Classification of Hemodynamic Responses Associated With Force and Speed Imagery for a Brain-Computer Interface

Yin, Xuxian; Xu, Baolei; Jiang, Cuiping; Fu, Yunfa; Wang, Zhidong; Li, Hongyi; Shi, Gang

doi:10.1007/s10916-015-0236-0

Cited by 19 publications

(14 citation statements)

References 33 publications

(34 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The LDA-based classification (achieving a 3.6% increase in the accuracy for MI tasks using the hybrid modality) showed that the NIRS signals contributed to the detection of the active/idle state as well as to the detection of active classes to confirm early activity detection. In two other similar studies, the MI of both the force and speed of hand clenching was decoded using hybrid EEG–NIRS (Yin et al, 2015b,c). In the first case, the extreme learning machine classifier was used to decode the responses associated with the force and speed imagery of the hand with an accuracy of 76.7%, whereas, for the second case (Yin et al, 2015c), the features of EEG and NIRS were combined and optimized using the joint mutual information selection criterion, again utilizing the extreme learning machines, in which case, the resulting average classification accuracy for the force and speed of hand clenching was 89%.…”

Section: Hardware Combinationmentioning

confidence: 99%

Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

2017

View full text Add to dashboard Cite

In this article, non-invasive hybrid brain–computer interface (hBCI) technologies for improving classification accuracy and increasing the number of commands are reviewed. Hybridization combining more than two modalities is a new trend in brain imaging and prosthesis control. Electroencephalography (EEG), due to its easy use and fast temporal resolution, is most widely utilized in combination with other brain/non-brain signal acquisition modalities, for instance, functional near infrared spectroscopy (fNIRS), electromyography (EMG), electrooculography (EOG), and eye tracker. Three main purposes of hybridization are to increase the number of control commands, improve classification accuracy and reduce the signal detection time. Currently, such combinations of EEG + fNIRS and EEG + EOG are most commonly employed. Four principal components (i.e., hardware, paradigm, classifiers, and features) relevant to accuracy improvement are discussed. In the case of brain signals, motor imagination/movement tasks are combined with cognitive tasks to increase active brain–computer interface (BCI) accuracy. Active and reactive tasks sometimes are combined: motor imagination with steady-state evoked visual potentials (SSVEP) and motor imagination with P300. In the case of reactive tasks, SSVEP is most widely combined with P300 to increase the number of commands. Passive BCIs, however, are rare. After discussing the hardware and strategies involved in the development of hBCI, the second part examines the approaches used to increase the number of control commands and to enhance classification accuracy. The future prospects and the extension of hBCI in real-time applications for daily life scenarios are provided.

show abstract

Section: Hardware Combinationmentioning

confidence: 99%

Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

2017

View full text Add to dashboard Cite

show abstract

“…The signal mean, signal peak, and signal slope in the 2–7 s (i.e., 5 s) windows from the onset were found to yield better classification accuracies for fNIRS-BCI using HRs ( Hong et al, 2015 ; Naseer and Hong, 2015 ). Like fMRI, the frequently used classifiers for the fNIRS features discrimination include LDA, SVM, extreme machine learning, Bayes classifiers, and neural networks ( Chan et al, 2012 ; Yin et al, 2015 ; Bui et al, 2016 ; Kim et al, 2016 ; Naseer et al, 2016b ; Ding et al, 2017 ).…”

Section: Role Of the Initial Dip In Bcimentioning

confidence: 99%

Existence of Initial Dip for BCI: An Illusion or Reality

Hong

Zafar

2018

Front. Neurorobot.

View full text Add to dashboard Cite

A tight coupling between the neuronal activity and the cerebral blood flow (CBF) is the motivation of many hemodynamic response (HR)-based neuroimaging modalities. The increase in neuronal activity causes the increase in CBF that is indirectly measured by HR modalities. Upon functional stimulation, the HR is mainly categorized in three durations: (i) initial dip, (ii) conventional HR (i.e., positive increase in HR caused by an increase in the CBF), and (iii) undershoot. The initial dip is a change in oxygenation prior to any subsequent increase in CBF and spatially more specific to the site of neuronal activity. Despite additional evidence from various HR modalities on the presence of initial dip in human and animal species (i.e., cat, rat, and monkey); the existence/occurrence of an initial dip in HR is still under debate. This article reviews the existence and elusive nature of the initial dip duration of HR in intrinsic signal optical imaging (ISOI), functional magnetic resonance imaging (fMRI), and functional near-infrared spectroscopy (fNIRS). The advent of initial dip and its elusiveness factors in ISOI and fMRI studies are briefly discussed. Furthermore, the detection of initial dip and its role in brain-computer interface using fNIRS is examined in detail. The best possible application for the initial dip utilization and its future implications using fNIRS are provided.

show abstract

“…Shin and Jeong used fNIRS to detect left and right leg movement tasks in a four-class BCI [ 42 ], and in prior studies we presented preliminary offline classification results using left and right foot tasks separately in a four-class motor-imagery-based fNIRS-BCI [ 22 , 23 ]. fNIRS has also been used to examine differences in motor imagery due to force of hand clenching or speed of tapping [ 34 ].…”

Section: Introductionmentioning

confidence: 99%

Virtual and Actual Humanoid Robot Control with Four-Class Motor-Imagery-Based Optical Brain-Computer Interface

Batula

Kim

Ayaz

2017

BioMed Research International

View full text Add to dashboard Cite

Motor-imagery tasks are a popular input method for controlling brain-computer interfaces (BCIs), partially due to their similarities to naturally produced motor signals. The use of functional near-infrared spectroscopy (fNIRS) in BCIs is still emerging and has shown potential as a supplement or replacement for electroencephalography. However, studies often use only two or three motor-imagery tasks, limiting the number of available commands. In this work, we present the results of the first four-class motor-imagery-based online fNIRS-BCI for robot control. Thirteen participants utilized upper- and lower-limb motor-imagery tasks (left hand, right hand, left foot, and right foot) that were mapped to four high-level commands (turn left, turn right, move forward, and move backward) to control the navigation of a simulated or real robot. A significant improvement in classification accuracy was found between the virtual-robot-based BCI (control of a virtual robot) and the physical-robot BCI (control of the DARwIn-OP humanoid robot). Differences were also found in the oxygenated hemoglobin activation patterns of the four tasks between the first and second BCI. These results corroborate previous findings that motor imagery can be improved with feedback and imply that a four-class motor-imagery-based fNIRS-BCI could be feasible with sufficient subject training.

show abstract

Classification of Hemodynamic Responses Associated With Force and Speed Imagery for a Brain-Computer Interface

Cited by 19 publications

References 33 publications

Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

Hybrid Brain–Computer Interface Techniques for Improved Classification Accuracy and Increased Number of Commands: A Review

Existence of Initial Dip for BCI: An Illusion or Reality

Virtual and Actual Humanoid Robot Control with Four-Class Motor-Imagery-Based Optical Brain-Computer Interface

Contact Info

Product

Resources

About