Abstract: Disclosed is a machine learning-based air handler and a control method thereof, the control method including collecting first data on an air quality of air flowing into the air handler, controlling a purification part based on the first data, collecting second data on an air quality of air passing through the purification part, and controlling the purification part according to a machine-learning model generated based on a setting value related to a control of the purification part, the first data, and the second data.

Abstract: A deep learning-based blood pressure estimation system using a photoplethysmography (PPG) signal detection ring is provided. The system may include a server, and the server may include a signal feature extraction component configured to extract PPG features from a PPG signal by using a first deep learning model, a user feature extraction component configured to extract user features, by using a second deep learning model, from a first test PPG signal measured using the PPG signal detection ring, systolic and diastolic test blood pressures measured using a conventional blood pressure monitor simultaneously with the first test PPG signal, and user information, and a blood pressure estimation component configured to estimate systolic and diastolic blood pressures from the PPG features and the user features by using a third deep learning model, wherein the PPG signal is measured using the PPG signal detection ring, and the server receives the PPG signal from the PPG signal detection ring through a terminal.

Abstract: A semiconductor device includes a command decoder configured to generate a block command, based on a command address, and a clock division circuit configured to divide an internal clock and an inverted internal clock to generate division clocks. In the present disclosure, the clock division circuit is configured to stop generating the division clocks for a block section when the block command is generated.

Abstract: A processing-in-memory (PIM)-based accelerating device includes a plurality of PIM devices, a PIM network system configured to control traffic of signals and data for the plurality of PIM devices, and a first interface configured to perform interfacing with a host device. The PIM network system controls the traffic so that the plurality of PIM devices perform different operations, the plurality of PIM devices perform different operations in groups, or the plurality of PIM devices perform the same operation in parallel.

Abstract: A deep-learning-based atrial fibrillation determination system using a photoplethysmography (PPG) signal detection ring is provided.

Abstract: Provided is a system for estimating oxygen saturation by using a photoplethysmography (PPG) signal sensing ring.

Abstract: This application relates to a modular electrostatic precipitator. In one aspect, the modular electrostatic precipitator includes a housing providing a flow path through which air is moved and a charging module configured to emit electromagnetic waves to the air. The precipitator may also include a first attaching/detaching unit configured to attach and detach the charging module to and from the housing and a particle collecting module configured to collect particles in the air by applying an electrostatic force to the air. The precipitator may further include a second attaching and detaching unit configured to attach and detach the particle collecting module to and from the housing.

Abstract: A wireless power transmitting device according to an embodiment may include a power transmission circuit and a processor. The processor may be configured to control the power transmission circuit to wirelessly transmit power to a first area around the wireless power transmitting device, perform a predetermined first operation when an obstacle is detected in a second area around the first area, and perform a predetermined second operation when it is detected that the obstacle has entered the first area.

Abstract: The present invention relates to a cycloidal speed reducer and a manufacturing method thereof, and more particularly, to a thin cycloidal speed reducer and a manufacturing method thereof that are capable of achieving a thin structure through an input member with a hollow portion.

Abstract: A Processing-in-Memory (PIM) computing system and a memory controller provide improved memory traffic efficiency and improved PIM operation efficiency by increasing a burst length of a PIM operation relative to a general memory request. In embodiments, the increased burst length allows the PIM operation to be performed in units of pages, wherein a page is management unit of a memory used in the PIM operation.

Abstract: Provided is an electronic apparatus and a method thereof. The method includes identifying pickup item information, identifying at least one storage place corresponding to the pickup item information among a plurality of storage places in the item storage center based on information on or regarding an item group located at each of the plurality of storage places, and providing information on the identified storage place and the pickup item information to a manager terminal, wherein the item group comprises at least one same item corresponding to an item group, and at least a portion of a plurality of item groups comprising a same item are stored in different storage places in the item storage center.

Abstract: A semiconductor device may include: a first receiver configured to receive a chip select signal from a receiving node to which a termination resistor is coupled and configured to generate a first internal chip select signal; a command pulse generation circuit configured to generate a command pulse for entering into a self-refresh operation based on an internal command address and the first internal chip select signal; and an operation control circuit configured to, when the semiconductor device enters the self-refresh operation based on the command pulse, generate a resistor value change signal that adjusts the value of the termination resistor.

Abstract: A Processing-in-Memory (PIM) computing system and a memory controller provide improved memory traffic efficiency and improved PIM operation efficiency by increasing a burst length of a PIM operation relative to a general memory request. In embodiments, the increased burst length allows the PIM operation to be performed in units of pages, wherein a page is management unit of a memory used in the PIM operation.

Abstract: A Processing-In-Memory (PIM) computing system and a PIM computation offloading method thereof perform PIM computation offloading using a DMA engine. The DMA engine is configured to process a transaction by respectively performing descriptor requests and PIM requests for one or more descriptors stored in a memory, in response to a memory request of a CPU. The memory includes a PIM unit and a memory array, which memory array may be a DRAM. In response to the PIM requests, the PIM unit performs PIM operations using information included in data provided to the DMA engine in response to the descriptor requests.

Abstract: The present invention relates to a device for analyzing a bio-signal, and a method therefor, and the method for analyzing a bio-signal comprises the steps of: removing bio-signal noise generated by a sensor; estimating the signal quality of the bio-signal for a preset unit time; classifying the bio-signal for the preset unit time into an abnormal signal or a normal signal; and determining whether an abnormal state episode occurs and a duration time thereof on the basis of the signal quality of the bio-signal for a plurality of unit times and the result of the classification.

Abstract: The present invention relates to a device and a method for analyzing an abnormal physiological signal, and the method for analyzing an abnormal physiological signal comprises the steps of: removing bio-signal noise generated by a sensor; estimating the signal quality of the bio-signal for a preset unit time; performing classification of an atrial fibrillation (AF), which is an abnormal signal, on the bio-signal for the unit time to classify same into an AF, which is an abnormal signal, and a normal sinus rhythm (NSR), which is a normal signal; determining whether an AF episode, which is an abnormal state episode, occurs and a duration time thereof, on the basis of the signal quality of preset number of consecutive unit times and the result of the classification of the AF, which is an abnormal signal; and calculating the load of the AF, which is an abnormal signal, on the basis of whether an AF episode, which is an abnormal state episode, occurs and the duration time thereof.

Abstract: The method for estimating mental health and providing solution for mental health by learning psychological data and biological data based on machine learning includes: (a) acquiring, by mental health estimating device, psychological data for testing and biological data for testing of test subject from terminal of the test subject in state in which first estimated model is learned by referring to estimated mental health data for learning output from the first estimated model and ground truth mental health data corresponding to the estimated mental health data after psychological data for learning and biological data for learning of learning subjects are input to the first estimated model; and (b) inputting, by the mental health estimating device, the psychological data for testing and the biological data for testing to the first estimated model to allow the first estimated model to output estimated mental health data for testing.

Abstract: A method of manufacturing a flip chip package includes forming a plurality of semiconductor chips and bonding the semiconductor chips to a package substrate. The method further includes electrically testing the plurality of semiconductor chips on the package substrate, molding the tested semiconductor chips, and singulating the molded chips. Electrically testing the semiconductor chips includes covering the semiconductor chips with a protection member.

Abstract: The method for estimating mental health and providing solution for mental health by learning psychological data and biological data based on machine learning includes: (a) acquiring, by mental health estimating device, psychological data for testing and biological data for testing of test subject from terminal of the test subject in state in which first estimated model is learned by referring to estimated mental health data for learning output from the first estimated model and ground truth mental health data corresponding to the estimated mental health data after psychological data for learning and biological data for learning of learning subjects are input to the first estimated model; and (b) inputting, by the mental health estimating device, the psychological data for testing and the biological data for testing to the first estimated model to allow the first estimated model to output estimated mental health data for testing.

Abstract: A memory system includes: a first memory module including first volatile memories; a second memory module including second volatile memories, non-volatile memories and a module controller; a memory controller controlling the first and second memory modules through second and third control buses, respectively; and a switch array electrically coupling the second and third control buses, wherein the module controller controls the switch array to electrically couple the second and third control buses in a backup operation for backing up data of the first volatile memories to the non-volatile memories, wherein the first and second memory modules include one or more first memory stacks and one or more second memory stacks, respectively, wherein the first volatile memories are stacked in the first memory stacks, and wherein the second volatile memories, the non-volatile memories and the module controller are stacked in the second memory stacks.