Vliv intra-writer normalizace na diagnózu vývojové dysgrafie založené na kvantitativní analýze online písma

Investor logo

Warning

This publication doesn't include Faculty of Economics and Administration. It includes Faculty of Arts. Official publication website can be found on muni.cz.
Title in English Influence of intra-writer normalization on developmental dysgraphia diagnosis based on quantitative analysis of online handwriting
Authors

ZVONČÁK Vojtěch MEKYSKA Jiří ŠAFÁROVÁ Katarína MUCHA Ján KISKA Tomáš LOSENICKÁ Barbora ČECHOVÁ Barbora FRANCOVÁ Pavlína SMÉKAL Zdeněk

Year of publication 2018
Type Article in Periodical
Magazine / Source Elektrorevue
MU Faculty or unit

Faculty of Arts

Citation
Web http://www.elektrorevue.cz/cz/download/vliv-intra-writer-normalizace-na-diagnozu-vyvojove-dysgrafie-zalozene-na-kvantitativni-analyze-online-pisma--influence-of-intra-writer-normalization-on-developmental-dysgraphia-diagnosis-based-on-quantitative-analys
Keywords developmental dysgraphia; child dysgraphia; digitizing tablets; HPSQ; SFFS; random forests; gradient boost trees; xgboost
Description Developmental dysgraphia (DD) in children population is manifested predominantly in slowness of writing, reduced written text readability, and impaired ability to plan and generate textual content. These symptoms affect children's capabilities of self-expressing and communicating. The goal of this work is the investigation and development of novel intra-writer normalization (IWN) methods in direction of improving DD diagnosis based on quantitative analysis of online handwriting. For this purpose, handwriting signals acquired by digitization tablet of 97 children were analyzed. Their ability to write was quantified by Handwriting proficiency screening questionnaire (HPSQ). From the acquired signals, conventional parameters were extracted. These parameters were consequently normalized by four IWN methods. The results show that stroke-based normalization based on the Z-score norm reduced an error of HPSQ prediction by 4% (from 23% to 19%). This proves the potential of such a~normalization to improve the automated diagnosis and assessment of DD.
Related projects:

You are running an old browser version. We recommend updating your browser to its latest version.