Fractional Order Derivatives Evaluation in Computerized Assessment of Handwriting Difficulties in School-aged Children

Zvončák, Vojtěch; Mucha, Ján; Galáž, Zoltán; Mekyska, Jiří; Šafárová, Katarína; Faundez-Zanuy, Marcos; Smékal, Zdeněk

doi:10.1109/icumt48472.2019.8970811

Cited by 10 publications

(7 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…. For more information, see our previous works [12], [14], [28]. An example of the selected combined loop task performed by a child with/without GD can be seen in Fig.…”

Section: Dataset and Methodology A Datasetmentioning

confidence: 99%

“…The essential of this study is the investigation of the several (non-equivalent) FD approximations as a new advanced approach of drawing/handwriting parameterisation. We developed this method to substitute the conventional differential derivatives in the feature extraction process (see our previous works [9]- [12], [28]) in order to improve the quantitative analysis of the GD. In the scope of this study, we utilized three FD approximations: Grünwald-Letnikov (GL), Riemann-Liouville (RL), and Caputo (C), implemented by Valério Duarte in Matlab [29]- [31].…”

Section: Fractional Order Derivativesmentioning

confidence: 99%

“…Considering the success of utilizing the FD (Grünwald-Letnikov approach) in Parkinson's disease dysgraphia analysis in our previous works [9]- [12], and in the assessment of GD in school-aged children [13], [28], this study, as a next logical step, has the following aims:…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of Various Fractional Order Derivatives Approaches in Assessment of Graphomotor Difficulties

et al. 2020

Self Cite

View full text Add to dashboard Cite

“…. For more information, see our previous works [12], [14], [28]. An example of the selected combined loop task performed by a child with/without GD can be seen in Fig.…”

Section: Dataset and Methodology A Datasetmentioning

confidence: 99%

Section: Fractional Order Derivativesmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of Various Fractional Order Derivatives Approaches in Assessment of Graphomotor Difficulties

et al. 2020

Self Cite

View full text Add to dashboard Cite

“…Using only conventional handwriting features, they trained an XGBoost [34] classifier and achieved 50 % sensitivity and 90 % specificity. In the same year, Zvoncak et al [35] used features based on fractional order derivatives to enrich a set of conventional features and analysed their correlation with HPSQ-C in 55 children (19 third-grade children, and 36 fourth-grade children) performing an alphabet writing task. With this setup, they reported that features based on fractional order derivatives improved quantification and robustness of the description of in-air movements.…”

Section: Introductionmentioning

confidence: 99%

Advanced Parametrization of Graphomotor Difficulties in School-Aged Children

et al. 2020

Self Cite

View full text Add to dashboard Cite

School-aged children spend 31-60 % of their time at school performing handwriting, which is a complex perceptual-motor skill composed of a coordinated combination of fine graphomotor movements. As up to 30 % of them experience graphomotor difficulties (GD), timely diagnosis of these difficulties and therapeutic intervention are of great importance. At present, an objective, computerized decision support system for the identification and assessment of GD in school-aged children is still missing. In this study, we propose three novel advanced handwriting parametrization techniques based on modulation spectra, fractional order derivatives, and tunable Q-factor wavelet transform to improve the identification of GD using online handwriting. For this purpose, we analyzed signals acquired from 7 basic graphomotor tasks performed by 53 children attending 3rd and 4th grade at several primary schools around the Czech Republic. Combining the newly proposed features with the conventionally used ones, we were able to identify GD with 84 % accuracy. In this study, we showed that using advanced parametrization of basic graphomotor movements can be potentially used to improve our capabilities of quantifying problems with the development of legible, fast-paced handwriting, and help with the early diagnosis of handwriting difficulties frequently manifested in developmental dysgraphia.

show abstract

“…They also investigated the possibility of using the fractional-order-derivative-based features in the computerized rating of the level of handwriting difficulties. They were able to estimate external validation scores with an error of 0.65 points (while the scale was in the range of 0-4) employing gradient boosting algorithms [11].…”

Section: State Of the Artmentioning

confidence: 99%

Discovering relationship between graphomotor difficulties and isochrony in childrens online handwriting

Gavenčiak¹,

Zvončák²,

Mekyska³

2022

Proceedings II of the 28st Conference STUDENT EEICT 2022: Selected Papers.

View full text Add to dashboard Cite

Approximately 30-60 % of the time children spend in school is associated with handwriting. However, up to 30% of them experience graphomotor difficulties (GD), which lead to a decrease in their academic performance. Current GD diagnostic methods are not unified and show signs of subjectivity which can lead to misdiagnosis. This paper proposes novel handwriting features based on movement isochorny that enable computerised assessment of GD with approximately 20 % error.

show abstract

Fractional Order Derivatives Evaluation in Computerized Assessment of Handwriting Difficulties in School-aged Children

Cited by 10 publications

References 27 publications

Analysis of Various Fractional Order Derivatives Approaches in Assessment of Graphomotor Difficulties

Analysis of Various Fractional Order Derivatives Approaches in Assessment of Graphomotor Difficulties

Advanced Parametrization of Graphomotor Difficulties in School-Aged Children

Discovering relationship between graphomotor difficulties and isochrony in childrens online handwriting

Contact Info

Product

Resources

About