Abstract: A reinforcement learning-based sensor data management system includes a processor configured to: manage virtualized objects that correspond to sensors included in a sensor network to update data received from each sensor and queries representing a data quality requested by an application; calculate an abstracted action that abstracts a size of an action space of the sensor network based on present state information of the virtualized objects and the queries; calculate scores for virtualized objects based on position relationships between the calculated abstracted action the virtualized objects; and assign priorities to the virtualized objects based on the calculated scores to update data received from the sensors to the virtualized objects according to the priorities.

Abstract: A reinforcement learning model is provided. The reinforcement learning model may include a skill regularized task decomposition model configured to perform a skill regularized task decomposition based on a determined data quality and a data augmentation model configured to perform data augmentation by generating an imaginary demo. The skill regularized task decomposition model may perform a skill embedding operation by implementing 2n-step state-action pairs, perform a skill regularization operation by implementing n-step transitions including states, actions, rewards, and next states, and perform an operation of decomposing a task in units of episodes into subtasks in units of n-steps.

Abstract: According to an exemplary embodiment of the present invention, a reinforcement learning method using a task decomposition inference model in a time-variant environment includes selecting a plurality of paired transitions having a time-invariant common characteristic and a time-variant different environmental characteristic from a dataset including a plurality of transition data, based on a cycle generative adversarial network (GAN), training an auto encoder to embed each of the time-variant part and the time-invariant part with respect to the plurality of paired transitions into a latent space, and performing reinforcement learning on a transition corresponding to data collected in the time-variant environment, using the trained auto encoder.

Abstract: A reinforcement learning-based sensor data management system includes a processor configured to: manage virtualized objects that correspond to sensors included in a sensor network to update data received from each sensor and queries representing a data quality requested by an application; calculate an abstracted action that abstracts a size of an action space of the sensor network based on present state information of the virtualized objects and the queries; calculate scores for virtualized objects based on position relationships between the calculated abstracted action the virtualized objects; and assign priorities to the virtualized objects based on the calculated scores to update data received from the sensors to the virtualized objects according to the priorities.

Abstract: A reference voltage generating circuit includes a reference voltage generating unit generating a uniform reference voltage in response to a bias voltage, a bias voltage generating unit generating the bias voltage, and a start-up circuit, after activating the bias voltage generating unit by receiving a first supply voltage, canceling a change of the first supply voltage to maintain a separation from the bias voltage generating unit. The circuit adopts a start-up circuit having a voltage distributing unit, thereby preventing a quiescent point of a bias voltage generating unit from entering a zero state and prevents a reference voltage from rising in a power-up state that an analog supply voltage rises according to a change of an external design environment such as a power, a temperature, a process parameter and the like, thereby generating a reference voltage more stably. As a result, current consumption and power consumption are minimized.

Abstract: A reference voltage generating circuit includes a reference voltage generating unit generating a uniform reference voltage in response to a bias voltage, a bias voltage generating unit generating the bias voltage, and a start-up circuit, after activating the bias voltage generating unit by receiving a first supply voltage, canceling a change of the first supply voltage to maintain a separation from the bias voltage generating unit. The circuit adopts a start-up circuit having a voltage distributing unit, thereby preventing a quiescent point of a bias voltage generating unit from entering a zero state and prevents a reference voltage from rising in a power-up state that an analog supply voltage rises according to a change of an external design environment such as a power, a temperature, a process parameter and the like, thereby generating a reference voltage more stably. As a result, current consumption and power consumption are minimized.

Abstract: Disclosed is a frequency synthesizer. The frequency synthesizer includes a phase frequency detector for generating an up signal and a down signal by detecting frequency and phase differences between a reference signal and a comparison signal, a charge pump for outputting a control signal according to the up signal and the down signal, a voltage controlled oscillator for outputting an oscillation output signal according to the control signal, a duty cycle correction circuit connected with the voltage controlled oscillator to compensate for a duty cycle of the oscillation output signal, and a feedback divider for providing the comparison signal to the phase frequency detector by dividing a frequency of the oscillation output signal.