Filtering by
- Creators: Walker, Erin
- Creators: Computer Science and Engineering Program
- Member of: Theses and Dissertations
in the form of logs from students' tablets and the vocal interaction between pairs of students. Thousands of different features were defined, and then extracted computationally from the audio and log data. Human coders used richer data (several video streams) and a thorough understand of the tasks to code episodes as
collaborative, cooperative or asymmetric contribution. Machine learning was used to induce a detector, based on random forests, that outputs one of these three codes for an episode given only a characterization of the episode in terms of superficial features. An overall accuracy of 92.00% (kappa = 0.82) was obtained when
comparing the detector's codes to the humans' codes. However, due irregularities in running the study (e.g., the tablet software kept crashing), these results should be viewed as preliminary.
The study of developing a real-time cross-platform collaboration system between VR and MR takes into consideration a scenario in which multiple device users are connected to a multiplayer network where they are guided to perform various tasks concurrently.
Usability testing was conducted to evaluate participant perceptions of the system. Users were required to assemble a chair in alternating turns; thereafter users were required to fill a survey and give an audio interview. Results collected from the participants showed positive feedback towards using VR and MR for collaboration. However, there are several limitations with the current generation of devices that hinder mass adoption. Devices with better performance factors will lead to wider adoption.
Transfer learning using different representations was also studied with a goal of building collaboration detectors for one task can be used with a new task. Data for building such detectors were collected in the form of verbal interaction and user action logs from students’ tablets. Three qualitative levels of interactivity were distinguished: Collaboration, Cooperation and Asymmetric Contribution. Machine learning was used to induce a classifier that can assign a code for every episode based on the set of features. The results indicate that machine learned classifiers were reliable and can transfer.
For the purpose of exploring alternative uses for Rolplay’s image processing technology, I have developed a scavenger hunt application that utilizes object detection technology. This concept has been chosen out of three different application concepts that have been created during the first semester of the project. The application runs on Android devices and is written in Java. This application contains a camera display window and a button that the user may press to open the list of items. The list will display each item in the list and whether it has been detected from the camera stream. In addition, the list has a refresh button that will generate a new list of items after it is pressed. This is to allow users to either continue searching for items after every item in the current list has been found. or create a new list entirely if they wish to start over. The application will also detect low light status and display a message prompting the user to turn on their flashlight if low light is detected. During the development process, additional modifications have been made according to feedback from users that have tested the app.