Yajurv Bhatia

Papers

Total Citations

H-Index

About

Yajurv Bhatia is a researcher at the forefront of affective computing, specializing in the emerging field of gait emotion recognition (GER). His work focuses on decoding human emotions from walking patterns using deep learning, with applications spanning smart home design, border security, robotics, virtual reality, and gaming. Bhatia’s major contributions include pioneering bi-modular neural architectures that integrate motion capture sensor data with sequential modeling. His most cited work, "Motion Capture Sensor-Based Emotion Recognition Using a Bi-Modular Sequential Neural Network" (2022), has garnered 25 citations, establishing a foundational approach for combining handcrafted features with deep learning. He further advanced the field with a LSTM-based framework (2021, 8 citations) that effectively captures temporal dependencies in gait sequences. His latest research (2025) introduces a novel bi-modal deep network that fuses handcrafted and learned features, achieving improved emotion classification accuracy. Bhatia’s work is notable for bridging traditional feature engineering with modern neural networks, offering robust solutions for real-time emotion sensing. His research holds significant promise for creating more intuitive human-computer interactions and adaptive intelligent environments.