Carleton University
Motion Artifact Data to Facilitate Bioelectric Signal Quality Analysis Research
Abstract
dc:description.abstractBioelectric signal quality analysis is important to address the challenges associated with contaminants, including motion artifacts. However, the limited availability of motion artifact data poses a challenge in developing and evaluating new tools (e.g., biases due to signal reuse). This research expands motion artifact data through two approaches. First, we deployed a Motion Artifact Signal Generation Toolkit to synthesize motion artifacts using Autoregressive, Markov Chain, and Recurrent Neural Network models. We extend model validation to non-cyclical motion artifacts. Second, we estimate motion artifacts in long-term ECG recordings using a template subtraction method, creating a motion artifact database of 84 signals. Additionally, we explore time-series segmentation of motion artifacts, leveraging a clustering pipeline, including k-means clustering, to partition long-term recordings based on signal statistics and attributes. These contributions greatly expand the public availability of motion artifacts for biomedical signal quality analysis researchers to use worldwide.
Degree
thesis:*- Name thesis:degree_name
- Master of Applied Science (M.App.Sc.)
- Level thesis:degree_level
- Master's
- Discipline thesis:degree_discipline
- Engineering, Biomedical
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kulpa, Jonathan Adam
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- Copyright © 2023 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en