TY - JOUR
T1 - Extracting duration information in a picture category decoding task using hidden Markov Models
AU - Pfeiffer, Tim
AU - Heinze, Nicolai
AU - Frysch, Robert
AU - Deouell, Leon Y.
AU - Schoenfeld, Mircea A.
AU - Knight, Robert T.
AU - Rose, Georg
N1 - Publisher Copyright:
© 2016 IOP Publishing Ltd.
PY - 2016/2/9
Y1 - 2016/2/9
N2 - Objective. Adapting classifiers for the purpose of brain signal decoding is a major challenge in brain-computer-interface (BCI) research. In a previous study we showed in principle that hidden Markov models (HMM) are a suitable alternative to the well-studied static classifiers. However, since we investigated a rather straightforward task, advantages from modeling of the signal could not be assessed. Approach. Here, we investigate a more complex data set in order to find out to what extent HMMs, as a dynamic classifier, can provide useful additional information. We show for a visual decoding problem that besides category information, HMMs can simultaneously decode picture duration without an additional training required. This decoding is based on a strong correlation that we found between picture duration and the behavior of the Viterbi paths. Main results. Decoding accuracies of up to 80% could be obtained for category and duration decoding with a single classifier trained on category information only. Significance. The extraction of multiple types of information using a single classifier enables the processing of more complex problems, while preserving good training results even on small databases. Therefore, it provides a convenient framework for online real-life BCI utilizations.
AB - Objective. Adapting classifiers for the purpose of brain signal decoding is a major challenge in brain-computer-interface (BCI) research. In a previous study we showed in principle that hidden Markov models (HMM) are a suitable alternative to the well-studied static classifiers. However, since we investigated a rather straightforward task, advantages from modeling of the signal could not be assessed. Approach. Here, we investigate a more complex data set in order to find out to what extent HMMs, as a dynamic classifier, can provide useful additional information. We show for a visual decoding problem that besides category information, HMMs can simultaneously decode picture duration without an additional training required. This decoding is based on a strong correlation that we found between picture duration and the behavior of the Viterbi paths. Main results. Decoding accuracies of up to 80% could be obtained for category and duration decoding with a single classifier trained on category information only. Significance. The extraction of multiple types of information using a single classifier enables the processing of more complex problems, while preserving good training results even on small databases. Therefore, it provides a convenient framework for online real-life BCI utilizations.
KW - brain-computer-interfaces
KW - classification
KW - electrocorticography
KW - hidden-Markov-models
KW - magnetoencephalography
KW - support-vector-machines
UR - http://www.scopus.com/inward/record.url?scp=84962450025&partnerID=8YFLogxK
U2 - 10.1088/1741-2560/13/2/026010
DO - 10.1088/1741-2560/13/2/026010
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
C2 - 26859831
AN - SCOPUS:84962450025
SN - 1741-2560
VL - 13
JO - Journal of Neural Engineering
JF - Journal of Neural Engineering
IS - 2
M1 - 026010
ER -