EAI Endorsed Transactions on Creative Technologies https://publications.eai.eu/index.php/ct <p>EAI Endorsed Transactions on Creative Technologies is open access, a peer-reviewed scholarly journal focused on a whole industrial project or framework integrating creative technologies, creative content management, and more. The journal publishes research articles, review articles, commentaries, editorials, technical articles, and short communications with a quarterly frequency (four issues per year). Authors are not charged for article submission and processing.</p> European Alliance for Innovation (EAI) en-US EAI Endorsed Transactions on Creative Technologies 2409-9708 <p>This is an open-access article distributed under the terms of the Creative Commons Attribution <a href="https://creativecommons.org/licenses/by/3.0/" target="_blank" rel="noopener">CC BY 3.0</a> license, which permits unlimited use, distribution, and reproduction in any medium so long as the original work is properly cited.</p> TailorEd: Classroom Configuration and Activity Identifiers (CCID & CAID) https://publications.eai.eu/index.php/ct/article/view/2229 <p>INTRODUCTION: The study of how classroom layout and activities affect learning outcomes of students with different demographics is difficult because it is hard to gather accurate information on the minute by minute progression of every class in a course. Furthermore, the process of data gathering must produce an abundance of data to work with and hence must be automated.</p> <p><br />OBJECTIVES: A machine learning model trained on images of a classroom and thus capable of accurately labeling the classroom layout and activity of many thousands of images much faster and cheaper than employing a human. </p> <p><br />METHODS: Transfer learning can allow for preexisting computer vision models to be retrained on a smaller, more specific dataset in order to still achieve a highly accurate result. </p> <p><br />RESULTS: In the case of the classroom layout, the final model achieved an accuracy of 97% on a four category classification. And for detecting the classroom activity, after experimentation with several different versions that could work on a very small sample sizes, the best model achieved an accuracy of 86.17%.</p> <p><br />CONCLUSION: In addition to showing that using computer vision to determine human activities is possible albeit more difficult than layouts of inanimate objects such as classroom desks, the study shows the differences between the use of self-supervised learning techniques and data augmentation techniques in order to overcome the problem of small training data-sets.</p> Andres Calle Quan Nguyen Kristin Lee Julia Voss Navid Shaghaghi Copyright (c) 2022 EAI Endorsed Transactions on Creative Technologies https://creativecommons.org/licenses/by/3.0/ 2022-07-28 2022-07-28 9 3 e1 e1 10.4108/eetct.v9i3.2229