Abstract: In one embodiment, a computer-implemented method includes receiving training data including a plurality of records, each record having a plurality of attributes. The training data is horizontally parallelized across two or more processing elements. This horizontal parallelizing includes dividing the training data into two or more subsets of records; assigning each subset of records to a corresponding processing element of the two or more processing elements; transmitting each subset of records to its assigned processing element; and sorting, at the two or more processing elements, the two or more subsets of records to two or more candidate leaves of a decision tree. The output from horizontally parallelizing is converted into input for vertically parallelizing the training data. The training data is vertically parallelized across the two or more processing elements. The decision tree is grown based at least in part on the horizontally parallelizing, the converting, and the vertically parallelizing.

Abstract: A computer implemented method for surface defect inspection that includes recording an optical image of a surface including a defect; converting the optical image including the defect into a heat map; extracting a region of interest including the defect from the heat map; and comparing the region of interest including the defect from the heat map to a binary classification model using a sliding window based voting mechanism to determine if the defect is greater than or less than a threshold failure value.

Abstract: Methods and systems for classification of sequence data include warping training sequence data according to a warping pattern. A neural network is trained using the warped training sequence data. Input sequence data is warped according to the warping pattern. The warped input sequence data is classified using the trained neural network.

Abstract: Scheduling automated visual inspection tasks includes capturing an image of a component to be inspected. A visual inspection model is formed with a model engine as a composite model of utility modules and functional modules to perform visual inspection of the image of the component. An abstract processing workflow of the visual inspection model is derived with a scheduler including dependencies between the utility modules and the functional modules. Performance of each of the functional modules is profiled with the scheduler by testing performance with available hardware resources to produce a performance profile. Parallel instances of each of the functional modules in a branch of the abstract processing workflow are scheduled with the scheduler according to the dependencies and the performance profiles. An indication of defects in the component is produced by processing the visual inspection model according to the scheduled functional modules.

Abstract: A computer-implemented method is provided for image-based defect detection. The method includes performing, by a processor device, template matching and subtraction on a set of training images and at least one template image to obtain a set of difference images. The difference images have defects, if any, highlighted therein. The method further includes generating, by the hardware processor applying a binary classification model to each of the training images in the set, activation heatmaps. The method also includes identifying, by the hardware processor, rough defect areas of interest in the activation heatmaps. The method additionally includes super-imposing, by the hardware processor, the activation heatmaps onto the difference images to obtain a set of super-imposed images, and highlight, as true defect areas, any areas in the super-imposed images having the defects from the difference images that overlap with the rough defect areas of interest from the activation heatmaps.

Abstract: Methods and systems for detecting abnormal connectivity on a product are provided. The methods receive an inspection image of the product including a defect, match the inspection image with a template image of the product to locate a corresponding normal region in the template image and obtain a differential image between the inspection image and the normal region. The method further includes forming a regional mask image from component masks. Each of the component masks includes a binary image of the template image with only one kind of components of the product remaining. The regional mask image is a region in its corresponding component mask that corresponds to the normal region. The method further includes determining, based on a calculation using the differential image and the at least one regional mask image, at least one of: connectivity relationship, connectivity type and connectivity scale of abnormal connectivity on the product.

Abstract: A SnBiSb series low-temperature lead-free solder and a preparation method thereof, which belongs to the technical field of low-temperature soldering. The lead-free solder includes by weight the following composition: 32.8-56.5% of Bi, 0.7-2.2% of Sb, with the remainder being Sn, wherein the weight percentages of Bi and Sb satisfy a relationship of b=0.006a2?0.672a+19.61=c, wherein the symbol a represents the weight percentage of Bi, the symbol b represents the weight percentage of Sb, and the range of c is ?1.85?c?1.85. The solder alloy has a peritectic or near peritectic structure with a low melting point, and has an excellent mechanical performance and reliability, and applicable to the field of low-temperature soldering.

Abstract: A computer-implemented method is provided for image-based, self-guided object detection. The method includes receiving, by a processor device, a set of images. Each of the images has a respective grid thereon that is labeled regarding a respective object to be detected using grid level label data. The method further includes training, by the processor device, a grid-based object detector using the grid level label data. The method also includes determining, by the processor device, a respective bounding box for the respective object in each of the images, by applying local segmentation to each of the images. The method additionally includes training, by the processor device, a Region-based Convolutional Neural Network (RCNN) for joint object localization and object classification using the respective bounding box for the respective object in each of the images as an input to the RCNN.

Abstract: A method of route discovery in wireless mesh networks comprises: receiving, by a first mesh network device of a wireless mesh network, from a second mesh network device of the wireless mesh network, a first route request identifying a destination mesh network device of the wireless mesh network and a first path selection metric value; determining a path selection metric increment, wherein the path selection metric increment reflects a radio channel contention by the first mesh network device and the second mesh network device; generating a second path selection metric value by adding the path selection metric increment to the first path selection metric value; and broadcasting a second route request identifying the destination mesh network device and the second path selection metric value.

Abstract: A mechanism is provided in a data processing system for distributed tree learning. A source processing instance distributes data record instances to a plurality of model update processing items. The plurality of model update processing items determine candidate leaf splitting actions in a decision tree in parallel based on the data record instances. The plurality of model update processing items send the candidate leaf splitting actions to a plurality of conflict resolve processing items. The plurality of conflict resolve processing items identifies conflict leaf splitting actions. The plurality of conflict resolve processing items applies tree structure changes to the decision tree in the plurality of model update processing items.

Abstract: A mechanism is provided in a data processing system for distributed tree learning. A source processing instance distributes data record instances to a plurality of model update processing items. The plurality of model update processing items determine candidate leaf splitting actions in a decision tree in parallel based on the data record instances. The plurality of model update processing items send the candidate leaf splitting actions to a plurality of conflict resolve processing items. The plurality of conflict resolve processing items identifies conflict leaf splitting actions. The plurality of conflict resolve processing items applies tree structure changes to the decision tree in the plurality of model update processing items.

Abstract: This disclosure provides a method for object detection. The method comprises receiving a user input that specifies one or more first regions and one or more second regions in a template image. The one or more second regions include one or more objects of interest. The method further comprises for each of the one or more first regions discovering a third region in an image under detection corresponding to the first region in the template image by matching the image under detection with the template image. The method further comprises computing a transformation function based on the matching from each of the one or more first regions to its corresponding third region. The method further comprises applying the computed transformation function to the one or more second regions to localize one or more fourth regions in the image under detection for the object detection.

Abstract: Semiconductor structures are provided. An exemplary semiconductor structure includes a semiconductor substrate having a first region and a second region and a plurality of first fins on the semiconductor substrate in the first region and a plurality of second fins on the semiconductor substrate in the second region. A first oxide layer is on side surfaces of the plurality of first fins; and a second oxide layer is on side surfaces of the second fins. A corner between a top surface and a side surface of each first fin is a first rounded corner. A corner between a top surface and a side surface of each second fin is a second rounded corner. A radius of curvature of the first rounded corner is different from a radius of curvature of the second corner.

Abstract: Semiconductor structures and fabrication methods thereof are provided. An exemplary fabrication process includes providing a semiconductor substrate having a first region and a second region and having a plurality of first fins in the first region and a plurality of second fins in the second region; performing a first oxidation process on the first fins to form a first oxide layer on surfaces of the first fins and to cause corners between top surfaces and side surface of the first fins to form first rounded corners; and performing a second oxidation process on the second fins to form a second oxide layer on surfaces of the second fins and to cause corners between top surfaces and side surface of the second fins to form second rounded corners. A radius of curvature of the first rounded corner is different from a radius of curvature of the second rounded corner.

Abstract: A device for driving light-emitting diodes (LEDs) includes an address transceiver, a processor, and at least one power supply. The address transceiver stores a communication address and receives a Konnex (KNX) protocol signal carrying a driving address. The address transceiver generates a driving signal when the driving address corresponds to the communication address. The processor, electrically connected to the address transceiver, receives the driving signal and generates a power starting signal according to the driving signal. The power supply, electrically connected to the processor and at least one light-emitting diode (LED) module, receives the power starting signal and uses the power starting signal to drive the LED module.

Abstract: Implementations of the present disclosure relate to methods, systems, and computer program products for quality evaluation. In one implementation, a computer-implemented method is disclosed. In the method, a pattern period may be extracted from an image of a target object, the pattern period indicating a period of a pattern that is repeated in the image. A reference image may be generated by repeating the pattern based on the extracted pattern period. Quality of the target object may be evaluated by comparing the generated reference image and the image of the target object. In other implementations, a computer-implemented system and a computer program product for quality evaluation are disclosed.

Abstract: This disclosure provides a method for object detection. The method comprises receiving a user input that specifies one or more first regions and one or more second regions in a template image. The one or more second regions include one or more objects of interest. The method further comprises for each of the one or more first regions discovering a third region in an image under detection corresponding to the first region in the template image by matching the image under detection with the template image. The method further comprises computing a transformation function based on the matching from each of the one or more first regions to its corresponding third region. The method further comprises applying the computed transformation function to the one or more second regions to localize one or more fourth regions in the image under detection for the object detection.

Abstract: The present disclosure provides a light beam adjusting device, an optical assembly and a lighting and/or signaling apparatus. The light beam adjusting device includes: a light collimating portion arranged to collimate a light beam; and a multi-focal converging portion arranged to converge the collimated light beam, the multi-focal converging portion including two or more converging surfaces, wherein at least two of the two or more converging surfaces have focal points separated spatially from each other.

Abstract: An efficient method and apparatus for identifying one or more targets in an image is presented. A matching operation is performed that compares the image against multiple templates jointly. The multiple templates are sorted into multiple clusters. The joint template matching operation achieves an improvement in performance by focusing on a subset of the clusters. For each grid location, clusters whose reference templates have low matching scores with the image content of the grid location are bypassed or excluded from the matching operation. This saving in computation load is made possible by the clustering of the templates, which can be performed offline and does not affect the performance of the joint template matching operation.

Abstract: An embodiment of present Utility Model application provides a light beam adjusting device and an optical device. The light beam adjusting device includes: one or more first light incidence face arranged to receive an incident light beam; one or more total reflection collimating face arranged to totally reflect the incident light beam from the first light incidence face to collimate the incident light beam; and a first light exit face, from which the collimated light beam is emitted. In the above light beam adjusting device and the optical device, the incident light beam is firstly collimated into a substantially parallel light beam and then exits from the light exit face, thereby improving the luminance of the emergent light and broaden the emergent light.