A spatio-temporal model for EEG-based person identification

Das, Banee Bandana; Kumar, Pradeep; Kar, Debakanta; Ram, Saswat Kumar; Babu, Korra Sathya; Mohapatra, Ramesh Kumar

doi:10.1007/s11042-019-07905-6

Cited by 37 publications

(27 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The EER value reported for 20 electrodes in the proposed method is much lower than the EER values obtained by the 64 electrodes in the state‐of‐the‐art methods. A recent work [18] uses deep learning techniques for feature extraction and classification. Using EC resting‐state EEG signals from PhysioNet database, [18] achieves a classification accuracy of 99.95% using 64 electrodes (EER value is not reported).…”

Section: Resultsmentioning

confidence: 99%

“…A recent work [18] uses deep learning techniques for feature extraction and classification. Using EC resting‐state EEG signals from PhysioNet database, [18] achieves a classification accuracy of 99.95% using 64 electrodes (EER value is not reported). For the same EEG data, our method gives a classification accuracy of 99.96% using 20 electrodes.…”

Section: Resultsmentioning

confidence: 99%

“…For the same EEG data, our method gives a classification accuracy of 99.96% using 20 electrodes. Our method achieves identical classification accuracy using a smaller number of electrodes (20) compared to [18] (64 electrodes) and hence requires shorter setup time and computational complexity on account of the reduced dimension of the data. The EEG frequency bands are different for different methods because each method selects the most suitable band that offers the lowest EER value.…”

Section: Resultsmentioning

confidence: 99%

“…Das et al . [18] proposed a spatio–temporal dense architecture, which uses the CNNs and long short‐term memory (LSTM) for feature generation and classification of resting‐state EEG signals. The work utilises the EEG signals from 64 channels and obtains an accuracy of 99.95% using EC resting‐state EEG signals from PhysioNet database.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

EEG‐based biometric identification using frequency‐weighted power feature

Monsy

Vinod

2020

IET biom.

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

EEG‐based biometric identification using frequency‐weighted power feature

Monsy

Vinod

2020

IET biom.

View full text Add to dashboard Cite

“…Diagnosis of any abnormal changes in the brain may indicate a disorder 14 , therefore awareness of the neuronal behavior along with the biomechanical structure can be remarkably effective 2 . Multimodal brain data, such as EEG and MRI have been collected in many studies 1 , 14 and the challenge now is to develop computational methods and tools that integrate these data for a better understanding of brain processes and for a better prediction of personal events 1 – 3 , 20 , 21 , 23 .…”

Section: Introductionmentioning

confidence: 99%

Design of MRI structured spiking neural networks and learning algorithms for personalized modelling, analysis, and prediction of EEG signals

Saeedinia

Jahed‐Motlagh

Tafakhori

et al. 2021

Sci Rep

View full text Add to dashboard Cite

This paper proposes a novel method and algorithms for the design of MRI structured personalized 3D spiking neural network models (MRI-SNN) for a better analysis, modeling, and prediction of EEG signals. It proposes a novel gradient-descent learning algorithm integrated with a spike-time-dependent-plasticity algorithm. The models capture informative personal patterns of interaction between EEG channels, contrary to single EEG signal modeling methods or to spike-based approaches which do not use personal MRI data to pre-structure a model. The proposed models can not only learn and model accurately measured EEG data, but they can also predict signals at 3D model locations that correspond to non-monitored brain areas, e.g. other EEG channels, from where data has not been collected. This is the first study in this respect. As an illustration of the method, personalized MRI-SNN models are created and tested on EEG data from two subjects. The models result in better prediction accuracy and a better understanding of the personalized EEG signals than traditional methods due to the MRI and EEG information integration. The models are interpretable and facilitate a better understanding of related brain processes. This approach can be applied for personalized modeling, analysis, and prediction of EEG signals across brain studies such as the study and prediction of epilepsy, peri-perceptual brain activities, brain-computer interfaces, and others.

show abstract