Cargando…
The effect of target and non-target similarity on neural classification performance: a boost from confidence
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 overloo...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2015
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4544215/ https://www.ncbi.nlm.nih.gov/pubmed/26347597 http://dx.doi.org/10.3389/fnins.2015.00270 |
_version_ | 1782386651558838272 |
---|---|
author | Marathe, Amar R. Ries, Anthony J. Lawhern, Vernon J. Lance, Brent J. Touryan, Jonathan McDowell, Kaleb Cecotti, Hubert |
author_facet | Marathe, Amar R. Ries, Anthony J. Lawhern, Vernon J. Lance, Brent J. Touryan, Jonathan McDowell, Kaleb Cecotti, Hubert |
author_sort | Marathe, Amar R. |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-4544215 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2015 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-45442152015-09-07 The effect of target and non-target similarity on neural classification performance: a boost from confidence Marathe, Amar R. Ries, Anthony J. Lawhern, Vernon J. Lance, Brent J. Touryan, Jonathan McDowell, Kaleb Cecotti, Hubert Front Neurosci Neuroscience 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. Frontiers Media S.A. 2015-08-05 /pmc/articles/PMC4544215/ /pubmed/26347597 http://dx.doi.org/10.3389/fnins.2015.00270 Text en Copyright © 2015 Marathe, Ries, Lawhern, Lance, Touryan, McDowell and Cecotti. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Marathe, Amar R. Ries, Anthony J. Lawhern, Vernon J. Lance, Brent J. Touryan, Jonathan McDowell, Kaleb Cecotti, Hubert The effect of target and non-target similarity on neural classification performance: a boost from confidence |
title | The effect of target and non-target similarity on neural classification performance: a boost from confidence |
title_full | The effect of target and non-target similarity on neural classification performance: a boost from confidence |
title_fullStr | The effect of target and non-target similarity on neural classification performance: a boost from confidence |
title_full_unstemmed | The effect of target and non-target similarity on neural classification performance: a boost from confidence |
title_short | The effect of target and non-target similarity on neural classification performance: a boost from confidence |
title_sort | effect of target and non-target similarity on neural classification performance: a boost from confidence |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4544215/ https://www.ncbi.nlm.nih.gov/pubmed/26347597 http://dx.doi.org/10.3389/fnins.2015.00270 |
work_keys_str_mv | AT maratheamarr theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT riesanthonyj theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT lawhernvernonj theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT lancebrentj theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT touryanjonathan theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT mcdowellkaleb theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT cecottihubert theeffectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT maratheamarr effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT riesanthonyj effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT lawhernvernonj effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT lancebrentj effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT touryanjonathan effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT mcdowellkaleb effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence AT cecottihubert effectoftargetandnontargetsimilarityonneuralclassificationperformanceaboostfromconfidence |