Abstract: In at least one embodiment, a reinforcement-learning-based searching approach is used to produce a training configuration for a machine-learning model. In at least one embodiment, 3D medical image segmentation is performed using learned image preprocessing parameters.

Abstract: Various examples of the present invention relate to an electronic device, and an autofocusing processing method in the electronic device, and the electronic device can: receive a first image obtained by imaging a subject at a first position of at least one lens, when autofocus searching is performed; perform image processing and autofocus processing for the first image; receive a second image obtained by imaging the subject at a second position of the lens; generate compensation information by using first brightness information of the first image and second brightness information of the second image; compensate for the brightness of the second image by using the compensation information; and perform image processing and autofocus processing for the second image of which the brightness has been compensated for.

Abstract: A self-powered module for gesture recognition is presented that utilizes small, low-cost photodiodes for both energy harvesting and gesture sensing. Operating in the photovoltaic mode, photodiodes harvest energy from ambient light. In the meantime, the instantaneously harvested power from individual photodiodes is monitored and exploited as a clue for sensing finger gestures in proximity. Harvested power from all photodiodes is aggregated to drive the whole gesture-recognition module including a micro-controller running the recognition algorithm. A robust, lightweight algorithm is provided to recognize finger gestures in the presence of ambient light fluctuations. Two prototypes are fabricated to facilitate user's interaction with smart glasses and smart watches.

Abstract: Disclosed herein are a real-time gas turbine simulation system and an execution method thereof, capable of verifying input and output signals of an actual gas turbine control system (GTCS) by simulating a gas turbine in real time to reduce trial and error in power plant operation in a gas turbine power generation system. The real-time gas turbine simulation system simulates a gas turbine to verify a GTCS for controlling a gas fuel through an actuator/sensor module and a safety integrity level (SIL) protection function through a protection module for the gas turbine, and includes a hardwire-in-the-loop (HIL) simulator connected to the actuator/sensor module and the protection module through one or more hardwires to simulate a time critical portion of the gas turbine in real time, and a network simulator connected to the GTCS through a network to simulate a non-time critical portion of the gas turbine in real time.

Abstract: The disclosed apparatus may include (1) at least one light-emitting device, (2) a boost circuit electrically coupled to the light-emitting device, and (3) a microcontroller that (A) receives, from a visual display system, a control signal indicating one or more points in time that the light-emitting device is to illuminate a portion of a visual display and (B) directs, based at least in part on the control signal, the boost circuit to provide a sufficient amount of power to the light-emitting device to enable the light-emitting device to illuminate the portion of the visual display at the points in time. Various other apparatuses, systems, and methods are also disclosed.

Abstract: The present invention relates to a method of activating an organic coating to enhance adhesion of the coating to a further coating and/or to other entities comprising applying a solvent and a surface chemistry and/or surface topography modifying agent to the organic coating. The invention also relates to a coated substrate having an activated coating, wherein the adhesion of the coating to a further coating and/or other entities has been enhanced by application of a solvent and a surface chemistry and/or surface topography modifying agent to the coating. The invention further relates to an activation treatment for an organic coating to enhance adhesion of the coating to a further coating and/or to other entities comprising a solvent and a surface chemistry and/or surface topography modifying agent and a method for the preparation of the activation treatment.

Abstract: Apparatuses, systems, and techniques to generate synthesized images including digital representations of groups of cells blended realistically with appropriate background images. In at least one embodiment, background image data and gene expression data are fused together to generate such a synthesized image using one or more neural networks.

Abstract: A printing system includes a host apparatus configured to transmit a command to a printer apparatus. The host apparatus includes a communicator configured to receive status information containing information indicating a status of the printer apparatus, which is transmitted by the printer apparatus; a monitor configured to monitor the status of the printer apparatus based on the information indicating the status of the printer apparatus, which is contained in the status information received by the communicator; a determiner configured to determine, based on a result of monitoring the printer apparatus by the monitor, whether a reset command to be transmitted to the printer apparatus is to be generated; and a generator configured to generate the reset command when the determiner determines that the reset command is to be generated. The communicator is configured to transmit the reset command generated by the generator to the printer apparatus.

Abstract: The disclosed embodiments provide computer-implemented systems and methods for batch picking optimization. The system may include one or more memory devices storing instructions and one or more processors configured to execute the instructions to receive an order comprising one or more items for picking. Additionally, the system may calculate one or more high density areas in a fulfillment center by calculating distances between a first item in the one or more items and at least one other item in the one or more items using a search algorithm. Additionally, the system may calculate nearest neighboring items for the one or more items and generate a high density area by choosing a plurality of the nearest neighboring items.

Abstract: Comparison logic compares boundaries of features of or more images based, at least in part, on identifying boundaries and indication logic coupled to the comparison logic to indicate whether the boundaries differ by at least a first threshold. The boundaries might comprise a first label mask representing boundaries of objects in an image that are boundaries in a segmentation determined from a segmentation process and a second label mask from a shape evaluation process applied to the first label mask. The indication logic might be configured to compare the first label mask and the second label mask to determine a quality of the segmentation. A neural network might perform the segmentation. Shape evaluation using the first label mask as an input and the second label mask as an output might be performed by a variational autoencoder. A graphical processing unit (GPU) might be used for the segmentation and/or the autoencoder.

Abstract: A noise detection method and a noise detection system are provided. The noise detection method includes: obtaining an audio signal; comparing the audio signal with a wave of a noise model to obtain a correlation value; and identifying whether the audio signal is a candidate noise signal based on the correlation value. The method can detect plugging noises effectively.

Abstract: The disclosed embodiments provide computer-implemented systems and methods for batch picking optimization. They system may include one or more memory devices storing instructions and one or more processors configured to execute the instructions to receive an order comprising one or more items for picking. Additionally, the system may calculate one or more high density areas in a fulfillment center by calculating distances between a first item in the one or more items and at least one other item in the one or more items using a search algorithm. Additionally, the system may calculate nearest neighboring items for the one or more items and generate a high density area by choosing a plurality of the nearest neighboring items.

Abstract: The present invention provides scanning mechanisms for imaging probes using for imaging mammalian tissues and structures using high resolution imaging, including high frequency ultrasound and/or optical coherence tomography. The imaging probes include adjustable rotational drive mechanism for imparting rotational motion to an imaging assembly containing either optical or ultrasound transducers which emit energy into the surrounding area. The imaging assembly includes a scanning mechanism having including a movable member configured to deliver the energy beam along a path out of said elongate hollow shaft at a variable angle with respect to said longitudinal axis to give forward and side viewing capability of the imaging assembly. The movable member is mounted in such a way that the variable angle is a function of the angular velocity of the imaging assembly.

Abstract: Apparatuses, systems, and techniques to perform training of neural networks using stacked transformed images. In at least one embodiment, a neural network is trained on stacked transformed images and trained neural network is provided to be used for processing images from an unseen domain distinct from a source domain, wherein stacked transformed images are transformed according to transformation aspects related to domain variations.

Abstract: The invention relates to a method for identifying individual trees in airborne lidar data and a corresponding computer program product. The method comprises: a. obtaining lidar data points of a group of one or more trees; b. define voxels in a regular 3D grid on the basis of the data points; c. applying an image segmentation algorithm to obtain at least one segment; and, if at least two segments are obtained: d. find the root voxel and branch voxels of a first segment and a second neighbouring segment; and e. merging the first and second segment if the distance between the first and second root voxel is less than a first threshold, the distance between the first root voxel and the closest second branch voxel is less than a second threshold; and the distance between the first branch voxels and the second branch voxels is less than a third threshold.

Abstract: A valve bridge system comprises a valve bridge configured to extend between at least two engine valves of an internal combustion engine. In one embodiment, a valve bridge guide is operatively connected to the valve bridge and configured to extend between at least two valve springs respectively corresponding to the at least two engine valves, the valve bridge guide defining a surface conforming to a valve spring of the at least two valve springs. In another embodiment, the valve bridge guide may comprise at least a first member maintained in a first fixed position relative to and at a predetermined distance from the valve bridge. In both embodiments, the valve bridge guide is configured to avoid contact with the valve bridge in a controlled state, but to permit contact with valve bridge to resist uncontrolled movement of the valve bridge.

Abstract: Various examples of the present invention relate to an electronic device, and an autofocusing processing method in the electronic device, and the electronic device can: receive a first image obtained by imaging a subject at a first position of at least one lens, when autofocus searching is performed; perform image processing and autofocus processing for the first image; receive a second image obtained by imaging the subject at a second position of the lens; generate compensation information by using first brightness information of the first image and second brightness information of the second image; compensate for the brightness of the second image by using the compensation information; and perform image processing and autofocus processing for the second image of which the brightness has been compensated for.

Abstract: Disclosed are a method and a user behavior data processing device, as well as a computer-readable storage medium. The user behavior data processing method includes: obtaining log information stored in a preset server at a fixed time, wherein, the log information comprises user behavior data which is captured and sent to the preset server by client; determining that whether row data satisfying a preset format exists in each row data of the log information, wherein, the row data is the data corresponding to each row of the log information; setting the row data satisfying the preset format as user behavior information; performing data statistics on the user behavior information according to a preset rule to obtain statistical information of the user behavior information.

Abstract: Disclosed is an iron-based amorphous alloy FeaBbSicREd, wherein a, b, and c represent, in atomic percentages, the contents of corresponding components, respectively; 83.0?a?87.0, 11.0<b<15.0, 2.0?c?4.0, and a+b+c=100; and d is the concentration of RE in the iron-based amorphous alloy, i.e. 10 ppm?d?30 ppm. The iron-based amorphous alloy has a saturation magnetic induction intensity of no less than 1.63 T, and same can be used to manufacture a magnetic core material for power transformers, motors and inverters.

Abstract: Methods and apparatus for automated medical image analysis using deep learning networks are disclosed. In a method of automatically performing a medical image analysis task on a medical image of a patient, a medical image of a patient is received. The medical image is input to a trained deep neural network. An output model that provides a result of a target medical image analysis task on the input medical image is automatically estimated using the trained deep neural network. The trained deep neural network is trained in one of a discriminative adversarial network or a deep image-to-image dual inverse network.