2020 Conference Archive
Copyright
This work is archived and distributed under the repository's Standard Copyright and Reuse License (opens in new tab). End users may copy, store, and distribute this work without restriction. For all other uses, permission must be obtained from the copyright owners or their authorized agents.
Conference Tracks
Teaching with Technology – Research
Abstract
During a classroom session, an instructor performs several activities, such as writing, speaking, gestures to explain a concept. A record of the time spent in each of these activities could be valuable for the instructors to identify the activities that engage the students more, thereby enhancing teaching effectiveness.
In this work, we present a preliminary study on profiling multiple activities of an instructor in the classroom using smartwatch sensor data. We use a benchmark dataset to test out the feasibility of classifying the activities. Different machine learning models and metrics are used to find an appropriate model.
Session Format
Poster
1
Location
Harborside Ballroom East
Publication Type and Release Option
Event
Recommended Citation
Chowdhury, Zayed Uddin; De, Pradipta; and Allen, Andrew, "Profiling Instructor Activities Using Smartwatch Sensors in a Classroom" (2020). SoTL Commons Conference. 18.
https://digitalcommons.georgiasouthern.edu/sotlcommons/SoTL/2020/18
Profiling Instructor Activities Using Smartwatch Sensors in a Classroom
Harborside Ballroom East
During a classroom session, an instructor performs several activities, such as writing, speaking, gestures to explain a concept. A record of the time spent in each of these activities could be valuable for the instructors to identify the activities that engage the students more, thereby enhancing teaching effectiveness.
In this work, we present a preliminary study on profiling multiple activities of an instructor in the classroom using smartwatch sensor data. We use a benchmark dataset to test out the feasibility of classifying the activities. Different machine learning models and metrics are used to find an appropriate model.
