Abstract: A detection element and a verification system are disclosed. The detection element includes a detection end for contacting a feature portion of the osteotomy guide tool; and a positioning target connected to the detection end and configured to provide a pose parameter of the feature portion of the osteotomy guide tool in a coordinate system of a trackable element. With this configuration, the osteotomy guide tool can be verified to avoid deformation of the osteotomy guide tool during repeated use or transportation, affecting its positioning accuracy and affecting the operation.

Abstract: An exemplary embodiment of the present invention provides a planar inductor including a substrate, a first magnetic layer, a conductive coil, and a second magnetic layer. The first magnetic layer can be disposed on at least a portion of the substrate. The conductive coil can be disposed on a first portion of the first magnetic layer. The second magnetic layer can be disposed on a second portion of the first magnetic layer and on at least a portion of the conductive coil.

Abstract: An approach is provided for adaptively compressing a deep learning model. An original deep learning model for different Internet of Things (IoT) devices is determined. Device information is collected from the IoT devices. Based on the device information, multiple recommendation engines are selected from a set of recommendation engines. Compression factor combinations are determined by using the multiple recommendation engines. Compression ratios and model accuracies for the compression factor combinations are determined. Based on the compression ratios and the model accuracies, an optimal compression factor combination is selected from the compression factor combinations. A compressed deep learning model is generated by compressing the original deep learning model by using the optimal compression factor. The compressed deep learning model is deployed to the IoT devices.

Abstract: A computer-implemented method for annotating images is disclosed. The computer-implemented method includes generating a saliency map corresponding to an input image, wherein the input image is an image that requires annotation, generating a behavior saliency map, wherein the behavior saliency map is a saliency map formed from an average of a plurality of objects contained within respective bounding boxes of a plurality of sample images, generating a historical saliency map, wherein the historical saliency map is a saliency map formed from an average of a plurality of tagged objects in the plurality of sample images, fusing the saliency map corresponding to the input image, the behavior saliency map, and the historical saliency map to form a fused saliency map, and generating, based on the fused saliency map, a bounding box around an object in the input image.

Abstract: In order to perform a semantic search based on a graph database, sets of nodes are selected from a plurality of nodes in a graph database. A set of nodes semantically matches a keyword in a natural language query. At least one target node is identified in the sets of nodes. A path is selected from candidate paths based on similarities between the candidate paths and a plurality of paths in the graph database. A graph query for retrieving information from the graph database is generated based on the selected path and the query target.

Abstract: In an approach to deploying parallelizable deep learning models by adapting to the computing devices, a deep learning model is split into a plurality of slices, where each slice can exchange data with related slices. Virtual models are created from the plurality of slices, where the virtual models are based on capabilities of a plurality of devices on which the one or more virtual models are to be deployed, and further where each virtual model contains each slice of the plurality of slices. The one or more virtual models are stored in a cache. Responsive to determining that the deep learning model is to be deployed on one or more devices, a candidate model is selected from the virtual models in the cache, where the selection is based on information from a device monitor about the devices.

Abstract: A detection element and a verification system are disclosed. The detection element includes a detection end for contacting a feature portion of the osteotomy guide tool; and a positioning target connected to the detection end and configured to provide a pose parameter of the feature portion of the osteotomy guide tool in a coordinate system of a trackable element. With this configuration, the osteotomy guide tool can be verified to avoid deformation of the osteotomy guide tool during repeated use or transportation, affecting its positioning accuracy and affecting the operation.

Abstract: A computer-implemented method for annotating images is disclosed. The computer-implemented method includes generating a saliency map corresponding to an input image, wherein the input image is an image that requires annotation, generating a behavior saliency map, wherein the behavior saliency map is a saliency map formed from an average of a plurality of objects contained within respective bounding boxes of a plurality of sample images, generating a historical saliency map, wherein the historical saliency map is a saliency map formed from an average of a plurality of tagged objects in the plurality of sample images, fusing the saliency map corresponding to the input image, the behavior saliency map, and the historical saliency map to form a fused saliency map, and generating, based on the fused saliency map, a bounding box around an object in the input image.

Abstract: A verification method of an osteotomy guide tool, a verification system and a detection element are disclosed. The verification method includes obtaining a pose parameter of a feature portion of an osteotomy guide tool in a coordinate system of a trackable element; then comparing the obtained pose parameter of the feature portion of the osteotomy guide tool with a corresponding standard value to obtain an offset between the pose parameter of the feature portion of the osteotomy guide tool and the standard value; if the offset is greater than an expected value, the osteotomy guide tool is determined as deformed. With this configuration, the osteotomy guide tool can be verified to avoid deformation of the osteotomy guide tool during repeated use or transportation, affecting its positioning accuracy and affecting the operation.

Abstract: An audio signal time sequence processing method and apparatus based on a neural network are provided. The audio signal time sequence processing method includes creating a combined network model, wherein the combined network model comprises a first network and a second network; acquiring a time-frequency graph of an audio signal; optimizing the time-frequency graph to obtain network input data; using the network input data to train the first network, and performing a feature extraction to obtain a multi-dimensional feature pattern; using the multi-dimensional feature pattern to construct a new feature vector; and inputting the new feature vector into the second network for training. The audio signal time sequence processing method solves a problem of an existing mapping transformation model based on a time sequence being unable to meet a multi-modal information application requirement.

Abstract: A verification method of an osteotomy guide tool, a verification system and a detection element are disclosed. The verification method includes obtaining a pose parameter of a feature portion of an osteotomy guide tool in a coordinate system of a trackable element; then comparing the obtained pose parameter of the feature portion of the osteotomy guide tool with a corresponding standard value to obtain an offset between the pose parameter of the feature portion of the osteotomy guide tool and the standard value; if the offset is greater than an expected value, the osteotomy guide tool is determined as deformed. With this configuration, the osteotomy guide tool can be verified to avoid deformation of the osteotomy guide tool during repeated use or transportation, affecting its positioning accuracy and affecting the operation.

Abstract: An exemplary embodiment of the present invention provides a planar inductor including a substrate, a first magnetic layer, a conductive coil, and a second magnetic layer. The first magnetic layer can be disposed on at least a portion of the substrate. The conductive coil can be disposed on a first portion of the first magnetic layer. The second magnetic layer can be disposed on a second portion of the first magnetic layer and on at least a portion of the conductive coil.

Abstract: An approach is provided in which an information handling system determines a current focus of a user composing a document. The current focus is based on a set of text in proximity to a current cursor location in the document. Next, the information handling system identifies a query based at least in part upon the current focus and queries a database using the identified query. In turn, the information handling system presents reference recommendations to the user that are generated from the query.

Abstract: A method, computer system, and computer program product for NLP-based domain modeling are provided. The embodiment may include receiving, by a processor, a plurality of documents related to business requirements. The embodiment may also include parsing the received documents to extract business concepts based on sentence analysis utilizing an NLP technology. The embodiment may further include generating domain models based on the extracted business concepts. The embodiment may also include clustering the generated domain models into specific domains.

Abstract: An ultrasonic image processing system comprising: a data receiving module for acquiring multiple sets of three-dimensional image data corresponding to a single target tissue; an image analyzing module for dividing, on the basis of any one group of the multiple sets of three-dimensional image data, a target region to obtain a three-dimensional volume structure boundary of the target region, and a safety boundary generated by outward expansion or inward contraction along the three-dimensional volume structure boundary; an image mapping module for establishing a spatial mapping relation between the multiple sets of three-dimensional image data, and according to the spatial mapping relation, mapping the three-dimensional volume structure boundary and the safety boundary of the target region to the other sets of three-dimensional image data; and an image marking module for marking, in a displayed image, corresponding three-dimensional volume structure boundaries and safety boundaries of the target region in the mu

Abstract: The present invention discloses a sealing assembly for a triple-eccentric metal hard sealing butterfly valve, comprising at least two metal sheets and at least two sealing rings made of a non-metal auxiliary material, wherein an annular groove is provided on one surface of each metal sheet, and each sealing ring is embedded in the corresponding annular groove. The present invention also discloses a sealing structure comprising the sealing assembly and a triple-eccentric hard sealing butterfly valve comprising the sealing structure. The present invention improves the reliability of the sealing and is completely sealed by the metal. The application of the sealing assembly according to the present invention enables the application range of the triple-eccentric butterfly valve to be extended to any medium, having high temperature, low temperature and severe working conditions, and extending the service life of the triple-eccentric sealing significantly.

Abstract: An approach is provided in which an information handling system determines a current focus of a user composing a document. The current focus is based on a set of text in proximity to a current cursor location in the document. Next, the information handling system identifies a query based at least in part upon the current focus and queries a database using the identified query. In turn, the information handling system presents reference recommendations to the user that are generated from the query.

Abstract: The present invention is a system and method for template extraction based on source code similarity. The system receives source code and groups the class files into classes based on naming rules and inheritance hierarchy. Features are parsed for each class and encoded a float value. The classes are clustered based on similarities of the features. A similarity value is calculated for the classes in a cluster and potential candidate classes are selected based on the similarity value or inheritance hierarchy. A feature subset is selected across all candidate classes and differences in the features in the subset are determined. The features are then decoded and the differences are parameterized to generate a template. A variable definition file is created to cross-reference features and variables. Source code can then be generated using the template and the variable definition file.

Abstract: The safety needle assembly comprises a housing including a proximal end and a distal end and defining an interior space. A barrel is rotatably received within the interior space of the housing. A needle hub is received within the proximal end of the housing. A needle, including a sharp distal tip, extends distally from the needle hub, through the barrel, and through the distal end of the housing. A safety shield defining a lumen is received within the interior space of the housing. The safety shield extends distally from the housing through the distal end of the housing. The needle extends through the lumen of the safety shield with the sharp distal tip exposed from the safety shield. A biasing member is received within the barrel and extends between the needle hub and the safety shield.

Abstract: The present invention is a system and method for template extraction based on source code similarity. The system receives source code and groups the class files into classes based on naming rules and inheritance hierarchy. Features are parsed for each class and encoded a float value. The classes are clustered based on similarities of the features. A similarity value is calculated for the classes in a cluster and potential candidate classes are selected based on the similarity value or inheritance hierarchy. A feature subset is selected across all candidate classes and differences in the features in the subset are determined. The features are then decoded and the differences are parameterized to generate a template. A variable definition file is created to cross-reference features and variables. Source code can then be generated using the template and the variable definition file.