http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Multiclass covert speech classifi cation using extreme learning machine
Dipti Pawar,Sudhir Dhage 대한의용생체공학회 2020 Biomedical Engineering Letters (BMEL) Vol.10 No.2
The objective of the proposed research is to classify electroencephalography (EEG) data of covert speech words. Six subjectswere asked to perform covert speech tasks i.e mental repetition of four diff erent words i.e ‘left’, ‘right’, ‘up’ and ‘down’. Fifty trials for each word recorded for every subject. Kernel-based Extreme Learning Machine (kernel ELM) was used formulticlass and binary classifi cation of EEG signals of covert speech words. We achieved a maximum multiclass and binaryclassifi cation accuracy of (49.77%) and (85.57%) respectively. The kernel ELM achieves signifi cantly higher accuracycompared to some of the most commonly used classifi cation algorithms in Brain–Computer Interfaces (BCIs). Our fi ndingssuggested that covert speech EEG signals could be successfully classifi ed using kernel ELM. This research involving theclassifi cation of covert speech words potentially leading to real-time silent speech BCI research.