{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,27]],"date-time":"2025-12-27T03:46:24Z","timestamp":1766807184892,"version":"3.41.2"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T00:00:00Z","timestamp":1663891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>In this paper, a nonlinear activation function (NAF) is proposed to constructed three recurrent neural network (RNN) models (Simple RNN (SRNN) model, Long Short-term Memory (LSTM) model and Gated Recurrent Unit (GRU) model) for sentiment classification. The Internet Movie Database (IMDB) sentiment classification experiment results demonstrate that the three RNN models using the NAF achieve better accuracy and lower loss values compared with other commonly used activation functions (AF), such as ReLU, SELU etc. Moreover, in terms of dynamic problems solving, a fixed-time convergent recurrent neural network (FTCRNN) model with the NAF is constructed. Additionally, the fixed-time convergence property of the FTCRNN model is strictly validated and the upper bound convergence time formula of the FTCRNN model is obtained. Furthermore, the numerical simulation results of dynamic Sylvester equation (DSE) solving using the FTCRNN model indicate that the neural state solutions of the FTCRNN model quickly converge to the theoretical solutions of DSE problems whether there are noises or not. Ultimately, the FTCRNN model is also utilized to realize trajectory tracking of robot manipulator and electric circuit currents computation for the further validation of its accurateness and robustness, and the corresponding results further validate its superior performance and widespread applicability.<\/jats:p>","DOI":"10.3389\/fnbot.2022.1022887","type":"journal-article","created":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T13:38:15Z","timestamp":1663940295000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["A novel activation function based recurrent neural networks and their applications on sentiment classification and dynamic problems solving"],"prefix":"10.3389","volume":"16","author":[{"given":"Qingyi","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingtao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,9,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00500-018-3653-4","article-title":"Automatic sentiment-oriented summarization of multi-documents using soft computing","volume":"4","author":"Abdi","year":"2018","journal-title":"Soft Comput."},{"key":"B2","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1016\/j.apm.2017.02.026","article-title":"Unique NSGA-II and MOPSO algorithms for improved dynamic cellular manufacturing systems considering human factors","volume":"48","author":"Azadeh","year":"2017","journal-title":"Appl. Math. Model."},{"key":"B3","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1016\/j.neunet.2019.12.028","article-title":"A new fixed-time stability theorem and its application to the fixed-time synchronization of neural networks","volume":"123","author":"Chen","year":"2020","journal-title":"Neural Netw."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1097","DOI":"10.1007\/s12559-020-09745-1","article-title":"A structural topic modeling-based bibliometric study of sentiment analysis literature","volume":"12","author":"Chen","year":"2020","journal-title":"Cogn. Comput."},{"key":"B5","doi-asserted-by":"publisher","first-page":"835","DOI":"10.1016\/j.sysconle.2006.04.004","article-title":"Solution to Sylvester equation associated to linear descriptor systems","volume":"55","author":"Darouach","year":"2006","journal-title":"Syst. Control Lett."},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-05617-9","article-title":"A better robustness and fast convergence zeroing neural network for solving dynamic nonlinear equations","author":"Gong","year":"2021","journal-title":"Neural Comput. Applic"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2020.00737","article-title":"A neural network framework for predicting the tissue-of-origin of 15 common cancer types based on RNA-Seq data","author":"He","year":"2020","journal-title":"Front. Bioeng. Biotechnol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/s40747-020-00178-9","article-title":"A robust zeroing neural network for solving dynamic nonlinear equations and its application to kinematic control of mobile manipulator","volume":"7","author":"Jin","year":"","journal-title":"Compl. Intell. Syst."},{"key":"B9","doi-asserted-by":"publisher","first-page":"777","DOI":"10.1007\/s11063-021-10426-9","article-title":"An improved finite time convergence recurrent neural network with application to time-varying linear complex matrix equation solution","volume":"53","author":"Jin","year":"","journal-title":"Neural Proc. Lett."},{"key":"B10","doi-asserted-by":"publisher","first-page":"659","DOI":"10.1016\/j.aej.2020.09.059","article-title":"An interference-tolerant fast convergence zeroing neural network for dynamic matrix inversion and its application to mobile manipulator path tracking","volume":"60","author":"Jin","year":"2021","journal-title":"Alexand. Eng. J."},{"key":"B11","doi-asserted-by":"publisher","first-page":"3183","DOI":"10.1016\/j.jfranklin.2022.02.022","article-title":"A robust fast convergence zeroing neural network and its applications to dynamic Sylvester equation solving and robot trajectory tracking","volume":"359","author":"Jin","year":"2022","journal-title":"J. Franklin Inst."},{"key":"B12","doi-asserted-by":"publisher","first-page":"4151","DOI":"10.1007\/s00521-019-04622-x","article-title":"Improved zeroing neural networks for finite time solving nonlinear equations","volume":"32","author":"Jin","year":"2020","journal-title":"Neural Comput. Applic."},{"key":"B13","doi-asserted-by":"publisher","first-page":"14297","DOI":"10.1007\/s00521-022-06905-2","article-title":"Novel activation functions-based ZNN models for fixed-time solving dynamic sylvester equation","volume":"34","author":"Jin","year":"","journal-title":"Neural Comput. Applic."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3179312","article-title":"A robust predefined-time convergence zeroing neural network for dynamic matrix inversion","author":"Jin","year":"","journal-title":"IEEE Trans. Cybern"},{"key":"B15","doi-asserted-by":"publisher","first-page":"5105","DOI":"10.1109\/TSMC.2021.3114213","article-title":"Neural dynamics for computing perturbed nonlinear equations applied to ACP-based lower limb motion intention recognition","volume":"52","author":"Jin","year":"","journal-title":"IEEE Trans. Syst. Man Cyber. Syst."},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2022.3144135","article-title":"Gradient-based differential neural-solution to time-dependent nonlinear optimization","author":"Jin","year":"","journal-title":"IEEE Trans. Automat. Contr."},{"key":"B17","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/s11063-012-9241-1","article-title":"Accelerating a recurrent neural network to finite-time convergence for solving time-varying Sylvester equation by using a sign-bi-power activation function","volume":"37","author":"Li","year":"2013","journal-title":"Inform. Proc. Lett."},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106044","article-title":"Activated gradients for deep neural networks","author":"Liu","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B19","doi-asserted-by":"publisher","first-page":"1452","DOI":"10.1109\/JAS.2022.105731","article-title":"Gradient-based differential kWTA network with application to competitive coordination of multiple robots","volume":"9","author":"Liu","year":"2022","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"B20","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1007\/s12559-020-09771-z","article-title":"Optimizing sentiment classification for arabic opinion texts","volume":"13","author":"Saeed","year":"2021","journal-title":"Cogn. Comput."},{"key":"B21","doi-asserted-by":"publisher","first-page":"073107","DOI":"10.1063\/5.0095384","article-title":"Complex dynamics in a Hopfield neural network under electromagnetic induction and electromagnetic radiation","volume":"32","author":"Wan","year":"","journal-title":"Chaos"},{"key":"B22","doi-asserted-by":"publisher","first-page":"2085","DOI":"10.1007\/s11071-022-07544-x","article-title":"Multistable dynamics in a hopfield neural network under electromagnetic radiation and dual bias currents","volume":"109","author":"Wan","year":"","journal-title":"Nonlinear Dyn."},{"key":"B23","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1007\/s12559-019-09669-5","article-title":"Optimal feature selection for learning-based algorithms for sentiment classification","volume":"12","author":"Wang","year":"2020","journal-title":"Cogn. Comput."},{"key":"B24","doi-asserted-by":"publisher","first-page":"7513","DOI":"10.1109\/TII.2021.3058343","article-title":"A noise-suppression ZNN model with new variable parameter for dynamic sylvester equation","volume":"17","author":"Xiao","year":"2021","journal-title":"IEEE Trans. Industr. Inf"},{"key":"B25","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.neunet.2017.11.011","article-title":"Nonlinear recurrent neural networks for finite-time solution of general time-varying linear matrix equations","volume":"98","author":"Xiao","year":"2018","journal-title":"Neural Netw."},{"key":"B26","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1109\/TCYB.2013.2253461","article-title":"A new performance index for the repetitive motion of mobile manipulators","volume":"44","author":"Xiao","year":"","journal-title":"IEEE Trans. Cybern."},{"key":"B27","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/s11063-013-9306-9","article-title":"From different Zhang functions to various ZNN models accelerated to finite-time convergence for time-varying linear matrix equation","volume":"39","author":"Xiao","year":"","journal-title":"Neural Process. Lett"},{"key":"B28","doi-asserted-by":"publisher","first-page":"2210","DOI":"10.1109\/TSMC.2018.2836968","article-title":"Solving time-varying system of nonlinear equations by finite-time recurrent neural networks with application to motion tracking of robot manipulators","volume":"49","author":"Xiao","year":"2019","journal-title":"IEEE Trans. Syst. Man Cyber. Syst."},{"key":"B29","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.compeleceng.2016.11.015","article-title":"A comparison study on active learning integrated ensemble approaches in sentiment analysis","volume":"57","author":"Yaslan","year":"2017","journal-title":"Comput. Electr. Eng."},{"key":"B30","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1140\/epjp\/s13360-022-02652-4","article-title":"Dynamic analysis and application in medical digital image watermarking of a new multi-scroll neural network with quartic nonlinear memristor","volume":"137","author":"Yu","year":"","journal-title":"Euro. Phys. J. Plus"},{"key":"B31","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1016\/j.neucom.2019.03.053","article-title":"A robust and fixed-time zeroing neural dynamics for computing time-variant nonlinear equation using a novel nonlinear activation function","volume":"350","author":"Yu","year":"2019","journal-title":"Neurocomputing"},{"key":"B32","doi-asserted-by":"publisher","first-page":"370","DOI":"10.3390\/fractalfract6070370","article-title":"Dynamic analysis and audio encryption application in IoT of a multi-scroll fractional-order memristive hopfield neural network","volume":"6","author":"Yu","year":"","journal-title":"Fractal Fract."},{"key":"B33","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1016\/j.apm.2019.02.032","article-title":"Review modus: text classification and sentiment prediction of unstructured reviews using a hybrid combination of machine learning and evaluation models","volume":"71","author":"Zablith","year":"2019","journal-title":"Appl. Math. Model"},{"key":"B34","first-page":"521","article-title":"Simulink modeling and comparison of Zhang neural networks and gradient neural networks for time-varying Lyapunov equation solving,","volume-title":"Proceedings of IEEE International Conference on Natural Computation","author":"Zhang","year":"2008"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1109\/TNN.2002.1031938","article-title":"A recurrent neural network for solving sylvester equation with time-varying coefficients","volume":"13","author":"Zhang","year":"2002","journal-title":"IEEE Trans. Neural Netw."},{"key":"B36","doi-asserted-by":"crossref","first-page":"3543","DOI":"10.1109\/ICMLC.2007.4370761","article-title":"Neural network for linear time-varying equation solving and its robotic application,","volume-title":"2007 International Conference on Machine Learning and Cybernetics","author":"Zhang","year":"2007"},{"key":"B37","doi-asserted-by":"publisher","first-page":"3270","DOI":"10.1109\/TSMC.2019.2920778","article-title":"Two hybrid multiobjective motion planning schemes synthesized by recurrent neural networks for wheeled mobile robot manipulators","volume":"51","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"B38","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1109\/TII.2019.2922694","article-title":"Two hybrid end-effector posture-maintaining and obstacle-limits avoidance schemes for redundant robot manipulators","volume":"16","author":"Zhang","year":"","journal-title":"IEEE Trans. Indust. Inform."},{"key":"B39","doi-asserted-by":"publisher","first-page":"3414","DOI":"10.1109\/TNNLS.2019.2944485","article-title":"An exponential-type anti-noise varying-gain network for solving disturbed time-varying inversion systems","volume":"31","author":"Zhang","year":"","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B40","doi-asserted-by":"publisher","first-page":"679","DOI":"10.1109\/TMECH.2018.2799724","article-title":"A varying-parameter convergent-differential neural network for solving joint-angular-drift problems of redundant robot manipulators","volume":"23","author":"Zhang","year":"","journal-title":"IEEE\/ASME Trans. Mechatron."},{"key":"B41","doi-asserted-by":"publisher","first-page":"5106","DOI":"10.1109\/TSMC.2018.2866843","article-title":"Robustness analysis of a power-type varying-parameter recurrent neural network for solving time-varying QM and QP problems and applications","volume":"50","author":"Zhang","year":"","journal-title":"IEEE Trans. Syst. Man Cybern. Syst"},{"key":"B42","doi-asserted-by":"publisher","first-page":"4110","DOI":"10.1109\/TAC.2018.2810039","article-title":"A new varying-parameter convergent-differential neural-network for solving time-varying convex QP problem constrained by linear-equality","volume":"63","author":"Zhang","year":"","journal-title":"IEEE Trans. Automat. Control"},{"key":"B43","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1109\/TAC.2019.2921681","article-title":"Varying-Parameter convergent-differential neural solution to time-varying overdetermined system of linear equations","volume":"65","author":"Zhang","year":"","journal-title":"IEEE Trans. Automat. Control"},{"key":"B44","doi-asserted-by":"publisher","first-page":"3135","DOI":"10.1109\/TCYB.2017.2760883","article-title":"A new varying-parameter recurrent neural-network for online solution of time-varying sylvester equation","volume":"48","author":"Zhang","year":"","journal-title":"IEEE Trans. Cybern."},{"key":"B45","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.matcom.2020.12.030","article-title":"Robust zeroing neural network for fixed-time kinematic control of wheeled mobile robot in noise-polluted environment","volume":"185","author":"Zhao","year":"2021","journal-title":"Math. Comp. Simulat."},{"key":"B46","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1016\/j.matcom.2022.02.019","article-title":"A combined power activation function based convergent factor-variable ZNN model for solving dynamic matrix inversion","volume":"197","author":"Zhu","year":"2022","journal-title":"Math. Comput. Simul."}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2022.1022887\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T13:38:21Z","timestamp":1663940301000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2022.1022887\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,23]]},"references-count":46,"alternative-id":["10.3389\/fnbot.2022.1022887"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2022.1022887","relation":{},"ISSN":["1662-5218"],"issn-type":[{"type":"electronic","value":"1662-5218"}],"subject":[],"published":{"date-parts":[[2022,9,23]]},"article-number":"1022887"}}