Vaibhav Gandhi

EEG-based mobile robot control through an adaptive brain–robot interface

A major challenge in two-class brain-computer interface (BCI) systems is the low bandwidth of the communication channel, especially while communicating and controlling assistive devices, such as a smart wheelchair or a telepresence mobile robot, which requires multiple motion command options in the form of forward, left, right, backward, and start/stop. To address this, an adaptive user-centric graphical user interface referred to as the intelligent adaptive user interface (iAUI) based on an adaptive shared control mechanism is proposed. The iAUI offers multiple degrees-of-freedom control of a robotic device by providing a continuously updated prioritized list of all the options for selection to the BCI user, thereby improving the information transfer rate. Results have been verified with multiple participants controlling a simulated as well as physical pioneer robot.

Quantum Neural Network-Based EEG Filtering for a Brain–Computer Interface

A novel neural information processing architecture inspired by quantum mechanics and incorporating the well-known Schrodinger wave equation is proposed in this paper. The proposed architecture referred to as recurrent quantum neural network (RQNN) can characterize a nonstationary stochastic signal as time-varying wave packets. A robust unsupervised learning algorithm enables the RQNN to effectively capture the statistical behavior of the input signal and facilitates the estimation of signal embedded in noise with unknown characteristics. The results from a number of benchmark tests show that simple signals such as dc, staircase dc, and sinusoidal signals embedded within high noise can be accurately filtered and particle swarm optimization can be employed to select model parameters. The RQNN filtering procedure is applied in a two-class motor imagery-based brain-computer interface where the objective was to filter electroencephalogram (EEG) signals before feature extraction and classification to increase signal separability. A two-step inner-outer fivefold cross-validation approach is utilized to select the algorithm parameters subject-specifically for nine subjects. It is shown that the subject-specific RQNN EEG filtering significantly improves brain-computer interface performance compared to using only the raw EEG or Savitzky-Golay filtered EEG across multiple sessions.

Evaluating Quantum Neural Network filtered motor imagery brain-computer interface using multiple classification techniques

The raw EEG signal acquired non-invasively from the sensorimotor cortex during the motor imagery (MI) performed by a brain-computer interface (BCI) user is naturally embedded with noise while the actual noise-free EEG is still unattainable. This paper compares the enhancement in information when filtering these noisy EEG signals while using a Schrodinger wave equation (SWE) based Recurrent Quantum Neural Network (RQNN) model and a Savitzky-Golay (SG) filtering model, while investigating over multiple classification techniques on several datasets. The RQNN model is designed to efficiently capture the statistical behavior of the input signal using an unsupervised learning scheme. The algorithm is robust to parametric sensitivity and does not make any a priori assumption about the true signal type or the embedded noise. The performance of both the filtering approaches, investigated for the BCI competition IV 2b dataset as well as the offline datasets on subjects in the BCI laboratory, over multiple classifiers shows that the RQNN can potentially be a flexible technique that can suit different classifiers for real-time EEG signal filtering. The average classification accuracy performance across all the subjects with the RQNN technique is better than the SG (and the unfiltered signal) by approximately 5% (and 7%) and 1% (and 4%) during the training and the evaluation stages respectively.

EEG denoising with a recurrent quantum neural network for a brain-computer interface

Brain-computer interface (BCI) technology is a means of communication that allows individuals with severe movement disability to communicate with external assistive devices using the electroencephalogram (EEG) or other brain signals. This paper presents an alternative neural information processing architecture using the Schrödinger wave equation (SWE) for enhancement of the raw EEG signal. The raw EEG signal obtained during the motor imagery (MI) of a BCI user is intrinsically embedded with non-Gaussian noise while the actual signal is still a mystery. The proposed work in the field of recurrent quantum neural network (RQNN) is designed to filter such non-Gaussian noise using an unsupervised learning scheme without making any assumption about the signal type. The proposed learning architecture has been modified to do away with the Hebbian learning associated with the existing RQNN architecture as this learning scheme was found to be unstable for complex signals such as EEG. Besides, this the soliton behaviour of the non-linear SWE was not properly preserved in the existing scheme. The unsupervised learning algorithm proposed in this paper is able to efficiently capture the statistical behaviour of the input signal while making the algorithm robust to parametric sensitivity. This denoised EEG signal is then fed as an input to the feature extractor to obtain the Hjorth features. These features are then used to train a Linear Discriminant Analysis (LDA) classifier. It is shown that the accuracy of the classifier output over the training and the evaluation datasets using the filtered EEG is much higher compared to that using the raw EEG signal. The improvement in classification accuracy computed over nine subjects is found to be statistically significant.

Quantum neural network based surface EMG signal filtering for control of robotic hand

A filtering methodology inspired by the principles of quantum mechanics and incorporating the well-known Schrodinger wave equation is investigated for the first time for filtering EMG signals. This architecture, referred to as a Recurrent Quantum Neural Network (RQNN) can characterize a non-stationary stochastic signal as time varying wave packets. An unsupervised learning rule allows the RQNN to capture the statistical behaviour of the input signal and facilitates estimation of an EMG signal embedded in noise with unknown characteristics. Results from a number of benchmark tests show that simple signals such as DC, staircase DC and sinusoidal signals embedded with a high level of noise can be accurately filtered. Particle swarm optimization is employed to select RQNN model parameters for filtering simple signals. In this paper, we present the RQNN filtering procedure, using heuristically selected parameters, to be applied to a new thirteen class EMG based finger movement detection system, for emulation in a Shadow Robotics robot hand. It is shown that the RQNN EMG filtering improves the classification performance compared to using only the raw EMG signals, across multiple feature extraction approaches and subjects. Effective control of the robot hand is demonstrated.

Project-based cooperative learning to enhance competence while teaching engineering modules

This paper focuses on teaching control systems to engineering students through a blending of traditional lectures; student-focused problem-based self-directed learning projects and student presentations. Engineering field constantly evolves and thus teaching a module to engineering students should involve current state-of-the-art research trends. The work presented in this paper revolves around three miniprojects, each project on a different aspect of control engineering and to be completed within 2 weeks each. The aim of these problem-based self-directed learning miniprojects is to get acquainted with the practical aspects of the theoretical learning that has been undertaken within the lectures, something that UK Standard for Professional Engineering Competence focuses on. After completion of the miniproject, the students present their work/discuss results as a PowerPoint presentation lasting 15 min and address queries from peers (compulsory) and tutor, thus promoting lifelong learning along with class participation and peer assessment. These projects also help the student to keep alight with the practical aspects of the current professional practices in industry. The inclusion of the blended approach has improved the students reading beyond the course requirements, has encouraged them towards deeper learning and also improved both their theoretical as well as practical aspects in engineering education.

Brain computer interface: A review

A brain-computer interface (BCI), also referred to as a mind-machine interface (MMI) or a brain-machine interface (BMI), provides a non-muscular channel of communication between the human brain and a computer system. With the advancements in low-cost electronics and computer interface equipment, as well as the need to serve people suffering from disabilities of neuromuscular disorders, a new field of research has emerged by understanding different functions of the brain. The electroencephalogram (EEG) is an electrical activity generated by brain structures and recorded from the scalp surface through electrodes. Researchers primarily rely on EEG to characterise the brain activity, because it can be recorded non-invasively by using portable equipment. The EEG or the brain activity can be used in real time to control external devices via a complete BCI system. A typical BCI scheme generally consists of a data acquisition system, pre-processing of the acquired signals, feature extraction process, classification of the features, post-processing of the classifier output, and finally the control interface and device controller. The post-processed output signals are translated into appropriate commands so as to control output devices, with several applications such as robotic arms, video games, wheelchair etc.

Characterising information correlation in a stochastic Izhikevich neuron

The Izhikevich spiking neuron model is a relatively new mathematical framework which is able to represent many observed spiking neuron behaviors, excitatory or inhibitory, by simply adjusting a set of four model parameters. This model is deterministic in nature and has achieved wide applications in analytical and numerical analysis of biological neurons due largely to its biological plausibility and computational efficiency. In this work we present a stochastic version of the Izhikevich neuron, and measure its performance in transmitting information in a range of biological frequencies. The work reveals that the deterministic Izhikevich model has a wide information transmission range and is generally better in transmitting information than its stochastic counterpart.

The Proposed Graphical User Interface (GUI)

A graphical user interface (GUI) is a front-end display for the brain–computer interface (BCI) user, and it plays a very important role in enhancing the performance of the complete BCI system. This interface can also be referred to as a brain–robot interface for a robot control application. This chapter details the major problems with some of the existing interfaces designed for robotic control. In order to address these issues, the interface presented in this book considers the practical requirements of a BCI user; i.e., realistic control of the movement of a robotic device through a novel GUI, referred to as the intelligent adaptive user interface (iAUI). This chapter gives an overview of the iAUI (for both autonomous and supervised control) within the complete BCI system, the iAUI architecture, flowchart, iAUI operation in an example scenario, interfacing MATLAB and Visual Basic, and also introduces an intelligent interface for a robot arm control.

Wrist Movement Detector for ROS Based Control of the Robotic Hand

Banking industry is a vital supply of finance in any country. Credit Risk analysis could be an essential and decisive task in banking sector. Loan sanction procedure will be followed supported the credit risk analysis of any client. Automation of deciding in money applications exploitation best algorithms and classifiers is way helpful. This work evaluates the adroitness of various Memory primarily based classifiers on credit risk analysis. The German credit information is taken for adroitness analysis and is finished exploitation open supply machine learning tool. The performances of various memory primarily based classifier square measure analyzed and a sensible guideline for choosing exceptional and compatible algorithmic rule for credit analysis is given.