Design of a Performance-based Feature Selection Technique for Motor Imagery based Brain Computer Interface Data
Mentor 1
Mohammad Rahman
Location
Union Wisconsin Room
Start Date
5-4-2019 1:30 PM
End Date
5-4-2019 3:30 PM
Description
Many of the algorithms for brain computer interface development are both complex and specific to a particular user as the most successful methodology can vary between individuals and sessions, creating significant hurdles in consistent design and development for practical BCI usage. The objective of this study was to develop a simple feature selection algorithm to improve the accuracy of a subject independent BCI algorithm and streamline the process of BCI algorithm development. The data used for this study was collected from the publicly available BCI competition III dataset IVa. The methods used were a novel performance based additive feature fusion algorithm working in conjunction with machine learning in order to classify the motor imagery signals into particular states. The results of this algorithm was a classification accuracy of 87% for a subject independent algorithm with less computation cost compared to more traditional methods. The conclusion of this study and its significance is that it developed a viable methodology for simple, efficient feature selection and BCI algorithm development, which leads to an overall increase in algorithm classification accuracy.
Design of a Performance-based Feature Selection Technique for Motor Imagery based Brain Computer Interface Data
Union Wisconsin Room
Many of the algorithms for brain computer interface development are both complex and specific to a particular user as the most successful methodology can vary between individuals and sessions, creating significant hurdles in consistent design and development for practical BCI usage. The objective of this study was to develop a simple feature selection algorithm to improve the accuracy of a subject independent BCI algorithm and streamline the process of BCI algorithm development. The data used for this study was collected from the publicly available BCI competition III dataset IVa. The methods used were a novel performance based additive feature fusion algorithm working in conjunction with machine learning in order to classify the motor imagery signals into particular states. The results of this algorithm was a classification accuracy of 87% for a subject independent algorithm with less computation cost compared to more traditional methods. The conclusion of this study and its significance is that it developed a viable methodology for simple, efficient feature selection and BCI algorithm development, which leads to an overall increase in algorithm classification accuracy.
