A5070473912- EEG and Brain-Computer Interfaces
- Blind Source Separation Techniques
- Dental materials and restorations
- Machine Fault Diagnosis Techniques
- Bone Tissue Engineering Materials
- Neural Networks and Applications
- Neuroscience and Neural Engineering
- Tensor decomposition and applications
- Spectroscopy and Chemometric Analyses
- Dental Implant Techniques and Outcomes
- Engineering Diagnostics and Reliability
- Fault Detection and Control Systems
- Image and Signal Denoising Methods
- Remote-Sensing Image Classification
- Gear and Bearing Dynamics Analysis
- Neural dynamics and brain function
- Metallurgy and Material Forming
- Muscle activation and electromyography studies
- Additive Manufacturing Materials and Processes
A P J Abdul Kalam Technological University
2025
Indian Institute of Technology Palakkad
2024
Amrita Vishwa Vidyapeetham
2018-2022
Kerala State Council for Science, Technology and Environment
2018
A novel approach of preprocessing EEG signals by generating spectrum image for effective Convolutional Neural Network (CNN) based classification Motor Imaginary (MI) recognition is proposed. The involves extracting the Variational Mode Decomposition (VMD) modes signals, from which Short Time Fourier Transform (STFT) all are arranged to form images. images generated provided as input CNN. two generic CNN architectures MI (EEGNet and DeepConvNet) pattern (AlexNet LeNet) used in this study....
Devising a reliable method for implementing brain computer interface (BCI) systems using electroencephalogram (EEG) signals is proposed. Applicability of two modal decomposition methods, variational mode (VMD) and empirical wavelet transform (EWT) on EEG identifying the four different motor imaginary movements by investigation event-related desynchronisation (ERD) activity in Mu-beta rhythm analysed compared. The from each electrode corresponding to sensorimotor cortex area are decomposed...
Brain is a high dimensional complex dynamical system whose governing equations are unknown. Its functions inferred through analysis of EEG signals which very difficult and task. The power spectrum remained as one the foremost method for feature extraction BCI applications. In context BCI, spatial information inevitable. Moreover while considering complicated circuitry involved in generation usual becomes insufficient. Recently developed data driven called dynamic mode decomposition (DMD)...
Hyperspectral data accounts for a huge volume of information. Analysing such large is very difficult. Besides atmospheric distortion also affect analysis. Many denoising techniques have been introduced to reduce the dimensionality as well removing distortions. This helps in improving accuracy classification. The work proposes application two dimensional Variational Mode Decomposition (VMD) feature extraction method acquired image. VMD decomposes image into different intrinsic mode functions...
Devising a reliable method for implementing brain computer interface (BCI) systems using electroencephalogram (EEG) signals is proposed. Applicability of two modal decomposition methods, variational mode (VMD) and empirical wavelet transform (EWT) on EEG identifying the four different motor imaginary movements by investigation event-related desynchronisation (ERD) activity in Mu-beta rhythm analysed compared. The from each electrode corresponding to sensorimotor cortex area are decomposed...