Analyses of pupils’ polygonal shape drawing strategy with respect to handwriting performance

Tabatabaey-Mashadi, Narges; Sudirman, Rubita; Guest, Richard; Khalid, Puspa Inayat

doi:10.1007/s10044-014-0423-5

Cited by 14 publications

(19 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous studies have suggested that some handwriting features (e.g. in-air time, drawing strategies and pen pressure) have the potential of indicating HWDs in children, although they have not been systematically examined [9], [16], [17], [20], [35]- [39]. For example, Rosenblum used a computerized digitizer system to compare the temporal handwriting features of two groups (non-proficient vs. proficient) of 8-9-year-old students [17].…”

Section: Tablet-based Evaluationmentioning

confidence: 99%

“…Machine learning is a fast-growing discipline which provides such a method of automatically learning to recognize complex patterns from data [41]. A few efforts [15], [20] have been made to develop automated methods for detecting HWDs using classification algorithms and showed promising results. For example, a significant study by Richardson et al [15] presented COACH (a Cumulative Online Algorithm for Classification of Handwriting deficiencies) based on the writing features such as pen's tilt, pressure and in air time and obtained overall classification accuracy of 75%; a recent study [20] also applied SVMs to detecting HWDs in children based on the triangle drawing strategy and obtained the accuracy and sensitivity of 63.48% and 68.57%, respectively.…”

Section: Tablet-based Evaluationmentioning

confidence: 99%

“…A few efforts [15], [20] have been made to develop automated methods for detecting HWDs using classification algorithms and showed promising results. For example, a significant study by Richardson et al [15] presented COACH (a Cumulative Online Algorithm for Classification of Handwriting deficiencies) based on the writing features such as pen's tilt, pressure and in air time and obtained overall classification accuracy of 75%; a recent study [20] also applied SVMs to detecting HWDs in children based on the triangle drawing strategy and obtained the accuracy and sensitivity of 63.48% and 68.57%, respectively. The studies [15], [20] have showed the potential of classification algorithms in detecting HWDs, but they are still at an early stage and have the following limitations.…”

Section: Tablet-based Evaluationmentioning

confidence: 99%

“…There has been a need for an automated method for detecting HWDs that can lower the cost of evaluation, provide support to inexperienced therapists and enable reevaluation throughout therapy to test for improvement [15]. To meet the need, a few studies ( [15], [20]) have attempted to use classification algorithms to detect HWDs automatically. The studies have shown the possibility of using classification algorithms to automatically detect HWDs, but they are still at an early stage and have the following limitations.…”

Section: Introductionmentioning

confidence: 99%

“…Second, only a small proportion of children have HWDs in real life, and thus the samples for classification are class-imbalanced data; however, the performance of classification algorithms on such a real (imbalanced) data set has not been examined. Third, they identified HWDs from drawing strategies [20] or handwriting features [15], but the potential of using classification algorithms to detect Chinese HWDs has not been explored. Each written language has its unique characteristics and formats [1].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Automated Detection of Children at Risk of Chinese Handwriting Difficulties Using Handwriting Process Information: An Exploratory Study

Lin

2019

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Handwriting difficulties (HWDs) in children have adverse effects on their confidence and academic progress. Detecting HWDs is the first crucial step toward clinical or teaching intervention for children with HWDs. To date, how to automatically detect HWDs is still a challenge, although digitizing tablets have provided an opportunity to automatically collect handwriting process information. Especially, to our best knowledge, there is no exploration into the potential of combining machine learning algorithms and the handwriting process information to automatically detect Chinese HWDs in children. To bridge the gap, we first conducted an experiment to collect sample data and then compared the performance of five commonly used classification algorithms (Decision tree, Support Vector Machine (SVM), Artificial Neural Network, Naïve Bayesian and k-Nearest Neighbor) in detecting HWDs. The results showed that: (1) only a small proportion (13%) of children had Chinese HWDs and each classification model on the imbalanced dataset (39 children at risk of HWDs versus 261 typical children) produced the results that were better than random guesses, indicating the possibility of using classification algorithms to detect Chinese HWDs; (2) the SVM model had the best performance in detecting Chinese HWDs among the five classification models; and (3) the performance of the SVM model, especially its sensitivity, could be significantly improved by employing the Synthetic Minority Oversampling Technique to handle the class-imbalanced data. This study gains new insights into which handwriting features are predictive of Chinese HWDs in children and proposes a method that can help the clinical and educational professionals to automatically detect children at risk of Chinese HWDs.

show abstract