Motor skills are crucial for young children’s academic and social growth, making early detection of motor skill delays critical. Although the current work in digital assessments and tablets in classrooms offer accessible diagnostic tools, they only provide general diagnostics. This leaves teachers to identify specific deficiencies, create lesson plans, and monitor progress, which is challenging due to high teacher-to-student ratios. We take a step towards an assessment that can identify development levels in specific instances of writing through the analysis of the relationship between shape drawings and the letter development levels of children in specific instances. In this study, we collected 133 letter writings and 339 shape drawings from 58 unique participants ages 3-5. Every letter writing was categorized as either developing or developed, and each letter was paired with the corresponding set of Rubine on Steroid features extracted from a series of circle, square, and triangle drawings. We grouped each of the features by development level of letter for the A, B, and C and calculated the Pearson Correlation Coefficient for each feature. We then took the top 15 correlated features and ran Unpaired T-tests to assess whether each feature exhibited significant differences among the different developmental groups. We found a weak to moderate relationship between the features and 40 out of 45 features demonstrated statistically significant differences when comparing them across the different developmental groups. Additionally, A further look into these features yielded insight into different aspects of shape drawings and their respective characteristics and their possible relationship to the developmental level of each letter.

From an early age, children begin developing critical motor skills, such as fine motor control, that contribute significantly to reading, writing, drawing, and more, all of which are important for communication and school readiness. Pediatricians can evaluate a child’s motor skills using activities and questionnaires. Sometimes these involve adults drawing with their child, but it can be difficult to fully evaluate a child’s drawings through a handful of sketches from limited direct assessments. We propose creating a sketching system that will collect free-form drawing data from parents and children that can then automatically differentiate a child’s sketch from an adult’s using only the pen strokes of their drawing. In this paper, we describe our study that collected sketches from 14 children aged 2 to 5 and 25 adults over 18. We contribute a machine learning classifier based on sketch recognition features from free-hand drawings capable of distinguishing children’s sketches from those made by adults with an F-measure of 0.906. These results indicate the potential of creating sketch-based applications for assessing children’s fine motor development.

The shift to virtual has changed our society and left an impact on nearly every part of our lives. Although it brought many challenges, global remote access also opened up a world of educational and professional opportunities for many people who did not have them before. In this work, we detail the findings of a study collecting feedback on inclusivity in virtual, in-person, and hybrid spaces, with the goal of building a greater understanding of the issues and personal challenges faced by access and equity stakeholders. From a survey of 104 individuals and detailed interviews with 12, we have used a mix of qualitative and quantitative methods to discover key challenges. The diversity of experiences and opinions was striking, with many winners and losers going into the virtual space. We propose some modifications to the online environment and in-person practices with the aim of furthering equality.

Engineering students need practical, open-ended problems to help them build their problem-solving skills and design abilities. However, large class sizes create a grading challenge for instructors as there is simply not enough time nor support to provide adequate feedback on many design problems. In this work, we describe an intelligent user interface to provide automated real-time feedback on hand-drawn free body diagrams that is capable of analyzing the internal forces of a sketched truss to evaluate open-ended design problems. The system is driven by sketch recognition algorithms developed for recognizing trusses and a robust linear algebra approach for analyzing trusses. Students in an introductory statics course were assigned a truss design problem as a homework assignment using either paper or our software. We used conventional content analysis on four focus groups totaling 16 students to identify key aspects of their experiences with the design problem and our software. We found that the software correctly analyzed all student submissions, students enjoyed the problem compared to typical homework assignments, and students found the problem to be good practice. Additionally, students using our software reported less difficulty understanding the problem, and the majority of all students said they would prefer the software approach over pencil and paper. We also evaluated the recognition performance on a set of 3000 sketches resulting in an f-score of 0.997. We manually reviewed the submitted student work which showed the handful of student complaints about recognition were largely due to user error.

Searching is a necessary tool for managing and navigating the massive amounts of data available in today's information age. While new searching methods have become increasingly popular and reliable in recent years, such as image-based searching, these methods may be more limited than text-based means in that they do not allow generic user input. Sketch-based searching is a method that allows users to draw generic search queries and return similar drawn images, giving more user control over their search content. In this paper, we present SketchSeeker, a system for indexing and searching across a large number of sketches quickly based on their similarity. SketchSeeker introduces a technique for indexing sketches in extremely compressed representations, which allows for fast, accurate retrieval augmented with a multilevel ranking subsystem. SketchSeeker was tested on a large set of sketches against existing sketch similarity metrics, and it shows significant improvements in terms of storage requirements, speed, and accuracy.

We present SABR (Sparse, Anchor-Based Representation), an analysis technique to decompose the speech signal into speaker-dependent and speaker-independent components. Given a collection of utterances for a particular speaker, SABR uses the centroid for each phoneme as an acoustic “anchor, ” then applies Lasso regularization to represent each speech frame as a sparse non-negative combination of the anchors. We illustrate the performance of the method on a speaker-independent phoneme recognition task and a voice conversion task. Using a linear classifier, SABR weights achieve significantly higher phoneme recognition rates than Mel frequency Cepstral coefficients. SABR weights can also be used directly to perform accent conversion without the need to train a speaker-to-speaker regression model.