Abstract: A method for generating reconstruction a reconstructed image is adapted to an input image having a target object. The method comprises converting the input image into a feature map with vectors by an encoder; performing a training procedure according to training images of reference objects to generate feature prototypes associated with the training images and store the feature prototypes to a memory; selecting a part of feature prototypes from the feature prototypes stored in the memory according to similarities between the feature prototypes and the feature vectors; generating a similar feature map according the part of feature prototypes and weights, wherein the weights represents similarities between the part of feature prototypes and the feature vectors; and converting the similar feature map into the reconstructed image by a decoder; wherein the encoder, the decoder and the memory form an auto-encoder.

Abstract: A chain system is provided that is attached to a continuous track of a tracked vehicle. Embodiments of the chain system can include cross chains that extend from a side chain, and a hook is disposed at a free end of each cross chain. To attach the chain system to the track, the hooks are attached to an inner edge of the track on a top surface of the track. Once all of the hooks are attached, the ends of the side chain are attached to each other and the chain is secured to the track to improve the traction of the track and the tracked vehicle.

Abstract: A chain system is provided that is attached to a continuous track of a tracked vehicle. Embodiments of the chain system can include cross chains that extend from a side chain, and a hook is disposed at a free end of each cross chain. To attach the chain system to the track, the hooks are attached to an inner edge of the track on a top surface of the track. Once all of the hooks are attached, the ends of the side chain are attached to each other and the chain is secured to the track to improve the traction of the track and the tracked vehicle.

Abstract: A method for generating reconstruction a reconstructed image is adapted to an input image having a target object. The method comprises converting the input image into a feature map with vectors by an encoder; performing a training procedure according to training images of reference objects to generate feature prototypes associated with the training images and store the feature prototypes to a memory; selecting a part of feature prototypes from the feature prototypes stored in the memory according to similarities between the feature prototypes and the feature vectors; generating a similar feature map according the part of feature prototypes and weights, wherein the weights represents similarities between the part of feature prototypes and the feature vectors; and converting the similar feature map into the reconstructed image by a decoder; wherein the encoder, the decoder and the memory form an auto-encoder.

Abstract: A method for training a defect detector comprises: obtaining a first reference image of a first reference object, wherein the first reference object has a defect and the first reference image has a first label indicating the defect; training a reconstruction model according to a second reference image of a second reference object associated with the first reference object, wherein a defect level of the second reference object is in a tolerable range with an upper limit; obtaining a target image of a target object associated with the first reference object and the second reference object; generating a second label according to the target image, the reconstruction model and an error calculation procedure, wherein the second label comprises a defect of the target object; and training a defect detector by performing a machine learning algorithm according to the first reference image, the target image and the second label.

Abstract: A method for labeling image comprises: obtaining a target image of a target object; generating a reconstruction image according to the target image and a reconstruction model, wherein the reconstruction model is trained with a plurality of reference images and a machine learning algorithm, each of the reference images is an image of a reference object whose defect level is in a tolerable range with an upper limit, and each of the reference objects is associated with the target object; generating a first difference image and a second difference image respectively by performing a first difference algorithm and a second difference algorithm respectively according to the target image and the reconstruction image; and generating an output image by performing a pixel-scale operation according to the first difference image and the second difference image, wherein the output image includes a label indicating a defect of the target object.

Abstract: A method for training a defect detector comprises: obtaining a first reference image of a first reference object, wherein the first reference object has a defect and the first reference image has a first label indicating the defect; training a reconstruction model according to a second reference image of a second reference object associated with the first reference object, wherein a defect level of the second reference object is in a tolerable range with an upper limit; obtaining a target image of a target object associated with the first reference object and the second reference object; generating a second label according to the target image, the reconstruction model and an error calculation procedure, wherein the second label comprises a defect of the target object; and training a defect detector by performing a machine learning algorithm according to the first reference image, the target image and the second label.

Abstract: A method for labeling image comprises: obtaining a target image of a target object; generating a reconstruction image according to the target image and a reconstruction model, wherein the reconstruction model is trained with a plurality of reference images and a machine learning algorithm, each of the reference images is an image of a reference object whose defect level is in a tolerable range with an upper limit, and each of the reference objects is associated with the target object; generating a first difference image and a second difference image respectively by performing a first difference algorithm and a second difference algorithm respectively according to the target image and the reconstruction image; and generating an output image by performing a pixel-scale operation according to the first difference image and the second difference image, wherein the output image includes a label indicating a defect of the target object.

Abstract: A chain system is provided that is attached to a continuous track of a tracked vehicle. Embodiments of the chain system can include cross chains that extend from a side chain, and a hook is disposed at a free end of each cross chain. To attach the chain system to the track, the hooks are attached to an inner edge of the track on a top surface of the track. Once all of the hooks are attached, the ends of the side chain are attached to each other and the chain is secured to the track to improve the traction of the track and the tracked vehicle.

Abstract: A test strip for use with an analyte meter comprises an integrated power source, such as a battery wherein the test strip is configured upon insertion into the meter to provide sufficient power for completing a sample assay without requiring a separate power source in the meter.

Abstract: An analyte meter is configured to digitally test for the presence of a test strip in the meter and for the presence of a sample in the test strip prior to activating an analog current measurement circuit of the meter. A test strip port connector having a plurality of contacts receives an inserted test strip in which the contacts electrically connect to electrodes on the test strip for digitally detecting both the presence of a test strip and a sample added to the test strip. A control circuit monitoring the contacts maintains the analyte meter in a low power mode until detecting both the test strip and the sample, whereupon the control circuit activates the meter and enables an analog analyte measurement circuit.

Abstract: A test strip for use with an analyte meter comprises an integrated power source, such as a battery wherein the test strip is configured upon insertion into the meter to provide sufficient power for completing a sample assay without requiring a separate power source in the meter.

Abstract: An analyte meter is configured to digitally test for the presence of a test strip in the meter and for the presence of a sample in the test strip prior to activating an analog current measurement circuit of the meter. A test strip port connector having a plurality of contacts receives an inserted test strip in which the contacts electrically connect to electrodes on the test strip for digitally detecting both the presence of a test strip and a sample added to the test strip. A control circuit monitoring the contacts maintains the analyte meter in a low power mode until detecting both the test strip and the sample, whereupon the control circuit activates the meter and enables an analog analyte measurement circuit.

Abstract: A method of routing messages to multiple consumers comprises determining a probability function defining message classification probabilities for each of a plurality of consumer sets, receiving a plurality of messages, classifying each message, storing each message in a queue, receiving notification of a consumer available to process a message, ascertaining the consumer set to which the available consumer belongs, accessing the probabilities for the ascertained consumer set, selecting a message classification according to the accessed probabilities, and transmitting a message, of the selected classification, to the available consumer.

Abstract: A system is provided for analyzing metabolomics data received from an analytical device across a group of samples. The system automatically receives a data matrix corresponding to each of the samples, wherein the data matrix includes rows corresponding to each of the samples and columns corresponding to a group of ions present in the respective samples. A processor is provided for determining a characteristic value corresponding to at least one of a group of components present in the samples, wherein the components are made up of at least a portion of the group of ions, using at least one of a correlation function and a factorization function. A user interface is in communication with the processor for displaying a visual indication of the characteristic value such that a user may receive a visual indication of the types of components present in the samples.

Abstract: A pigment contains one or more substantially spherical-shaped beads. Each substantially spherical-shaped bead includes one or more high aspect ratio particles encapsulated within an encapsulating material. Resinous compositions containing this pigment and a plastic, for example a polycarbonate, have a flowline-free colored, sparkling and/or metallescent appearance.

Abstract: A pigment contains one or more substantially spherical-shaped beads. Each substantially spherical-shaped bead includes one or more high aspect ratio particles encapsulated within an encapsulating material. Resinous compositions containing this pigment and a plastic, for example a polycarbonate, have a flowline-free colored, sparkling and/or metallescent appearance.

Abstract: Embodiments of this invention comprise a pigment comprising one or more substantially spherical-shaped beads, wherein each substantially spherical-shaped bead comprises one or more high aspect ratio particles encapsulated within an encapsulating material. Embodiments also comprise a resinous composition comprising said pigment. Yet further embodiments comprise a method of preparing said pigment via suspension polymerization.