Vliv intra-writer normalizace na diagnózu vývojové dysgrafie založené na kvantitativní analýze online písma
Loading...
Date
2018-12-31
Authors
Zvončák, Vojtěch
Mekyska, Jiří
Šafárová, Katarína
Mucha, Ján
Kiska, Tomáš
Losenická, Barbora
Čechová, Barbora
Francová, Pavlína
Smékal, Zdeněk
ORCID
Advisor
Referee
Mark
Journal Title
Journal ISSN
Volume Title
Publisher
International Society for Science and Engineering, o.s.
Abstract
U dětí se vývojová dysgragrafie (VD) projevuje pomalejším psaním, zhoršenou čitelností písma a zároveň negativním vlivem na plánování a generování obsahového textu. Takové projevy VD můžou v průběhu dospívání škodlivě působit na sebevyjadřování a komunikační dovednosti dítěte. Cílem této studie je výzkum nových normalizačních metod IWN (Intra-writer normalization methods), které povedou ke zlepšení diagnózy VD založené na kvantitativní analýze online písma. Pro tento účel bylo analyzováno písmo 97 dětí, které psaly zadaný text na digitalizační tablet. Jejich schopnost psát byla hodnocena pomocí škály HPSQ (Handwriting proficiency screening questionnaire). Ze záznamu písemného projevu byly extrahovány konvenční parametry, které se následně normalizovaly pomocí čtyř nových IWN metod. Z výsledků vyplývá, že tahově orientovaná normalizace využívající normu z-skór snížila chybu odhadu HPSQ při hodnocení VD z 23% na 19%. Tato studie dokazuje, že tahově orientovaná IWN má slibný potenciál na poli automatizované diagnózy a hodnocení VD.
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 Zscore 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.
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 Zscore 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.
Description
Keywords
Citation
Document type
Peer-reviewed
Document version
Published version
Date of access to the full text
Language of document
cs
Study field
Comittee
Date of acceptance
Defence
Result of defence
Document licence
(C) 2018 Elektrorevue