Abstract: Systems, methods, and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

Abstract: Methods and systems are provided for singulating, orienting, and delivering oriented objects (e.g., embryos) to a desired location (e.g., a plate containing a selected medium).

Abstract: A support link for a self-stacking spiral conveyor belt, which includes a carrier on which a self-stacking spiral conveyor belt is supportable, a set of orthogonally arranged rolling elements connected to the carrier, in use to guide the carrier along a conveyor path and an interlink mountable onto the carrier. The interlink is connectable to a matched interlink of an adjacent support link through couplers disposed on opposing ends thereof, whereby the connection of a plurality of support links results in a support chain. Furthermore, there is provided a supporting frame defining the conveyor path on which the support chain is movable and a motor driving the support chain by means of a drive gear, which interacted with a drive interface disposed on each support link.

Abstract: Apparatuses and methods for storing and dispensing a continuous feed of adhesive bandages. In one embodiment, the apparatus comprises a housing, a cover, and a plurality of rotating elements which may comprise one or more spools and one or more rollers, wherein a continuous feed of bagged adhesive bandages may be dispensed from a spooled loading system. In one embodiment, the apparatus comprises a housing, a cover, a plurality of rotating elements which may comprise one or more spools and one or more rollers, and a bandage magazine, wherein a continuous feed of bagged adhesive bandages may be dispensed from a magazine loading system. Two embodiments of a method are presented which correspond to each embodiment of the apparatuses, and comprise individual steps of loading, storing, and dispensing a plurality of bagged adhesive bandages, wherein the dispensing further comprises individual steps of separating, removing, and collecting a bag within which an adhesive bandage may be stored.

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

Abstract: Systems, methods, and computer program products for image recognition in which instructions are executable by a processor to dynamically generate simulated documents and corresponding images, which are then used to train a fully convolutional neural network. A plurality of document components are provided, and the processor selects subsets of the document components. The document components in each subset are used to dynamically generate a corresponding simulated document and a simulated document image. The convolutional neural network processes the simulated document image to produce a recognition output. Information corresponding to the document components from which the image was generated is used as an expected output. The recognition output and expected output are compared, and weights of the convolutional neural network are adjusted based on the differences between them.

Abstract: Described herein are methods and systems for detecting electrical discharges that precede electrical fires in electrical wiring. One or more sensor devices coupled to a circuit detect one or more signal waveforms generated by electrical activity on the circuit. The sensor devices identify one or more transient signals within the one or more signal waveforms, and generate one or more transient characteristics based upon the identified transient signals. A server communicably coupled to the sensor devices receives the one or more transient characteristics. The server analyzes the one or more transient characteristics to identify one or more electrical discharge indications. The server generates one or more alert signals when one or more electrical discharge indications are identified.

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

Abstract: Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).

Abstract: Described herein are methods and systems for detecting electrical discharges that precede electrical fires in electrical wiring. One or more sensor devices coupled to a circuit detect one or more signal waveforms generated by electrical activity on the circuit. The sensor devices identify one or more transient signals within the one or more signal waveforms, and generate one or more transient characteristics based upon the identified transient signals. A server communicably coupled to the sensor devices receives the one or more transient characteristics. The server analyzes the one or more transient characteristics to identify one or more electrical discharge indications. The server generates one or more alert signals when one or more electrical discharge indications are identified.

Abstract: Disclosed is an approach of on-device partial recognition that includes performing partial recognition on an image of a document captured by a mobile device to detect and/or recognize a specific area (e.g., barcodes, non-relevant text, etc.) and filling the recognized area with a solid color. Because the solid color area has a maximum compression ratio, this approach can lead to image size reduction and increased network throughput for client-server based data recognition where further processing such as advanced data extraction is performed at the server side. The approach can be enforced with neural network algorithms to exclude non-relevant information (e.g., logos, phrases, words, etc.).

Abstract: Systems and methods for image modification to increase contrast between text and non-text pixels within the image. In one embodiment, an original document image is scaled to a predetermined size for processing by a convolutional neural network. The convolutional neural network identifies a probability that each pixel in the scaled is text and generates a heat map of these probabilities. The heat map is then scaled back to the size of the original document image, and the probabilities in the heat map are used to adjust the intensities of the text and non-text pixels. For positive text, intensities of text pixels are reduced and intensities of non-text pixels are increased in order to increase the contrast of the text against the background of the image. Optical character recognition may then be performed on the contrast-adjusted image.

Abstract: Described herein are methods and systems for estimating an originating location of a power quality event in an electrical grid. Each of a plurality of sensor devices connected to the electrical grid detects an input signal generated by electrical activity on the electrical grid, generates an output signal based upon the detected input signal, and transmits power quality data to a computing device via a communications network, where the power quality data is based upon the output signal. The computing device is configured to analyze the power quality data from at least a subset of the sensor devices to determine a power quality event occurring in the electrical grid, estimate an originating location of the power quality event based upon the power quality data, and transmit a notification to one or more remote computing devices based upon the estimated originating location of the power quality event.

Abstract: Systems and methods for image modification to increase contrast between text and non-text pixels within the image. In one embodiment, an original document image is scaled to a predetermined size for processing by a convolutional neural network. The convolutional neural network identifies a probability that each pixel in the scaled is text and generates a heat map of these probabilities. The heat map is then scaled back to the size of the original document image, and the probabilities in the heat map are used to adjust the intensities of the text and non-text pixels. For positive text, intensities of text pixels are reduced and intensities of non-text pixels are increased in order to increase the contrast of the text against the background of the image. Optical character recognition may then be performed on the contrast-adjusted image.

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

Abstract: Described herein are methods and systems for detection and notification of electrical power outages and power quality. A sensor coupled to a circuit transmits a keepalive packet to a server. The sensor detects an input signal generated by electrical activity. The sensor generates an output signal based upon the input signal. The sensor monitors the output signal. During a clock cycle, the sensor determines whether a rising edge occurred and transmits a fault packet to the server when the rising edge occurred prior to a predetermined clock value or when no rising edge occurred. The server receives the fault packet from the sensor and listens for keepalive packets. The server transmits a power outage notification when no keepalive packets are received for at least a defined time period after the fault packet is received. The server transmits a power restoration notification when one or more keepalive packets are subsequently received.

Abstract: An auto-rotation module having a single-layer neural network on a user device can convert a document image to a monochrome image having black and white pixels and segment the monochrome image into bounding boxes, each bounding box defining a connected segment of black pixels in the monochrome image. The auto-rotation module can determine textual snippets from the bounding boxes and prepare them into input images for the single-layer neural network. The single-layer neural network is trained to process each input image, recognize a correct orientation, and output a set of results for each input image. Each result indicates a probability associated with a particular orientation. The auto-rotation module can examine the results, determine what degree of rotation is needed to achieve a correct orientation of the document image, and automatically rotate the document image by the degree of rotation needed to achieve the correct orientation of the document image.

Abstract: A bicycle steering bearing assembly includes features for internal routing of actuator cables. Apertures through the elements of the steerer bearing assembly are configured to provide for the maximum actuator cable size while providing uniform application of forces to the steerer tube and upper bearing. Such apertures may be angled or partially angled from vertical, and may be or may include tapered sections. The apertures may also include a relief feature.

Abstract: Described herein are methods and systems for detecting electrical discharges that precede electrical fires in electrical wiring. One or more sensor devices coupled to a circuit detect one or more signal waveforms generated by electrical activity on the circuit. The sensor devices identify one or more transient signals within the one or more signal waveforms, and generate one or more transient characteristics based upon the identified transient signals. A server communicably coupled to the sensor devices receives the one or more transient characteristics. The server analyzes the one or more transient characteristics to identify one or more electrical discharge indications. The server generates one or more alert signals when one or more electrical discharge indications are identified.

Abstract: System, methods, and devices for measuring the performance of a component of a communications network recently installed by a technician using proactive network maintenance parameters, and further assessing the installation performed by the technician.