Handwriting is an essential skill for developing sensorimotor and intellectual skills in children. Handwriting constitutes a complex activity relying on cognitive, visual-motor, memory and linguistic abilities, and is therefore challenging to master, especially for children with learning difficulties such as those with cognitive, sensorimotor or memory deficits. Recently-emerged haptic guidance systems have a potential to facilitate the acquisition of handwriting skills in both adults and children. In this paper we present a longitudinal experimental study that examined the effects of haptic guidance to improve handwriting skills in children with cognitive and fine motor delays as a function of the handwriting complexity in terms of visual familiarity and haptic difficulty. A haptic-based handwriting training platform that provides haptic guidance along the trajectory of a handwriting task was utilized. 12 children with cognitive and fine motor delays defined in terms of intellectual difficulty (IQ score) and mild motor difficulty in pincer grasp control, participated in the study. Children were divided into two groups, a target group and a control group. The target group completed haptic-guided training and pencil-and-paper test whereas the control group took only the pencil-and-paper test without any training. A total of 32 handwriting tasks was used in the study where 16 tasks were used for training while the entire 32 tasks were completed for evaluation. Results demonstrated that the target group performed significantly better than the control group for handwriting tasks that are visually familiar but haptically difficult (Wilcoxon signed-rank test, p $<; $ 0.01). An improvement was also seen in the performance of untrained tasks as well as trained tasks (Spearman's linear correlation coefficient, 0.667; p $=$ 0.05). In addition to confirming that haptic guidance can significantly improve motor functions, this study revealed a significant effect of task difficulty (visual familiarity and haptic complexity) on the effectiveness of haptic guidance for handwriting skill acquisition for children with cognitive and fine motor delays.

Handwriting style is an important aspect affecting the quality of handwriting. Adhering to one style is crucial for languages that follow cursive orthography and possess multiple handwriting styles, such as Arabic. The majority of available studies analyze Arabic handwriting style from static documents, focusing only on pure styles. In this study, we analyze handwriting samples with mixed styles, pure styles (Ruq’ah and Naskh), and samples without a specific style from dynamic features of the stylus and hand kinematics. We propose a model for classifying handwritten samples into four classes based on adherence to style. The stylus and hand kinematics data were collected from 50 participants who were writing an Arabic text containing all 28 letters and covering most Arabic orthography. The parameter search was conducted to find the best hyperparameters for the model, the optimal sliding window length, and the overlap. The proposed model for style classification achieves an accuracy of 88%. The explainability analysis with Shapley values revealed that hand speed, pressure, and pen slant are among the top 12 important features, with other features contributing nearly equally to style classification. Finally, we explore which features are important for Arabic handwriting style detection.

A sensorimotor skill is a sequence of motions generated in response to external stimuli and aiming to accomplish a particular task. It can be communicated to reproduce the task in a distant environment with similar settings. In this work, we conceptualize a multi-modal sensorimotor skill communication system that incorporates modeling, simulation, and evaluation of the sensorimotor skill. The proposed sensorimotor skill communication system can be applied for learning a specific style of human sensorimotor skill and teaching the skill to distant learners, which can be implemented in a variety of applications such as Tele-consultation, Tele-diagnosis, Tele-treatment, Tele-monitoring, and Tele-support. To understand the processes behind the communication of sensorimotor skill we review the representation of a human sensorimotor system from the neurobiological perspective. Then we analyze the existing literature on sensorimotor skill communication systems and propose a taxonomy of currently available methods for sensorimotor skill modeling, simulation, and evaluation. Furthermore, we propose a benchmark for evaluating the quality of the sensorimotor skill communication system. We present a case study aiming to demonstrate modeling the dental sensorimotor skill of periodontal probing. Lastly, we discuss challenges and limitations and provide perspectives for future research in developing sensorimotor skill communication systems.

Currently available dental simulators provide a wide range of visual, auditory, and haptic cues to play back the pre-recorded skill, however, they do not extract skill descriptors and do not attempt to model the skill. To ensure efficient communication of a sensorimotor skill, a model that captures the skill's main features and provides real-time feedback and guidance based on the user's expertise is desirable. To develop this model, a complex periodontal probing skill can be considered as a composition of primitives, that can be extracted from the recordings of several professionals performing the probing task. This model will be capable of evaluating the user's proficiency level to ensure adaptation and providing corresponding guidance and feedback. We developed a SVM model that characterizes the sensorimotor skill of periodontal probing by detecting the specific region of the tooth being probed. We explore the features affecting the accuracy of the model and provide a reduced feature set capable of capturing the regions with relatively high accuracy. Finally, we consider the problem of periodontal pocket detection. The SVM model trained to detect pockets was able to achieve a recall around 0.68. We discuss challenges associated with pocket detection and propose directions for future work.