@article{kim2021p300,

title = {P300 Brain--Computer Interface-Based Drone Control in Virtual and Augmented Reality},

author = {Soram Kim and Seungyun Lee and Hyunsuk Kang and Sion Kim and Minkyu Ahn},

doi = {https://doi.org/10.3390/s21175765},

year  = {2021},

date = {2021-08-27},

journal = {Sensors},

volume = {21},

number = {17},

pages = {5765},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Since the emergence of head-mounted displays (HMDs), researchers have attempted to introduce virtual and augmented reality (VR, AR) in brain–computer interface (BCI) studies. However, there is a lack of studies that incorporate both AR and VR to compare the performance in the two environments. Therefore, it is necessary to develop a BCI application that can be used in both VR and AR to allow BCI performance to be compared in the two environments. In this study, we developed an opensource-based drone control application using P300-based BCI, which can be used in both VR and AR. Twenty healthy subjects participated in the experiment with this application. They were asked to control the drone in two environments and filled out questionnaires before and after the experiment. We found no significant (p > 0.05) difference in online performance (classification accuracy and amplitude/latency of P300 component) and user experience (satisfaction about time length, program, environment, interest, difficulty, immersion, and feeling of self-control) between VR and AR. This indicates that the P300 BCI paradigm is relatively reliable and may work well in various situations},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lim2021superior,

title = {Superior Facilitation of an Action Observation Network by Congruent Character Movements in Brain--Computer Interface Action-Observation Games},

author = {Hyunmi Lim and Jeonghun Ku},

doi = {https://doi.org/10.1089/cyber.2020.0231},

year  = {2021},

date = {2021-08-04},

journal = {Cyberpsychology, Behavior, and Social Networking},

volume = {24},

number = {8},

pages = {566--572},

publisher = {Mary Ann Liebert, Inc., publishers 140 Huguenot Street, 3rd Floor New~…},

abstract = {Action observation (AO) is a promising strategy for promoting motor function in neural rehabilitation. Recently, brain–computer interface (BCI)-AO game rehabilitation, which combines AO therapy with BCI technology, has been introduced to improve the effectiveness of rehabilitation. This approach can improve motor learning by providing feedback, which can be interactive in an observation task, and the game contents of the BCI-AO game paradigm can affect rehabilitation. In this study, the effects of congruent rather than incongruent feedback in a BCI-AO game on mirror neurons were investigated. Specifically, the mu suppression with congruent and incongruent BCI-AO games was measured in 17 healthy adults. The mu suppression in the central motor cortex was significantly higher with the congruent BCI-AO game than with the incongruent one. In addition, the satisfaction evaluation results were excellent for the congruent case. These results support the fact that providing feedback congruent with the motion of an action video facilitates mirror neuron activity and can offer useful guidelines for the design of BCI-AO games for rehabilitation},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{eldeeb2021trial,

title = {Trial by trial EEG based BCI for distress versus non distress classification in individuals with ASD},

author = {Safaa Eldeeb and Busra T Susam and Murat Akcakaya and Caitlin M Conner and Susan W White and Carla A Mazefsky},

url = {https://www.nature.com/articles/s41598-021-85362-8},

year  = {2021},

date = {2021-03-16},

journal = {Scientific Reports},

volume = {11},

number = {1},

pages = {1--13},

publisher = {Nature Publishing Group},

abstract = {Autism spectrum disorder (ASD) is a neurodevelopmental disorder that is often accompanied by impaired emotion regulation (ER). There has been increasing emphasis on developing evidence-based approaches to improve ER in ASD. Electroencephalography (EEG) has shown success in reducing ASD symptoms when used in neurofeedback-based interventions. Also, certain EEG components are associated with ER. Our overarching goal is to develop a technology that will use EEG to monitor real-time changes in ER and perform intervention based on these changes. As a first step, an EEG-based brain computer interface that is based on an Affective Posner task was developed to identify patterns associated with ER on a single trial basis, and EEG data collected from 21 individuals with ASD. Accordingly, our aim in this study is to investigate EEG features that could differentiate between distress and non-distress conditions. Specifically, we investigate if the EEG time-locked to the visual feedback presentation could be used to classify between WIN (non-distress) and LOSE (distress) conditions in a game with deception. Results showed that the extracted EEG features could differentiate between WIN and LOSE conditions (average accuracy of 81%), LOSE and rest-EEG conditions (average accuracy 94.8%), and WIN and rest-EEG conditions (average accuracy 94.9%).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{memmott2021bcipy,

title = {BciPy: brain--computer interface software in Python},

author = {Tab Memmott and Aziz Koçanaoğullari and Matthew Lawhead and Daniel Klee and Shiran Dudy and Melanie Fried-Oken and Barry Oken},

doi = {https://doi.org/10.1080/2326263X.2021.1878727},

year  = {2021},

date = {2021-02-02},

journal = {Brain-Computer Interfaces},

pages = {1-18},

publisher = {Taylor & Francis},

abstract = {There are high technological and software demands associated with conducting Brain–Computer Interface (BCI) research. In order to accelerate the development and accessibility of BCIs, it is worthwhile to focus on open-source and community desired tooling. Python, a prominent computer language, has emerged as a language of choice for many research and engineering purposes. In this article, BciPy, an open-source, Python-based software for conducting BCI research is presented. It was developed with a focus on restoring communication using Event-Related Potential (ERP) spelling interfaces; however, it may be used for other non-spelling and non-ERP BCI paradigms. Major modules in this system include support for data acquisition, data queries, stimuli presentation, signal processing, signal viewing and modeling, language modeling, task building, and a simple Graphical User Interface (GUI).},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{son2020development,

title = {Development of a flickering action video based steady state visual evoked potential triggered brain computer interface-functional electrical stimulation for a rehabilitative action observation game},

author = {Ji Eun Son and Hyoseon Choi and Hyunmi Lim and Jeonghun Ku},

editor = {Severin P. Schwarzacher and Carlos Gómez},

doi = {10.3233/THC-209051},

year  = {2020},

date = {2020-06-04},

journal = {Technology and Health Care},

volume = {28},

number = {S1},

pages = {509-519},

publisher = {IOS Press},

abstract = {BACKGROUND:

This study focused on developing an upper limb rehabilitation program. In this regard, a steady state visual evoked potential (SSVEP) triggered brain computer interface (BCI)-functional electrical stimulation (FES) based action observation game featuring a flickering action video was designed.



OBJECTIVE:

In particular, the synergetic effect of the game was investigated by combining the action observation paradigm with BCI based FES.



METHODS:

The BCI-FES system was contrasted under two conditions: with flickering action video and flickering noise video. In this regard, 11 right-handed subjects aged between 22–27 years were recruited. The differences in brain activation in response to the two conditions were examined.



RESULTS:

The results indicate that T3 and P3 channels exhibited greater Mu suppression in 8–13 Hz for the action video than the noise video. Furthermore, T4, C4, and P4 channels indicated augmented high beta (21–30 Hz) for the action in contrast to the noise video. Finally, T4 indicated suppressed low beta (14–20 Hz) for the action video in contrast to the noise video.



CONCLUSION:

The flickering action video based BCI-FES system induced a more synergetic effect on cortical activation than the flickering noise based system.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{choi2019brain,

title = {Brain computer interface-based action observation game enhances mu suppression in patients with stroke},

author = {Hyoseon Choi and Hyunmi Lim and Joon Woo Kim and Youn Joo Kang and Jeonghun Ku},

doi = {https://doi.org/10.3390/electronics8121466},

year  = {2019},

date = {2019-12-02},

journal = {Electronics},

volume = {8},

number = {12},

pages = {1466},

publisher = {Multidisciplinary Digital Publishing Institute},

abstract = {Action observation (AO), based on the mirror neuron theory, is a promising strategy to promote motor cortical activation in neurorehabilitation. Brain computer interface (BCI) can detect a user’s intention and provide them with brain state-dependent feedback to assist with patient rehabilitation. We investigated the effects of a combined BCI-AO game on power of mu band attenuation in stroke patients. Nineteen patients with subacute stroke were recruited. A BCI-AO game provided real-time feedback to participants regarding their attention to a flickering action video using steady-state visual-evoked potentials. All participants watched a video of repetitive grasping actions under two conditions: (1) BCI-AO game and (2) conventional AO, in random order. In the BCI-AO game, feedback on participants’ observation scores and observation time was provided. In conventional AO, a non-flickering video and no feedback were provided. The magnitude of mu suppression in the central motor, temporal, parietal, and occipital areas was significantly higher in the BCI-AO game than in the conventional AO. The magnitude of mu suppression was significantly higher in the BCI-AO game than in the conventional AO both in the affected and unaffected hemispheres. These results support the facilitatory effects of the BCI-AO game on mu suppression over conventional AO},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{lim2019multiple,

title = {Multiple-command single-frequency SSVEP-based BCI system using flickering action video},

author = {Hyunmi Lim and Jeonghun Ku},

doi = {https://doi.org/10.1016/j.jneumeth.2019.01.005},

year  = {2019},

date = {2019-01-16},

journal = {Journal of Neuroscience Methods},

volume = {314},

pages = {21-27},

publisher = {Elsevier},

abstract = {Background

The number of commands in a brain–computer interface (BCI) system is important. This study proposes a new BCI technique to increase the number of commands in a single BCI system without loss of accuracy.



New method

We expected that a flickering action video with left and right elbow movements could simultaneously activate the different pattern of event-related desynchronization (ERD) according to the video contents (e.g., left or right) and steady-state visually evoked potential (SSVEP). The classification accuracy to discriminate left, right, and rest states was compared under the three following feature combinations: SSVEP power (19–21 Hz), Mu power (8–13 Hz), and simultaneous SSVEP and Mu power.



Results

The SSVEP feature could discriminate the stimulus condition, regardless of left or right, from the rest condition, while the Mu feature discriminated left or right, but was relatively poor in discriminating stimulus from rest. However, combining the SSVEP and Mu features, which were evoked by the stimulus with a single frequency, showed superior performance for discriminating all the stimuli among rest, left, or right.



Comparison with the existing method

The video contents could activate the ERD differently, and the flickering component increased its accuracy, such that it revealed a better performance to discriminate when considering together.



Conclusions

This paradigm showed possibility of increasing performance in terms of accuracy and number of commands with a single frequency by applying flickering action video paradigm and applicability to rehabilitation systems used by patients to facilitate their mirror neuron systems while training.},

keywords = {},

pubstate = {published},

tppubtype = {article}

}

@article{pereira2018cross,

title = {Cross-Subject EEG Event-Related Potential Classification for Brain-Computer Interfaces Using Residual Networks},

author = {Arnaldo Pereira and Dereck Padden and Jay Jantz and Kate Lin and Ramses Alcaide-Aguirre},

doi = {10.13140/RG.2.2.16257.10086},

year  = {2018},

date = {2018-09-20},

urldate = {2018-01-01},

abstract = {EEG event-related potentials, and the P300 signal in

particular, are promising modalities for brain-computer interfaces (BCI). But the nonstationarity of EEG signals and

their differences across individuals have made it difficult to

implement classifiers that can determine user intent without having to be retrained or calibrated for each new user

and sometimes even each session. This is a major impediment to the development of consumer BCI. Recently, the

EEG BCI literature has begun to apply convolutional neural

networks (CNNs) for classification, but experiments have

largely been limited to training and testing on single subjects. In this paper, we report a study in which EEG data

were recorded from 66 subjects in a visual oddball task

in virtual reality. Using wide residual networks (WideResNets), we obtain state-of-the-art performance on a test set

composed of data from all 66 subjects together. Additionally, a minimal preprocessing stream to convert EEG data

into square images for CNN input while adding regularization is presented and shown to be viable. This study also

provides some guidance on network architecture parameters based on experiments with different models. Our results show that it may possible with enough data to train

a classifier for EEG-based BCIs that can generalize across

individuals without the need for individual training or calibration.

},

keywords = {},

pubstate = {published},

tppubtype = {article}

}