Subspace techniques for task-independent EEG person identification

Kumar, Mari Ganesh; Saranya,; Narayanan, Shrikanth; Sur, Mriganka; Murthy, Hema A.

doi:10.1109/embc.2019.8857426

Cited by 3 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown in previous works evidence that EEG has biometric potential under the performance of different tasks ( Vinothkumar et al, 2018 , DelPozo-Banos et al, 2018 ; Kong et al, 2018 ; Kumar et al, 2019 ; Fraschini et al, 2019 ). In this work, the explore EEG as a biometric modality under this challenging multi-task perspective.…”

Section: Introductionmentioning

confidence: 93%

A deep descriptor for cross-tasking EEG-based recognition

Mota

Silva

Luz

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

Due to the application of vital signs in expert systems, new approaches have emerged, and vital signals have been gaining space in biometrics. One of these signals is the electroencephalogram (EEG). The motor task in which a subject is doing, or even thinking, influences the pattern of brain waves and disturb the signal acquired. In this work, biometrics with the EEG signal from a cross-task perspective are explored. Based on deep convolutional networks (CNN) and Squeeze-and-Excitation Blocks, a novel method is developed to produce a deep EEG signal descriptor to assess the impact of the motor task in EEG signal on biometric verification. The Physionet EEG Motor Movement/Imagery Dataset is used here for method evaluation, which has 64 EEG channels from 109 subjects performing different tasks. Since the volume of data provided by the dataset is not large enough to effectively train a Deep CNN model, it is also proposed a data augmentation technique to achieve better performance. An evaluation protocol is proposed to assess the robustness regarding the number of EEG channels and also to enforce train and test sets without individual overlapping. A new state-of-the-art result is achieved for the cross-task scenario (EER of 0.1%) and the Squeeze-and-Excitation based networks overcome the simple CNN architecture in three out of four cross-individual scenarios.

show abstract

Section: Introductionmentioning

confidence: 93%

A deep descriptor for cross-tasking EEG-based recognition

Mota

Silva

Luz

et al. 2021

PeerJ Computer Science

View full text Add to dashboard Cite

show abstract

“…i-vector system [7] and the x-vector system [8]. Preliminary results on the proposed approaches were presented in [9], and are encouraging. This paper provides a consolidated analysis of these systems and shows that the proposed modifications are better than simple early and late fusion techniques used for modeling channel information.…”

mentioning

confidence: 90%

“…In [9], modified versions of the i-vector and the x-vector systems to recognize individuals using multi-channel EEG were proposed by the authors. In [9], only preliminary results were discussed with no inter-task or inter-subject analysis. This manuscript presents an in-depth analysis of the subspace systems proposed in [9] using two datasets.…”

Section: B Contributionsmentioning

confidence: 99%

“…In [9], only preliminary results were discussed with no inter-task or inter-subject analysis. This manuscript presents an in-depth analysis of the subspace systems proposed in [9] using two datasets. Dataset 1 is a modified version of the dataset used in [9] with 30 subjects and 12 different tasks.…”

Section: B Contributionsmentioning

confidence: 99%

“…This manuscript presents an in-depth analysis of the subspace systems proposed in [9] using two datasets. Dataset 1 is a modified version of the dataset used in [9] with 30 subjects and 12 different tasks. Dataset 1 is the primary dataset that has been used in all the experiments.…”

Section: B Contributionsmentioning

confidence: 99%

See 2 more Smart Citations

Evidence of Task-Independent Person-Specific Signatures in EEG Using Subspace Techniques

Kumar

Narayanan

Sur

et al. 2021

IEEE Trans.Inform.Forensic Secur.

Self Cite

View full text Add to dashboard Cite

Electroencephalography (EEG) signals are promising as alternatives to other biometrics owing to their protection against spoofing. Previous studies have focused on capturing individual variability by analyzing task/condition-specific EEG. This work attempts to model biometric signatures independent of task/condition by normalizing the associated variance. Toward this goal, the paper extends ideas from subspace-based textindependent speaker recognition and proposes novel modifications for modeling multi-channel EEG data. The proposed techniques assume that biometric information is present in the entire EEG signal and accumulate statistics across time in a high dimensional space. These high dimensional statistics are then projected to a lower dimensional space where the biometric information is preserved. The lower dimensional embeddings obtained using the proposed approach are shown to be taskindependent. The best subspace system identifies individuals with accuracies of 86.4% and 35.9% on datasets with 30 and 920 subjects, respectively, using just nine EEG channels. The paper also provides insights into the subspace model's scalability to unseen tasks and individuals during training and the number of channels needed for subspace modeling.

show abstract