Our research bridges the gap between computational methods and neuroscience, developing innovative solutions for brain-computer interfaces, mental workload assessment, and neural signal analysis through advanced machine learning and signal processing techniques.
Tale Research specializes in developing cutting-edge computational approaches to understand and interpret neural activity. Our interdisciplinary team combines expertise in neuroscience, machine learning, and signal processing to tackle the most challenging problems in brain research.
We address the fundamental challenge of analyzing high-dimensional EEG datasets with small sample sizes through specialized artificial neural networks and advanced optimization techniques, enabling breakthrough applications in clinical diagnostics and cognitive enhancement.
Explore our groundbreaking research in computational neuroscience, from seizure prediction to neural signatures of financial decision-making.
Our pioneering seizure detection algorithm combines multi-modal EEG signal processing with machine learning to predict seizure onset up to 15 minutes before clinical manifestation. This early warning system allows patients and caregivers crucial preparation time, reducing injury risk and improving quality of life for epilepsy patients.
Mental workload refers to the cognitive effort required to perform tasks, encompassing task demands, cognitive resources, and perceived difficulty. Our research develops advanced EEG-based methods to objectively measure mental workload in real-time, with applications in workplace design, human-computer interaction, and safety-critical environments.
Independent Component Analysis (ICA) is fundamental to our EEG processing pipeline, separating mixed neural signals into independent components. Our methodology isolates neural signals from artifacts (eye movements, muscle activity), enabling accurate interpretation of brain activity patterns essential for effective brain-computer interface systems.
Our Neuro-Finance research bridges neuroscience and behavioral economics to decode neural mechanisms underlying financial decision-making. By monitoring brain activity during simulated trading scenarios, we identify neural markers predicting risk assessment, loss aversion, and decision confidence with remarkable accuracy.