Abstract: The present disclosure comprises: a solid-state circuit breaker, which is arranged between a battery system and a line and includes a semiconductor switch for providing an electrical connection or insulation between the battery system and the line according to the voltage applied to a gate terminal; an interrupter switch for providing a physical connection or separation between the solid-state circuit breaker and the line; and a rack battery management system which controls a gate driver applying the gate voltage, so as to provide insulation between the battery system and the line according to the result of sensing a current flowing between the battery system and the line, and which controls the interrupter switch to physically separate the solid-state circuit breaker from the line.

Abstract: The present disclosure relates to a power device protection apparatus. A power device protection apparatus according to an embodiment of the present invention comprises: a comparator which is connected to a power device, and determines whether an overcurrent of the power device occurs; and a control unit which controls the comparator so as to change, by software, a overcurrent reference value for determining whether the overcurrent occurs, wherein the control unit receives temperature information of the power device, changes the overcurrent reference value on the basis of the temperature information, and performs the overcurrent reference value change according to the temperature information, on the basis of the characteristics of the power device.

Abstract: A method and an apparatus for learning an artificial neural network for data prediction. The method includes: obtaining first output data through a first artificial neural network for future data prediction based on an input time series data set; obtaining second output data through a second artificial neural network for past data reconstruction using the first output data of the first artificial neural network; calculating a cost function using the first output data of the first artificial neural network and the second output data of the second artificial neural network; and learning the first artificial neural network using the cost function.

Abstract: Provided is a mobile terminal including a display unit to which multiple images are output; a sensing unit that detects a touch gesture as being applied to a first image among the multiple images; and a controller that changes an output state of the first image based on the touch gesture. In a state where the output state of the first image is output, when at least one image is selected from among the multiple images, the controller performs control in such a way that at least one selected image overlaps the first image serving as a reference image, and sets the first image and at least one image that overlaps the first image serving as the reference image so that the first image and at least one image belong to a first group. Accordingly, the stored multiple images are quickly categorized on one screen without being moved to a different screen.