Abstract: Disclosed are a device and a method for anomaly detection of a gas sensor. The device includes a measuring unit that extracts a characteristic of a gas supplied from the outside, generates data based on the extracted characteristic, and outputs the data, and a data processing unit that receives the data, determines whether an error occurs in the data, and outputs an anomaly detection result based on a result of determining whether the error occurs in the data. The measuring unit performs a calibration operation or an environment adjusting operation before extracting the characteristic, and the data processing unit determines whether the error occurs in the data, based on machine learning.

Abstract: Disclosed is a time-series data processing device that includes a preprocessor, a learner, and a predictor. The preprocessor generates time-series interval data based on a time interval of time-series data, generates feature interval data based on a time interval of each of features of the time-series data, and preprocesses the time-series data. The learner generates a weight group of a prediction model for generating a prediction result based on the time-series interval data, the feature interval data, and the preprocessed time-series data. The predictor generates a time-series weight, which depends on a feature weight of each of the features and a time flow of the time-series data, based on the time-series interval data, the feature interval data, and the preprocessed time-series data and generates a prediction result based on the feature weight and the time-series weight.

Abstract: An electronic device for reinforcement learning related to medical data and a method of operating the same are provided. The method includes obtaining an actual event related to medical data of a patient and a virtual event generated based on the actual event, determining a probability of the virtual event occurring, based on the medical data, and based on the actual event, the virtual event, and the probability of the virtual event, training a model to determine a state value for a reward of an action that is performed in a current state of the patient.

Abstract: The present disclosure relates to a method and apparatus for performing sensor drift compensation based on double cycling measurement. A method for performing drift correction according to gas sensor measurement according to an embodiment of the present disclosure may comprise: obtaining first measurement data for a reference gas for each sensor using one or more sensors in a first cycle; obtaining second measurement data for a target gas for each sensor using the one or more sensors in a second cycle; and generating a drift-corrected feature for each sensor based on a ratio calculated by dividing the second measurement data by the first measurement data.

Abstract: A metal detecting system using search-coil type sensor includes sensor modules that detect respective objects which move around the corresponding sensor modules, each sensor module having one or more sensors that include respective housings having respective inner spaces, respective cores formed to be inserted into the inner spaces of the housings, and respective coils which are each wound around a portion of an outer circumferential surface of each of the housings, the portion corresponding to a position of each of the cores; imaging units that image the respective objects that move around the corresponding sensor modules and image respective persons possessing the respective objects; impedance matching units that are connected to a plurality of the sensor modules, respectively, and perform impedance matching; and amplifiers that are connected to the impedance matching units, respectively, and amplify a fine current and voltage generated during approach of the objects to the sensor modules.

Abstract: Disclosed are a three-dimensional (3D) simulation method and a 3D simulation apparatus. The 3D simulation method disclosed herein includes a step (S20) of separating point cloud data including a road, an obstacle, and a cargo transportation route into road data and obstacle data, a step (S40) of converting the road data into road mesh data, and converting the obstacle data into obstacle mesh data, a step (S60) of constructing a virtual environment by merging the road mesh data with the obstacle mesh data, a step (S80) of loading a specific cargo transportation route to the virtual environment, a step (S100) of loading a 3D transport truck and a 3D cargo to a predetermined point of the cargo transportation route, and a step (S120) of performing a route survey simulation while virtually driving the 3D transport truck and the 3D cargo along the cargo transportation route.

Abstract: Disclosed is a device which includes a data manager, a learner, and a predictor. The data manager generates output data based on time-series data, receives device prediction results corresponding to the output data from the prediction devices, and calculates device errors based on the difference between device prediction results and time-series data. The learner may adjust a parameter group of a prediction model for generating device weights, based on device prediction results and device errors. The predictor generates the ensemble result of first and second device prediction results based on device weights.

Abstract: A multi-measurement apparatus using a search-coil type sensor includes: sensor modules, each of which has one or more sensors including respective housings having respective inner spaces, respective cores formed to be inserted into the inner spaces of the housings, and respective coils which are each wound around a portion of an outer circumferential surface of each of the housings, the portion corresponding to a position of each of the cores; impedance matching units that are connected to a plurality of the sensors, respectively, and perform impedance matching; and amplifiers that are connected to the impedance matching units, respectively, and amplify a fine current and voltage generated during approach of objects to the sensors.

Abstract: An apparatus for correcting non-polarity and measuring displacement of an object using a search-coil type sensor includes a plurality of sensors that include respective housings having respective inner spaces, respective cores formed to be inserted into the inner spaces of the housings, and respective coils which are each wound around a portion of an outer circumferential surface of each of the housings, the portion corresponding to a position of each of the cores. The plurality of sensors are arranged in parallel with each other. A position of a core and a coil with respect to one housing differs from a position of a core and a coil with respect to another housing. An induced magnetic field is formed due to a distance change with respect to the object containing iron (Fe).

Abstract: Provided is a multi-port gas flow rate control apparatus. The multi-port gas flow rate control apparatus includes a gas supply chamber configured to supply a measurement gas input through one gas inflow channel while allowing the measurement gas to diverge into a plurality of flows, a plurality of gas divergence flow channels each having one side connected to the gas supply chamber and configured to transfer the measurement gas flowing through the gas supply chamber to a plurality of gas sensors, respectively, and a gas measurement chamber configured to accommodate the plurality of gas sensors, including the plurality of gas divergence flow channels configured to connect to the gas supply chamber to the plurality of gas sensors to transfer a gas outflow diverging through the gas supply chamber to the plurality of accommodated gas sensors, and configured to discharge the gas outflow sensed by the plurality of gas sensors.

Abstract: Disclosed is an apparatus for exploring an optimized treatment pathway of a target patient, which includes an episode sampling module that receives a virtual electronic medical record (EMR) episode, calculates a similarity between a first current state of the target patient, which corresponds to the received virtual EMR episode, and a second current state of a patient, which corresponds to each of a plurality of EMR episodes, extracts an EMR episode, and outputs a pair of the virtual EMR episode and the extracted EMR episode, a state value evaluation module that predicts an expected value of a reward, a treatment method learning module that predicts an optimized treatment method and optimized timing of treatment and provides an external prediction model with the current state of the target patient and the treatment method, and a virtual episode generation module that generates a new virtual EMR episode.

Abstract: Disclosed is an artificial intelligence apparatus for detecting a target gas, which includes a mixed gas measurement unit that measures a mixed gas collected in a plurality of domains through a sensor array to generate sensing data including heterogeneous domain measurement data measured from the mixed gas collected in a domain different from the target gas and target domain measurement data measured from the mixed gas collected from the same domain as the target gas, a heterogeneous intelligence model deep learning unit that receives the heterogeneous domain measurement data to train a heterogeneous intelligence model, a target intelligence model deep learning unit that receives the heterogeneous intelligence model and the target domain measurement data to train a target intelligence model, and a target gas detection unit that determines whether an environmental gas includes the target gas using the target intelligence model.

Abstract: Disclosed is an apparatus, which includes a preprocessor that generates raw data, generates preprocessed time series data, and generates preprocessed learning data, and a learner that receives the preprocessed learning data as input data and trains a prediction model such that the similarity between a first future state predicted using the input data and a second future state predicted using data included in the same cluster as the input data increases and such that the similarity between the first future state and a third future state predicted using data included in a different cluster from the input data decreases, and the prediction model is a machine learning model for predicting a future state of the time series data at an arbitrary time point.

Abstract: Provided is a device for ensembling data received from prediction devices and a method of operating the same. The device includes a data manager, a learner, and a predictor. The data manager receives first and second device prediction results from first and second prediction devices, respectively. The learner may adjust a weight group of a prediction model for generating first and second item weights, first and second device weights, based on the first and second device prediction results. The first and second item weights depend on first and second item values, respectively, of the first and second device prediction results. The first device weight corresponds to the first prediction device, and the second device weight corresponds to the second prediction device. The predictor generates an ensemble result of the first and second device prediction results, based on the first and second item weights and the first and second device weights.

Abstract: Provided are a QT heat treated high carbon hot rolled steel sheet, a high carbon cold rolled steel sheet, a QT heat treated high carbon cold rolled steel sheet, and manufacturing methods thereof, wherein the QT heat treated high carbon hot rolled steel sheet comprises, in weight %, C: 1.0-1.4%, Si: 0.1-0.4%, Mn: 0.1-0.8%, Cr: 0.3-11%, W: 0.05-2.5%, P: 0.03% or less, S: 0.03% or less, Al: 0.02% or less, and the balance being Fe and other inevitable impurities, the average size of carbides being 0.1-20 ?m.

Abstract: An NFC device that receive a data frame with a start pattern including first and second pattern signals, and a data pattern corresponding to the start pattern. The NFC device comprising an analog-to-digital converter which generates first and second input signals based on the first and second pattern signals, respectively, a modem that includes a first sub-matched filter which multiplies a first match signal by the first and second input signals to respectively calculate first and second result values of the first match signal and multiplies a second match signal by the first and second input signals to respectively calculate first and second result values of the second match signal. The first sub-matched filter determines reception of the start pattern when the first and second result values of the first match signal or the first and second result values of the second match signal exceed a predetermined start pattern threshold.

Abstract: Disclosed herein a method and apparatus for learning a multi-label ensemble based on multi-center prediction accuracy. According to an embodiment of the present disclosure, there is provided a multi-label ensemble learning method comprising: collecting a prediction value for learning data for each of a plurality of prediction models; calculating a prediction error of each of the prediction models using the prediction value of each of the prediction models and a correct answer prediction value; generating a weight label for each of the prediction models based on the prediction error; and learning an ensemble weight prediction model for predicting a weight of each of the prediction models using the weight label.

Abstract: Disclosed are a method and apparatus for selective ensemble prediction based on dynamic model combination. The method of ensemble prediction according to an embodiment of the present disclosure includes: collecting prediction values for input data of each of the prediction models; calculating a model weight of each of the prediction models using a pre-trained ensemble model that uses the prediction value as an input; selecting at least some model weights from the model weights using a predetermined optimal model combination parameter; and calculating an ensemble prediction value for the input data based on the selected model weight and a prediction value of a prediction model corresponding to the selected model weight.

Abstract: Disclosed are a gas detection intelligence training system and an operating method thereof. The gas detection intelligence training system includes a mixing gas measuring device that collects an environmental gas from a surrounding environment, generates a mixing gas based on the collected environmental gas and a target gas, senses the mixing gas by using a first sensor array and a second sensor array under a first sensing condition and a second sensing condition, respectively, and generates measurement data based on the sensed results of the first sensor array and the second sensor array, and a detection intelligence training device including a processor that generates an ensemble prediction model based on the measurement data.

Abstract: Disclosed herein is a method and apparatus for predicting a future state and reliability based on time series data. In the method and the apparatus, a future state is predicted by preprocessing past state data and executing an algorithm based on the preprocessed past state data to generate a trained model, followed by preprocessing current state data and executing an algorithm based on the created trained model, the preprocessed current state data, and the preprocessed past state data.