Abstract: Provided is an indoor unit for an air-conditioning apparatus capable of preventing crazing, which occurs in a fixing claw or a claw receiver due to intrusion of oil or solvent. The indoor unit for an air-conditioning apparatus includes a rear casing and a front casing. An upper wall is formed, and an overlap portion is formed. The fixing claw is provided, and the claw receiver is provided. The upper wall has a front portion on a front side with respect to the fixing claw, and the claw receiver protrudes rearward from the overlap portion. A recessed portion which is opened upward is formed on a front side of the claw receiver of the overlap portion.

Abstract: An object is to simplify a structure of a holding fixture which holds the shape of an aircraft panel, and to hold the aircraft panel in an appropriate shape. A holding fixture includes: a plurality of gripping units configured to grip edge portions on two opposite sides of a fuselage panel including a skin; and a support body configured to integrally support the plurality of gripping units, the support body being provided corresponding to the fuselage panel to be gripped by the plurality of gripping units, wherein the plurality of gripping units hold the fuselage panel such that the gripping units grip the edge portions of the fuselage panel, and the fuselage panel has a curved shape in cross section taken in a direction perpendicular to a one axis direction, and the holding fixture is configured to be conveyable in a state of holding the fuselage panel.

Abstract: To hold a long member in the original shape of the long member at a precise position, a long member assembling device has: a plurality of hand parts configured to grip a long member; arm parts and trunk parts configured to move the hand parts to adjust the positions of the plurality of hand parts gripping the long member; a storage unit in which the original shape of the long member is stored; and a control unit configured to, on the basis of the original shape of the long member stored in the storage unit, drive the arm parts and the trunk parts to adjust the positions of the plurality of hand parts gripping the long member such that the shape of the long member gripped by the plurality of hand parts matches the original shape of the long member stored in the storage unit.

Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.

Abstract: There is a desire to accurately learn a detection model. Provided is a computer-implemented method including acquiring an input image; acquiring an annotated image designating a region of interest in the input image; inputting the input image to a detection model that generates an output image showing a target region from the input image; calculating an error between the output image and the annotated image, using a loss function that weights an error inside the region of interest more heavily than an error outside the region of interest; and updating the detection model in a manner to reduce the error.

Abstract: An input device includes a pressure-sensitive sensor including a first sensing unit and a second sensing unit, and a pressing unit that is disposed on the pressure-sensitive sensor and undergoes buckling deformation. A bottom of the pressing unit is disposed on the first sensing unit, and a top of the pressing unit is disposed on the second sensing unit.

Abstract: A front panel for on-board liquid crystal displays has a high hardness resin composition (B) on at least one side of a layer containing a resin (A) having a polycarbonate resin (a1). The front panel satisfies the following conditions (i) to (iv): (i) the thickness of the layer containing a high hardness resin composition (B) is 10 to 250 ?m, and the total thickness of the layer containing a resin (A) comprising a polycarbonate resin (a1) and the layer containing a high hardness resin composition (B) is 100 to 3,000 ?m; (ii) the high hardness resin composition (B) consists of any one of specific resin compositions (B1) to (B3); (iii) the retardation of the front panel is 3,000 nm or more; and (iv) the standard deviation of the second derivative of the irregular shape of the hard coat layer having irregularities is 0.1 or more.

Abstract: An indoor unit of an air-conditioning apparatus includes: an air purifying filter including a filter body for air purification, a pair of bearing units, and a pair of protrusions that extend outward from the filter body; and an air filter for dust collection including a pair of shaft units coupled with the respective bearing units, and a pair of supports accommodating the respective protrusions. The protrusions are placed into the respective supports from the direction of the respective shaft units.

Abstract: To provide a robot control system and a robot control method capable of placing a component grasped by a robot hand at an accurate location on another member. A robot control system is provided with: a robot hand configured to grasp a clip; a camera configured to capture an image of the clip grasped by the robot hand, a calculation unit configured to calculate a position of the clip or an inclination of a component based on an imaging result of the clip captured by the camera, and a robot control unit configured to control the robot hand to adjust, based on the position of the clip or the inclination of the component calculated by the calculation unit, a position or an inclination of the robot hand and move the clip to a stringer.

Abstract: In order to hold a long member without using a fixing jig and without deforming the long member in holding the long member, a long member assembling device is provided with: multiple hand parts for gripping a long member; and arm parts and trunk parts for moving the hand parts to adjust the positions of the hand parts gripping the long member. The hand parts have a configuration such that, when the positions thereof are adjusted by the arm parts and the trunk parts, the hand parts are capable of moving in the longitudinal direction of the long member while gripping the long member.

Abstract: Provided is an indoor unit for an air-conditioning apparatus, which is capable of detecting a room temperature without impairing a design of the air-conditioning apparatus. The indoor unit for an air-conditioning apparatus according to the present invention includes: a housing having a rear surface mounted to a wall and having an air inlet and an air outlet formed therein; a heat exchanger and an air-sending device arranged on a main air passage extending from the air inlet to the air outlet; and a room temperature sensor configured to detect a temperature of an intake air. The housing has an air intake port from which air to be sent to the room temperature sensor is allowed to be taken, the air intake port being provided in a side surface adjacent to the rear surface. The room temperature sensor is arranged on an air passage connecting the air intake port and the main air passage. The air intake port is opened toward a rear surface side of the housing.

Abstract: A method, computer system, and computer program product for predicting an occurrence of a symptom in a patient are provided. The embodiment may include reading, into a memory, a plurality of time-series prediction models used for predicting the occurrence of the symptom, wherein the time-series prediction models were trained in advance using plural data sets of training data obtained from a plurality of patients, each training data comprising prodrome data and data associated with the occurrence of the symptom. The embodiment may also include selecting at least one time-series prediction model from the time-series prediction models using historical data sets of prodrome data obtained from a patient and data associated with the occurrence of the symptom. The embodiment may further include inputting, to the at least one selected time-series prediction model, current prodrome data obtained from the patient to output a result predicting the occurrence of the symptom.

Abstract: A method, computer system, and a computer program product for digital image recognition determination using a learned model is provided. The present invention may include acquiring a first determination result by making a determination concerning first data, using a first learned model. The present invention may include selecting a partial region of the first data. The present invention may then include generating second data obtained by applying a first alteration process to the partial region. The present invention may also include acquiring a second determination result by making a determination concerning the second data, using a second learned model. The present invention may lastly include obtaining a final determination result based on the first determination result and the second determination result.

Abstract: A production facility is provided with: an AGV for transporting a plurality of fuselage panels of multiple types having different shapes in a mixed state on a previously determined transport path; a plurality of A/Rs for riveting the fuselage panels; work areas set so as to correspond to the respective A/Rs in which the A/Rs move to rivet the fuselage panels; and a buffer area, set beforehand in the transport path adjacent to the work area, to which the A/R corresponding to the adjacent work area moves so as to rivet the fuselage panel. When there is no fuselage panel to be riveted in the work area adjacent to the buffer area and the fuselage panel to be riveted is present in the buffer area, a control device moves the A/R corresponding to the work area adjacent to the buffer area to the buffer area to rivet the fuselage panel.

Abstract: The purpose of the present invention is to provide a sealant application nozzle and a sealant application device that can apply a suitable amount of sealant uniformly and with which rapid work can be performed. A sealant application nozzle is provided with: a porous impregnation part that can be impregnated with sealant and elastically deforms by contact with a chamfered part; a sealant supply path that supplies sealant to the impregnation part; a base part that surrounds the impregnation part such that the tip part of the impregnation part is exposed to the outside; and a retention space that is formed between the base part and the impregnation part and retains the sealant.

Abstract: Image classification using a generated mask image is performed by generating a mask image that extracts a target area from an input image, extracting an image feature map of the input image by inputting the input image in a first neural network including at least one image feature extracting layer, masking the image feature map by using the mask image, and classifying the input image by inputting the masked image feature map to a second neural network including at least one classification layer.

Abstract: A method, system and computer program product for presenting content (e.g., advertisements) to vehicle occupants. An image of the occupants of the vehicle is obtained. The vehicle occupants, such as the driver, are then identified from the image. After obtaining the driving history of the driver, which includes any information that indicates a risk posed to the driver in not paying attention to the road, a risk degree of the driver getting into an accident from viewing content on the electronic billboard is assessed. A “watch ability” of the vehicle occupants to watch content is calculated, based, at least in part, on the driver's risk degree. If the value of the watch ability exceeds a threshold value, then the content preferences of the vehicle occupants are obtained which are used to determine the contents to be presented on the electronic billboard which are targeted to the vehicle occupants.

Abstract: An input device includes a casing having a recess in its inner surface, and a pressure-sensitive sensor disposed in the recess. The pressure-sensitive sensor is fixed in the recess so that a sensing surface of the pressure-sensitive sensor and a bottom surface of the recess are in contact with each other.

Abstract: Methods and systems are provided for training a neural network with augmented data. A dataset comprising a plurality of classes is obtained for training a neural network. Prior to initiation of training, the dataset may be augmented by performing affine transformations of the data in the dataset, wherein the amount of augmentation is determined by a data augmentation variable. The neural network is trained with the augmented dataset. A training loss and a difference of class accuracy for each class is determined. The data augmentation variable is updated based on the total loss and class accuracy for each class. The dataset is augmented by performing affine transformations of the data in the dataset according to the updated data augmentation variable, and the neural network is trained with the augmented dataset.

Abstract: A method, computer system, and a computer program product for predicting a variation of sequential blood glucose levels by using deep learning is provided. The present invention may include training a predictor associated with a user by using a deep learning network. The present invention may further include predicting a plurality of sequential blood glucose levels by the trained predictor based on at least one meal image, at least one time-period, and at least one set of data associated with a plurality of blood glucose levels of the user.