Affiliation:
1. Worcester Polytechnic Institute, Worcester, MA, USA
2. Columbia University, New York, NY, USA
Abstract
Technology advances and lower equipment costs are enabling non-invasive, convenient recording of brain data outside of clinical settings in more real-world environments, and by non-experts. Despite the growing interest in and availability of brain signal datasets, most analytical tools are made for experts in the specific device technology, and have rigid constraints on the type of analysis available. We developed BrainEx to support interactive exploration and discovery within brain signals datasets. BrainEx takes advantage of algorithms that enable fast exploration of complex, large collections of time series data, while being easy to use and learn. This system enables researchers to perform similarity search, explore feature data and natural clustering, and select sequences of interest for future searches and exploration, while also maintaining the usability of a visual tool. In addition to describing the distributed architecture and visual design for BrainEx, this paper reports on a benchmark experiment showing that it outperforms other existing systems for similarity search. Additionally, we report on a preliminary user study in which domain experts used the visual exploration interface and affirmed that it meets the requirements. Finally, it presents a case study using BrainEx to explore real-world, domain-relevant data.
Funder
National Science Foundation
WPI-UML Collaborative Seed Grant
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Networks and Communications,Human-Computer Interaction,Social Sciences (miscellaneous)
Reference78 articles.
1. Aligning gene expression time series with time warping algorithms
2. Phylter: A System for Modulating Notifications in Wearables Using Physiological Sensing
3. Physiological indicators of task demand, fatigue, and cognition in future digital manufacturing environments
4. Building predictive models of emotion with functional near-infrared spectroscopy
5. Donald J. Berndt and James Clifford. 1994. Using Dynamic Time Warping to Find Patterns in Time Series . In Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining ( Seattle, WA) (AAAIWS'94). AAAI Press, 359--370. Donald J. Berndt and James Clifford. 1994. Using Dynamic Time Warping to Find Patterns in Time Series. In Proceedings of the 3rd International Conference on Knowledge Discovery and Data Mining (Seattle, WA) (AAAIWS'94). AAAI Press, 359--370.