Papers
3
Total Citations
51
H-Index
3
About
Preeti Kumari is a researcher specializing in biomedical signal processing, human-computer interaction, and assistive technology, with a particular focus on leveraging machine learning to decode human physiological signals for real-world applications. Her most impactful work centers on the analysis of Surface Electromyography (sEMG) signals, where she has pioneered the use of Wavelet Packet Transform (WPT) combined with Support Vector Machine (SVM) classifiers to achieve accurate movement classification. Her 2016 study on elbow movement classification using Fine Gaussian SVM, which has garnered 30 citations, demonstrated a robust pipeline for denoising, feature extraction, and classification of sEMG signals acquired from healthy subjects — a contribution that has meaningfully advanced prosthetics and rehabilitation engineering. A companion study on binary movement classification using Linear SVM further cemented her expertise, earning 18 citations. More recently, Kumari has expanded her research horizon into multimodal biosignal integration, combining brain and eye signals with RFID technology to develop shared-control interfaces for assistive robotics. Collectively, her work reflects a sustained commitment to improving the quality of life for individuals with disabilities through intelligent, signal-driven human-machine interfaces.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3