Development of a Novel Motor Imagery Control Technique and Application in a Gaming Environment

EEG-based motor imagery channel selection and classification using hybrid optimization and two-tier deep learning

Brain-computer interface (BCI) technology holds promise for individuals with profound motor impairments, offering the potential for communication and control. Motor imagery (MI)-based BCI systems are particularly relevant in this context. Despite their potential, achieving accurate and robust classification of MI tasks using electroencephalography (EEG) data remains a significant challenge. In this paper, we employed the Minimum Redundancy Maximum Relevance (MRMR) algorithm to optimize channel selection. Furthermore, we introduced a hybrid optimization approach that combines the War Strategy Optimization (WSO) and Chimp Optimization Algorithm (ChOA). This hybridization significantly enhances the classification model's overall performance and adaptability. A two-tier deep learning architecture is proposed for classification, consisting of a Convolutional Neural Network (CNN) and a modified Deep Neural Network (M-DNN). The CNN focuses on capturing temporal correlations within EEG data, while the M-DNN is designed to extract high-level spatial characteristics from selected EEG channels. Integrating optimal channel selection, hybrid optimization, and the two-tier deep learning methodology in our BCI framework presents an enhanced approach for precise and effective BCI control. Our model got 95.06% accuracy with high precision. This advancement has the potential to significantly impact neurorehabilitation and assistive technology applications, facilitating improved communication and control for individuals with motor impairments.

A Method for the Spatial Interpolation of EEG Signals Based on the Bidirectional Long Short-Term Memory Network

The precision of electroencephalograms (EEGs) significantly impacts the performance of brain-computer interfaces (BCI). Currently, the majority of research into BCI technology gives priority to lightweight design and a reduced electrode count to make it more suitable for application in wearable environments. This paper introduces a deep learning-based time series bidirectional (BiLSTM) network that is designed to capture the inherent characteristics of EEG channels obtained from neighboring electrodes. It aims to predict the EEG data time series and facilitate the conversion process from low-density EEG signals to high-density EEG signals. BiLSTM pays more attention to the dependencies in time series data rather than mathematical maps, and the root mean square error can be effectively restricted to below 0.4μV, which is less than half the error in traditional methods. After expanding the BCI Competition III 3a dataset from 18 channels to 60 channels, we conducted classification experiments on four types of motor imagery tasks. Compared to the original low-density EEG signals (18 channels), the classification accuracy was around 82%, an increase of about 20%. When juxtaposed with real high-density signals, the increment in the error rate remained below 5%. The expansion of the EEG channels showed a substantial and notable improvement compared with the original low-density signals.

Vegetation Evolution: An Optimization Algorithm Inspired by the Life Cycle of Plants

In this paper, we have observed that different types of plants in nature can use their own survival mechanisms to adapt to various living environments. A new population-based vegetation evolution (VEGE) algorithm is proposed to solve optimization problems by interactively simulating the growth and maturity periods of plants. In the growth period, individuals explore their local areas and grow in potential directions, while individuals generate many seed individuals and spread them as widely as possible in the maturity period. The main contribution of our proposed VEGE is to balance exploitation and exploration from a novel perspective, which is to perform these two periods in alternation to switch between two different search capabilities. To evaluate the performance of the proposed VEGE, we compare it with three well-known algorithms in the evolutionary computation community: differential evolution, particle swarm optimization, and enhanced fireworks algorithm — and run them on 28 benchmark functions with 2-dimensions (2D), 10D, and 30D with 30 trial runs. The experimental results show that VEGE is efficient and promising in terms of faster convergence speed and higher accuracy. In addition, we further analyze the effects of the composition of VEGE on performance, and some open topics are also given.

Electro-Encephalography and Electro-Oculography in Aeronautics: A Review Over the Last Decade (2010-2020)

Electro-encephalography (EEG) and electro-oculography (EOG) are methods of electrophysiological monitoring that have potentially fruitful applications in neuroscience, clinical exploration, the aeronautical industry, and other sectors. These methods are often the most straightforward way of evaluating brain oscillations and eye movements, as they use standard laboratory or mobile techniques. This review describes the potential of EEG and EOG systems and the application of these methods in aeronautics. For example, EEG and EOG signals can be used to design brain-computer interfaces (BCI) and to interpret brain activity, such as monitoring the mental state of a pilot in determining their workload. The main objectives of this review are to, (i) offer an in-depth review of literature on the basics of EEG and EOG and their application in aeronautics; (ii) to explore the methodology and trends of research in combined EEG-EOG studies over the last decade; and (iii) to provide methodological guidelines for beginners and experts when applying these methods in environments outside the laboratory, with a particular focus on human factors and aeronautics. The study used databases from scientific, clinical, and neural engineering fields. The review first introduces the characteristics and the application of both EEG and EOG in aeronautics, undertaking a large review of relevant literature, from early to more recent studies. We then built a novel taxonomy model that includes 150 combined EEG-EOG papers published in peer-reviewed scientific journals and conferences from January 2010 to March 2020. Several data elements were reviewed for each study (e.g., pre-processing, extracted features and performance metrics), which were then examined to uncover trends in aeronautics and summarize interesting methods from this important body of literature. Finally, the review considers the advantages and limitations of these methods as well as future challenges.

Brain wave classification using long short-term memory network based OPTICAL predictor

Brain-computer interface (BCI) systems having the ability to classify brain waves with greater accuracy are highly desirable. To this end, a number of techniques have been proposed aiming to be able to classify brain waves with high accuracy. However, the ability to classify brain waves and its implementation in real-time is still limited. In this study, we introduce a novel scheme for classifying motor imagery (MI) tasks using electroencephalography (EEG) signal that can be implemented in real-time having high classification accuracy between different MI tasks. We propose a new predictor, OPTICAL, that uses a combination of common spatial pattern (CSP) and long short-term memory (LSTM) network for obtaining improved MI EEG signal classification. A sliding window approach is proposed to obtain the time-series input from the spatially filtered data, which becomes input to the LSTM network. Moreover, instead of using LSTM directly for classification, we use regression based output of the LSTM network as one of the features for classification. On the other hand, linear discriminant analysis (LDA) is used to reduce the dimensionality of the CSP variance based features. The features in the reduced dimensional plane after performing LDA are used as input to the support vector machine (SVM) classifier together with the regression based feature obtained from the LSTM network. The regression based feature further boosts the performance of the proposed OPTICAL predictor. OPTICAL showed significant improvement in the ability to accurately classify left and right-hand MI tasks on two publically available datasets. The improvements in the average misclassification rates are 3.09% and 2.07% for BCI Competition IV Dataset I and GigaDB dataset, respectively. The Matlab code is available at https://github.com/ShiuKumar/OPTICAL .

A Shaping Procedure to Modulate Two Cognitive Tasks to Improve a Sensorimotor Rhythm-Based Brain-Computer Interface System

This study aimed to propose an adapted feedback using a psychological learning technique based on Skinner's shaping method to help the users to modulate two cognitive tasks (right-hand motor imagination and relaxed state) and improve better control in a Brain-Computer Interface. In the first experiment, a comparative study between performance in standard feedback (N = 9) and shaping method (N = 10) was conducted. The NASA Task Load Index questionnaire was applied to measure the user's workload. In the second experiment, a single case study was performed (N = 5) to verify the continuous learning by the shaping method. The first experiment showed significant interaction effect between sessions and group (F(1, 17) = 5.565; p = .031) which the shaping paradigm was applied. A second interaction effect demonstrates a higher performance increase in the relax state task with shaping procedure (F(1, 17) = 5. 038; p = .038). In NASA-TXL an interaction effect was obtained between the group and the cognitive task in Mental Demand (F(1, 17) = 6, 809; p = .018), Performance (F(1, 17) = 5, 725; p = .029), and Frustration (F(1, 17) = 9, 735; p = .006), no significance was found in Effort. In the second experiment, a trial-by-trial analysis shows an ascendant trend learning curve for the cognitive task with the lowest initial acquisition (relax state). The results suggest the effectiveness of the shaping procedure to modulate brain rhythms, improving mainly the cognitive task with greater initial difficulty and provide better interaction perception.