2018/09/13 by Luis Alfredo Moctezuma, Moctezuma, Luis Alfredo, Marta Molinas +1 · 1 citation
Computer Science · Medicine · Neuroscience · #Blind Source Separation Techniques #ECG Monitoring and Analysis #EEG and Brain-Computer Interfaces #FOS: Biological sciences #FOS: Computer and information sciences #FOS: Electrical engineering #Machine Learning (cs.LG) #Neural Networks and Applications #Neurons and Cognition (q-bio.NC) #Signal Processing (eess.SP) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1809.06697
openalex publication_date 2018/09/13 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
When brain activity is translated into commands for real applications, the\npotential for human capacities augmentation is promising. In this paper, EMD is\nused to decompose EEG signals during Imagined Speech in order to use it as a\nbiometric marker for creating a Biometric Recognition System. For each EEG\nchannel, the most relevant Intrinsic Mode Functions (IMFs) are decided based on\nthe Minkowski distance, and for each IMF 4 features are computed: Instantaneous\nand Teager energy distribution and Higuchi and Petrosian Fractal Dimension. To\ntest the proposed method, a dataset with 20 subjects who imagined 30\nrepetitions of 5 words in Spanish, is used. Four classifiers are used for this\ntask - random forest, SVM, naive Bayes, and k-NN - and their performances are\ncompared. The accuracy obtained (up to 0.92 using Linear SVM) after 10-folds\ncross-validation suggest that the proposed method based on EMD can be valuable\nfor creating EEG-based biometrics of imagined speech for Subjects\nidentification.\n