Subject and class specific frequency bands selection for multiclass motor imagery classification

2011 ◽  
Vol 21 (2) ◽  
pp. 123-130 ◽  
Author(s):  
Heung-Il Suk ◽  
Seong-Whan Lee
Keyword(s):  
Motor Imagery ◽  
Frequency Bands ◽  
Specific Frequency ◽  
Selection For

Effect of Geometric Shape of Periodic Cavities in Attenuating Baseframe Vibration

2020 ◽  
Author(s):  
S. N. Das ◽  
Kachita Kohli ◽  
Ayush Kumar ◽  
G. R. Sabareesh
Keyword(s):  
Stop Band ◽  
Rotating Machinery ◽  
Vibration Level ◽  
Structural Vibrations ◽  
Frequency Bands ◽  
Natural Modes ◽  
Vibration Attenuation ◽  
Specific Frequency ◽  
Different Shapes ◽  
Air Cavities

Abstract Vibration attenuation is an important factor while designing rotating machinery since frequency lying in the range corresponding to natural modes of structures can result in resonance and ultimately failure. Damping dissipates energy in the system, which reduces the vibration level. The mitigation of vibrations can be achieved by designing the base frame with periodic air holes. The periodicity in air holes result in vibration attenuation by providing a stop band. A finite element-based approach is developed to predict the modal and frequency response. The analysis is carried out with different shapes of periodic cavities in order to study the effectiveness of periodic stop bands in attenuating vibrations. The amount of mass removed due to the periodic cavities is kept constant. It is seen that better attenuation is obtained in case of periodic cavities compared to a uniform base frame. Among the different geometries tested, rectangular cavities showed better results than circular and square cavities. As a result, it is seen that waves propagate along periodic cells only within specific frequency bands called the “Pass bands”, while these waves are completely blocked within other frequency bands called the “Stopbands”. The air cavities filter structural vibrations in certain frequency bands resulting in effective attenuation.

Channel Selection for Optimal EEG Measurement in Motor Imagery-Based Brain-Computer Interfaces

2020 ◽  
pp. 2150003
Author(s):  
Pasquale Arpaia ◽  
Francesco Donnarumma ◽  
Antonio Esposito ◽  
Marco Parvis
Keyword(s):  
Motor Imagery ◽  
Classification Accuracy ◽  
State Of The Art ◽  
Binary Classification ◽  
Brain Computer Interfaces ◽  
Eeg Signals ◽  
Non Invasive ◽  
Computer Interfaces ◽  
Selection For ◽  
A Performance

A method for selecting electroencephalographic (EEG) signals in motor imagery-based brain-computer interfaces (MI-BCI) is proposed for enhancing the online interoperability and portability of BCI systems, as well as user comfort. The attempt is also to reduce variability and noise of MI-BCI, which could be affected by a large number of EEG channels. The relation between selected channels and MI-BCI performance is therefore analyzed. The proposed method is able to select acquisition channels common to all subjects, while achieving a performance compatible with the use of all the channels. Results are reported with reference to a standard benchmark dataset, the BCI competition IV dataset 2a. They prove that a performance compatible with the best state-of-the-art approaches can be achieved, while adopting a significantly smaller number of channels, both in two and in four tasks classification. In particular, classification accuracy is about 77–83% in binary classification with down to 6 EEG channels, and above 60% for the four-classes case when 10 channels are employed. This gives a contribution in optimizing the EEG measurement while developing non-invasive and wearable MI-based brain-computer interfaces.

Sign in / Sign up

Export Citation Format

Share Document