Přístupnostní navigace
E-přihláška
Vyhledávání Vyhledat Zavřít
Detail publikace
BAGHEL, N., SINGH, D, DUTTA, M.K., BURGET, R., & MYSKA, V. Truth Identification from EEG Signal by using Convolution neural network: Lie Detection
Originální název
Truth Identification from EEG Signal by using Convolution neural network: Lie Detection
Typ
článek ve sborníku ve WoS nebo Scopus
Jazyk
angličtina
Originální abstrakt
Identification of statement is truth or lie is a major problem. It has various applications for safety and clime control. Traditionally physiological activities are monitored during the question-answer round and compare to a normal level. However, because the subject can control his/her physiological reactions, therefore, to overcome these brain signals are used to identify the truth. Brain signal is the first to respond to any sensory impulses which can be used to identify the person is telling the truth or lying. The EEG signals describe the brain signal activity of a person. In this paper, a deep learning method has been used for automatic truth identification from EEG signals by using a convolution neural network. The proposed model has taken 14 channel EEG signals as input to convolution neural network for classification of the signal into the truth or lies statements. The proposed method has achieved up to 84.44% accuracy to identify a person is telling a truth or lie. The proposed method is non-invasive, efficient and robust and has low time complexity making it suitable for realtime applications.
Klíčová slova
EEG Signal,truth identification,deep neural network,lie detection
Autoři
Vydáno
11. 8. 2020
Nakladatel
IEEE
Místo
Milan, Italy
ISBN
978-1-7281-6376-5
Kniha
2020 43rd International Conference on Telecommunications and Signal Processing (TSP)
Strany od
550
Strany do
553
Strany počet
4
BibTex
@inproceedings{BUT164724, author="Vojtěch {Myška} and Radim {Burget}", title="Truth Identification from EEG Signal by using Convolution neural network: Lie Detection", booktitle="2020 43rd International Conference on Telecommunications and Signal Processing (TSP)", year="2020", pages="550--553", publisher="IEEE", address="Milan, Italy", doi="10.1109/TSP49548.2020.9163497", isbn="978-1-7281-6376-5" }