Avatar

N. D. Londhe

N. D. Londhe is with the National Institute of Technology Raipur, Raipur 492010, India. Senior Member, IEEE.


Contributions

  • Improving Performance of Devanagari Script Input-Based P300 Speller Using Deep Learning
    Improving Performance of Devanagari Script Input-Based P300 Speller Using Deep Learning

    Highlights: Classification of P300 using two deep learning algorithms i.e. deep convolution neural network (DCNN) and stacked autoencoder (SAE), customized and fine-tuned for Devanagari Script (DS) based P300 speller; A novel double batch training approach to handle the computational burden; A leaky ReLU activation function is used in DCNN to overcome dying ReLU problem; Improvement in the performance of DS based P300 speller for reduced number of trials; Reduced the time to spell the character from 16 sec to 9.6 sec; Achieved classification accuracy of 88.22% just in three trials.

Login

New Here? Sign Up

Looking for increased exposure in the field of biomedical engineering? EMBS offers journals, conferences and a community for biomedical engineers. Membership includes PULSE Magazine.

Join EMBS