Aptima, Inc.

Wright State University

Georgiy Levchuk

Mitch Zakin

Nathan Schurr

Darby Hering

E Webb Stacy

Jared Freeman

Wayne Shebilske

Charlotte Shabarekh

Methods to infer user behavior are disclosed comprising a process of predefining one or more activities for a user application, providing a processor based device and user interface configured to operate with the device to support the user with tasks using the user application, the user application communicating an intent message to a transformative power management (TPM) application and the TPM configured to define and output an instruction for the application given the intention and the predefined activities. In some embodiments, the methods are implemented on a processor based device. In some embodiments, the systems and methods apply pattern recognition algorithms and pattern learning algorithms to manage the power allocation to power consuming devices.

Systems and methods to infer user behavior

Example embodiments of systems and methods for network pattern matching provide the ability to match hidden networks from noisy data sources using probabilistic matching analysis. The algorithms may map roles and patterns to observed entities. The outcome is a set of plausible network models. The pattern-matching methodology of these systems and methods may enable the solution of three challenges associated with social network analysis, namely network size and complexity, uncertain and incomplete data, and dynamic network structure.

Systems and methods for network pattern matching

Embodiments of this invention comprise modeling a subject's state and the influence of training treatments, or actions, on that state to create a training policy. Both state and effects of actions are modeled as probabilistic using Partially Observable Markov Decision Process (POMDP) techniques. Utilizing this model and the resulting training policy with subjects creates an effective decision aid for instructors to improve learning relative to a traditional scenario selection strategy.

Probabilistic decision making system and methods of use

Methods for power management are disclosed comprising a process of predefining one or more power mode for a user application, providing a processor based device and user interface configured to operate with the device to support the user with tasks using the user application, the user application communicating an intent message to a transformative power management (TPM) application and the TPM configured to define and output a power mode instruction for the application given the intention and the predefined power modes. In some embodiments, the methods are implemented on a processor based device. In some embodiments, the systems and methods apply pattern recognition algorithms and pattern learning algorithms to manage the power allocation to power consuming devices.

Systems and methods of power management

A method for power management comprising inferring a user behavior from an action, inferring a mission state from the action and an event, forecasting a forecasted action from the user behavior and the mission state and outputting an instruction to modify a power resource allocation based on the forecasted action. A processor based assembly for power management of at least one device comprising a means to infer a user behavior from an action, a means to infer a mission state from the action and an event, a means to forecast and a means to plan power management from the inferred information. In some embodiments, the systems and methods apply pattern recognition algorithms and pattern learning algorithms to manage the power allocation to power consuming devices.

Systems and methods of power management based on user behavior

Example embodiments of systems and methods for network pattern matching provide the ability to match hidden networks from noisy data sources using probabilistic multi-attribute graph matching analysis. The algorithms may map roles and patterns to observed entities. The outcome is a set of plausible network models. The pattern-matching methodology of these systems and methods may enable the solution of three challenges associated with social network analysis, namely network size and complexity, uncertain and incomplete data, and dynamic network structure.

Embodiments of the disclosed systems and methods comprise systems and methods for recognizing actions of an object and matching those actions with expected patterns of actions. In some embodiments, the methods recognize actions using statistical classifiers and aggregate data about locomotions, actions, and interactions of the object to infer patterns of that object using a pattern recognition algorithm. In some embodiments, the systems and methods are further able to select responses to recognized patterns and learn patterns over time.

Systems and methods for recognizing and reacting to spatiotemporal patterns

Embodiments of this invention comprise modeling a subject's state and the influence of training scenarios, or actions, on that state to create a training policy. Both state and effects of actions are modeled as probabilistic using Partially Observable Markov Decision Process (POMDP) techniques. The POMDP is well suited to decision-theoretic planning under uncertainty. Utilizing this model and the resulting training policy with real world subjects creates a surprisingly effective decision aid for instructors to improve learning relative to a traditional scenario selection strategy. POMDP provides a more valid representation of trainee state and training effects, thus it is capable of producing more valid recommendations concerning how to structure training to subjects.

Growing community of inventors

South Grafton, MA, United States of America

Georgiy Levchuk