Abstract: A universal deep probabilistic decision-making framework for dynamic process modeling and control, referred to as Deep Probabilistic Decision Machines (DPDM), is presented. A predictive model enables the generative simulations of likely future observation sequences for future or counterfactual conditions and action sequences given the process state. Then, the action policy controller, also referred to as decision-making controller, is optimized based on predictive simulations. The optimal action policy controller is designed to maximize the relevant key performance indicators (KPIs) relying on the predicted experiences of sensor and target observations for different actions over the near future.

Abstract: A method for providing a location tracking service on the basis of context-aware information of a location tracker, according to the present invention, transmits a signal while changing a communication method by classify a situation as an emergency situation and a normal state which is a non-emergency situation according to the context-aware information of the location tracker, such that it is possible to use power consumption reduced by a low-power communication method in the normal state, and in case of the emergency situation, to safely handle the emergency situation through a sufficient power communication method.

Abstract: A universal deep probabilistic decision-making framework for dynamic process modeling and control, referred to as Deep Probabilistic Decision Machines (DPDM), is presented. A predictive model enables the generative simulations of likely future observation sequences for future or counterfactual conditions and action sequences given the process state. Then, the action policy controller, also referred to as decision-making controller, is optimized based on predictive simulations. The optimal action policy controller is designed to maximize the relevant key performance indicators (KPIs) relying on the predicted experiences of sensor and target observations for different actions over the near future.

Abstract: Repeated random-outcome trials together with affective, cognitive, and behavioral measures of liking and wanting may be used to assess consumer preferences. In an exemplary implementation of this invention, in each trial, a participant selects one of two sources (e.g., one of two beverage dispensers) of a product (e.g., a beverage). Each source dispenses the product randomly, with a probability initially unknown to the participant, but which he or she may guess while trying to select the most desired product. Affective measures of a participant's facial valence and sympathetic nervous system activation are taken while deciding on, anticipating the arrival of, receiving, using, evaluating, and reflecting on the product. The affective measures are combined with cognitive self-report questionnaire items and with behavioral measures to infer wanting and liking of a product.

Abstract: A physically animated visual display is a robotic device, capable of multiple degree-of-freedom motion, that is adapted to improve a user's emotional state, cognitive performance, and comfort level through reactive and goal-directed manipulation of the position of the display. The affective-cognitive system comprises a feature extraction subsystem for deriving physical information about a user from data obtained from sensors, a perception subsystem for processing the data in order to determine the user's current emotional state, affective-cognitive state, or posture, an action selection subsystem for determining an action to be taken in response, and a motor system for physically animating the robotic device in accordance with the determined action. The system may include feedback modeling based on a reaction of the user to the movement of the apparatus increasing or decreasing the probability of choosing the current behavior based on the user's reaction.