Identifying and strengthening physiological/neurophysiological states predictive of superior performance

Inventors

Bach, David • Chelian, Suhas • DEGUZMAN, PAUL • Dmochowski, Jacek • Kruse, Amy • MCBURNETT, WILL • Miller, Steven L. • NUGENT, III, THOMAS F. • Sajda, Paul

Assignees

Optios Inc

Abstract

To identify physiological states that are predictive of a person's performance, a system provides physiological and behavioral interfaces and a data processing pipeline. Physiological sensors generate physiological data about the person while performing a task. The behavioral interface generates performance data about the person while performing the task. The pipeline collects the physiological and performance data along with reference data from a population of people performing the same or similar tasks. In various implementations, the physiological states are brain states. In one implementation, the pipeline computes bandpower ratios. In another implementation, the pipeline decomposes the physiological data into frequency-banded components, identifies brain states derived from the decomposed data—for example, clusters of correlations of decomposed data envelopes—grades the performance data, compares the graded performance data to the brain states, and identifies statistical relationships between the brain states and levels of performance.

Core Innovation

The disclosure describes predicting whether a person is in a physiological state conducive to making or performing high-quality or highly accurate decisions and/or actions. Physiological sensors are equipped to the person and sensor data are generated in time windows preceding and including a first set of decisions and/or actions. The sensor data are decomposed and bandpassed into components that extend across frequency bands, and correlations between characteristics of the decomposed and bandpassed data are identified to identify physiological states.

Performance is measured and quantified with respect to the first set of decisions and/or actions, and correlations between the physiological states and performance are identified. A second set of correlations between the sensor data or derivatives of the sensor data and performance is also identified. New sensor data are collected in time windows preceding a second set of decisions and/or actions, decomposed and bandpassed, and a current physiological state is identified from the new set of sensor data.

The current physiological state is compared with the physiological states identified earlier, and based on that comparison an expected value of the person's performance on the second set of decisions and/or actions is generated before the person makes or performs the second set. The described embodiments also include a system architecture with a physiological interface and a data processing pipeline configured to perform the decomposition, bandpassing, correlation identification, performance measurement, state identification, comparison, and expected-value generation.

Claims Coverage

Two independent claims are identified. Across these claims, the core inventive framework covers time-windowed physiological sensor data, decomposition and bandpassing across frequency bands, correlation-based identification of physiological states tied to quantified performance, and comparison of a current physiological state to prior states to generate an expected performance value before a later set of decisions/actions.

The independent claims center on a physiology-to-performance prediction framework using time-windowed sensor data, frequency-band decomposition with bandpassing, correlation-based identification of physiological states, and comparison to generate an expected performance value prior to later decisions/actions.

Stated Advantages

Documented Applications