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/3516.491406","volume":"1","author":"R Isermann","year":"1996","unstructured":"Isermann R (1996) Modeling and design methodology for mechatronic systems. IEEE\/ASME Trans Mechatron 1(1):16\u201328","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"1","key":"7062_CR2","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1109\/TIE.2012.2183841","volume":"60","author":"J Yang","year":"2012","unstructured":"Yang J, Li S, Yu X (2012) Sliding-mode control for systems with mismatched uncertainties via a disturbance observer. IEEE Trans Industr Electron 60(1):160\u2013169","journal-title":"IEEE Trans Industr Electron"},{"key":"7062_CR3","doi-asserted-by":"crossref","unstructured":"Arimoto S, Kawamura S, Miyazaki F (1984) Bettering operation of dynamic systems by learning: a new control theory for servomechanism or mechatronics systems. In: The 23rd ieee conference on decision and control, pp. 1064\u20131069 . IEEE","DOI":"10.1109\/CDC.1984.272176"},{"issue":"3","key":"7062_CR4","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.1109\/TMECH.2020.2973085","volume":"25","author":"J Li","year":"2020","unstructured":"Li J, Wang Y, Li Y, Luo W (2020) Reference trajectory modification based on spatial iterative learning for contour control of two-axis NC systems. IEEE\/ASME Trans Mechatron 25(3):1266\u20131275","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"9","key":"7062_CR5","doi-asserted-by":"publisher","first-page":"2670","DOI":"10.1109\/TCYB.2017.2748418","volume":"48","author":"W He","year":"2017","unstructured":"He W, Huang B, Dong Y, Li Z, Su C-Y (2017) Adaptive neural network control for robotic manipulators with unknown deadzone. IEEE Trans Cybern 48(9):2670\u20132682","journal-title":"IEEE Trans Cybern"},{"issue":"4","key":"7062_CR6","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TMECH.2020.2992038","volume":"25","author":"P Zhang","year":"2020","unstructured":"Zhang P, Wu Z, Dong H, Tan M, Yu J (2020) Reaction-wheel-based roll stabilization for a robotic fish using neural network sliding mode control. IEEE\/ASME Trans Mechatron 25(4):1904\u20131911","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"4","key":"7062_CR7","doi-asserted-by":"publisher","first-page":"2989","DOI":"10.1007\/s11071-019-05077-4","volume":"98","author":"M Bucolo","year":"2019","unstructured":"Bucolo M, Buscarino A, Famoso C, Fortuna L, Frasca M (2019) Control of imperfect dynamical systems. Nonlinear Dyn 98(4):2989\u20132999","journal-title":"Nonlinear Dyn"},{"key":"7062_CR8","doi-asserted-by":"crossref","unstructured":"Bucolo M, Buscarino A, Famoso C, Fortuna L, Frasca M (1984) Smart control of imperfect electromechanical systems. In: 2019 IEEE international conference on systems, man and cybernetics (SMC), pp. 1882\u20131886 (2019). IEEE","DOI":"10.1109\/SMC.2019.8914052"},{"key":"7062_CR9","doi-asserted-by":"publisher","first-page":"29573","DOI":"10.1109\/ACCESS.2021.3058506","volume":"9","author":"M Bucolo","year":"2021","unstructured":"Bucolo M, Buscarino A, Famoso C, Fortuna L, Gagliano S (2021) Imperfections in integrated devices allow the emergence of unexpected strange attractors in electronic circuits. IEEE Access 9:29573\u201329583","journal-title":"IEEE Access"},{"key":"7062_CR10","doi-asserted-by":"crossref","unstructured":"Li Q, Qian J, Zhu Z, Bao X, Helwa MK, Schoellig AP (2017) Deep neural networks for improved, impromptu trajectory tracking of quadrotors. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 5183\u20135189. IEEE","DOI":"10.1109\/ICRA.2017.7989607"},{"issue":"11","key":"7062_CR11","doi-asserted-by":"publisher","first-page":"2004","DOI":"10.1109\/TNNLS.2014.2302475","volume":"25","author":"C Yang","year":"2014","unstructured":"Yang C, Li Z, Cui R, Xu B (2014) Neural network-based motion control of an underactuated wheeled inverted pendulum model. IEEE Trans Neural Netw Learn Syst 25(11):2004\u20132016","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"7062_CR12","doi-asserted-by":"crossref","unstructured":"Tran M-D, Kang H-J (2015) A local neural networks approximation control of uncertain robot manipulators. In: International conference on intelligent computing, pp. 551\u2013557 . Springer","DOI":"10.1007\/978-3-319-22053-6_58"},{"issue":"3","key":"7062_CR13","doi-asserted-by":"publisher","first-page":"620","DOI":"10.1109\/TCYB.2015.2411285","volume":"46","author":"W He","year":"2015","unstructured":"He W, Chen Y, Yin Z (2015) Adaptive neural network control of an uncertain robot with full-state constraints. IEEE Trans Cybern 46(3):620\u2013629","journal-title":"IEEE Trans Cybern"},{"issue":"2","key":"7062_CR14","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/s00521-015-1873-4","volume":"27","author":"P Van Cuong","year":"2016","unstructured":"Van Cuong P, Nan WY (2016) Adaptive trajectory tracking neural network control with robust compensator for robot manipulators. Neural Comput Appl 27(2):525\u2013536","journal-title":"Neural Comput Appl"},{"issue":"3","key":"7062_CR15","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1109\/TSMC.2015.2429555","volume":"46","author":"W He","year":"2016","unstructured":"He W, Dong Y, Sun C (2016) Adaptive neural impedance control of a robotic manipulator with input saturation. IEEE Trans Syst Man Cybern Syst 46(3):334\u2013344. https:\/\/doi.org\/10.1109\/TSMC.2015.2429555","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"4","key":"7062_CR16","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/TSMC.2015.2453138","volume":"46","author":"T Li","year":"2016","unstructured":"Li T, Duan S, Liu J, Wang L, Huang T (2016) A spintronic memristor-based neural network with radial basis function for robotic manipulator control implementation. IEEE Trans Syst Man Cybern Syst 46(4):582\u2013588. https:\/\/doi.org\/10.1109\/TSMC.2015.2453138","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"key":"7062_CR17","doi-asserted-by":"crossref","unstructured":"Wang F, Chao Z-q, Huang L-b, Li H-y, Zhang C-q (2017) Trajectory tracking control of robot manipulator based on RBF neural network and fuzzy sliding mode. Cluster Computing, 1\u201311","DOI":"10.1007\/s10586-017-1538-4"},{"issue":"1","key":"7062_CR18","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1109\/TIE.2018.2826450","volume":"66","author":"Y Jian","year":"2019","unstructured":"Jian Y, Huang D, Liu J, Min D (2019) High-precision tracking of piezoelectric actuator using iterative learning control and direct inverse compensation of hysteresis. IEEE Trans Industr Electron 66(1):368\u2013377","journal-title":"IEEE Trans Industr Electron"},{"issue":"5","key":"7062_CR19","doi-asserted-by":"publisher","first-page":"932","DOI":"10.1109\/TSMC.2017.2690460","volume":"49","author":"S Li","year":"2019","unstructured":"Li S, Shao Z, Guan Y (2019) A dynamic neural network approach for efficient control of manipulators. IEEE Trans Syst Man Cybern Syst 49(5):932\u2013941. https:\/\/doi.org\/10.1109\/TSMC.2017.2690460","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"7","key":"7062_CR20","doi-asserted-by":"publisher","first-page":"1195","DOI":"10.1016\/j.automatica.2004.01.026","volume":"40","author":"A Tayebi","year":"2004","unstructured":"Tayebi A (2004) Adaptive iterative learning control for robot manipulators. Automatica 40(7):1195\u20131203","journal-title":"Automatica"},{"issue":"1\u20132","key":"7062_CR21","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s10514-012-9283-2","volume":"33","author":"AP Schoellig","year":"2012","unstructured":"Schoellig AP, Mueller FL, D\u2019Andrea R (2012) Optimization-based iterative learning for precise quadrocopter trajectory tracking. Auton Robot 33(1\u20132):103\u2013127","journal-title":"Auton Robot"},{"issue":"3","key":"7062_CR22","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MCS.2006.1636313","volume":"26","author":"DA Bristow","year":"2006","unstructured":"Bristow DA, Tharayil M, Alleyne AG (2006) A survey of iterative learning control. IEEE Control Syst Mag 26(3):96\u2013114","journal-title":"IEEE Control Syst Mag"},{"issue":"11","key":"7062_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-017-9363-y","volume":"61","author":"M Abdelatti","year":"2018","unstructured":"Abdelatti M, Yuan C, Zeng W, Wang C (2018) Cooperative deterministic learning control for a group of homogeneous nonlinear uncertain robot manipulators. Sci China Inf Sci 61(11):1\u201319","journal-title":"Sci China Inf Sci"},{"issue":"1","key":"7062_CR24","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1162\/EVCO_a_00143","volume":"24","author":"A Cully","year":"2016","unstructured":"Cully A, Mouret J-B (2016) Evolving a behavioral repertoire for a walking robot. Evol Comput 24(1):59\u201388","journal-title":"Evol Comput"},{"key":"7062_CR25","doi-asserted-by":"crossref","unstructured":"Martinez-Cantin R (2017) Bayesian optimization with adaptive kernels for robot control. In: 2017 IEEE international conference on robotics and automation (ICRA), pp. 3350\u20133356 . IEEE","DOI":"10.1109\/ICRA.2017.7989380"},{"issue":"7","key":"7062_CR26","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","volume":"18","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527\u20131554","journal-title":"Neural Comput"},{"issue":"15","key":"7062_CR27","doi-asserted-by":"publisher","first-page":"3929","DOI":"10.3390\/en13153929","volume":"13","author":"C Napole","year":"2020","unstructured":"Napole C, Barambones O, Calvo I, Velasco J (2020) Feedforward compensation analysis of piezoelectric actuators using artificial neural networks with conventional PID controller and single-neuron PID based on hebb learning rules. Energies 13(15):3929","journal-title":"Energies"},{"issue":"12","key":"7062_CR28","doi-asserted-by":"publisher","first-page":"2687","DOI":"10.1016\/j.physb.2010.03.050","volume":"405","author":"X Zhang","year":"2010","unstructured":"Zhang X, Tan Y, Su M, Xie Y (2010) Neural networks based identification and compensation of rate-dependent hysteresis in piezoelectric actuators. Physica B 405(12):2687\u20132693","journal-title":"Physica B"},{"key":"7062_CR29","doi-asserted-by":"crossref","unstructured":"Napole C, Barambones O, Derbeli M, Silaa MY, Calvo I, Velasco J (2020) Tracking control for piezoelectric actuators with advanced feed-forward compensation combined with PI control. In: Multidisciplinary Digital Publishing Institute Proceedings, vol. 64, p. 29","DOI":"10.3390\/IeCAT2020-08481"},{"key":"7062_CR30","doi-asserted-by":"crossref","unstructured":"Liang Y, Xu S, Hong K, Wang G, Zeng T (2019) Neural network modeling and single-neuron proportional-integral-derivative control for hysteresis in piezoelectric actuators. Measurement and Control -London- Institute of Measurement and Control- 52(9\u201310):002029401986684","DOI":"10.1177\/0020294019866846"},{"key":"7062_CR31","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.isatra.2016.01.005","volume":"61","author":"W Zeng","year":"2016","unstructured":"Zeng W, Wang Q, Liu F, Wang Y (2016) Learning from adaptive neural network output feedback control of a unicycle-type mobile robot. ISA Trans 61:337\u2013347","journal-title":"ISA Trans"},{"key":"7062_CR32","doi-asserted-by":"crossref","unstructured":"Kong L, Li D, Zou J, He W (2020) Neural networks-based learning control for a piezoelectric nanopositioning system. IEEE\/ASME Trans Mechatron, 1\u20131","DOI":"10.1109\/TMECH.2020.2997801"},{"issue":"2","key":"7062_CR33","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1109\/JAS.2017.7510820","volume":"5","author":"H Yang","year":"2018","unstructured":"Yang H, Liu J (2018) An adaptive RBF neural network control method for a class of nonlinear systems. IEEE\/CAA J Autom Sinica 5(2):457\u2013462","journal-title":"IEEE\/CAA J Autom Sinica"},{"issue":"5","key":"7062_CR34","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1109\/TNNLS.2020.3003950","volume":"32","author":"H Liang","year":"2020","unstructured":"Liang H, Liu G, Zhang H, Huang T (2020) Neural-network-based event-triggered adaptive control of nonaffine nonlinear multiagent systems with dynamic uncertainties. IEEE Trans Neural Netw Learn Syst 32(5):2239\u20132250","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"7062_CR35","doi-asserted-by":"crossref","unstructured":"Slama S, Errachdi A, Benrejeb M (2018) Model reference adaptive control for mimo nonlinear systems using RBF neural networks. In: 2018 international conference on advanced systems and electric technologies (IC_ASET), pp. 346\u2013351 . IEEE","DOI":"10.1109\/ASET.2018.8379880"},{"issue":"3","key":"7062_CR36","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1109\/37.588158","volume":"17","author":"M Goldfarb","year":"1997","unstructured":"Goldfarb M, Celanovic N (1997) Modeling piezoelectric stack actuators for control of micromanipulation. IEEE Control Syst Mag 17(3):69\u201379","journal-title":"IEEE Control Syst Mag"},{"issue":"4","key":"7062_CR37","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1109\/3516.891044","volume":"5","author":"H Adriaens","year":"2000","unstructured":"Adriaens H, De Koning WL, Banning R (2000) Modeling piezoelectric actuators. IEEE\/ASME Trans Mechatron 5(4):331\u2013341","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"1","key":"7062_CR38","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.sna.2007.04.062","volume":"138","author":"HC Liaw","year":"2007","unstructured":"Liaw HC, Shirinzadeh B, Smith J (2007) Enhanced sliding mode motion tracking control of piezoelectric actuators. Sens Actuators A 138(1):194\u2013202","journal-title":"Sens Actuators A"},{"key":"7062_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ultras.2016.08.017","volume":"73","author":"F Cruz","year":"2017","unstructured":"Cruz F, Simas Filho E, Albuquerque M, Silva I, Farias C, Gouv\u00eaa L (2017) Efficient feature selection for neural network based detection of flaws in steel welded joints using ultrasound testing. Ultrasonics 73:1\u20138","journal-title":"Ultrasonics"},{"key":"7062_CR40","doi-asserted-by":"crossref","unstructured":"Li J, Qi C, Li Y, Wu Z (2021) Prediction and compensation of contour error of CNC systems based on LSTM neural-network. IEEE\/ASME Trans Mechatron, 1\u20131","DOI":"10.1109\/TMECH.2021.3068354"},{"issue":"3","key":"7062_CR41","first-page":"1377","volume":"25","author":"C Hu","year":"2020","unstructured":"Hu C, Ou T, Chang H, Zhu Y, Zhu L (2020) Deep GRU neural network prediction and feedforward compensation for precision multiaxis motion control systems. IEEE\/ASME Trans Mechatron 25(3):1377\u20131388","journal-title":"IEEE\/ASME Trans Mechatron"},{"issue":"2","key":"7062_CR42","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1023\/A:1018966222807","volume":"10","author":"RJ Erb","year":"1993","unstructured":"Erb RJ (1993) Introduction to backpropagation neural network computation. Pharm Res 10(2):165\u2013170","journal-title":"Pharm Res"},{"issue":"3","key":"7062_CR43","doi-asserted-by":"publisher","first-page":"697","DOI":"10.1109\/TNN.2002.1000134","volume":"13","author":"MJ Er","year":"2002","unstructured":"Er MJ, Wu S, Lu J, Toh HL (2002) Face recognition with radial basis function (RBF) neural networks. IEEE Trans Neural Netw 13(3):697\u2013710","journal-title":"IEEE Trans Neural Netw"},{"issue":"2","key":"7062_CR44","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1162\/neco.1991.3.2.246","volume":"3","author":"J Park","year":"1991","unstructured":"Park J, Sandberg IW (1991) Universal approximation using radial-basis-function networks. Neural Comput 3(2):246\u2013257","journal-title":"Neural Comput"},{"key":"7062_CR45","unstructured":"Gao Z (2006) Scaling and bandwidth-parameterization based controller tuning. In: Proceedings of the American control conference 6:4989\u20134996"},{"issue":"20","key":"7062_CR46","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1016\/j.ifacol.2015.10.194","volume":"48","author":"M Scheel","year":"2015","unstructured":"Scheel M, Berndt A, Simanski O (2015) Iterative learning control: an example for mechanical ventilated patients. IFAC-PapersOnLine 48(20):523\u2013527","journal-title":"IFAC-PapersOnLine"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07062-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07062-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07062-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,15]],"date-time":"2022-07-15T09:28:26Z","timestamp":1657877306000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07062-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,7]]},"references-count":46,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["7062"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07062-2","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2022,3,7]]},"assertion":[{"value":"29 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}