The effect of target and non-target similarity on neural classification performance: a boost from confidence

• Published in: Frontiers in neuroscience Vol. 9; p. 270
• Main Authors: Marathe, Amar R., Ries, Anthony J., Lawhern, Vernon J., Lance, Brent J., Touryan, Jonathan, McDowell, Kaleb, Cecotti, Hubert
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 05.08.2015; Frontiers Media S.A
• Subjects: Algorithms; Brain research; Classification; Decision theory; Human subjects; Image retrieval; International conferences; Laboratories; Neuroscience; United States > US; classification; rapid serial visual presentation; EEG; brain-computer interface; single-trial analysis; confidence
• ISSN: 1662-453X; 1662-4548; 1662-453X
• DOI: 10.3389/fnins.2015.00270

Brain computer interaction (BCI) technologies have proven effective in utilizing single-trial classification algorithms to detect target images in rapid serial visualization presentation tasks. While many factors contribute to the accuracy of these algorithms, a critical aspect that is often overlooked concerns the feature similarity between target and non-target images. In most real-world environments there are likely to be many shared features between targets and non-targets resulting in similar neural activity between the two classes. It is unknown how current neural-based target classification algorithms perform when qualitatively similar target and non-target images are presented. This study address this question by comparing behavioral and neural classification performance across two conditions: first, when targets were the only infrequent stimulus presented amongst frequent background distracters; and second when targets were presented together with infrequent non-targets containing similar visual features to the targets. The resulting findings show that behavior is slower and less accurate when targets are presented together with similar non-targets; moreover, single-trial classification yielded high levels of misclassification when infrequent non-targets are included. Furthermore, we present an approach to mitigate the image misclassification. We use confidence measures to assess the quality of single-trial classification, and demonstrate that a system in which low confidence trials are reclassified through a secondary process can result in improved performance.