{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T15:11:06Z","timestamp":1776784266267,"version":"3.51.2"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T00:00:00Z","timestamp":1694563200000},"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. Robot. AI"],"abstract":"<jats:p><jats:bold>Introduction:<\/jats:bold> Handwriting is a complex task that requires coordination of motor, sensory, cognitive, memory, and linguistic skills to master. The extent these processes are involved depends on the complexity of the handwriting task. Evaluating the difficulty of a handwriting task is a challenging problem since it relies on subjective judgment of experts.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> In this paper, we propose a machine learning approach for evaluating the difficulty level of handwriting tasks. We propose two convolutional neural network (CNN) models for single- and multilabel classification where single-label classification is based on the mean of expert evaluation while the multilabel classification predicts the distribution of experts\u2019 assessment. The models are trained with a dataset containing 117 spatio-temporal features from the stylus and hand kinematics, which are recorded for all letters of the Arabic alphabet.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> While single- and multilabel classification models achieve decent accuracy (96% and 88% respectively) using all features, the hand kinematics features do not significantly influence the performance of the models.<\/jats:p><jats:p><jats:bold>Discussion:<\/jats:bold> The proposed models are capable of extracting meaningful features from the handwriting samples and predicting their difficulty levels accurately. The proposed approach has the potential to be used to personalize handwriting learning tools and provide automatic evaluation of the quality of handwriting.<\/jats:p>","DOI":"10.3389\/frobt.2023.1193388","type":"journal-article","created":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T13:02:27Z","timestamp":1694610147000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Assessing handwriting task difficulty levels through kinematic features: a deep-learning approach"],"prefix":"10.3389","volume":"10","author":[{"given":"Vahan","family":"Babushkin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haneen","family":"Alsuradi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Hassan","family":"Jamil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhamed Osman","family":"Al-Khalil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mohamad","family":"Eid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,9,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3140","DOI":"10.1038\/s41598-020-60011-8","article-title":"Extending the spectrum of dysgraphia: A data driven strategy to estimate handwriting quality","volume":"10","author":"Asselborn","year":"2020","journal-title":"Sci. Rep."},{"key":"B2","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1038\/s41746-018-0049-x","article-title":"Automated human-level diagnosis of dysgraphia using a consumer tablet","volume":"1","author":"Asselborn","year":"2018","journal-title":"npj Digit. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"1648","DOI":"10.1016\/j.ridd.2014.03.024","article-title":"The effect of computer-assisted therapeutic practice for children with handwriting deficit: A comparison with the effect of the traditional sensorimotor approach","volume":"35","author":"Chang","year":"2014","journal-title":"Res. Dev. Disabil."},{"key":"B4","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s11251-005-5774-2","article-title":"Towards a personalized task selection model with shared instructional control","volume":"34","author":"Corbalan","year":"2006","journal-title":"Instr. Sci."},{"key":"B5","first-page":"36","article-title":"Automatic text difficulty classifier","author":"Curto","year":"2015"},{"key":"B6","doi-asserted-by":"publisher","first-page":"169","DOI":"10.3389\/fpsyg.2015.00169","article-title":"Basic and supplementary sensory feedback in handwriting","volume":"6","author":"Danna","year":"2015","journal-title":"Front. Psychol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"21541","DOI":"10.1038\/s41598-020-78611-9","article-title":"Dysgraphia detection through machine learning","volume":"10","author":"Drot\u00e1r","year":"2020","journal-title":"Sci. Rep."},{"key":"B8","doi-asserted-by":"publisher","first-page":"e20126","DOI":"10.2196\/20126","article-title":"A tablet app for handwriting skill screening at the preliteracy stage: instrument validation study","volume":"8","author":"Dui","year":"2020","journal-title":"JMIR Serious Games"},{"key":"B9","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1080\/19411243.2018.1534634","article-title":"Handwriting acquisition and intervention: A systematic review","volume":"11","author":"Fancher","year":"2018","journal-title":"J. Occup. Ther. Sch. Early Intervention"},{"key":"B10","volume-title":"Shapley values for feature selection: The good, the bad, and the axioms","author":"Fryer","year":"2021"},{"key":"B11","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1007\/978-3-540-24775-3_5","article-title":"Discriminative methods for multi-labeled classification","volume-title":"Advances in knowledge discovery and data mining","author":"Godbole","year":"2004"},{"key":"B12","volume-title":"The shifting paradigm of teaching: Personalized learning according to teachers","author":"Jenkins","year":"2016"},{"key":"B13","first-page":"268","article-title":"Structural features extraction for handwritten arabic personal names recognition","author":"Kacem","year":"2012"},{"key":"B14","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1080\/08856257.2011.593821","article-title":"The effectiveness of assistive technologies for children with special needs: A review of research-based studies","volume":"26","author":"Maor","year":"2011","journal-title":"Eur. J. Special Needs Educ."},{"key":"B15","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1109\/THMS.2016.2586605","article-title":"Identification and rating of developmental dysgraphia by handwriting analysis","volume":"47","author":"Mekyska","year":"2016","journal-title":"IEEE Trans. Human-Machine Syst."},{"key":"B16","first-page":"181","volume-title":"Challenges in baseline detection of Arabic script based languages","author":"Naz","year":"2014"},{"key":"B17","doi-asserted-by":"publisher","first-page":"5516","DOI":"10.1038\/s41598-017-05105-6","article-title":"Children\u2019s first handwriting productions show a rhythmic structure","volume":"7","author":"Pagliarini","year":"2017","journal-title":"Sci. Rep."},{"key":"B18","doi-asserted-by":"publisher","first-page":"298","DOI":"10.5014\/ajot.62.3.298","article-title":"Development, reliability, and validity of the handwriting proficiency screening questionnaire (HPSQ)","volume":"62","author":"Rosenblum","year":"2008","journal-title":"Am. J. Occup. Ther."},{"key":"B19","doi-asserted-by":"publisher","first-page":"933","DOI":"10.2466\/pms.2003.96.3.933","article-title":"The in air phenomenon: temporal and spatial correlates of the handwriting process","volume":"96","author":"Rosenblum","year":"2003","journal-title":"Percept. Mot. Ski."},{"key":"B20","first-page":"307","article-title":"A value for n-persons games","volume":"28","author":"Shapley","year":"1953","journal-title":"Ann. Math. Stud."},{"key":"B21","first-page":"25","volume-title":"A literature survey on algorithms for multi-label learning","author":"Sorower","year":"2010"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.4018\/jdwm.2007070101","article-title":"Multi-label classification: an overview","volume":"3","author":"Tsoumakas","year":"2007","journal-title":"Int. J. Data Warehous. Min. (IJDWM)"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1016\/j.patcog.2006.12.019","article-title":"ML-KNN: A lazy learning approach to multi-label learning","volume":"40","author":"Zhang","year":"2007","journal-title":"Pattern Recognit."}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2023.1193388\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,13]],"date-time":"2023-09-13T13:02:32Z","timestamp":1694610152000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2023.1193388\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,13]]},"references-count":23,"alternative-id":["10.3389\/frobt.2023.1193388"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2023.1193388","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9,13]]},"article-number":"1193388"}}