Abstract: Disclosed are methods of training a deep learning model and predicting a class and an electronic device for performing the methods. A method of training a deep learning model may include identifying training data labeled for each class, determining whether to augment the training data based on overall recognition performance indicating prediction accuracy of the deep learning model calculated in a previous epoch, augmenting the training data based on class-specific recognition performance indicating class-specific prediction accuracy of the deep learning model calculated in the previous epoch, predicting a class by inputting the training data or the training data that is augmented to the deep learning model according to a determination of whether to augment the training data, and training the deep learning model based on a labeled class and the predicted class.

Abstract: An apparatus and a method for performing liquid treatment for a substrate are provided. The apparatus for treating the substrate includes a treating container having a treatment space inside the treating container, a substrate support unit to support a substrate in the treatment space, and a liquid supply unit to supply treatment liquid to the substrate supported by the substrate support unit. The liquid supply unit includes a nozzle, a supply line to supply the treatment liquid to the nozzle and having a first valve mounted in the supply line, and a discharge line branching from a branch point which is a point downstream of the first valve in the supply line to discharge the treatment liquid from the supply line, and having a second valve mounted in the discharge line. A valve is absent in an area between the branch point and the nozzle, in the supply line.

Abstract: Disclosed is an apparatus and method for augmenting training data using a notch filter. The method may include obtaining original data, and obtaining training data having a modified frequency component from the original data by filtering the original data using a filter configured to remove a component of a predetermined frequency band.

Abstract: Disclosed are methods of training an acoustic scene classification model and classifying an acoustic scene and an electronic device for performing the methods. The training method of an acoustic scene classification model includes inputting training data labeled as an acoustic scene to the acoustic scene classification model that is repeatedly trained by using the training data and outputting a first result predicting the acoustic scene, updating the weight of the auxiliary model configured to induce training of the acoustic scene classification model, based on a weight of the acoustic scene classification model and a weight of an auxiliary model in a previous epoch, inputting the training data to the auxiliary model and outputting a second result, calculating a cost function, based on the first result, the second result, and labeling of acoustic data, and updating the weight of the acoustic scene classification model, based on the cost function.

Abstract: The present invention relates to a polymer, an organic solar cell comprising the polymer, and a perovskite solar cell comprising the polymer. The polymer according to the present invention has excellent absorption ability for visible light and an energy level suitable for the use as an electron donor compound in a photo-active layer of the organic solar cell, thereby increasing the light conversion efficiency of the organic solar cell. In addition, the polymer according to the present invention has high hole mobility, and is used as a compound for a hole transport layer, and thus can improve efficiency and service life of the perovskite solar cell without an additive.

Abstract: A substrate treating method includes moving a first component of a substrate treatment device to a preset position in response to a treating process of the substrate treatment device, detecting, by a plurality of position detection sensors, a position of the first component, vision-testing, by a vision sensor, a positional state of the first component, and determining an operational state of an error in the detection of the plurality of position detection sensors or a malfunction of the substrate treatment device based on a detection result obtained by the plurality of position detection sensor and a test result obtained by the vision sensor.

Abstract: Disclosed is a method and apparatus for label encoding in a multi-sound event interval. The method includes identifying an event interval in which a plurality of sound events occurs in a sound signal, separating a sound source into sound event signals corresponding to each sound event by performing sound source separation on the event interval, determining energy information for each of the sound event signals, and performing label encoding based on the energy information.

Abstract: A vehicle inner communication system according to one embodiment can comprise: a plurality of electronic device groups provided in a vehicle; and a control unit, which uses bus communication individually connected to the electronic devices within the electronic device group and series communication by which the electronic devices inside the electronic device group are connected, so as to sense electronic devices within the electronic device group and control operations.

Abstract: The present invention relates to a polymer, an organic solar cell comprising the polymer, and a perovskite solar cell comprising the polymer. The polymer according to the present invention has excellent absorption ability for visible light and an energy level suitable for the use as an electron donor compound in a photo-active layer of the organic solar cell, thereby increasing the light conversion efficiency of the organic solar cell. In addition, the polymer according to the present invention has high hole mobility, and is used as a compound for a hole transport layer, and thus can improve efficiency and service life of the perovskite solar cell without an additive.

Abstract: A substrate treating apparatus includes a plurality of load ports on which carriers having substrates received therein are placed, a plurality of process chambers that perform processes on the substrates, and a transfer robot that transfers the substrates between the load ports and the process chambers. The transfer robot is movable along a transfer passage having a lengthwise direction formed along a first direction, the load ports and the process chambers are arranged along the first direction on one side and an opposite side of the transfer passage, and the transfer robot transfers the substrates between the carriers placed on the load ports and the process chambers.

Abstract: Disclosed are a training method for a learning model for recognizing an acoustic signal, a method of recognizing an acoustic signal using the learning model, and devices for performing the methods. The method of recognizing an acoustic signal using a learning model includes identifying an acoustic signal including an acoustic event or acoustic scene, determining an acoustic feature of the acoustic signal, dividing the determined acoustic feature for each of a plurality of frequency band intervals, and determining the acoustic event or acoustic scene included in the acoustic signal by inputting the divided acoustic features to a trained learning model.

Abstract: Disclosed are a film and a photoelectric device including the compound of Chemical Formula 1 and configured to selectively absorb light in a blue wavelength region, and an image sensor and electronic device including the same: In Chemical Formula 1, each substituent is the same as defined in the detailed description.

Abstract: The present invention relates to: a phenazine-based compound having a particular substituent; an electrolytic liquid comprising same for a redox flow battery; and a redox flow battery. The phenazine-based compound is a multi-redox organic substance capable of inducing a two-stage reversible redox reaction and shows high solubility in a non-aqueous solvent. Thus, the employment of the phenazine-based compound can provide an electrolytic liquid for a redox flow battery, capable of expressing high energy density, and a redox flow battery.

Abstract: An exemplary catheter can be provided, which can include, for example a source fiber(s) configured to (i) receive a near infrared spectroscopic (NIRS) radiation, and (ii) provide the NIRS radiation to a portion(s) of a sample(s), a detection fiber(s) configured to receive a return radiation from the sample(s) that can be based on the NIRS radiation that was provided to the portion(s) of the sample(s), and an ablation electrode(s) configured to ablate the sample(s) based on the return radiation. The source fiber(s), the detection fiber(s), and the ablation electrode(s) can be integrated into the single sheath. The ablation electrode(s) can be a radiofrequency ablation electrode.

Abstract: The present invention relates to a method for preparing a solid-state photonic crystal IPN composite functionalized with an enzyme, a photonic crystal IPN composite prepared by the method, and a biosensor using the photonic crystal IPN composite. The method of the present invention includes (1) mixing a nonreactive chiral dopant with a reactive nematic mesogen, curing the mixture, and removing the chiral dopant while maintaining a helical structure, to form a solid-state helical photonic crystal structure, (2) infiltrating a PAA hydrogel into the internal space of the photonic crystal structure, followed by curing to form an IPN-structured composite, and (3) immobilizing an enzyme in the IPN-structured composite. The PAA hydrogel is infiltrated into the solid-state helical photonic crystal structure and the enzyme is immobilized such that a pH change caused by the enzymatic reaction induces shrinkage and expansion of the PAA hydrogel, leading to a color change.

Abstract: Disclosed are a substrate treating apparatus, an eccentricity inspection apparatus, an eccentricity inspection method, and a recording medium for measuring the amount of eccentricity of a spin chuck. The substrate treating apparatus includes a process chamber, a support unit that supports a substrate and rotates the substrate about a support shaft of a spin chuck, and an eccentricity inspection device that inspects eccentricity of the support shaft. The eccentricity inspection device includes an image acquisition unit that obtains an image of the substrate supported on the support unit and an eccentricity measurement unit that obtains edge data of the substrate from the image of the substrate and measures an amount of eccentricity of the support shaft, based on the edge data.

Abstract: Disclosed are an organic device including a first electrode and a second electrode facing each other and an active layer between the first electrode and the second electrode, wherein the active layer includes compound represented by Chemical Formula 1, and an image sensor including the same. In Chemical Formula 1, L1, L2, R1, R2, Ar1, Ar2, X1, X2, m1, m2, n1, and n2 are the same as described in the detailed description.

Abstract: The present invention relates to a polymer, an organic solar cell comprising the polymer, and a perovskite solar cell comprising the polymer. The polymer according to the present invention has excellent absorption ability for visible light and an energy level suitable for the use as an electron donor compound in a photo-active layer of the organic solar cell, thereby increasing the light conversion efficiency of the organic solar cell. In addition, the polymer according to the present invention has high hole mobility, and is used as a compound for a hole transport layer, and thus can improve efficiency and service life of the perovskite solar cell without an additive.

Abstract: The present invention relates to a phosphor monomolecular compound, an organic transistor using same, and a water splitting and hydrogen production photocatalytic system using same. More specifically, the present invention comprises a water-soluble monomolecular compound including 1,5-naphtyridine-2,6-dione structure as a phosphor monomolecular compound.

Abstract: Disclosed is an apparatus and method for augmenting training data using a notch filter. The method may include obtaining original data, and obtaining training data having a modified frequency component from the original data by filtering the original data using a filter configured to remove a component of a predetermined frequency band.