Deep learned BLSTM for online handwriting modeling simulating the Beta-Elliptic approach
[Display omitted] The beta-elliptic model (BEM) has proven a great success in several applications such as handwriting recognition and analysis, handwriting identification, the effect of age on the kinematics of hand movements, etc. With the emergence of deep learning technologies during the last ye...
Saved in:
| Published in | Engineering science and technology, an international journal Vol. 35; p. 101215 |
|---|---|
| Main Authors | , , , , , , , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier B.V
01.11.2022
Elsevier |
| Subjects | |
| Online Access | Get full text |
Cover
Loading…
| Abstract | [Display omitted]
The beta-elliptic model (BEM) has proven a great success in several applications such as handwriting recognition and analysis, handwriting identification, the effect of age on the kinematics of hand movements, etc. With the emergence of deep learning technologies during the last years and their application in several fields, the implementation of beta-elliptic model with a simple multi-stage deep learned recurrent neural network (RNN) is required. In this paper, we propose a new online handwriting trajectory modeling by simulating the beta-elliptical approach to limit the calculation time and to have an end-to-end description system meeting the needs of mobile device users. The developed model deploys a multi-stage architecture based deep learned recurrent neural network (RNN) with bidirectional Long Short-Term Memory (BLSTM) that simulates the process of extracting the dynamic and geometric parameters composing the beta-elliptical vector. This architecture encompasses the pre-processing, segmentation, and approximation steps of the trajectory in its two velocity and geometric profiles and is traced by only neural computation sequences. To evaluate our model, a similarity degree between the beta-elliptic and BLSTM estimation models is measured by means of MAE (mean absolute error) and RMSE (Root Mean Square Error) metrics. Experimental results on LMCA and ADAB datasets show the efficiency of the proposed RNN model for online handwriting trajectory modeling consisting of 3.75%, 5.26% for RMSE, and 1.69%, 2.75% for MAE respectively. |
|---|---|
| AbstractList | The beta-elliptic model (BEM) has proven a great success in several applications such as handwriting recognition and analysis, handwriting identification, the effect of age on the kinematics of hand movements, etc. With the emergence of deep learning technologies during the last years and their application in several fields, the implementation of beta-elliptic model with a simple multi-stage deep learned recurrent neural network (RNN) is required. In this paper, we propose a new online handwriting trajectory modeling by simulating the beta-elliptical approach to limit the calculation time and to have an end-to-end description system meeting the needs of mobile device users. The developed model deploys a multi-stage architecture based deep learned recurrent neural network (RNN) with bidirectional Long Short-Term Memory (BLSTM) that simulates the process of extracting the dynamic and geometric parameters composing the beta-elliptical vector. This architecture encompasses the pre-processing, segmentation, and approximation steps of the trajectory in its two velocity and geometric profiles and is traced by only neural computation sequences. To evaluate our model, a similarity degree between the beta-elliptic and BLSTM estimation models is measured by means of MAE (mean absolute error) and RMSE (Root Mean Square Error) metrics. Experimental results on LMCA and ADAB datasets show the efficiency of the proposed RNN model for online handwriting trajectory modeling consisting of 3.75%, 5.26% for RMSE, and 1.69%, 2.75% for MAE respectively. [Display omitted] The beta-elliptic model (BEM) has proven a great success in several applications such as handwriting recognition and analysis, handwriting identification, the effect of age on the kinematics of hand movements, etc. With the emergence of deep learning technologies during the last years and their application in several fields, the implementation of beta-elliptic model with a simple multi-stage deep learned recurrent neural network (RNN) is required. In this paper, we propose a new online handwriting trajectory modeling by simulating the beta-elliptical approach to limit the calculation time and to have an end-to-end description system meeting the needs of mobile device users. The developed model deploys a multi-stage architecture based deep learned recurrent neural network (RNN) with bidirectional Long Short-Term Memory (BLSTM) that simulates the process of extracting the dynamic and geometric parameters composing the beta-elliptical vector. This architecture encompasses the pre-processing, segmentation, and approximation steps of the trajectory in its two velocity and geometric profiles and is traced by only neural computation sequences. To evaluate our model, a similarity degree between the beta-elliptic and BLSTM estimation models is measured by means of MAE (mean absolute error) and RMSE (Root Mean Square Error) metrics. Experimental results on LMCA and ADAB datasets show the efficiency of the proposed RNN model for online handwriting trajectory modeling consisting of 3.75%, 5.26% for RMSE, and 1.69%, 2.75% for MAE respectively. |
| ArticleNumber | 101215 |
| Author | Hamdi, Yahia Dhahri, Habib Qahtani, Abdulrahman M. Boubaker, Houcine Alharithi, Fahd S. Almutiry, Omar Rabhi, Besma Alimi, Adel M. |
| Author_xml | – sequence: 1 givenname: Yahia surname: Hamdi fullname: Hamdi, Yahia email: yahia.hamdi@regim.usf.tn organization: REGIM-Lab REsearch Groups in Intelligent Machines, University of Sfax, National Engineering School of Sfax, LR11ES48, 3038 Sfax, Tunisia – sequence: 2 givenname: Houcine surname: Boubaker fullname: Boubaker, Houcine organization: REGIM-Lab REsearch Groups in Intelligent Machines, University of Sfax, National Engineering School of Sfax, LR11ES48, 3038 Sfax, Tunisia – sequence: 3 givenname: Besma surname: Rabhi fullname: Rabhi, Besma organization: REGIM-Lab REsearch Groups in Intelligent Machines, University of Sfax, National Engineering School of Sfax, LR11ES48, 3038 Sfax, Tunisia – sequence: 4 givenname: Abdulrahman M. surname: Qahtani fullname: Qahtani, Abdulrahman M. organization: Department of Computer Science, College of Computers and Information Technology, Taif University, P.O.Box. 11099, Taif 21944, Saudi Arabia – sequence: 5 givenname: Fahd S. surname: Alharithi fullname: Alharithi, Fahd S. organization: Department of Computer Science, College of Computers and Information Technology, Taif University, P.O.Box. 11099, Taif 21944, Saudi Arabia – sequence: 6 givenname: Omar surname: Almutiry fullname: Almutiry, Omar organization: College of Applied Computer Science, King Saud University, Riyadh, Saudi Arabia – sequence: 7 givenname: Habib surname: Dhahri fullname: Dhahri, Habib organization: College of Applied Computer Science, King Saud University, Riyadh, Saudi Arabia – sequence: 8 givenname: Adel M. surname: Alimi fullname: Alimi, Adel M. organization: REGIM-Lab REsearch Groups in Intelligent Machines, University of Sfax, National Engineering School of Sfax, LR11ES48, 3038 Sfax, Tunisia |
| BookMark | eNp9kM1Kw0AUhQepYK19Axd5gdSZSTI_G8HWv0LFhRXcDZOZm3ZCmgmTqPj2Jo2IK1fncuB83HPO0aT2NSB0SfCCYMKuykUJbWf2C4opHSxKshM0pb3EWAo2-XOfoXnblhhjIikhGZuit1uAJqpAhxpstNy8bJ-iwofI15WrIdrr2n4G17l6Fx28hWo4Wnd4r_TR6_YQLaHT8V1VuaZzJtJNE7w2-wt0WuiqhfmPztDr_d129Rhvnh_Wq5tNbBLGu5jnjHKdF4mxaZImWtJUGmmsSLTFPBdCSI4xByMLSpjkglOwfROacytAFskMrUeu9bpUTXAHHb6U104dDR92Sof-sQpUThIqJROC4SQ1xOaZJBkwkaapFpnEPSsdWSb4tg1Q_PIIVsPYqlTj2GoYW41j97HrMQZ9zw8HQbXGQW3AugCm6x9x_wO-AYrbif8 |
| Cites_doi | 10.1109/ICASSP40776.2020.9053993 10.1142/S0218001407005272 10.1016/j.patcog.2008.10.017 10.1016/j.patcog.2019.02.013 10.1016/j.cose.2020.101973 10.1007/BF00336740 10.1016/bs.host.2018.07.006 10.1109/72.279181 10.1142/S0218001420520072 10.1109/ICDARW.2019.50114 10.1038/s41598-021-00477-2 10.1109/21.44021 10.1037/0096-1523.17.1.198 10.1109/78.650093 10.1016/S0001-6918(98)00034-1 10.1080/10255842.2020.1714235 10.1007/s42452-020-2234-1 10.1109/MC.2007.314 10.1007/BF00335240 10.36227/techrxiv.13902650.v1 10.1007/s00422-014-0600-z 10.1109/TPAMI.2016.2572693 10.3745/JIPS.02.0006 10.1109/ICDAR.2017.152 10.1007/s10032-007-0046-0 10.1109/ICDAR.2019.00093 |
| ContentType | Journal Article |
| Copyright | 2022 Karabuk University |
| Copyright_xml | – notice: 2022 Karabuk University |
| DBID | 6I. AAFTH AAYXX CITATION DOA |
| DOI | 10.1016/j.jestch.2022.101215 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access CrossRef DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: DOA name: Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2215-0986 |
| ExternalDocumentID | oai_doaj_org_article_b132996886034c1db5915e68444a8590 10_1016_j_jestch_2022_101215 S2215098622001240 |
| GroupedDBID | 0R~ 0SF 4.4 457 5VS 6I. AACTN AAEDT AAEDW AAFTH AAIKJ AALRI AAXUO ABMAC ACGFS ADBBV ADEZE AEXQZ AFTJW AGHFR AITUG ALMA_UNASSIGNED_HOLDINGS AMRAJ BCNDV EBS EJD FDB GROUPED_DOAJ HZ~ IPNFZ IXB KQ8 M41 M~E NCXOZ O9- OK1 RIG ROL SSZ AAYXX ADVLN AFJKZ CITATION |
| ID | FETCH-LOGICAL-c367t-7b627abf3cd4343a9249c9cd83ad07b88897007ec9f21697872ed9862b7d8e9f3 |
| IEDL.DBID | IXB |
| ISSN | 2215-0986 |
| IngestDate | Sun Sep 29 07:14:51 EDT 2024 Thu Sep 26 16:35:49 EDT 2024 Tue Jul 25 20:59:07 EDT 2023 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Beta-elliptic model Online Handwriting modeling RNN Deep Learning BLSTM |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c367t-7b627abf3cd4343a9249c9cd83ad07b88897007ec9f21697872ed9862b7d8e9f3 |
| OpenAccessLink | https://www.sciencedirect.com/science/article/pii/S2215098622001240 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_b132996886034c1db5915e68444a8590 crossref_primary_10_1016_j_jestch_2022_101215 elsevier_sciencedirect_doi_10_1016_j_jestch_2022_101215 |
| PublicationCentury | 2000 |
| PublicationDate | November 2022 2022-11-00 2022-11-01 |
| PublicationDateYYYYMMDD | 2022-11-01 |
| PublicationDate_xml | – month: 11 year: 2022 text: November 2022 |
| PublicationDecade | 2020 |
| PublicationTitle | Engineering science and technology, an international journal |
| PublicationYear | 2022 |
| Publisher | Elsevier B.V Elsevier |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier |
| References | Schomaker, L.R.B.: Simulation and recognition of handwriting movements: a vertical approach to modeling human motor behavior. Ph.D. Thesis, Nijmegen University, Netherlands, 991. Y. Hamdi, H. Boubaker, T. Dhieb, A, Elbaati, Alimi., A. (2019). Hybrid DBLSTM-SVM based Beta-elliptic-CNN Models for Online Arabic Characters Recognition. In International Conference on Document Analysis and Recognition (ICDAR), pages 803-808. Bullock, Grossberg (b0080) 1988 O’Reilly, Plamondon (b0110) 2009; 42 Boubaker, Chaabouni, Tagougui, Kherallah, Alimi (b0130) 2013; 10 Boubaker, Tagougui, El Abed, Kherallah, Alimi (b0220) 2014; 10 Nguyen, Nakagawa (b0245) 2015 Graves, Fernández, Gomez, Schmidhuber (b0035) 2006 Schuster, Paliwal (b0205) 1997; 45 Alimi (b0115) 1997 Ehsan, Babak (b0010) 2018; 38 (2021). Njah, Ltaief, Bezine, Alimi (b0225) 2012; 9 Zenati, Ouarda, Alimi (b0170) 2020; 23 pp. 1-6, 2019. Gangadhar, Denny, Srinivasa (b0095) 2007 Kalveram (b0070) 1998 Boubaker, Elbaati, Tagougui, ElAbed, Kherallah, Alimi (b0250) 2012 2 Kherallah, Elbaati, Abed, Alimi (b0255) 2008 Morasso, Mussa Ivaldi (b0085) 1982; 45 Bengio, Simard, Frasconi (b0200) 1994; 5 I. Sutskever, J. Martens, and G. Hinton. Generating text with recurrent neural networks. In ICML, 2011. 446 (2020). https:// 10.1007/s. I. Sutskever, G. E. Hinton, and G. W. Taylor. The recurrent temporal restricted boltzmann machine. pages 1601–1608, 2008. Boulanger-Lewandowski, Bengio, Vincent (b0190) 2012 André, Kostrubiec, Buisson, Albaret, Zanone (b0100) 2014; 108 Akouaydi, H., Njah, S., Ouarda, W., Samit, A., Zayed, M., and Alimi M adel, Convolutional Neural Networks for Online Arabic Characters Recognition with Beta-Elliptic Knowledge Domain Pittman (b0030) 2007; 40 Viviani, Schneider (b0120) 1991; 17 Hollerbach (b0065) 1981; 156 Ehsan, Babak (b0015) 2018; 38 Zhang, J., Du, J., Dai, L.: A gru-based encoderdecoder approach with attention for online handwritten mathematical expression recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 902–907. IEEE (2017). Hamdi, Boubaker, Dhieb, Elbaati, Alimi (b0140) 2019 Graves, Mohamed, Hinton (b0040) 2013 Rabhi, Besma; Elbaati, Abdelkarim; Boubaker, Houcine; Hamdi, Yahia; Hussain, Amir; Alimi, Adel; Temporal Order and Pen Velocity Recovery for Character Handwriting Based on Sequence-to-Sequence with Attention Mode. Bezine, Kefi, Alimi, M. (b0125) 2007; 21 Graves (b0050) 2012 Zhu, Tokuno, Nakagawa (b0230) 2006 Plamondon, O’Reilly, Remi, Duval (b0060) 2013; 4 Cong, B. G., Kingsbury, C. -C. Yang and T. Liu, “Fast Training of Deep Neural Networks for Speech Recognition,” Mehendale, N. Facial emotion recognition using convolutional neural networks (FERC). Ltaief, Bezine, Alimi (b0135) 2016 SN Appl. Sci. Galen, Weber (b0075) 1998; 100 Huang, Zhang (b0105) 2021 Xu, ShangGuan, Ding (b0215) 2021; 11 Dhieb, Rezzoug, Boubaker, Gorce, Alimi (b0155) 2019; 22 ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020, pp. 6884-6888. Keysers, Deselaers, Rowley, Wang, Carbune (b0025) 2017; 39 Jemni, Kessentini, Kanoun (b0045) 2020 Plamondon (b0055) 1989; 19 Choudhury, Prasanna (b0175) 2019; 91 Ly, Nguyen, Nguyen, Nakagawa (b0235) 2017 Cong, Kingsbury, Yang, Liu (b0260) 2020 Dhieb, Njah, Boubaker, Ouarda, Ayed, Alimi (b0150) 2020; 97 Hamdi, Y., Akouaydi, H., Boubaker. H., Alimi, M. Adel; Handwriting: Quality Analysis using Online-Offline Models. arXiv:2021.06693. Volkova, Deriuga, Osadchyi, Radyvonenko (b0240) 2018 Boulanger-Lewandowski (10.1016/j.jestch.2022.101215_b0190) 2012 Choudhury (10.1016/j.jestch.2022.101215_b0175) 2019; 91 Cong (10.1016/j.jestch.2022.101215_b0260) 2020 André (10.1016/j.jestch.2022.101215_b0100) 2014; 108 10.1016/j.jestch.2022.101215_b0195 Volkova (10.1016/j.jestch.2022.101215_b0240) 2018 Hamdi (10.1016/j.jestch.2022.101215_b0140) 2019 Zenati (10.1016/j.jestch.2022.101215_b0170) 2020; 23 Ltaief (10.1016/j.jestch.2022.101215_b0135) 2016 Boubaker (10.1016/j.jestch.2022.101215_b0130) 2013; 10 Bullock (10.1016/j.jestch.2022.101215_b0080) 1988 Viviani (10.1016/j.jestch.2022.101215_b0120) 1991; 17 Boubaker (10.1016/j.jestch.2022.101215_b0220) 2014; 10 Schuster (10.1016/j.jestch.2022.101215_b0205) 1997; 45 Alimi (10.1016/j.jestch.2022.101215_b0115) 1997 Huang (10.1016/j.jestch.2022.101215_b0105) 2021 Boubaker (10.1016/j.jestch.2022.101215_b0250) 2012 10.1016/j.jestch.2022.101215_b0160 Xu (10.1016/j.jestch.2022.101215_b0215) 2021; 11 Ehsan (10.1016/j.jestch.2022.101215_b0015) 2018; 38 Graves (10.1016/j.jestch.2022.101215_b0035) 2006 Galen (10.1016/j.jestch.2022.101215_b0075) 1998; 100 10.1016/j.jestch.2022.101215_b0005 Hollerbach (10.1016/j.jestch.2022.101215_b0065) 1981; 156 Kherallah (10.1016/j.jestch.2022.101215_b0255) 2008 Plamondon (10.1016/j.jestch.2022.101215_b0055) 1989; 19 10.1016/j.jestch.2022.101215_b0165 Dhieb (10.1016/j.jestch.2022.101215_b0150) 2020; 97 Nguyen (10.1016/j.jestch.2022.101215_b0245) 2015 Plamondon (10.1016/j.jestch.2022.101215_b0060) 2013; 4 Jemni (10.1016/j.jestch.2022.101215_b0045) 2020 Njah (10.1016/j.jestch.2022.101215_b0225) 2012; 9 Dhieb (10.1016/j.jestch.2022.101215_b0155) 2019; 22 Zhu (10.1016/j.jestch.2022.101215_b0230) 2006 Bengio (10.1016/j.jestch.2022.101215_b0200) 1994; 5 10.1016/j.jestch.2022.101215_b0090 O’Reilly (10.1016/j.jestch.2022.101215_b0110) 2009; 42 Ly (10.1016/j.jestch.2022.101215_b0235) 2017 Kalveram (10.1016/j.jestch.2022.101215_b0070) 1998 Bezine (10.1016/j.jestch.2022.101215_b0125) 2007; 21 Graves (10.1016/j.jestch.2022.101215_b0050) 2012 10.1016/j.jestch.2022.101215_b0210 Keysers (10.1016/j.jestch.2022.101215_b0025) 2017; 39 Graves (10.1016/j.jestch.2022.101215_b0040) 2013 Gangadhar (10.1016/j.jestch.2022.101215_b0095) 2007 Ehsan (10.1016/j.jestch.2022.101215_b0010) 2018; 38 Pittman (10.1016/j.jestch.2022.101215_b0030) 2007; 40 10.1016/j.jestch.2022.101215_b0180 10.1016/j.jestch.2022.101215_b0145 Morasso (10.1016/j.jestch.2022.101215_b0085) 1982; 45 10.1016/j.jestch.2022.101215_b0020 10.1016/j.jestch.2022.101215_b0185 |
| References_xml | – start-page: 803 year: 2019 end-page: 808 ident: b0140 article-title: Hybrid DBLSTM-SVM based Beta-elliptic-CNN models for online Arabic characters recognition publication-title: International Conference on Document Analysis and Recognition (ICDAR) contributor: fullname: Alimi – start-page: 382 year: 1997 end-page: 386 ident: b0115 article-title: An evolutionary neuro-fuzzy approach to recognize online Arabic handwriting publication-title: Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on, IEEE. contributor: fullname: Alimi – volume: 19 start-page: 1060 year: 1989 end-page: 1072 ident: b0055 article-title: An evaluation of motor models of handwriting publication-title: IEEE Trans. Syst. Man Cybern. contributor: fullname: Plamondon – volume: 21 start-page: 5 year: 2007 end-page: 19 ident: b0125 article-title: On the beta-elliptic model for the control of the human arm movement publication-title: Internat. J. Pattern Recognit. Artifi. Intell. contributor: fullname: M. – year: 2006 ident: b0230 article-title: Segmentation of on-line handwritten Japanese text Using SVM for improving text recognition publication-title: Document Analysis Systems VII. DAS 2006. Lecture Notes in Computer Science contributor: fullname: Nakagawa – year: 2006 ident: b0035 article-title: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks publication-title: ICML contributor: fullname: Schmidhuber – year: 2008 ident: b0255 article-title: The on/off (LMCA) dual Arabic handwriting database publication-title: 11th International conference on frontiers in handwriting recognition (ICFHR). Montréal, Québec, Canada contributor: fullname: Alimi – start-page: 5 year: 2017 end-page: 9 ident: b0235 article-title: Deep convolutional recurrent network for segmentation-free offline handwritten japanese text recognition publication-title: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR) contributor: fullname: Nakagawa – volume: 10 start-page: 57 year: 2013 end-page: 63 ident: b0130 article-title: Handwriting and hand drawing velocity modeling by superposing beta impulses and continuous training component publication-title: Internat. J. Compute. Sci. Issues (IJCSI) contributor: fullname: Alimi – year: 2013 ident: b0040 article-title: Speech recognition with deep recurrent neural networks publication-title: Proc. ICASSP contributor: fullname: Hinton – year: 2021 ident: b0105 article-title: A novel sigma-lognormal parameter extractor for online signatures publication-title: Document Analysis and Recognition – ICDAR 2021. ICDAR 2021. Lecture Notes in Computer Science contributor: fullname: Zhang – volume: 10 start-page: 503 year: 2014 end-page: 522 ident: b0220 article-title: Graphemes segmentation for arabic online handwriting modeling publication-title: J. Inf. Process. Syst. contributor: fullname: Alimi – start-page: 477 year: 2016 end-page: 482 ident: b0135 article-title: A spiking motor-model for online handwriting movements generation publication-title: 2016 15th International Conference on Frontiers in Handwriting Recognition (ICFHR) contributor: fullname: Alimi – volume: 38 start-page: 229 year: 2018 end-page: 316 ident: b0010 article-title: Shoja: Deep Neural Networks for Natural Language Processing publication-title: Handbook of Statistics contributor: fullname: Babak – start-page: 541 year: 2012 end-page: 557 ident: b0250 article-title: Online Arabic databases and applications publication-title: Guide to OCR for Arabic Scripts contributor: fullname: Alimi – start-page: 6884 year: 2020 end-page: 6888 ident: b0260 article-title: Fast training of deep neural networks for speech recognition publication-title: ICASSP 2020–2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) contributor: fullname: Liu – volume: 4 start-page: 248 year: 2013 end-page: 255 ident: b0060 article-title: The lognormal handwriter: learning, performing, and declining publication-title: Front. Psychol. contributor: fullname: Duval – volume: 108 start-page: 321 year: 2014 end-page: 336 ident: b0100 article-title: A parsimonious oscillatory model of handwriting publication-title: Biol. Cybernet. contributor: fullname: Zanone – volume: 23 start-page: 470 year: 2020 end-page: 482 ident: b0170 article-title: SSDIS-BEM: A new signature steganography document image system based on beta elliptic modeling publication-title: Eng. Sci. Technol. Internat. J. contributor: fullname: Alimi – volume: 38 start-page: 229 year: 2018 end-page: 316 ident: b0015 article-title: Deep neural networks for natural language processing publication-title: Handbk. Stat. contributor: fullname: Babak – volume: 17 start-page: 198 year: 1991 end-page: 218 ident: b0120 article-title: A developmental study of the relation between geometry and kinematics in drawing movements publication-title: J. Experiment. Psychol. Human Percept. Perform. contributor: fullname: Schneider – volume: 5 start-page: 157 year: 1994 end-page: 166 ident: b0200 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Trans. Neural Networks contributor: fullname: Frasconi – start-page: 218 year: 2018 end-page: 222 ident: b0240 article-title: Improvement of character segmentation using recurrent neural networks and dynamic programming publication-title: IEEE Second International Conference on Data Stream Mining & Processing (DSMP) contributor: fullname: Radyvonenko – year: 2020 ident: b0045 article-title: Improving recurrent neural networks for offline arabic handwriting recognition by combining different language models publication-title: J. Pattern Recog. Artif. Intell. contributor: fullname: Kanoun – year: 1998 ident: b0070 article-title: A neural oscillator model learning given trajectories, or how an allo-imitation algorithm can be implemented into a motor controller publication-title: Motor Control and Human Skill: A Multi-disciplinary Perspective contributor: fullname: Kalveram – volume: 40 start-page: 49 year: 2007 end-page: 54 ident: b0030 article-title: Handwriting recognition: Tablet PC text input publication-title: IEEE Comput. contributor: fullname: Pittman – start-page: 69 year: 2007 end-page: 84 ident: b0095 article-title: An oscillatory neuromotor model of handwriting generation publication-title: IJDAR contributor: fullname: Srinivasa – volume: 45 start-page: 2673 year: 1997 end-page: 2681 ident: b0205 article-title: Bidirectional recurrent neural networks publication-title: IEEE Trans. Signal Process. contributor: fullname: Paliwal – volume: 42 year: 2009 ident: b0110 article-title: Development of a sigma-lognormal representation for on-line signatures publication-title: Pattern Recognit. contributor: fullname: Plamondon – volume: 11 start-page: 21033 year: 2021 ident: b0215 article-title: Accurate prediction of protein torsion angles using evolutionary signatures and recurrent neural network publication-title: Sci. Rep. contributor: fullname: Ding – year: 1988 ident: b0080 article-title: The VITE: a neural command circuit for generating arm and articulator trajectories publication-title: Dynamic Patterns in Complex Systems contributor: fullname: Grossberg – volume: 45 start-page: 131 year: 1982 end-page: 142 ident: b0085 article-title: Trajectory Formation and Handwriting a Computational Model publication-title: Biological Cybernetics contributor: fullname: Mussa Ivaldi – year: 2012 ident: b0190 article-title: Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription publication-title: Proceedings of the Twenty-nine International Conference on Machine Learning (ICML’12) contributor: fullname: Vincent – volume: 91 start-page: 200 year: 2019 end-page: 215 ident: b0175 article-title: Representation of online handwriting using multi-component sinusoidal model publication-title: Pattern Recognit.s contributor: fullname: Prasanna – volume: 9 start-page: 142 year: 2012 end-page: 151 ident: b0225 article-title: The PerTOHS theory for f or On- On - line handwriting segmentation publication-title: Int. J. Comput. Sci. Issues contributor: fullname: Alimi – volume: 97 year: 2020 ident: b0150 article-title: Towards a novel biometric system for forensic document examination publication-title: Computers & Security contributor: fullname: Alimi – volume: 156 start-page: 139 year: 1981 ident: b0065 article-title: An oscillation theory of handwriting publication-title: Biol. Cybern. contributor: fullname: Hollerbach – year: 2012 ident: b0050 article-title: Sequence transduction with recurrent neural networks publication-title: ICML Representation Learning Worksop contributor: fullname: Graves – start-page: 176 year: 2015 end-page: 180 ident: b0245 article-title: An improved segmentation of online English handwritten text using recurrent neural networks publication-title: 2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR) contributor: fullname: Nakagawa – volume: 100 start-page: 195 year: 1998 end-page: 216 ident: b0075 article-title: On-line size control in handwriting demonstrates the continuous nature of motor programs publication-title: Acta Psychol. contributor: fullname: Weber – volume: 39 start-page: 1180 year: 2017 end-page: 1194 ident: b0025 article-title: Multi-language online handwriting recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. contributor: fullname: Carbune – volume: 22 start-page: S188 year: 2019 end-page: S190 ident: b0155 article-title: Effect of age on hand drawing movement kinematics publication-title: Comput. Methods Biomechan. Biomed. Eng. contributor: fullname: Alimi – ident: 10.1016/j.jestch.2022.101215_b0005 doi: 10.1109/ICASSP40776.2020.9053993 – ident: 10.1016/j.jestch.2022.101215_b0090 – start-page: 382 year: 1997 ident: 10.1016/j.jestch.2022.101215_b0115 article-title: An evolutionary neuro-fuzzy approach to recognize online Arabic handwriting contributor: fullname: Alimi – volume: 21 start-page: 5 issue: 01 year: 2007 ident: 10.1016/j.jestch.2022.101215_b0125 article-title: On the beta-elliptic model for the control of the human arm movement publication-title: Internat. J. Pattern Recognit. Artifi. Intell. doi: 10.1142/S0218001407005272 contributor: fullname: Bezine – volume: 42 issue: 12 year: 2009 ident: 10.1016/j.jestch.2022.101215_b0110 article-title: Development of a sigma-lognormal representation for on-line signatures publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2008.10.017 contributor: fullname: O’Reilly – start-page: 176 year: 2015 ident: 10.1016/j.jestch.2022.101215_b0245 article-title: An improved segmentation of online English handwritten text using recurrent neural networks contributor: fullname: Nguyen – volume: 91 start-page: 200 year: 2019 ident: 10.1016/j.jestch.2022.101215_b0175 article-title: Representation of online handwriting using multi-component sinusoidal model publication-title: Pattern Recognit.s doi: 10.1016/j.patcog.2019.02.013 contributor: fullname: Choudhury – volume: 97 year: 2020 ident: 10.1016/j.jestch.2022.101215_b0150 article-title: Towards a novel biometric system for forensic document examination publication-title: Computers & Security doi: 10.1016/j.cose.2020.101973 contributor: fullname: Dhieb – volume: 4 start-page: 248 issue: 1 year: 2013 ident: 10.1016/j.jestch.2022.101215_b0060 article-title: The lognormal handwriter: learning, performing, and declining publication-title: Front. Psychol. contributor: fullname: Plamondon – volume: 156 start-page: 139 issue: 39 year: 1981 ident: 10.1016/j.jestch.2022.101215_b0065 article-title: An oscillation theory of handwriting publication-title: Biol. Cybern. doi: 10.1007/BF00336740 contributor: fullname: Hollerbach – volume: 10 start-page: 57 issue: 5 year: 2013 ident: 10.1016/j.jestch.2022.101215_b0130 article-title: Handwriting and hand drawing velocity modeling by superposing beta impulses and continuous training component publication-title: Internat. J. Compute. Sci. Issues (IJCSI) contributor: fullname: Boubaker – year: 2006 ident: 10.1016/j.jestch.2022.101215_b0035 article-title: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks contributor: fullname: Graves – volume: 38 start-page: 229 year: 2018 ident: 10.1016/j.jestch.2022.101215_b0010 article-title: Shoja: Deep Neural Networks for Natural Language Processing publication-title: Handbook of Statistics doi: 10.1016/bs.host.2018.07.006 contributor: fullname: Ehsan – volume: 9 start-page: 142 issue: 5 year: 2012 ident: 10.1016/j.jestch.2022.101215_b0225 article-title: The PerTOHS theory for f or On- On - line handwriting segmentation publication-title: Int. J. Comput. Sci. Issues contributor: fullname: Njah – year: 2012 ident: 10.1016/j.jestch.2022.101215_b0190 article-title: Modeling temporal dependencies in high-dimensional sequences: Application to polyphonic music generation and transcription contributor: fullname: Boulanger-Lewandowski – volume: 5 start-page: 157 issue: 2 year: 1994 ident: 10.1016/j.jestch.2022.101215_b0200 article-title: Learning long-term dependencies with gradient descent is difficult publication-title: IEEE Trans. Neural Networks doi: 10.1109/72.279181 contributor: fullname: Bengio – ident: 10.1016/j.jestch.2022.101215_b0165 – year: 2020 ident: 10.1016/j.jestch.2022.101215_b0045 article-title: Improving recurrent neural networks for offline arabic handwriting recognition by combining different language models publication-title: J. Pattern Recog. Artif. Intell. doi: 10.1142/S0218001420520072 contributor: fullname: Jemni – ident: 10.1016/j.jestch.2022.101215_b0145 doi: 10.1109/ICDARW.2019.50114 – volume: 23 start-page: 470 year: 2020 ident: 10.1016/j.jestch.2022.101215_b0170 article-title: SSDIS-BEM: A new signature steganography document image system based on beta elliptic modeling publication-title: Eng. Sci. Technol. Internat. J. contributor: fullname: Zenati – start-page: 477 year: 2016 ident: 10.1016/j.jestch.2022.101215_b0135 article-title: A spiking motor-model for online handwriting movements generation contributor: fullname: Ltaief – volume: 11 start-page: 21033 year: 2021 ident: 10.1016/j.jestch.2022.101215_b0215 article-title: Accurate prediction of protein torsion angles using evolutionary signatures and recurrent neural network publication-title: Sci. Rep. doi: 10.1038/s41598-021-00477-2 contributor: fullname: Xu – volume: 19 start-page: 1060 issue: 5 year: 1989 ident: 10.1016/j.jestch.2022.101215_b0055 article-title: An evaluation of motor models of handwriting publication-title: IEEE Trans. Syst. Man Cybern. doi: 10.1109/21.44021 contributor: fullname: Plamondon – start-page: 6884 year: 2020 ident: 10.1016/j.jestch.2022.101215_b0260 article-title: Fast training of deep neural networks for speech recognition contributor: fullname: Cong – start-page: 218 year: 2018 ident: 10.1016/j.jestch.2022.101215_b0240 article-title: Improvement of character segmentation using recurrent neural networks and dynamic programming contributor: fullname: Volkova – volume: 38 start-page: 229 year: 2018 ident: 10.1016/j.jestch.2022.101215_b0015 article-title: Deep neural networks for natural language processing publication-title: Handbk. Stat. doi: 10.1016/bs.host.2018.07.006 contributor: fullname: Ehsan – volume: 17 start-page: 198 issue: 1 year: 1991 ident: 10.1016/j.jestch.2022.101215_b0120 article-title: A developmental study of the relation between geometry and kinematics in drawing movements publication-title: J. Experiment. Psychol. Human Percept. Perform. doi: 10.1037/0096-1523.17.1.198 contributor: fullname: Viviani – volume: 45 start-page: 2673 issue: 11 year: 1997 ident: 10.1016/j.jestch.2022.101215_b0205 article-title: Bidirectional recurrent neural networks publication-title: IEEE Trans. Signal Process. doi: 10.1109/78.650093 contributor: fullname: Schuster – ident: 10.1016/j.jestch.2022.101215_b0185 – start-page: 803 year: 2019 ident: 10.1016/j.jestch.2022.101215_b0140 article-title: Hybrid DBLSTM-SVM based Beta-elliptic-CNN models for online Arabic characters recognition contributor: fullname: Hamdi – ident: 10.1016/j.jestch.2022.101215_b0195 – start-page: 541 year: 2012 ident: 10.1016/j.jestch.2022.101215_b0250 article-title: Online Arabic databases and applications contributor: fullname: Boubaker – year: 1988 ident: 10.1016/j.jestch.2022.101215_b0080 article-title: The VITE: a neural command circuit for generating arm and articulator trajectories contributor: fullname: Bullock – volume: 100 start-page: 195 year: 1998 ident: 10.1016/j.jestch.2022.101215_b0075 article-title: On-line size control in handwriting demonstrates the continuous nature of motor programs publication-title: Acta Psychol. doi: 10.1016/S0001-6918(98)00034-1 contributor: fullname: Galen – year: 2006 ident: 10.1016/j.jestch.2022.101215_b0230 article-title: Segmentation of on-line handwritten Japanese text Using SVM for improving text recognition contributor: fullname: Zhu – year: 2012 ident: 10.1016/j.jestch.2022.101215_b0050 article-title: Sequence transduction with recurrent neural networks contributor: fullname: Graves – year: 2008 ident: 10.1016/j.jestch.2022.101215_b0255 article-title: The on/off (LMCA) dual Arabic handwriting database contributor: fullname: Kherallah – volume: 22 start-page: S188 issue: sup1 year: 2019 ident: 10.1016/j.jestch.2022.101215_b0155 article-title: Effect of age on hand drawing movement kinematics publication-title: Comput. Methods Biomechan. Biomed. Eng. doi: 10.1080/10255842.2020.1714235 contributor: fullname: Dhieb – start-page: 5 year: 2017 ident: 10.1016/j.jestch.2022.101215_b0235 article-title: Deep convolutional recurrent network for segmentation-free offline handwritten japanese text recognition contributor: fullname: Ly – ident: 10.1016/j.jestch.2022.101215_b0020 doi: 10.1007/s42452-020-2234-1 – year: 1998 ident: 10.1016/j.jestch.2022.101215_b0070 article-title: A neural oscillator model learning given trajectories, or how an allo-imitation algorithm can be implemented into a motor controller contributor: fullname: Kalveram – volume: 40 start-page: 49 issue: 9 year: 2007 ident: 10.1016/j.jestch.2022.101215_b0030 article-title: Handwriting recognition: Tablet PC text input publication-title: IEEE Comput. doi: 10.1109/MC.2007.314 contributor: fullname: Pittman – volume: 45 start-page: 131 year: 1982 ident: 10.1016/j.jestch.2022.101215_b0085 article-title: Trajectory Formation and Handwriting a Computational Model publication-title: Biological Cybernetics doi: 10.1007/BF00335240 contributor: fullname: Morasso – ident: 10.1016/j.jestch.2022.101215_b0160 doi: 10.36227/techrxiv.13902650.v1 – volume: 108 start-page: 321 year: 2014 ident: 10.1016/j.jestch.2022.101215_b0100 article-title: A parsimonious oscillatory model of handwriting publication-title: Biol. Cybernet. doi: 10.1007/s00422-014-0600-z contributor: fullname: André – year: 2021 ident: 10.1016/j.jestch.2022.101215_b0105 article-title: A novel sigma-lognormal parameter extractor for online signatures contributor: fullname: Huang – volume: 39 start-page: 1180 issue: 6 year: 2017 ident: 10.1016/j.jestch.2022.101215_b0025 article-title: Multi-language online handwriting recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2016.2572693 contributor: fullname: Keysers – volume: 10 start-page: 503 issue: 4 year: 2014 ident: 10.1016/j.jestch.2022.101215_b0220 article-title: Graphemes segmentation for arabic online handwriting modeling publication-title: J. Inf. Process. Syst. doi: 10.3745/JIPS.02.0006 contributor: fullname: Boubaker – ident: 10.1016/j.jestch.2022.101215_b0180 doi: 10.1109/ICDAR.2017.152 – start-page: 69 year: 2007 ident: 10.1016/j.jestch.2022.101215_b0095 article-title: An oscillatory neuromotor model of handwriting generation publication-title: IJDAR doi: 10.1007/s10032-007-0046-0 contributor: fullname: Gangadhar – year: 2013 ident: 10.1016/j.jestch.2022.101215_b0040 article-title: Speech recognition with deep recurrent neural networks contributor: fullname: Graves – ident: 10.1016/j.jestch.2022.101215_b0210 doi: 10.1109/ICDAR.2019.00093 |
| SSID | ssj0001921156 |
| Score | 2.2689247 |
| Snippet | [Display omitted]
The beta-elliptic model (BEM) has proven a great success in several applications such as handwriting recognition and analysis, handwriting... The beta-elliptic model (BEM) has proven a great success in several applications such as handwriting recognition and analysis, handwriting identification, the... |
| SourceID | doaj crossref elsevier |
| SourceType | Open Website Aggregation Database Publisher |
| StartPage | 101215 |
| SubjectTerms | Beta-elliptic model BLSTM Deep Learning Online Handwriting modeling RNN |
| SummonAdditionalLinks | – databaseName: DOAJ Directory of Open Access Journals dbid: DOA link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LSwMxEA7iSQ_iE-uLHLwGu9lHkqP1QRHrxRZ6W_KYlRasRSv-fWeSruxJL95CWJJlJmS-2Z35PsYutbNZbvte4OEATFAyKYx1mQiSqEVC0RSOEsXRUzWcFA_TctqR-qKasEQPnAx35UgJ3VRaV_288FlwpclKwHWKwurSpGw9KzvJ1DzhFpyMynIY00Tf6Krtm4vFXXO8cuO_CClpSpIqbicuRfr-TnjqhJz7Xbazxor8Or3jHtuAxT7b7jAIHrDpLcCSR-kHCHzw-DwecYShPBFgcPos_kW0RYsXHjVvaPAxe42aXThE9McHsLKCSjfw8vC85Rg_ZJP7u_HNUKzFEoTPK7USylVSWdfkPlCzqKW8yhsfdG5DXzlMdI1CPADeNDKrMHdUEgKaRToVNJgmP2Kbi7cFHDNO7bXaG_BVA4VugnGAKEkDqOBtkZkeE62p6mXixKjbYrF5nUxbk2nrZNoeG5A9f54lRus4gX6u136u__Jzj6nWG_UaHKSgj0vNft3-5D-2P2VbtGTqQjxjm6v3TzhHOLJyF_HkfQPjidgV priority: 102 providerName: Directory of Open Access Journals |
| Title | Deep learned BLSTM for online handwriting modeling simulating the Beta-Elliptic approach |
| URI | https://dx.doi.org/10.1016/j.jestch.2022.101215 https://doaj.org/article/b132996886034c1db5915e68444a8590 |
| Volume | 35 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDI6mneCAeIrxUg5co7Vp1yRHNkATAi4MabcqDxcNiW0aQ_x97LSFceHArY2StnIs219qf2bsUjubZjbxApUDEKCkUhjrUhEkUYuEvModAcWHx2L8nN9NB9MOG7W1MJRW2dj-2qZHa92M9Btp9pezWf9JordKDEbklBaEjgntMHF7UhHfdPhzzmIQ4sQmrjRf0IK2gi6meb2i8Y1_JaSkIUn9cTc8VCTy33BUG87ndpftNFEjv6o_bI91YL7Ptje4BA_Y9BpgyWMTCAh8eP80eeAYkPKaCoPTAfknERjNX3jsfkMX77O32L0LLzEO5ENYW0FJHGhGPG_Zxg_Z8-3NZDQWTdsE4bNCrYVyhVTWVZkPVDZqCWF544PObEiUQ8hrFEYG4E0l0wJRpJIQSI5OBQ2myo5Yd76YwzHjVGirvQFfVJDrKhgHGC9pABW8zVPTY6IVVbms2THKNm3staxFW5Joy1q0PTYkeX7PJW7rOLBYvZTN5pYOATKiMK2LJMt9GtzApANAzclzqwcm6THV7kb5S1XwUbM_X3_y75WnbIvu6iLEM9Zdrz7gHKORtbuIKP4iKt0Xa37cEg |
| link.rule.ids | 315,786,790,870,2115,3525,27955,27956,45907 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1Lb9swDCa67rDtMOyJZU8ddhUSy4olHZduRbYlvTQFchP0oIsUWBp0Kfr3R8r2ll122E2QLdugCJKfTH4E-GhjqOowSZKUAwmgVEq6ECuZFVOLZN3qyEBxedbML_S39XR9BCdDLQynVfa2v7PpxVr3M-NemuPdZjM-V-StJo4ick4LIsd0D-7rKWE9ruJbz_4ctDjCOKWLKy-QvGIooSt5XldkfctvCaV4SnGD3AMXVZj8DzzVgfc5fQKP-7BRfOq-7Ckc4fYZPDogE3wO68-IO1G6QGAWs8X5aikoIhUdF4bgE_I7ZjDaXorS_oYHPzc_SvsuGlIgKGa4D5KzOMiOJDHQjb-Ai9Mvq5O57PsmyFQ3Zi9NbJQJsa1T5rrRwBAruZRtHfLERMK8zlBogMm1qmoIRhqFmQUZTbbo2volHG-vt_gKBFfa2uQwNS1q22YXkQImi2hyCrpyI5CDqPyuo8fwQ97Yle9E61m0vhPtCGYsz9_3Mrl1mbi-ufT97vpICJlgmLXNpNapynHqqimS6mgdLO3wCMywG_4vXaFHbf75-tf_vfIDPJivlgu_-Hr2_Q085CtdReJbON7f3OI7Ck328X1RvV9k-d5C |
| 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=Deep+learned+BLSTM+for+online+handwriting+modeling+simulating+the+Beta-Elliptic+approach&rft.jtitle=Engineering+science+and+technology%2C+an+international+journal&rft.au=Hamdi%2C+Yahia&rft.au=Boubaker%2C+Houcine&rft.au=Rabhi%2C+Besma&rft.au=Qahtani%2C+Abdulrahman+M.&rft.date=2022-11-01&rft.pub=Elsevier+B.V&rft.issn=2215-0986&rft.eissn=2215-0986&rft.volume=35&rft_id=info:doi/10.1016%2Fj.jestch.2022.101215&rft.externalDocID=S2215098622001240 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2215-0986&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2215-0986&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2215-0986&client=summon |