S
Samarendra Dandapat
Researcher at Indian Institute of Technology Guwahati
Publications - 200
Citations - 2877
Samarendra Dandapat is an academic researcher from Indian Institute of Technology Guwahati. The author has contributed to research in topics: Wavelet & Wavelet transform. The author has an hindex of 21, co-authored 179 publications receiving 2205 citations. Previous affiliations of Samarendra Dandapat include Indian Institute of Technology Kanpur & Nanyang Technological University.
Papers
More filters
Discrimination of Types of Seizure Using Brain Rhythms Based on Markov Transition Field and Deep Learning
TL;DR: 2D images for the DL pipeline have been generated from brain rhythms, which already displayed remarkable performance in analyzing various brain activities, and the Markov transition field transformation technique has been employed for 2D image construction by preserving statistical dynamics characteristics of EEG signals.
Book ChapterDOI
Inverse Filtering Based Feature for Analysis of Vowel Nasalization
TL;DR: An inverse filtering based technique is used to develop a novel feature, which represents the amount of nasalization present in a vowel, which has good separability for oral vowels and nasalized vowels.
Journal ArticleDOI
Automated Detection of Heart Valve Diseases Using Stationary Wavelet Transform and Attention-Based Hierarchical LSTM Network
TL;DR: In this article , a stationary wavelet transform (SWT) decomposition was used for phonocardiogram (PCG)-based heart valve disease (HVD) detection for primary healthcare units.
Proceedings ArticleDOI
A Multi-Scale Residual Neural Network for ECG Based Person Identification
TL;DR: In this article , a multiscale residual neural network (MS-ResNet) architecture was proposed to exploit the morphological shape of the ECG waveforms and their inter-relationship for biometric application.
Journal ArticleDOI
Vector Quantization Approach to Classification of Stressed Speech
S. Ramamohan,Samarendra Dandapat +1 more
TL;DR: In this paper, a stressed (emotional) speech recognition system is designed based on Vector-Quantization (VQ) approach using Generalized Lloyd algorithm using frequency, amplitude and phase features extracted from the Sinusoidal model of speech and these parameters are used for characterization of stressed speech.