Computer Interface Control Research Articles

Design of Brain Computer Interface Control System Based on Neural Network

Design of Brain Computer Interface Control System Based on Neural Network

Automatic control of reactive brain computer interfaces

This article discusses theoretical and practical aspects of real-time brain computer interface control methods based on Bayesian statistics. The theoretical aspects include how the data from the brain computer interface can be translated into a Gaussian mixture model that is used in the Bayesian statistics-based control methods. The practical aspects include how the control methods improve the performance of the brain computer interface. We use a reactive brain computer interface based on a visual oddball paradigm for the investigation and improvement of the performance of automatic control and feedback algorithms used in the system. By using automatic control for selection of the stimuli for the visual oddball experiment, the target stimulus is identified faster than if no automatic control is used. Finally, we introduce transfer learning using Gaussian mixture models, enabling a ready-to-use setup.

Application of Control Algorithm in the Design of Automatic Crimping Device for Connecting Pipe and Ground Wire

Due to the low effectiveness and poor quality of manual crimping of grounding wires, the author proposes the design of an automatic crimping device for connecting tube grounding wires based on intelligent fully automatic technology. The device consists of a microcontroller, an upper computer control interface, an electric push rod, an infrared sensor, a pressure transmitter, and other devices. The staff used the upper computer monitoring interface to set the relevant parameters for grounding wire crimping, and used X-ray digital imaging technology to measure the crimping size of the grounding wire. The size met the set parameter conditions. Through the PID control algorithm in the microcontroller, the stepper motor was controlled to push the clamp to move, completing the automatic crimping of the grounding wire. The X-ray detection method was introduced to detect the quality of the grounding wire after the crimping was completed. The experimental results show that the average deviation between the measured crimping size of the grounding wire and the actual measurement size by the automatic crimping device is only 0.06 mm, indicating that its measurement results are accurate; The success rate of crimping exceeds 95%. The above experimental results verify that the designed crimping device has high stability and reliability, and good quality detection effect.

Design and development of a SLPM-based deployable robot

AbstractWith the progress of industry, people are facing more and more complicated tasks, which cannot be completed by conventional rigid robot. For this, a deployable robot based on spherical linkage parallel mechanism was proposed to satisfy relevant requirements for the degrees of freedom in this study. Based on the design of robot model and its control box, a mathematical model for the robot was established, and the relationship between motion space and drive space was deduced accordingly. Subsequently, a control system consisting of the upper and lower computers was introduced. Two control modes, that is, Joystick control and remote control, were developed. The upper computer control interface for the robot was completed by MATLAB construction. At last, the two control modes as well as autonomous detection were demonstrated by motion test. This achievement will further advance the applications of deployable robot in job aid and intelligent exploration.

Real-time Bayesian Control of Reactive Brain Computer Interfaces

This paper introduces an improved method for real-time brain computer interface control. We demonstrate how Bayesian optimization and feedback can be used to achieve faster statistical convergence by controlling the sequence of stimuli shown in a brain computer interface based on a visual oddball paradigm.

Dependence of Brain–Computer Interface Control Training on Personality Traits

Personality traits (PTs) are predictors of the success of control of brain-computer interfaces (BCIs); however, it is unknown how the PTs that are optimal for BCI control changes during training. The paper for the first time analyzes the correlations between PTs and the accuracy of the classification (AC) of brain states in imagining the movements of the hands, feet, and locomotion during 10-day training of ten volunteers in BCI control. In the first 3 days of training, the AC is higher for more stressed and anxious volunteers; in the last days, for calmer ones. In the middle of the training period, AC is higher in low-demonstrativeness persons, it is more pronounced when imagining foot movements. Correlations of low demonstrativeness, as well as of foresight and self-control with AC when imagining foot movements are revealed significantly more often than when imagining hand movements and locomotions. During almost the entire period of training, AC with locomotion imagination is higher in individualists. The results make it possible to propose individually-oriented recommendations for the use of BCI based on the imagination of movements for the rehabilitation of patients with motor disorders.

The impact of distractions on intracortical brain–computer interface control of a robotic arm

ABSTRACT The objective of the study was to evaluate the impact of distractions on intracortical brain–computer interface (BCI) performance. Two individuals with tetraplegia had microelectrode arrays implanted into their motor cortex. Each used a BCI to move a robotic arm between two targets as quickly as possible, performed alone and with distractions. Performance outcomes were similar across conditions, except for a drop in the median path efficiency in the motor action distraction for Subject P2 (p = 0.033, Mann–Whitney U-test). Other distraction conditions resulted in intermittent impairments in performance, but were not statistically different from the no distraction condition. Both subjects rated the overall difficulty of the task with and without distractions as low. Consistent levels of BCI performance were mirrored by small differences in neural firing rates across conditions, demonstrating that experienced BCI users can maintain performance on a simple reaching task under these various conditions.

Thin-film microfabrication and intraoperative testing of µECoG and iEEG depth arrays for sense and stimulation

Objective. Intracranial neural recordings and electrical stimulation are tools used in an increasing range of applications, including intraoperative clinical mapping and monitoring, therapeutic neuromodulation, and brain computer interface control and feedback. However, many of these applications suffer from a lack of spatial specificity and localization, both in terms of sensed neural signal and applied stimulation. This stems from limited manufacturing processes of commercial-off-the-shelf (COTS) arrays unable to accommodate increased channel density, higher channel count, and smaller contact size. Approach. Here, we describe a manufacturing and assembly approach using thin-film microfabrication for 32-channel high density subdural micro-electrocorticography (µECoG) surface arrays (contacts 1.2 mm diameter, 2 mm pitch) and intracranial electroencephalography (iEEG) depth arrays (contacts 0.5 mm × 1.5 mm, pitch 0.8 mm × 2.5 mm). Crucially, we tackle the translational hurdle and test these arrays during intraoperative studies conducted in four humans under regulatory approval. Main results. We demonstrate that the higher-density contacts provide additional unique information across the recording span compared to the density of COTS arrays which typically have electrode pitch of 8 mm or greater; 4 mm in case of specially ordered arrays. Our intracranial stimulation study results reveal that refined spatial targeting of stimulation elicits evoked potentials with differing spatial spread. Significance. Thin-film, μECoG and iEEG depth arrays offer a promising substrate for advancing a number of clinical and research applications reliant on high-resolution neural sensing and intracranial stimulation.

Benefits of deep learning classification of continuous noninvasive brain–computer interface control

Objective. Noninvasive brain–computer interfaces (BCIs) assist paralyzed patients by providing access to the world without requiring surgical intervention. Prior work has suggested that EEG motor imagery based BCI can benefit from increased decoding accuracy through the application of deep learning methods, such as convolutional neural networks (CNNs). Approach. Here, we examine whether these improvements can generalize to practical scenarios such as continuous control tasks (as opposed to prior work reporting one classification per trial), whether valuable information remains latent outside of the motor cortex (as no prior work has compared full scalp coverage to motor only electrode montages), and the existing challenges to the practical implementation of deep-learning based continuous BCI control. Main results. We report that: (1) deep learning methods significantly increase offline performance compared to standard methods on an independent, large, and longitudinal online motor imagery BCI dataset with up to 4-classes and continuous 2D feedback; (2) our results suggest that a variety of neural biomarkers for BCI, including those outside the motor cortex, can be detected and used to improve performance through deep learning methods, and (3) tuning neural network output will be an important step in optimizing online BCI control, as we found the CNN models trained with full scalp EEG also significantly reduce the average trial length in a simulated online cursor control environment. Significance. This work demonstrates the benefits of CNNs classification during BCI control while providing evidence that electrode montage selection and the mapping of CNN output to device control will be important design choices in CNN based BCIs.

EEG based brain-computer interface control applications: A comprehensive review

Brain computer interfaces (BCI) is a tool that can make user requests to computerized systems by directly processing brain signals. In order to perform the procedures to be performed, brain signals must be classified. For this purpose, many classification algorithms have been tried with machine learning. The purpose of this study is to talk about both the type of brain signals used in the brain computer interface and the machine learning techniques used in the classification of these signals. In addition, summary information about the classification methods used in brain computer interface control applications in recent years are given in a table.

Design and Implementation of Medical Ultrasound Remote Control Software Based on Sensor Design.

With the development of medical technology, medical ultrasound technology is widely used in the diagnosis of human diseases. It has become an indispensable diagnostic method in modern clinical medicine by detecting the internal physiology or tissue structure of the human body by ultrasound and then discovering diseases. Based on this, this paper designs a medical ultrasonic remote control software based on sensor design. The system software communicates with the stimulator through the Bluetooth port of the mobile phone and can send the parameter information input by the mobile phone to the field-programmable gate array of the stimulator for compilation. The upper computer control interface with a remote communication function is written by Lab VIEW software. A socket is used to establish inter-network process connection, and medical ultrasonic equipment simulates hardware key input according to the received control instructions so as to achieve the purpose of remote control. Experiments show that, compared with other systems, the infrared human body temperature measurement system with the functions of environmental temperature compensation and distance compensation can effectively reduce the influence of environmental temperature, distance, and other factors and has the advantages of non-contact, low power consumption, fast response speed, high sensitivity, and high accuracy, which is suitable for rapid and accurate human body temperature measurement in crowded places with large traffic.

Brain–computer control interface design for virtual household appliances based on steady-state visually evoked potential recognition

Brain–computer interface is a new form of interaction between humans and machines. This interaction helps the human brain control or operate external devices directly using electroencephalograph (EEG) signals. In this study, we first adopt a canonical correlation analysis method to find the stimulation frequency by calculating the correlation coefficient between the EEG data and multiple sets of harmonics with different frequencies. Then, we select the maximum correlation coefficient as the stimulus frequency and consequently identify steady-state visual evoked potentials. Afterward, we introduce power spectral density to adjust the stimulus frequency and a voting mechanism to reduce the false activation rate. Finally, we build a virtual household electrical appliance brain–computer control interface, which achieves over 72.84% accuracy for three classification problems.

Human-Machine Interface for a Smart Wheelchair

The paper describes the integration of hardware and software with sensor technology and computer processing to develop the next generation intelligent wheelchair. The focus is a computer cluster design to test high performance computing for smart wheelchair operation and human interaction. The LabVIEW cluster is developed for real-time autonomous path planning and sensor data processing. Four small form factor computers are connected over a Gigabit Ethernet local area network to form the computer cluster. Autonomous programs are distributed across the cluster for increased task parallelism to improve processing time performance. The distributed programs operating frequency for path planning and motion control is 50Hz and 12.3Hz for 0.3 megapixel robot vision system. To monitor the operation and control of the distributed LabVIEW code, network automation is integrated into the cluster software along with a performance monitor. A link between the computer motion control program and the wheelchair joystick control of the drive train is developed for the computer control interface. A perception sensor array and control circuitry is integrated with the computer system to detect and respond to the wheelchair environment. Multiple cameras are used for image processing and scanning laser rangefinder sensors for obstacle avoidance in the cluster program. A centralized power system is integrated to power the smart wheelchair along with the cluster and sensor feedback system. The on board computer system is evaluated for cluster processing performance for the smart wheelchair, incorporating camera machine vision and LiDAR perception for terrain obstacle detection, operating in urban scenarios.

Research on the Control System of Indoor Cleaning Robots Based on LED Optical Communication

In order to realize the control of indoor cleaning robot, a design scheme of wireless communication technology based on white LED is proposed. The system between the host computer and indoor cleaning robot is through the white LED to achieve wireless communication. Through the host computer control interface, to the indoor cleaning robot to send control instructions to achieve the clean robot wireless remote control. The system can be widely used in any place under the white LED coverage, can basically realize the local control platform through the white wireless communication to the control of the clean robot, but also to meet the public for the visible light intelligent control system of the expectations and basic needs.

On the Relationship Between Attention Processing and P300-Based Brain Computer Interface Control in Amyotrophic Lateral Sclerosis.

Our objective was to investigate the capacity to control a P3-based brain-computer interface (BCI) device for communication and its related (temporal) attention processing in a sample of amyotrophic lateral sclerosis (ALS) patients with respect to healthy subjects. The ultimate goal was to corroborate the role of cognitive mechanisms in event-related potential (ERP)-based BCI control in ALS patients. Furthermore, the possible differences in such attentional mechanisms between the two groups were investigated in order to unveil possible alterations associated with the ALS condition. Thirteen ALS patients and 13 healthy volunteers matched for age and years of education underwent a P3-speller BCI task and a rapid serial visual presentation (RSVP) task. The RSVP task was performed by participants in order to screen their temporal pattern of attentional resource allocation, namely: (i) the temporal attentional filtering capacity (scored as T1%); and (ii) the capability to adequately update the attentive filter in the temporal dynamics of the attentional selection (scored as T2%). For the P3-speller BCI task, the online accuracy and information transfer rate (ITR) were obtained. Centroid Latency and Mean Amplitude of N200 and P300 were also obtained. No significant differences emerged between ALS patients and Controls with regards to online accuracy (p = 0.13). Differently, the performance in controlling the P3-speller expressed as ITR values (calculated offline) were compromised in ALS patients (p < 0.05), with a delay in the latency of P3 when processing BCI stimuli as compared with Control group (p < 0.01). Furthermore, the temporal aspect of attentional filtering which was related to BCI control (r = 0.51; p < 0.05) and to the P3 wave amplitude (r = 0.63; p < 0.05) was also altered in ALS patients (p = 0.01). These findings ground the knowledge required to develop sensible classes of BCI specifically designed by taking into account the influence of the cognitive characteristics of the possible candidates in need of a BCI system for communication.

Cortical excitability correlates with the event-related desynchronization during brain–computer interface control

Objective. Brain–computer interfaces (BCIs) based on motor control have been suggested as tools for stroke rehabilitation. Some initial successes have been achieved with this approach, however the mechanism by which they work is not yet fully understood. One possible part of this mechanism is a, previously suggested, relationship between the strength of the event-related desynchronization (ERD), a neural correlate of motor imagination and execution, and corticospinal excitability. Additionally, a key component of BCIs used in neurorehabilitation is the provision of visual feedback to positively reinforce attempts at motor control. However, the ability of visual feedback of the ERD to modulate the activity in the motor system has not been fully explored. Approach. We investigate these relationships via transcranial magnetic stimulation delivered at different moments in the ongoing ERD related to hand contraction and relaxation during BCI control of a visual feedback bar. Main results. We identify a significant relationship between ERD strength and corticospinal excitability, and find that our visual feedback does not affect corticospinal excitability. Significance. Our results imply that efforts to promote functional recovery in stroke by targeting increases in corticospinal excitability may be aided by accounting for the time course of the ERD.

Alpha-band lateralization during auditory selective attention for brain–computer interface control

In this paper, we investigated selective attention to auditory stimuli as a control mechanism for a Brain–Computer Interface (BCI). For BCIs using visual stimuli, the use of steady state or code modulated visual evoked potentials yields high performance. In this work, these approaches were transferred and tested in the auditory domain. The attentional modulation of code-modulated auditory evoked potentials (c-AEPs) and steady state auditory evoked potentials (SSAEPs) showed only a small effect, which is not sufficient for BCI control. However, for both kinds of stimuli, we found a spatial attention-related alpha-band lateralization that allows classification accuracies above 70% and thereby can be used for controlling a BCI.

Offline Analysis for Designing Electrooculogram Based Human Computer Interface Control for Paralyzed Patients

Currently, majority of persons were immobilized and need aid from caretakers due to disability. To reduce and overcome such problem, there was a need for developing human–computer interface (HCI) with the help of biosignals. In this paper, we propose a two-channel elecctrooculograpy (EOG)-based HCI to encourage the contact ability as well as value of life for paralyzed persons who cannot speak or shift their extremity by using 20 subjects with the help of ADT26 Bio amplifier. EOG signals were collected for 11 tasks from both vertical and horizontal eye movement by using gold-platted electrodes. The extracted EOG signals were processed with convolution and Plancherel theorem to obtain the features. Layered recurrent neural network (LRNN) was implemented to analyze the extracted features and then converted into a sequence of commands to control the HCI. A graphical user interface was developed using MATLAB to help a user to convey their thoughts. This paper shows an average classification accuracy of 90.72% for convolution features and 91.28% for Plancherel features. Off-line single trail analysis was also performed to analyze the recognition accuracy of the proposed HCI system. The off-line analysis displayed that Plancherel features using LRNN were high compared to convolution features using LRNN. From this paper, we found that LRNN architecture using Plancherel features was more suitable for developing EOG-based HCI. Single trail analysis was conducted to identify the recognizing accuracy in offline. The off-line results indicated that in comparison with other EOG-based HCI systems, our system was user friendly and needs minimum training to operate.

Design and Experiment of a Kinematic and Mechanical Test System for Excavation of Mole Crickets

The high-efficiency excavation of mole cricket is associated to their motion pattern and the action mode of digging force. In this paper, we present a kinematic and mechanical test system for synchronously acquiring the excavation motion and digging force of mole crickets. This system can realize the synchronous acquisition of mechanical data and image data during the excavation of mole crickets. According to the excavation characteristics of the mole cricket, the structure of the mechanical test system was designed to realize the capturing of the digging force. Based on LabVIEW software, a host computer control interface of the software system was designed, which can realize the data acquisition, calibration and playback. A synchronous trigger module was designed to ensure the synchronism of high-speed image and digging force acquisition. The results show that proposed test system can synchronously obtain the kinematic and mechanical data of the excavation of mole crickets, and provide the equipment guarantee for further study.

The impact of goal-oriented task design on neurofeedback learning for brain-computer interface control.

Neurofeedback training teaches individuals to modulate brain activity by providing real-time feedback and can be used for brain-computer interface control. The present study aimed to optimize training by maximizing engagement through goal-oriented task design. Participants were shown either a visual display or a robot, where each was manipulated using motor imagery (MI)-related electroencephalography signals. Those with the robot were instructed to quickly navigate grid spaces, as the potential for goal-oriented design to strengthen learning was central to our investigation. Both groups were hypothesized to show increased magnitude of these signals across 10 sessions, with the greatest gains being seen in those navigating the robot due to increased engagement. Participants demonstrated the predicted increase in magnitude, with no differentiation between hemispheres. Participants navigating the robot showed stronger left-hand MI increases than those with the computer display. This is likely due to success being reliant on maintaining strong MI-related signals. While older participants showed stronger signals in early sessions, this trend later reversed, suggesting greater natural proficiency but reduced flexibility. These results demonstrate capacity for modulating neurofeedback using MI over a series of training sessions, using tasks of varied design. Importantly, the more goal-oriented robot control task resulted in greater improvements.