Intelligent Robotic Chair With Thought Control and Communication Aid Using Higher Order Spectra Band Features

• Published in: IEEE sensors journal Vol. 22; no. 18; pp. 17362 - 17369
• Main Authors: Nataraj, Sathees Kumar, Al-Turjman, Fadi, Adom, Abdul Hamid Bin, R, Sitharthan, M, Rajesh, R, Kumar
• Format: Journal Article
• Language: English
• Published: New York IEEE 15.09.2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: bispectrum estimation (B (f1; Brain modeling; brain sensor; Classification; Classifiers; Communication; Communication aids; Communications systems; Data acquisition; Electroencephalography; Entropy; f2; Feature extraction; Frequencies; Intelligent robot chair with communication aid (IRCC); multilayer neural network (MLNN); Multilayers; Navigation; Navigation systems; Neural networks; Robot sensors; Signal processing; Spectra; Task analysis; thought evoked potentials (TEP); Waveforms
• ISSN: 1530-437X; 1558-1748
• DOI: 10.1109/JSEN.2020.3020971

In recent years, EEG-based navigation and communication systems for differentially enabled communities have been progressively receiving more attention. To provide a navigation system with a communication aid, a customized protocol using thought evoked sensor potentials has been proposed in this research work to aid the differentially enabled communities. This study presents the higher order robotic sensor spectra-based features to categorize seven basic tasks that include Forward, Left, Right, Yes, NO, Help and Relax; that can be used for navigating a robot chair and also for communications using an oddball paradigm. The proposed system records the eight-channel wireless electroencephalography signal from ten subjects while the subject was perceiving seven different tasks. The recorded brain wave signals are pre-processed to remove the interference waveforms and segmented into six frequency band signals, i.e. Delta, Theta, Alpha, Beta, Gamma1-1 and Gamma-2. The frequency band signals are segmented into frame samples of equal length and are used to extract the features using bispectrum estimation. Further, statistical features such as the mean of bispectral magnitude and entropy using the bispectrum region are extracted and formed as a feature set. The extracted feature sets are tenfold cross validated using multilayer neural network classifier. From the results, it is observed that the entropy of bispectral magnitude feature based classifier model has the maximum classification accuracy of 84.71% and the mean of the bispectral magnitude feature based classifier model has the minimum classification accuracy of 68.52 %.