A5042831035- EEG and Brain-Computer Interfaces
- Blind Source Separation Techniques
- Power Systems Fault Detection
- HVDC Systems and Fault Protection
- Neuroscience and Neural Engineering
- High-Voltage Power Transmission Systems
- Neural Networks and Applications
- Epilepsy research and treatment
- Digital Imaging for Blood Diseases
- Power System Reliability and Maintenance
- Vehicle License Plate Recognition
- Currency Recognition and Detection
- AI in cancer detection
- Islanding Detection in Power Systems
- GNSS positioning and interference
- COVID-19 diagnosis using AI
- Power Line Inspection Robots
- Ionosphere and magnetosphere dynamics
- Neonatal and fetal brain pathology
- Earthquake Detection and Analysis
- Power Line Communications and Noise
Indian Institute of Technology Roorkee
2024
KIIT University
2017-2022
In this paper, a novel protection scheme is proposed for bipolar line commutated converter (LCC) high voltage direct current (HVDC) transmission lines which detects the fault, identifies pole of fault and estimates location fault. The uses features extracted from rectifier end DC signals. Long short term memory (LSTM) deep learning method has been designed as classifier well predictor carrying out different tasks. Three modules have namely LSTM-FD detection, LSTM-FI identification LSTM-FL...
Fault location estimation methods have been suggested by researchers decades back after the development of transmission lines for power transmission. But there are several drawbacks exist such as incapability to locate high resistance faults, boundary intercircuit change in line parameters, evolving etc. Hence, a method should be developed, which can address all problems conventional fault methods. One solutions artificial intelligence (AI) due ability learn and think. In this article, an...
Most of the fault location methods in high voltage direct current (HVDC) transmission lines usemethods which require signals from both ends. It will be difficult to estimate if signal recorded is not correct due communication problems.Hence a robust method required can locate with minimum error. In this work, faults are located using boosting ensembles HVDC based on single terminal (DC) signals. The processed obtain input features that vary distance. These obtained by taking maximum half...
Epilepsy or recurrent seizures is one of the most common non communicable neurological disorder that prevalent in today's world population are sudden outburst excess electrical activity neurons. can be detected from Electroencephalogram (EEG) as EEG captures and presents brain. Non-invasive scalp generally used where electrodes placed on order to record brain activity. In this work a unsupervised machine learning technique explored which cluster extract features recordings (noninvasive)...
In this work, advanced learning and moving window-based methods have been used for epileptic seizure detection. Epilepsy is a disorder of the central nervous system roughly affects 50 million people worldwide. The most common non-invasive tool studying brain activity an patient electroencephalogram. Accurate detection onset still elusive work. Electroencephalogram signals belonging to pediatric patients from Children’s Hospital Boston, Massachusetts Institute Technology in work validate...