Continuous electroencephalogram classification using a Connectionist Model based on Populations of Neurons

• Grant number: 12/15178-7
• Support Opportunities: Scholarships in Brazil - Master
• Effective date (Start): May 01, 2013
• Effective date (End): March 31, 2014
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: João Luís Garcia Rosa
• Grantee: Denis Renato de Moraes Piazentin
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

Electroencephalogram classification (EEG) consists of, from the EEG signal, detecting information about the state of the brain to identify, for example, actions and intentions of an individual. EEG classification is one way of working with brain-computer interfaces (BCI) and may have several applications, among which stands out the use in electronic games, helping people with disabilities or physical limitations and to improve control of complex machines, such as an airplane. The continuous EEG classification is considered one of the current challenges in BCI research and has several features that make it a complex task, like high dimensionality and noise. The Freeman's K models are part of a new class of connectionist models that simulate the dynamic behavior of populations of neurons. The K models have been applied to various problems of classification and prediction with success, including EEG classification, and often have showed better results compared to other models when applied in tasks of high complexity and noisy data. Thus, this research plan includes the investigation and application of a neural network based on the K models for the task of continuous electroencephalogram classification. The performance of the network will be evaluated by comparing the results with the main approaches used in literature and the methods of the state of the art. As a final result, it is expected that this work can help the development of future works in the area, and that the developed model can be used to classify EEGs with better results.

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

GARCIA ROSA, JOAO LUIS; PIAZENTIN, DENIS R. M.. A new cognitive filtering approach based on Freeman K3 Neural Networks. APPLIED INTELLIGENCE, v. 45, n. 2, p. 363-382, SEP 2016. (12/15178-7, 12/09268-3)

Academic Publications

(References retrieved automatically from State of São Paulo Research Institutions)

PIAZENTIN, Denis Renato de Moraes. K-sets of neural networks and its application on motor imagery classification. 2014. Master's Dissertation - Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC/SB) São Carlos.