Quantitative Assessment Of Handwriting Movement For Specific Groups

As a specific fine movement, handwriting movement closely relates to human brain function and cognitive level. Few studies have paid attention to the distribution of handwriting ability of health groups, and the evaluation system of handwriting motor abilities. In this paper, we focused on the healthy children and adults with neurodegenerative disease. We investigated the human handwriting development when the nervous system changes. The main contents are as follows:(1) The trend analysis of handwriting motor function. As a basic tool to help child express and learning, handwriting plays an important role in children’s cognitive and psychological development process. The research on the development trend of the children’s handwriting motor function is helpful to establish the normal pattern data, and provides an effective contrast method for children of different ages with diseases.In this paper, the motion force was analyzed based on the three-dimensional force information, and the motion consistency parameters were proposed. With kinematic and kinetic characteristics, we studied the handwriting motor function by quantitative assessment. The results showed that children with higher grade have shorter movement time, higher velocity, and fewer changes in the direction of velocity curve, smaller force and total energy to complete handwriting tasks. The indirect visual feedback experiment was designed to validate that children in higher grades have better sense of spacing. The proposed features are effective in measuring the development of handwriting movement.(2) The characteristic analysis of handwriting disability. Neurodegenerative diseases can cause sustained damage to brain function. Although drug treatment has a certain role in the control of the disease, it still cannot prevent the development of disease. It is significant to explore new and effective biomarkers to achieve early diagnosis and condition monitoring of the disease.In this paper, we designed the quantitative detection method of Parkinson’s handwriting performance. The results showed that there were significant differences in speed, acceleration, NCR, PFA and PFA features between the PD group and the control group. We believed that this method can help to detect the potential abnormal changes of human fine motor function, which is beneficial for the assistant diagnosis.(3) The auxiliary diagnosis based on handwriting features and machine learning algorithms. The traditional score scale is difficult to quantitatively monitor the progress of the disease, and the single feature based on the statistical analysis method cannot provide an effective distinction between groups accurately. The more intelligent screening and testing tools are needed to be explored.We constructed the handwritten motion feature set based on the statistical analysis results. Besides, the machine learning methods were introduced for the group classification, and the effect of those methods was analyzed. The improvement of the accuracy and effectiveness of classification is helpful to automatically screen writing difficulties and diagnosis diseases.In summary, this paper presented a quantitative analysis of the development trend of handwriting function in different groups. A number of features were extracted to evaluate the handwriting ability of children and patients with Parkinson’s disease. A handwriting movement information acquisition and analysis system was constructed. Based on our study, more handwriting samples of healthy people will be collected, which contributes to the combination of the clinical application and the computer-based quantitative score model providing support for the auxiliary diagnosis and intervention training clinically.