Adili Tuheti
Papers
1
Total Citations
6
H-Index
1
About
Adili Tuheti is a rising force in biomedical signal processing and human-computer interaction (HCI), with a focused expertise in electrooculography (EOG)-based systems. His most cited work, "Residual Self-Calibrated Network With Multi-Scale Channel Attention for Accurate EOG-Based Eye Movement Classification" (2024, 6 citations), addresses a critical bottleneck in EOG-HCI technology: the challenge of accurately classifying eye movements from noisy, multi-channel signals. Tuheti’s key contribution is the development of a novel deep learning architecture that integrates residual self-calibration with multi-scale channel attention mechanisms. This innovation significantly enhances the precision and robustness of eye movement classification, a fundamental step for applications in assistive robots and augmented reality gaming. By tackling the noise and variability inherent in EOG signals, his work directly improves the reliability of hands-free control interfaces for users with motor impairments. Though early in his career, Tuheti’s research has already garnered attention for its practical impact on industrial HCI systems, positioning him as a promising contributor to the next generation of adaptive, attention-driven neural networks for real-world biosignal applications.
Research Focus
Key Achievements
Top Papers
- 1