Skip to main content
Have a personal or library account? Click to login
A face-machine interface utilizing EEG artifacts from a neuroheadset for simulated wheelchair control Cover

A face-machine interface utilizing EEG artifacts from a neuroheadset for simulated wheelchair control

Open Access
|Jul 2021

Figures & Tables

Figure 1:

The proposed face-machine interface system for simulated wheelchair control using artifacts from an EEG neuroheadset.

Table 1.

The commands for simulated wheelchair control.

Commands No.ActionsOutput commands
1Jaw chewing on both sidesForward
2Jaw chewing on the left sideTurn Left
3Jaw chewing on the right sideTurn Right
4Winking both eyesBackward
5Winking the left eyeTurn Left
6Winking the right eyeTurn Right
OptionalWinking the left eye and then the right eye within 3 secEnable/Disable System
Figure 2:

Components of the EEG signal acquisition process using an Emotiv EPOC X neuroheadset.

Figure 3:

Examples of EEG signals from the Emotiv Neuroheadset: (a) left eye winking, (b) right eye winking, and (c) both eyes winking.

Figure 4:

Examples of EEG signals from the Emotiv Neuroheadset during: (a) left side jaw chewing, (b) right side jaw chewing, and (c) jaw chewing on both sides.

Figure 5:

Flowchart of the proposed classification decisions.

if JL >TJL & JR>TJR,Decision is “Com#1”
if JL>JR & JL>TJL,Decision is “Com#2”
if JR>JL & JR>TJR,Decision is “Com#3”
if WL >TWL & WR>TWR,Decision is “Com#4”
if WL >WR & WL>TWL,Decision is “Com#5”
if WR>WL & WR>TWR,Decision is “Com#6”
Otherwise,No Decision
Figure 6:

The proposed modalities for simulated wheelchair control.

Table 2.

The command sequence for testing the performance of the proposed system.

Sequence No.CommandsSequence No.Commands
1Turn Left7Turn Right
2Turn Right8Turn Left
3Turn Right9Backward
4Turn Left10Turn Left
5Forward11Turn Right
6Backward12Forward
Table 3.

Results of the proposed control modalities.

Average accuracy (%)
ParticipantsProposed modality #1Proposed modality #2
195.8100
295.8100
391.795.8
487.595.8
591.7100
687.591.7
795.895.8
891.795.8
Mean ± SD92.2 ± 3.4696.9 ± 2.94
Figure 7:

(a) The testing route (total distance: 30 m). (b) A sample scenario encountered by the simulated power wheelchair during testing.

Figure 8:

The average times taken by all participants to complete route 1.

Figure 9:

The average times taken by all participants to complete route 2.

Language: English
Page range: 1 - 10
Submitted on: Apr 15, 2021
Published on: Jul 28, 2021
Published by: International Journal on Smart Sensing and Intelligent Systems
In partnership with: Paradigm Publishing Services
Publication frequency: Volume open

© 2021 Theerat Saichoo, Poonpong Boonbrahm, Yunyong Punsawad, published by International Journal on Smart Sensing and Intelligent Systems
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.