Limits...
A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery.

Nurse ES, Karoly PJ, Grayden DB, Freestone DR - PLoS ONE (2015)

Bottom Line: The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge.Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure.Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

View Article: PubMed Central - PubMed

Affiliation: NeuroEngineering Laboratory, Department of Electrical & Electronic Engineering, The University of Melbourne, Melbourne, VIC, Australia, 3010; Centre for Neural Engineering, The University of Melbourne, Melbourne, VIC, Australia, 3010.

ABSTRACT
This work describes a generalized method for classifying motor-related neural signals for a brain-computer interface (BCI), based on a stochastic machine learning method. The method differs from the various feature extraction and selection techniques employed in many other BCI systems. The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge. Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure. The results showed that the average performance of the new algorithm outperformed other published methods using the Berlin BCI IV (2008) competition dataset and was comparable to the best results in the Berlin BCI II (2002-3) competition dataset. The new method was also applied to electroencephalography (EEG) data recorded from five subjects undertaking a hand squeeze task and demonstrated high levels of accuracy with a mean classification accuracy of 78.9% after five-fold cross-validation. Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

No MeSH data available.


Related in: MedlinePlus

Results for BCI II data set 4.The classification accuracy for the current study is compared to previous work by (1) Zhang et al. (2) Neal (3) Hoffmann (4) Huang et al. (5) Mensh (6) Brugger et al. Only the top 6 competition entrants are shown. The red dashed line represents chance outcome (50%). White dashed lines indicate minor gridlines.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4482677&req=5

pone.0131328.g004: Results for BCI II data set 4.The classification accuracy for the current study is compared to previous work by (1) Zhang et al. (2) Neal (3) Hoffmann (4) Huang et al. (5) Mensh (6) Brugger et al. Only the top 6 competition entrants are shown. The red dashed line represents chance outcome (50%). White dashed lines indicate minor gridlines.

Mentions: The output accuracy for the BCI IV dataset three is shown in Fig 3. These results are reported in terms of accuracy as the information needed to determine Cohen’s kappa was not available. Fig 3 shows the results for each subject and the averaged result from the best network for our algorithm alongside the competition results [20]. The classification accuracy for the current study was 58.1% and 46.6% for Subject 1 and 2, respectively (average of 52.4%). This is higher than three of the previous published results for both datasets, and approximately equal to the winning entrant (59.5% and 34.3% for subjects 1 and 2, with an average of 46.9%). The same process was repeated for the BCI II data set four. The classification results are shown in Fig 4. The performance of our system was comparable to other competition entrants, with 75% accuracy.


A Generalizable Brain-Computer Interface (BCI) Using Machine Learning for Feature Discovery.

Nurse ES, Karoly PJ, Grayden DB, Freestone DR - PLoS ONE (2015)

Results for BCI II data set 4.The classification accuracy for the current study is compared to previous work by (1) Zhang et al. (2) Neal (3) Hoffmann (4) Huang et al. (5) Mensh (6) Brugger et al. Only the top 6 competition entrants are shown. The red dashed line represents chance outcome (50%). White dashed lines indicate minor gridlines.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4482677&req=5

pone.0131328.g004: Results for BCI II data set 4.The classification accuracy for the current study is compared to previous work by (1) Zhang et al. (2) Neal (3) Hoffmann (4) Huang et al. (5) Mensh (6) Brugger et al. Only the top 6 competition entrants are shown. The red dashed line represents chance outcome (50%). White dashed lines indicate minor gridlines.
Mentions: The output accuracy for the BCI IV dataset three is shown in Fig 3. These results are reported in terms of accuracy as the information needed to determine Cohen’s kappa was not available. Fig 3 shows the results for each subject and the averaged result from the best network for our algorithm alongside the competition results [20]. The classification accuracy for the current study was 58.1% and 46.6% for Subject 1 and 2, respectively (average of 52.4%). This is higher than three of the previous published results for both datasets, and approximately equal to the winning entrant (59.5% and 34.3% for subjects 1 and 2, with an average of 46.9%). The same process was repeated for the BCI II data set four. The classification results are shown in Fig 4. The performance of our system was comparable to other competition entrants, with 75% accuracy.

Bottom Line: The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge.Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure.Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

View Article: PubMed Central - PubMed

Affiliation: NeuroEngineering Laboratory, Department of Electrical & Electronic Engineering, The University of Melbourne, Melbourne, VIC, Australia, 3010; Centre for Neural Engineering, The University of Melbourne, Melbourne, VIC, Australia, 3010.

ABSTRACT
This work describes a generalized method for classifying motor-related neural signals for a brain-computer interface (BCI), based on a stochastic machine learning method. The method differs from the various feature extraction and selection techniques employed in many other BCI systems. The classifier does not use extensive a-priori information, resulting in reduced reliance on highly specific domain knowledge. Instead of pre-defining features, the time-domain signal is input to a population of multi-layer perceptrons (MLPs) in order to perform a stochastic search for the best structure. The results showed that the average performance of the new algorithm outperformed other published methods using the Berlin BCI IV (2008) competition dataset and was comparable to the best results in the Berlin BCI II (2002-3) competition dataset. The new method was also applied to electroencephalography (EEG) data recorded from five subjects undertaking a hand squeeze task and demonstrated high levels of accuracy with a mean classification accuracy of 78.9% after five-fold cross-validation. Our new approach has been shown to give accurate results across different motor tasks and signal types as well as between subjects.

No MeSH data available.


Related in: MedlinePlus