A5093815954- Time Series Analysis and Forecasting
- Anomaly Detection Techniques and Applications
- Neuroscience of respiration and sleep
- Advanced Statistical Methods and Models
- Respiratory Support and Mechanisms
- EEG and Brain-Computer Interfaces
- Non-Invasive Vital Sign Monitoring
University of Florida
2024-2025
Applied Optimization (United States)
2025
Detecting cognitive states and impairments through EEG signals is crucial for applications in aviation medicine has broad the field of human-machine interaction. However, existing methods often fail to capture fine-grained neural dynamics critical brain processes due limited temporal resolution inadequate signal decomposition techniques. To address this, we introduce Spectral Intensity Stability (SIS) algorithm, a novel technique that analyzes stability competition dominant frequency...
Detecting cognitive states and impairments through EEG signals is crucial for applications in aviation medicine has broad the field of human-machine interaction. However, existing methods often fail to capture fine-grained neural dynamics critical brain processes due limited temporal resolution inadequate signal decomposition techniques. To address this, we introduce Spectral Intensity Stability (SIS) algorithm, a novel technique that analyzes stability competition dominant frequency...
This study introduces a novel entropy-based methodology to quantitatively characterize non-linear transient breathing dynamics under respiratory stress. Environmental and pathophysiological stressors can disrupt the system's gas exchange, leading compromise compensatory mechanisms. We present data-driven approach that systematically evaluates classical features alongside entropic as key indicators demonstrate conventional metrics like rate ( B R ), time of inspiration T I expiration E ) fail...
As aviation systems in commercial operations continue to grow complexity, the anomalies exhibited by these become more elaborate and difficult detect. To address challenge of detecting complex anomalies, deep learning models have been used extensively anomaly detection studies, at expense end-user interpretability. Aiming maintain same level interpretability as traditional threshold-exceedance methods, we our development prediction using ordinal patterns their distributions throughout...