Thesis
Active learning for activity recognition
Washington State University
Master of Science (MS), Washington State University
2014
Handle:
https://hdl.handle.net/2376/100097
Abstract
Activity recognition in smart home environments is a crucial step towards fully autonomous assistance and health monitoring. Due to high variance in house configurations and sensor placements, it is important to use the sensor data for training a learning algorithm. Since ground-truth activity corresponding to the sensor data cannot usually be obtained automatically, the sensor data should be labeled by a person in order to employ supervised methods. Abundance of sensor data makes it infeasible to label all of the data, and active learning can be used to intelligently pick the most informative data to be labeled. This project investigates several activelearning methods as applied to CASAS smart home sensor data for activity recognition and presents a crowd-sourcing application for annotation.
Metrics
3 File views/ downloads
15 Record Views
Details
- Title
- Active learning for activity recognition
- Creators
- Salikh Bagaveyev
- Contributors
- Diane J. Cook (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525183901842
- Language
- English
- Resource Type
- Thesis