Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for data communication with differentially private intersection dataset. On example method includes: determining a plurality of bias parameters based on a parameter for establishing a differential privacy (DP) data protection; determining an intersection dataset based on client data from a client device and server data from the server device; updating the intersection dataset based on the client data and the plurality of bias parameters; and returning the updated intersection data having the DP data protection to the client device.

Abstract: A laparoscopic image smoke removal method based on a generative adversarial network, and belongs to the technical field of computer vision. The method includes: processing a laparoscopic image sample to be processed using a smoke mask segmentation network to acquire a smoke mask image; inputting the laparoscopic image sample to be processed and the smoke mask image into a smoke removal network, and extracting features of the laparoscopic image sample to be processed using a multi-level smoke feature extractor to acquire a light smoke feature vector and a heavy smoke feature vector; and acquiring, according to the light smoke feature vector, the heavy smoke feature vector and the smoke mask image, a smoke-free laparoscopic image by filtering out smoke information and maintaining a laparoscopic image by using a mask shielding effect. The method has the technical effects of robustness and ability of being embedded into a laparoscopic device for use.

Abstract: A method for evaluating a verification model includes receiving a first and a second set of verification results where each verification result indicates whether a primary model or an alternative model verifies an identity of a user as a registered user. The method further includes identifying each verification result in the first and second sets that includes a performance metric. The method also includes determining a first score of the primary model based on a number of the verification results identified in the first set that includes the performance metric and determining a second score of the alternative model based on a number of the verification results identified in the second set that includes the performance metric. The method further includes determining whether a verification capability of the alternative model is better than a verification capability of the primary model based on the first score and the second score.

Abstract: A laparoscopic image smoke removal method based on a generative adversarial network, and belongs to the technical field of computer vision. The method includes: processing a laparoscopic image sample to be processed using a smoke mask segmentation network to acquire a smoke mask image; inputting the laparoscopic image sample to be processed and the smoke mask image into a smoke removal network, and extracting features of the laparoscopic image sample to be processed using a multi-level smoke feature extractor to acquire a light smoke feature vector and a heavy smoke feature vector; and acquiring, according to the light smoke feature vector, the heavy smoke feature vector and the smoke mask image, a smoke-free laparoscopic image by filtering out smoke information and maintaining a laparoscopic image by using a mask shielding effect. The method has the technical effects of robustness and ability of being embedded into a laparoscopic device for use.

Abstract: A method and system for segmenting three-dimensional images of pancreases and tumors, including: acquiring 3D images of the pancreas and the tumor and preprocessing same with a soft tissue window to control the intensity value of the image within a set range; cropping all images into block-shaped regions of a set size and feeding same into a trained convolutional neural network model, and when training a network, dynamically adjusting the learning weight between the pancreas and the tumor under the guidance of temperature to learn the features of the pancreas and the tumor; and after performing data preprocessing on the 3D images of the pancreas and labels, using the trained network model for online testing and evaluating, and outputting the segmentation result.

Abstract: A resistance device for exercise bike and bike trainer wherein the resistance is generated and adjusted by the rotation of a conductor and movement of one or a group of permanent magnets proximate to the conductor. The resistance training apparatus of the present disclosure can include a housing, a controller that connects to a computer, one or more sensors, a conductor/brake disk configured to rotate around a first axis, a magnet holding assembly for holding one or more magnets, a drive motor that is controlled by the electronic board to precisely move the magnet holding assembly form a first position to a second position along a second axis, wherein resistance is generated and adjusted by the rotation of conductor/brake disk and the position of the one or more magnets relative to the conductor as the magnetic holding assembly moves along the second axis.

Abstract: An integrated method for uploading data on a blockchain comprising: receiving an editable text data or an editable form data by the data source computer device; determining whether a file update time of the editable text data or the editable form data is later than a last change time stored by the service server and corresponding to the data by the data source computer device; sending the data to the service server when the data source computer device determined that the file update time is later than the last change time by the data source computer device; executing a corresponding service that is able to access data of a blockchain and upload the data to the blockchain according to the data from the data source computer device by the service server. Therefore, the data can be efficiently and quickly uploaded to the blockchain.

Abstract: An intelligent interactive real road simulation training device that simulates the real road grade and slope change while playing video based on the geographic location of the road from the pre-processed video and the speed of the user. With the video playing, the user sees the road moving as the user moves, and the speed of the road moving by is based upon the user's speed on the exercise training equipment. The user also feels the grade and slope change as the road grade and slope changes on the video. The invention can be integrated into any exercise training equipment such as a bicycle trainer or treadmill.

Abstract: In some examples, octree serialization can include non-transitory machine-readable medium storing instructions, the instructions executable by a processing resource to evaluate two or more nodes sequentially in an octree structure until a leaf node is reached, wherein the two or more nodes include at least one non-leaf node, and generate a serialized octree document based on a respective node identifier in a header associated with each node of the two or more nodes.

Abstract: An example technique for generating slice data from a voxel representation can include obtaining a shape specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include obtaining a material specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include merging the shape specification and the material specification to create a voxel representation of the 3-D object, wherein each voxel in the voxel representation includes a plurality of data types. The example technique for generating slice data from a voxel representation can also include generating slice data from the voxel representation, wherein the slice data provides a higher resolution than that provided by the voxel representation using the plurality of data types.

Abstract: An example technique for generating slice data from the tree data structure representation of a three dimensional (3-D) object can include obtaining a shape specification of the 3-D object and obtaining a material specification of the 3-D object. The example technique for generating slice data from the tree data structure representation of a 3-D object can also include merging the shape specification and the material specification to create a tree data structure representation of the 3-D object. The example technique for generating slice data from the tree data structure representation of a 3-D object can also include generating slice data from the tree data structure.

Abstract: An example technique for generating slice data from a voxel representation can include obtaining a shape specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include obtaining a material specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include merging the shape specification and the material specification to create a voxel representation of the 3-D object, wherein each voxel in the voxel representation includes a plurality of data types. The example technique for generating slice data from a voxel representation can also include generating slice data from the voxel representation, wherein the slice data provides a higher resolution than that provided by the voxel representation using the plurality of data types.

Abstract: An example technique for generating slice data from a voxel representation can include obtaining a shape specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include obtaining a material specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include merging the shape specification and the material specification to create a voxel representation of the 3-D object, wherein each voxel in the voxel representation includes a plurality of data types. The example technique for generating slice data from a voxel representation can also include generating slice data from the voxel representation, wherein the slice data provides a higher resolution than that provided by the voxel representation using the plurality of data types.

Abstract: A method includes obtaining from an online social media site a plurality of instances of images of objects associated with a person; analyzing with a data processor the plurality of instances of the images with a plurality of predetermined style classifiers to obtain a score for each image for each style classifier; and determining with the data processor, based on the obtained scores, a likely preference of the person for a particular style of object. The plurality of instances of images of objects associated with the person can be images that were posted, shared or pinned by person, and images that the person expressed a preference for. In a non-limiting embodiment the object is clothing, and the style can include a fashion style or fashion genre including color preferences. A system and a computer program product to perform the method are also disclosed.

Abstract: A train bulk cargo loading system having a disconnected railroad track scale, includes a disconnected railroad track scale (1), a tractor (2), a lifting scraping plow (4), a controllable vibration charging hopper (6), a surge bin (8), a belt conveyor (9) and a control terminal (7). The train bulk cargo loading system having the disconnected railroad track scale has a low overall height and a small footprint, thus reducing the construction and production costs. The system integrates loading, trimming, measuring and data sharing, and features uniform loading, balanced train wheel pressure, and accurate measuring. Thus, huge human and material resources consumption caused by uneven loading of an original loading system, large wheel pressure deviation and secondary trimming and measuring required by the railway department may be avoided, significantly reducing the construction cost and operation cost.

Abstract: A method includes obtaining from an online social media site a plurality of instances of images of objects associated with a person; analyzing with a data processor the plurality of instances of the images with a plurality of predetermined style classifiers to obtain a score for each image for each style classifier; and determining with the data processor, based on the obtained scores, a likely preference of the person for a particular style of object. The plurality of instances of images of objects associated with the person can be images that were posted, shared or pinned by person, and images that the person expressed a preference for. In a non-limiting embodiment the object is clothing, and the style can include a fashion style or fashion genre including color preferences. A system and a computer program product to perform the method are also disclosed.

Abstract: In some examples, octree serialization can include non-transitory machine-readable medium storing instructions, the instructions executable by a processing resource to evaluate two or more nodes sequentially in an octree structure until a leaf node is reached, wherein the two or more nodes include at least one non-leaf node, and generate a serialized octree document based on a respective node identifier in a header associated with each node of the two or more nodes.

Abstract: A method includes obtaining from an online social media site a plurality of instances of images of objects associated with a person; analyzing with a data processor the plurality of instances of the images with a plurality of predetermined style classifiers to obtain a score for each image for each style classifier; and determining with the data processor, based on the obtained scores, a likely preference of the person for a particular style of object. The plurality of instances of images of objects associated with the person can be images that were posted, shared or pinned by person, and images that the person expressed a preference for. In a non-limiting embodiment the object is clothing, and the style can include a fashion style or fashion genre including color preferences. A system and a computer program product to perform the method are also disclosed.

Abstract: A method includes obtaining from an online social media site a plurality of instances of images of objects associated with a person; analyzing with a data processor the plurality of instances of the images with a plurality of predetermined style classifiers to obtain a score for each image for each style classifier; and determining with the data processor, based on the obtained scores, a likely preference of the person for a particular style of object. The plurality of instances of images of objects associated with the person can be images that were posted, shared or pinned by person, and images that the person expressed a preference for. In a non-limiting embodiment the object is clothing, and the style can include a fashion style or fashion genre including color preferences. A system and a computer program product to perform the method are also disclosed.

Abstract: An example technique for generating slice data from a voxel representation can include obtaining a shape specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include obtaining a material specification of the 3-D object. The example technique for generating slice data from a voxel representation can also include merging the shape specification and the material specification to create a voxel representation of the 3-D object, wherein each voxel in the voxel representation includes a plurality of data types. The example technique for generating slice data from a voxel representation can also include generating slice data from the voxel representation, wherein the slice data provides a higher resolution than that provided by the voxel representation using the plurality of data types.