Adham Atyabi

Evolutionary feature selection and electrode reduction for EEG classification

EEG signals usually have a high dimensionality which makes it difficult for classifiers to learn the difference of various classes in the underlying pattern in the signal. This paper investigates several evolutionary algorithms used to reduce the dimensionality of the data. The study presents electrode and feature reduction methods based on Genetic Algorithms (GA) and Particle Swarm Optimization (PSO). Evolution-based methods are used to generate a set of indexes presenting either electrode seats or feature points that maximizes the output of a weak classifier. The results are interpreted based on the dimensionality reduction achieved, the significance of the lost accuracy, and the possibility of improving the accuracy by passing the chosen electrode/feature sets to alternative classifiers.

Dimension reduction in EEG data using Particle Swarm Optimization

EEG data contains high-dimensional data that requires considerable computational power for distinguishing different classes. Dimension reduction is commonly used to reduces the necessary training time of the classifiers with some degree of accuracy lost. The dimension reduction is usually performed on either feature or electrode space. In this study, a new dimension reduction method that reduce the number of electrodes and features using variations of Particle Swarm Optimization (PSO) is used. The variation is in terms of parameter adjustment and adding a mutation operator to the PSO. The results are assessed based on the dimension reduction percentage, the potential of selected electrodes and the degree of performance lost. An Extreme Learning Machine (ELM) is used as the primary classifier to evaluate the sets of electrodes and features selected by PSO. Two alternative classifiers such as Polynomial SVM and Perceptron are used for further evaluation of the reduced dimension data. The results indicate the potential of variations of PSO for reducing up to 99% of the data with minimal performance lost.

Multiplying the mileage of your dataset with subwindowing

This study is focused on improving the classification performance of EEG data through the use of some data restructuring methods. In this study, the impact of having more training instances/samples vs. using shorter window sizes is investigated. The BCI2003 IVa dataset is used to examine the results. The results not surprisingly indicate that, up to a certain point, having higher numbers of training instances significantly improves the classification performance while the use of shorter window sizes tends to worsen performance in a way that usually cannot fully be compensated for by the additional instances, but tends to provide useful gain in overall performance for small divisors into two or three subepochs.We have moreover determined that use of an incomplete set of overlapping windows can have little effect, and is inapplicable for the smallest divisors, but that use of overlapping subepochs from three specific non-overlapping areas (start, middle and end) of a superepoch tends to contribute significant additional information. Examination of a division into five equal non-overlapping areas indicates that for some subjects the first or last fifth contributes significantly less information than the middle three fifths.

The impact of segmentation and replication on non-overlapping windows: An EEG study

It is a common phenomenon that classification techniques applied to human EEG data are often more successful for some subjects than others. One reason may be that subjects differ in the degree and length of time that they can continue to be engaged with the experimental task at hand. EEG recording can be a time-consuming, tedious and challenging procedure that often involves having subjects remain physically still for extended periods of time while repeatedly performing various mental, computational, imagery or other tasks. Hence, it can be expected that their level of involvement with the task may fluctuate, causing difficulties in using data from the entire task period for classification. This effect is more likely to appear on recordings in which the task period is longer than usual as in the dataset IVa from BCI competition III in which the task time duration is set to 3.5s. This study investigates the impact on classification performance of using data from various fragments of the complete time period. The goal is to improve classification performance by providing higher concentration on some segments than others. The results indicate the importance of focusing on the middle and final sub-epochs, and poorer performance during earlier sub-windows.

Adapting subject-independent task-specific EEG feature masks using PSO

Dimension reduction is an important step toward asynchronous EEG based BCI systems, with EA based Feature/ Electrode Reduction (FR/ER) methods showing significant potential for this purpose. A PSO based approach can reduce 99% of the EEG data in this manner while demonstrating generalizability through the use of 3 new subsets of features/electrodes that are selected based on the best performing subset on the validation set, the best performing subset on the testing set, and the most commonly used features/electrodes in the swarm. This study is focused on applying the subsets generated from 4 subjects on a 5th one. Two schemes for this are implemented based on i) extracting separate subsets of feature/electrodes for each subject (out of 4 subjects) and combining the final products together for use with the 5th subject, and ii) concatenating the preprocessed EEG data of 4 subjects together and extracting the desired subset with PSO for use with the 5th subject. The results indicate the feasibility of generating subsets of feature/electrode indexes that are task specific and can be used on new subjects.

Biasing the overlapping and non-overlapping sub-windows of EEG recording

EEG recording involves having subjects sit on a chair for a couple of hours without being allowed to move and being asked to repeatedly perform various mental, computational, motor imaginary or any other tasks for some specific amount of time. This is a time consuming, boring and complicated procedure during which there is no guarantee that the subject will maintain the proper level of concentration on the requested task at all times, this is apart from the possible muscle activity that might be accidentally generated. This might cause complications in terms of generating signals that do not necessarily contain useful information for classification in the whole tasks time duration. This effect is more likely to appear on recordings in which the task period is longer than usual as in the dataset IVa from BCI competition III in which the task time duration is set to 3.5s. This study investigate the impact of various fragments of time on classification performance. The idea is to improve the classification performance by providing higher concentration on segments of the signal that we assume the subject had better concentration on the task. The results indicate the importance of the middle and end sub-epochs while it illustrate lower performance during the earlier sub-windows.

A hierarchal planning framework for AUV mission management in a spatiotemporal varying ocean

The purpose of this paper is to provide a hierarchical dynamic mission planning framework for a single autonomous underwater vehicle (AUV) to accomplish task-assign process in a limited time interval while operating in an uncertain undersea environment, where spatio-temporal variability of the operating field is taken into account. To this end, a high level reactive mission planner and a low level motion planning system are constructed. The high level system is responsible for task priority assignment and guiding the vehicle toward a target of interest considering on-time termination of the mission. The lower layer is in charge of generating optimal trajectories based on sequence of tasks and dynamicity of operating terrain. The mission planner is able to reactively re-arrange the tasks based on mission/terrain updates while the low level planner is capable of coping unexpected changes of the terrain by correcting the old path and re-generating a new trajectory. As a result, the vehicle is able to undertake the maximum number of tasks with certain degree of maneuverability having situational awareness of the operating field. The computational engine of the mentioned framework is based on the biogeography based optimization (BBO) algorithm that is capable of providing efficient solutions. To evaluate the performance of the proposed framework, firstly, a realistic model of undersea environment is provided based on realistic map data, and then several scenarios, treated as real experiments, are designed through the simulation study. Additionally, to show the robustness and reliability of the framework, Monte-Carlo simulation is carried out and statistical analysis is performed. The results of simulations indicate the significant potential of the two-level hierarchical mission planning system in mission success and its applicability for real-time implementation.

Hybrid Motion Planning Task Allocation Model for AUV’s Safe Maneuvering in a Realistic Ocean Environment

This paper presents a hybrid route-path planning model for an Autonomous Underwater Vehicle’s task assignment and management while the AUV is operating through the variable littoral waters. Several prioritized tasks distributed in a large scale terrain is defined first; then, considering the limitations over the mission time, vehicle’s battery, uncertainty and variability of the underlying operating field, appropriate mission timing and energy management is undertaken. The proposed objective is fulfilled by incorporating a route-planner that is in charge of prioritizing the list of available tasks according to available battery and a path-planer that acts in a smaller scale to provide vehicle’s safe deployment against environmental sudden changes. The synchronous process of the task assign-route and path planning is simulated using a specific composition of Differential Evolution and Firefly Optimization (DEFO) Algorithms. The simulation results indicate that the proposed hybrid model offers efficient performance in terms of completion of maximum number of assigned tasks while perfectly expending the minimum energy, provided by using the favorable current flow, and controlling the associated mission time. The Monte-Carlo test is also performed for further analysis. The corresponding results show the significant robustness of the model against uncertainties of the operating field and variations of mission conditions.

Mixture of autoregressive modeling orders and its implication on single trial EEG classification

Autoregressive (AR) models are of commonly utilized feature types in Electroencephalogram (EEG) studies due to offering better resolution, smoother spectra and being applicable to short segments of data. Identifying correct ARs modeling order is an open challenge. Lower model orders poorly represent the signal while higher orders increase noise. Conventional methods for estimating modeling order includes Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and Final Prediction Error (FPE). This article assesses the hypothesis that appropriate mixture of multiple AR orders is likely to better represent the true signal compared to any single order. Better spectral representation of underlying EEG patterns can increase utility of AR features in Brain Computer Interface (BCI) systems by increasing timely & correctly responsiveness of such systems to operators thoughts. Two mechanisms of Evolutionary-based fusion and Ensemble-based mixture are utilized for identifying such appropriate mixture of modeling orders. The classification performance of the resultant AR-mixtures are assessed against several conventional methods utilized by the community including 1) A well-known set of commonly used orders suggested by the literature, 2) conventional order estimation approaches (e.g., AIC, BIC and FPE), 3) blind mixture of AR features originated from a range of well-known orders. Five datasets from BCI competition III that contain 2, 3 and 4 motor imagery tasks are considered for the assessment. The results indicate superiority of Ensemble-based modeling order mixture and evolutionary-based order fusion methods within all datasets.

Multiplication of EEG samples through replicating, biasing, and overlapping

EEG recording is a time consuming operation during which the subject is expected to stay still for a long time performing tasks. It is reasonable to expect some fluctuation in the level of focus toward the performed task during the task period. This study is focused on investigating various approaches for emphasizing regions of interest during the task period. Dividing the task period into three segments of beginning, middle and end, is expectable to improve the overall classification performance by changing the concentration of the training samples toward regions in which subject had better concentration toward the performed tasks. This issue is investigated through the use of techniques such as i) replication, ii) biasing, and iii) overlapping. A dataset with 4 motor imagery tasks (BCI Competition III dataset IIIa) is used. The results illustrate the existing variations within the potential of different segments of the task period and the feasibility of techniques that focus the training samples toward such regions.