User Identification

User identification research focuses on reliably distinguishing individuals based on their unique behavioral or physiological patterns, aiming to enhance security and personalization across various applications. Current efforts explore diverse data sources, including keystroke dynamics, eye movements, pressure patterns from smart textiles, and even mmWave radar signals from gestures, employing machine learning models like convolutional neural networks, recurrent neural networks (RNNs, LSTMs, GRUs), and contrastive learning approaches. These advancements have implications for improving security in digital systems, personalizing user experiences in virtual and augmented reality, and enabling novel healthcare applications like sleep apnea monitoring.