Share This Author
Fractal and EMD based removal of baseline wander and powerline interference from ECG signals
A Novel Signal Modeling Approach for Classification of Seizure and Seizure-Free EEG Signals
- Anubha Gupta, Pushpendra Singh, Mandar Karlekar
- Computer ScienceIEEE Transactions on Neural Systems and…
- 22 March 2018
A novel signal model for EEG data is proposed that best captures the attributes of these signals and hence, allows to boost the classification accuracy of seizure and seizure-free epochs.
U-Segnet: Fully Convolutional Neural Network Based Automated Brain Tissue Segmentation Tool
- Pulkit Kumar, Pravin Nagar, C. Arora, Anubha Gupta
- Computer Science25th IEEE International Conference on Image…
- 12 June 2018
A Fully Convolutional Neural Network (FCN) tool, that is a hybrid of two widely used deep learning segmentation architectures SegNet and U-Net, for improved brain tissue segmentation is proposed and shown that the proposed U-SegNet architecture, improves segmentation performance, as measured by average dice ratio, to 89.74% on the widely used IBSR dataset.
A new approach for estimation of statistically matched wavelet
Methods are presented to design a finite impulse response/infinite impulse response (FIR/IIR) biorthogonal perfect reconstruction filterbank, leading to the estimation of a compactly supported/infinitely supported statistically matched wavelet.
Classification of Schizophrenia versus normal subjects using deep learning
The proposed stacked autoencoder (SAE) based 2-stage architecture for disease diagnosis is able to classify normal and Schizophrenia subjects with 10-fold cross-validation accuracy that is better compared to the existing methods used on the same dataset.
Variable Step-Size LMS Algorithm for Fractal Signals
The performance of the proposed fractal-based variable step-size least mean square (FB-VSLMS) algorithm is compared with the unsigned VSLMS algorithm and is observed to be better for the class of nonstationary signals considered.
Joint Power-Domain and SCMA-Based NOMA System for Downlink in 5G and Beyond
A joint power and code-domain non-orthogonal multiple access technique for the fifth-generation (5G) wireless networks and beyond and a downlink system, where the users’ experience diverse channel conditions, is considered.
SD-Layer: Stain Deconvolutional Layer for CNNs in Medical Microscopic Imaging
A stain deconvolutional layer affixed at the front of CNN that performs two functions: it transforms the input RGB microscopic images to Optical Density (OD) space and this layer deconvolves OD image with the stain basis learned through backpropagation and provides tissue-specific stain absorption quantities as input to the following CNN layers.
Stain Color Normalization and Segmentation of Plasma Cells in Microscopic Images as a Prelude to Development of Computer Assisted Automated Disease Diagnostic Tool in Multiple Myeloma
Baseline Wander and Power-Line Interference Removal from ECG Signals Using Fourier Decomposition Method
- Pushpendra Singh, Ishita Srivastava, Amit Singhal, Anubha Gupta
- Computer ScienceAdvances in Intelligent Systems and Computing
- 8 August 2018
The proposed Fourier decomposition method has been shown to preserve shape characteristics of ECG signals of heart abnormalities and is effective over previously used EMD-based methods.