Browsing by Author "Talab, Aida Khorshid"

Feeding difficulty and malnutrition are common phenomena in disabled people. Feeding is often time consuming, unpleasant, and may result in asphyxiation. In many cases, robotic aids are applied to assist disabled people in eating. In particular, for people with severe disabilities including sensory losses and difficulty in basic physical mobility, assistive robots that require any movement from users cannot be applicable. A robotic system which can be controlled merely by thoughts and brain signals would be quite a remarkable aid for them. Brain Machine Interface (BMI) is a direct communication pathway between brain and an external electronic device. BMIs aim to translate brain activities into control commands. To design a system that translates brain waves to desired commands, motor imagery tasks classification is the core part of this work. Classification accuracy not only depends on how capable the classifier is but also on the input data. Feature extraction highlights the properties of signal that make it distinct from the signals of the other mental tasks. Performance of BMIs directly depends on the effectiveness of the feature extraction and classification algorithms. If a feature provides large interclass difference for different classes, the applied classifier exhibits a better performance. In this work, the application of time domain features for time-series Electroencephalogram (EEG) signal is discussed. Time domain features have low computational complexity; thus, they can be considered as a suitable option for real-time BMI systems. This study includes a comprehensive assessment of time domain features in which their effectiveness has been evaluated with two classifiers, namely Support Vector Machine (SVM) and Fuzzy C-means (FCM). Experimental verifications of the selected combination of feature and classifier have been done. Based on the requirements for real-time performance, a prototype of an EEG-based feeding robot has been developed. Experimental results show that the developed BMI was able to perform the required tasks in real-time, with tolerable errors of around 17% in average, which can be further supervised to be reduced or eliminated. For further research, combining some of the effective features and applying fusion classifiers are suggested to improve the performance of the BMI system.

The importance of Brain Machine Interface (BMI) calls for its continued improvement. BMI is a direct communication link between the brain and an external electronic device. BMIs aim to translate brain activities into control commands. Designing a system that translates brain waves into desired commands requires motor imagery task classification. Improvement of this translation not only depends on how capable the classifier is but also depends on the data fed to the classifier. Feature extraction highlights the properties of a signal that make it distinct from the signals of other mental tasks. The performance of BMIs directly depends on the effectiveness of the applied feature extraction and classification algorithms. If a feature provides a significant interclass difference for different classes, the applied classifier exhibits a better performance. In this work, to realize an interface between motor imagery task and an external device, a feature extraction method for Electroencephalogram (EEG) signal is introduced. This method uses signal dependent orthogonal transform based on the decomposition of linear prediction filter of impulse response matrix of the signal of interest. Two decomposition methods, known as singular value decomposition and QR decomposition, are applied for the proposed feature extraction method. Additionally, a new EEG channel selection method based on wrapper type method is proposed. This study is conducted on BCI completion III, dataset IIIa, which is a multiclass cued motor imagery EEG dataset. The obtained results are benchmarked against discrete cosine transform (DCT), adaptive autoregressive (AAR) based method, and different extensions of the state-of-the-art, Common Spatial Pattern (CSP) method, as well as the obtained results of the winners of competitions on this dataset. The best obtained results of the proposed methods reached an average accuracy of 81.38% with the capacity of generalization, which is the second best in terms of accuracy among all the available methods. A point to consider is that the best result belongs to a subject specific method with fine tuning of all parameters. The future direction of this research is to investigate more about the best choice of the relevant parameters to further improve performance.