Conference proceeding
Spatiotemporal integration of neuronal activity for single-trial classifications of bistable perception
2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, pp 2189-2193
01 Jan 2007
Abstract
This paper aims to understand how the discriminative information of neuronal population activity evolves and accumulates over time. We present two classes of approaches namely the probability-based and response-based approaches to predict the perceptual reports of a trained macaque monkey on a single-trial basis by integrating neural signals from multiple electrodes across time. We extend the probability-based integration originally using only the quadratic discriminant analysis (QDA) by considering also the linear discriminant analysis (LDA) and logistic regression methods. Furthermore, we introduce the response-based integration for the QDA, LDA and logistic regression methods. Experimental examples demonstrate the effectiveness of these approaches for determining the perceptual state of a brain under study by integrating its localized spatiotemporal neuronal activity.
Metrics
1 Record Views
Details
- Title
- Spatiotemporal integration of neuronal activity for single-trial classifications of bistable perception
- Creators
- Zhisong Wang - University of HoustonAlexander Maier - National Institutes of HealthDavid A. Leopold - National Institutes of HealthHualou Liang - The University of Texas Health Science Center at HoustonIEEE
- Publication Details
- 2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6, pp 2189-2193
- Series
- IEEE International Joint Conference on Neural Networks (IJCNN)
- Publisher
- IEEE
- Number of pages
- 2
- Grant note
- RO1 NS0543 14; ROI MH072034 / NIH; United States Department of Health & Human Services; National Institutes of Health (NIH) - USA Whitehall Foundation
- Resource Type
- Conference proceeding
- Language
- English
- Academic Unit
- School of Biomedical Engineering, Science, and Health Systems
- Web of Science ID
- WOS:000254291102018
- Scopus ID
- 2-s2.0-51749093738
- Other Identifier
- 991019320709004721
InCites Highlights
Data related to this publication, from InCites Benchmarking & Analytics tool:
- Collaboration types
- Domestic collaboration
- Web of Science research areas
- Computer Science, Artificial Intelligence
- Computer Science, Software Engineering