Implementing Remote Presence Using Quadcopter Control by a Non-Invasive BCI Device

Lin, Jzau-Sheng; Jiang, Ziyang

doi:10.13189/csit.2015.030405

Cited by 23 publications

(13 citation statements)

References 14 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Additionally, the performance of the LDA-1 for identifying 12 Hz flickering square was worse for subject 3 and 5, with accuracy of 78.10 1.50 % and 78.15 1.50 %, respectively. This may be caused by the interference of the alpha frequency band (8)(9)(10)(11)(12)(13). The interesting frequency band (11.75-12.25 Hz) for 12 HZ SSVEP signals was corrupted by alpha frequency band, which the EOG signal may be resident in the SSVEP signals.…”

Section: A Offline Bci Calibration Resultsmentioning

confidence: 99%

“…This brain-computer/machine interface (BCI/BMI) system can interpret EEG signal as instructions to control external devices directly (e.g., robot-assisted device) [9] and then bypass the normal motor control pathways. At present, many BCI/BMI applications have been established in various fields, such as object operation in 2D [10] or 3D space [11], remote device teleoperation [12], biometric identification [13] and emotion recognition [14]. More prominently, the BCI/BMI technology has been already adopted to drive prosthetic devices for limbs rehabilitation [15], [16].…”

mentioning

confidence: 99%

See 1 more Smart Citation

Robot-Assisted Rehabilitation System Based on SSVEP Brain-Computer Interface for Upper Extremity

Chu

Zhao

Zou

et al. 2018

2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)

View full text Add to dashboard Cite

Traditional rehabilitation therapies have limited effect on the motor recovery for a tetraplegia patient. Brain-computer interface (BCI) systems allow patients to send commands or intents to control external devices without depending on the normal way of peripheral nerves and muscles. And hence it can provide an alternative control and communication method with a potential to replace, restore, even reinforce lost movement ability for individuals with neurological damages. In the study, we proposed a robot-assisted rehabilitation system for upper extremity based on non-invasive electroencephalogram (EEG) BCI, which enables the injured upper extremity to achieve motor function. Six participants conducted three speed modes of movement with a BCI-controlled robot. The steady-state visual evoked potentials (SSVEPs) was adopted to establish the BCI system. Experimental results of the healthy participants were analyzed to indicate the feasibility of a BCI-driven robot-assisted rehabilitation system, with an average accuracy of about 80 %. This study gives a preliminary evidence that the integrated robot-assisted rehabilitation system combined with SSVEP-based BCI will make future rehabilitation therapy more effective. I. INTRODUCTION HE Cerebral Palsy (CP), Amyotrophic Lateral Sclerosis (ALS), Spinal Cord Injury (SCI), and brain stroke can result in the loss of the movement function for individuals with partial or severe paralysis, which seriously affected quantity of daily life in their homes, workplaces, and communities. However, with effective rehabilitation therapies, impaired

show abstract

Section: A Offline Bci Calibration Resultsmentioning

confidence: 99%

mentioning

confidence: 99%

Robot-Assisted Rehabilitation System Based on SSVEP Brain-Computer Interface for Upper Extremity

Chu

Zhao

Zou

et al. 2018

2018 IEEE International Conference on Robotics and Biomimetics (ROBIO)

View full text Add to dashboard Cite

show abstract

“…In 2012, Yipeng et al designed a BCI system that was using motor imagery (MI) signals acquired from thinking left, thinking right and thinking push combined with the artifact signals from eye blinking and tooth clenching in order to control an AR drone [2]. A different setup was suggested by Byung et al, where a hybrid interface was used [3]. In their study, the drone was controlled by using a low-cost electroencephalographic (EEG) headset together with an eye-tracking device.…”

Section: Introductionmentioning

confidence: 99%

Mind Controlled Drone: An Innovative Multiclass SSVEP based Brain Computer Interface

Chiuzbaian

Jakobsen

Puthusserypady

2019

2019 7th International Winter Conference on Brain-Computer Interface (BCI)

View full text Add to dashboard Cite

A crucial element lost in the context of a neurodegenerative disease is the possibility to freely explore and interact with the world around us. The work presented in this paper is focused on developing a brain-controlled Assistive Device (AD) to aid individuals in exploring the world around them with the help of a computer and their thoughts. By using the potential of a noninvasive Steady-State Visual Evoked Potential (SSVEP)based Brain Computer Interface (BCI) system, the users can control a flying robot (also known as UAV or drone) in 3D physical space. From a video stream received from a video camera mounted on the drone, users can experience a degree of freedom while controlling the drone in 3D. The system proposed in this study uses a consumer-oriented headset, known as Emotiv Epoch in order to record the electroencephalogram (EEG) data. The system was tested on ten able-bodied subjects where four distinctive SSVEPs (5.3 Hz, 7 Hz, 9.4 Hz and 13.5 Hz) were detected and used as control signals for actuating the drone. A highly customizable visual interface was developed in order to elicit each SSVEP. The data recorded was filtered with an 8 th order Butterworth bandpass filter and a fast Fourier transform (FFT) spectral analysis of the signal was applied in other to detect and classify each SSVEP. The proposed BCI system resulted in an average Information Transfer Rate (ITR) of 10 bits/min and a Positive Predictive Value (PPV) of 92.5%. The final conducted tests have demonstrated that the system proposed in this paper can easily control a drone in 3D space.

show abstract

“…Brain activity can be characterized by various signal modalities, such as invasive ElectroCorticoGraphy (ECoG) (Miller et al, 2010 ; Hiremath et al, 2015 ), non-invasive electroencephalogram (EEG) (Lazarou et al, 2018 ), the functional Magnetic Resonance Imaging (fMRI) (Cohen et al, 2014 ), and the functional Near-Infrared Spectroscopy (fNIRS) (Naseer and Hong, 2015 ). Due to its manageability, easy capture, high time resolution and relative cost effectiveness, the EEG signal has been widely adopted for substantial BCI applications, such as remote quadcopter control (Lin and Jiang, 2015 ), motion rehabilitation (Xu et al, 2011 ; Zhao et al, 2016 ), biometric authentication (Palaniappan, 2008 ), and emotions prediction (Padilla-Buritica et al, 2016 ). Currently, the electrophysiological brain patterns used in EEG-based BCI systems are mainly Steady-State Visual Evoked Potentials (SSVEPs) (Chen et al, 2015 ; Zhang et al, 2015 ; Zhao et al, 2016 ; Nakanishi et al, 2018 ), P300 (Cavrini et al, 2016 ), sensorimotor rhythms (SMRs) (Yuan and He, 2014 ; He et al, 2015 ), and motion-related cortical potential (MRCP, one kind of a slow cortical potential) (Karimi et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network

et al. 2018

View full text Add to dashboard Cite

High accuracy decoding of electroencephalogram (EEG) signal is still a major challenge that can hardly be solved in the design of an effective motor imagery-based brain-computer interface (BCI), especially when the signal contains various extreme artifacts and outliers arose from data loss. The conventional process to avoid such cases is to directly reject the entire severely contaminated EEG segments, which leads to a drawback that the BCI has no decoding results during that certain period. In this study, a novel decoding scheme based on the combination of Lomb-Scargle periodogram (LSP) and deep belief network (DBN) was proposed to recognize the incomplete motor imagery EEG. Particularly, instead of discarding the entire segment, two forms of data removal were adopted to eliminate the EEG portions with extreme artifacts and data loss. The LSP was utilized to steadily extract the power spectral density (PSD) features from the incomplete EEG constructed by the remaining portions. A DBN structure based on the restricted Boltzmann machine (RBM) was exploited and optimized to perform the classification task. Various comparative experiments were conducted and evaluated on simulated signal and real incomplete motor imagery EEG, including the comparison of three PSD extraction methods (fast Fourier transform, Welch and LSP) and two classifiers (DBN and support vector machine, SVM). The results demonstrate that the LSP can estimate relative robust PSD features and the proposed scheme can significantly improve the decoding performance for the incomplete motor imagery EEG. This scheme can provide an alternative decoding solution for the motor imagery EEG contaminated by extreme artifacts and data loss. It can be beneficial to promote the stability, smoothness and maintain consecutive outputs without interruption for a BCI system that is suitable for the online and long-term application.

show abstract

Implementing Remote Presence Using Quadcopter Control by a Non-Invasive BCI Device

Cited by 23 publications

References 14 publications

Robot-Assisted Rehabilitation System Based on SSVEP Brain-Computer Interface for Upper Extremity

Robot-Assisted Rehabilitation System Based on SSVEP Brain-Computer Interface for Upper Extremity

Mind Controlled Drone: An Innovative Multiclass SSVEP based Brain Computer Interface

A Decoding Scheme for Incomplete Motor Imagery EEG With Deep Belief Network

Contact Info

Product

Resources

About