Research work
ORCID Profile: https://orcid.org/0000-0001-7259-976X
Optimized EEG Based Mood Detection with Signal Processing and Deep Neural Networks for Brain-Computer Interface
Biomedical Physics & Engineering Express2023-02-06 | Journal article
DOI: 10.1088/2057-1976/acb942
Part of ISSN: 2057-1976
CONTRIBUTORS: Subhrangshu Adhikary; Kushal Jain; Biswajit Saha; Deepraj Chowdhury; Kushal Jain
http://dx.doi.org/10.1088/2057-1976/acb942
Contributors: Subhrangshu Adhikary (Author, 0000-0003-1779-3070)Kushal Jain (Author)Biswajit Saha (Author)Deepraj Chowdhury (Author)Kushal Jain (0000-0001-7259-976X)
Electroencephalogram (EEG) is a very promising and widely implemented procedure to study brain signals and activities by amplifying and measuring the post-synaptical potential arising from electrical impulses produced by neurons and detected by specialized electrodes attached to specific points in the scalp. It can be studied for detecting brain abnormalities, headaches, and other conditions. However, there are limited studies performed to establish a smart decision-making model to identify EEG’s relation with the mood of the subject. In this experiment, EEG signals of 28 healthy human subjects have been observed with consent and attempts have been made to study and recognise moods. Savitzky-Golay band-pass filtering and Independent Component Analysis have been used for data filtration. Different neural network algorithms have been implemented to analyze and classify the EEG data based on the mood of the subject. The model is further optimised by the usage of Blackman window-based Fourier Transformation and extracting the most significant frequencies for each electrode. Using these techniques, up to 96.01% detection accuracy has been obtained.
Fuzzy Logic on Long Short-Term Memory for Smart Person-Identification System through Electroencephalogram
2021 6th International Conference on Signal Processing, Computing and Control
(ISPCC)2021-10-07 | Journal article
DOI: 10.1109/ispcc53510.2021.9609504
CONTRIBUTORS: Kushal Jain; Subhrangshu Adhikary; Kushal Jain; Biswajit Saha; Chandan Koner
URL: http://dx.doi.org/10.1109/ispcc53510.2021.9609504
Contributors: Kushal Jain (0000-0001-7259-976X)Subhrangshu Adhikary (Author)Kushal Jain (Author)Biswajit Saha (Author)Chandan Koner (Author)
Abstract:
Brain functions through communication in between the network of numerous nerves by means of electrical signals produced as a result of post synaptical potential. Electroen-cephalogram (EEG) is a technique in which specialized electrodes are placed in certain parts of the scalp in order to measure the magnetic fields arisen by the electrical signal transmission within the brain. The brain waves although follow a certain regular pattern, it still varies at a minute scale from person to person. This gives us the motivation to develop a smart decision-making system to identify a person based on brain waves. For this, we have developed a deep learning recurrent neural network model based on Long Short-Term Memory to outperform all existing work. We have also compared the results with other popular machine learning algorithm. The experiment has been conducted on 28 human subjects under different psychological conditions with consent and obtained over 90% identification accuracy. The model could be easily deployed for several theft or privacy protection application such as embedding the setup within a smart helmet and granting access to only the owner.
