Anomaly Detection in Time Series Brain Data Collected Using Functional Near-Infrared Spectroscopy Public
Downloadable Contentopen in viewer
This project explores algorithms that detect motion anomalies in data collected using Functional Near-Infrared Spectroscopy (fNIRS). fNIRS is a new type of noninvasive brain imaging technology that provides information about the dynamic cognitive state of individuals doing tasks in the real world. The portability of fNIRS allows researchers to model brain activity in everyday situations. The data is collected using many sensors, contributing to its complexity and justifying analysis using statistical and machine learning methods. The study of anomaly detection of fNIRS is well sought-after as finding anomalies leads to more accurate data analysis. The results of this research include anomaly detection methods and a platform that allows others to analyze their own data using these methods.
- This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.
- Date created
- Resource type
- Rights statement
Permanent link to this page: https://digital.wpi.edu/show/qb98mj00v