Summary of Handwriting-based Automated Assessment and Grading Of Degree Of Handedness: a Pilot Study, by Smriti Bala et al.
Handwriting-based Automated Assessment and Grading of Degree of Handedness: A Pilot Study
by Smriti Bala, Venugopalan Y. Vishnu, Deepak Joshi
First submitted to arxiv on: 2 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Human-Computer Interaction (cs.HC)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents a novel approach to quantify degree of handedness (DoH) by analyzing dominant and non-dominant handwriting traits. The authors extracted features from segmented handwriting signals, known as strokes, and used machine learning algorithms such as Convolutional Neural Network (CNN), Multilayer Perceptron, and Davies Bouldin Index for automated grading of DoH. The results show that the CNN-based method outperformed others with an average classification accuracy of 95.06% under stratified 10-fold cross-validation. The authors also compared their computational methods with widely used DoH assessment questionnaires from Edinburgh Inventory (EI), finding around 90% agreement between the two approaches. This study demonstrates the potential for automated grading of DoH using handwriting signals, which could have applications in neuroscience, rehabilitation, physiology, psychometry, behavioral sciences, and forensics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study shows how machines can be used to figure out how “left- or right-handed” someone is based on their handwriting. The researchers took handwriting from 43 people with different levels of handedness and used special computer algorithms to analyze the writing. They found that a type of machine learning called Convolutional Neural Network (CNN) was best at guessing how left- or right-handed someone was, getting it right about 95% of the time. The researchers also compared their method with a standard way of measuring handedness, and found they agreed most of the time. This could be useful in many fields, such as understanding how our brains work, helping people recover from injuries, and even solving crimes. |
Keywords
» Artificial intelligence » Classification » Cnn » Machine learning » Neural network
