Madhuri Bawane

Hierarchical Classifier employing Optimised Neural Networks

With recent advances in Electroencephalogram (EEG) signal processing and biomedical instrumentati... more With recent advances in Electroencephalogram (EEG) signal processing and biomedical instrumentation, brain machine interfaces are used for rehabilitation of people suffering from neuromuscular disorders. This paper presents a novel method employing Hierarchical classifier using optimised Neural Networks to classify left-hand movement, right-hand movement and word generation using EEG signals. One of the most important components of brain computer interface (BCI) is feature extraction of EEG signals. Power spectral density (PSD) is used for feature extraction from EEG signals. The proposed pre-processing and reconfiguration of PSD samples make them more discriminative & yield appropriately organized feature vectors. The adaptation of network weights using Comprehensive Learning Particle Swarm Optimization (CLPSO) is proposed to improve the performance of Neural Network (NN). Further, the two level hierarchical neural network is used to enhance the discriminative property of the featu...

Download

Classification of Mental Task Based on EEG Processing Using Self Organising Feature Map

2014 Sixth International Conference on Intelligent Human-Machine Systems and Cybernetics, 2014

AN electroencephalograph (EEG) based computer interface system, also known as brain-computer inte... more AN electroencephalograph (EEG) based computer interface system, also known as brain-computer interface (BCI), offers a new means of computer interaction for those with paralysis or severe neuromuscular disorders. This paper illustrates a novel method using Self Organizing Feature Map (SOFM) to classify left-hand movement imagination, right-hand movement imagination, and word generation from EEG. Welch's periodogram, a power spectrum density (PSD) estimation which is very powerful preprocessing method capable of handling both the noisy and non-stationary natures of EEG signals is used for feature extraction. Further, we classify the PSD feature using SOFM. SOFM is arranged deliberately in a specific fashion and trained with variable learning rate to classify various mental tasks under consideration. A classification accuracy obtained using SOFM is compared with other existing techniques.

Classification of Mental Tasks using EEG and Hierarchical Classifier employing Optimised Neural Networks

International Journal of Computer Applications, Jan 15, 2016

With recent advances in Electroencephalogram (EEG) signal processing and biomedical instrumentati... more With recent advances in Electroencephalogram (EEG) signal processing and biomedical instrumentation, brain machine interfaces are used for rehabilitation of people suffering from neuromuscular disorders. This paper presents a novel method employing Hierarchical classifier using optimised Neural Networks to classify left-hand movement, right-hand movement and word generation using EEG signals. One of the most important components of brain computer interface (BCI) is feature extraction of EEG signals. Power spectral density (PSD) is used for feature extraction from EEG signals. The proposed pre-processing and reconfiguration of PSD samples make them more discriminative & yield appropriately organized feature vectors. The adaptation of network weights using Comprehensive Learning Particle Swarm Optimization (CLPSO) is proposed to improve the performance of Neural Network (NN). Further, the two level hierarchical neural network is used to enhance the discriminative property of the features and hence better classification accuracy is achieved. Results are verified on BCI benchmarking database as well as our own experimental database. Results obtained using the proposed methods are compared with other contemporary methods such as Linear Discrimination

Download

Uploads

Papers by Madhuri Bawane

Log In