Abstract
We introduce a novel procedure that extends the time feasibility for classification of early human actions. Its major characteristic is to use epoch training data from a wider time duration before action onset (i.e., within the intention period) instead of data from localized sliding windows. This is the case of time-specific and selected fixed classifiers. Our approach models human actions from EEG signals and leverages on amplitudes and power frequencies to construct fifteen groups of action vectors, which were subjected to a set of classifiers. Regarding early classification our approach did it earlier than both time-specific and selected fixed classifiers. Moreover, our results reported an increase in classification performance.
Original language | English |
---|---|
Title of host publication | Proceedings - 2017 Brazilian Conference on Intelligent Systems, BRACIS 2017 |
Number of pages | 6 |
Publisher | IEEE Signal Processing Society |
Publication date | 28 Jun 2017 |
Pages | 240-245 |
ISBN (Electronic) | 9781538624074 |
DOIs | |
Publication status | Published - 28 Jun 2017 |
Event | 6th Brazilian Conference on Intelligent Systems, BRACIS 2017 - Uberlandia, Brazil Duration: 2 Oct 2017 → 5 Oct 2017 |
Conference
Conference | 6th Brazilian Conference on Intelligent Systems, BRACIS 2017 |
---|---|
Country/Territory | Brazil |
City | Uberlandia |
Period | 02/10/2017 → 05/10/2017 |
Sponsor | Brazilian Computer Society (SBC), Capes, CNPq, et al., Faculdade de Computacao (FACOM/UFU), Fapemig, Universidade Federal de Uberlandia (UFU) |
Series | Proceedings - 2017 Brazilian Conference on Intelligent Systems, BRACIS 2017 |
---|---|
Volume | 2018-January |
Bibliographical note
Publisher Copyright:© 2017 IEEE.
Keywords
- Anticipation
- classification procedure
- EEG
- Single-trial