Abstract: Examples of methods for thermal image generation are described. In some examples, a method may include determining a score map based on first features from a model, a simulated thermal image at a first resolution, and second features of the simulated thermal image. In some examples, the method may include generating a thermal image at a second resolution based on the score map, the first features, and the second features, where the second resolution may be greater than the first resolution.

Abstract: Described herein are compounds that are inhibitors of p21-activated kinases (PAKS). In particular, the compounds described herein are demonstrated to be selective PAK4 inhibitors. The compounds described herein are also demonstrated to reduce the expression of key immune checkpoint molecules, such as PD-1 and CHEK2. Also described herein are pharmaceutical compositions containing such compounds, methods for using such compounds in the treatment of cancers, more specifically, the treatment of pancreatic and lung cancers, and to related uses.

Abstract: Examples of methods are described. In some examples, a method includes generating, using a first branch of a machine learning model, a first agent map based on a layer image. In some examples, the method includes generating, using a second branch of the machine learning model, a second agent map. In some examples, the first agent map and the second agent map indicate printing locations for different agents.

Abstract: Examples of methods for point cloud alignment are described herein. In some examples, a method includes orienting a model point cloud or a scanned point cloud based on a set of initial orientations. In some examples, the method includes determining, using a first portion of a machine learning model, first features of the model point cloud and second features of the scanned point cloud. In some examples, the method includes determining, using a second portion of the machine learning model, correspondence scores between the first features and the second features based on the set of initial orientations. In some examples, the method includes globally aligning the model point cloud and the scanned point cloud based on the correspondence scores.

Abstract: An example device includes: a memory storing instructions; and a processor connected to the memory. The instructions are to cause the processor to: receive predetermined locations of a fluidic input location and fluidic output locations at a three-dimensional (3D) object model; generate respective paths between the fluidic input and each of the fluidic outputs via associated portions of the 3D object model; replace the respective paths with respective hollow connectors that have respective fluidic resistance selected such that each of the fluidic outputs have a predetermined flow rate from the fluidic input to the fluid outputs; and store, at the memory, data indicative of locations and dimensions of the respective hollow connectors, relative to the fluidic input and the fluidic outputs, the data for use by a three-dimensional printer to print a part that includes the fluidic input, the fluidic outputs and the respective hollow connectors.

Abstract: Examples of methods are described herein. In some examples, a method includes determining a quantity of inner voxels in a canonical direction from each surface voxel of a set of surface voxels of a three-dimensional (3D) object model. In some examples, the method includes generating an encoded representation of the 3D object model, the encoded representation indicating a location of each surface voxel and the quantity of inner voxels for each surface voxel.

Abstract: Examples of methods are described. In some examples, a method may include printing a first solid material phase region. In some examples, the method may include printing a second solid material phase region distanced from the first solid material phase region. In some examples, the method may include printing a plurality of distanced beams, each having a thickness that is not more than one millimeter, to form a weak material phase region between the first solid material phase region and the second solid material phase region. In some examples, the weak material phase region has a volumetric density less than one.

Abstract: A disk-drive suspension includes a load beam, a flexure laid on top of the load beam, a first terminal provided on the flexure, and a first bump arranged on a top surface of the first terminal. The first terminal includes a narrow part having a first width in a first direction and including a center of the first terminal, and a wide part having a second width in the first direction greater than the first width. The wide part and the narrow part are arranged in a second direction intersecting the first direction. The first bump has, at the center, a first height from a bottom surface of the first terminal. The first height is greater than the first width.

Abstract: Examples of a thermal behavior prediction method are described herein. In some examples of the thermal behavior prediction method, a predicted heat map of a layer corresponding to a three-dimensional (3D) model is computed using at least one neural network. The predicted heat map is computed based on a contone map corresponding to the 3D model.

Abstract: Examples of methods for monitoring additive manufacturing by an electronic device are described herein. In some examples, a predicted thermal image is calculated for a layer. In some examples, a captured thermal image is obtained for the layer. In some examples, a risk score is calculated for the layer based on the predicted thermal image and the captured thermal image. In some examples, a mitigation operation is performed in response to determining that the risk score is outside of a threshold range.

Abstract: Examples of methods for determining displacement maps are described herein. In some examples of the methods, a method includes determining a displacement map for a three-dimensional (3D) object model based on a compensated point cloud. In some examples, the method includes assembling the displacement map on the 3D object model for 3D manufacturing.

Abstract: Examples of methods for predicting object deformations are described herein. In some examples, a method includes predicting a point cloud. In some examples, the predicted point cloud indicates a predicted object deformation. In some examples, the point cloud may be predicted using a machine learning model and edges determined from an input point cloud.

Abstract: Examples of methods are described. In some examples, a method includes determining, using a variational autoencoder model, a latent space representation. In some examples, the latent space representation is of object model data. In some examples, the method includes predicting manufacturing powder degradation. In some examples, predicting the manufacturing powder degradation is based on the latent space representation.

Abstract: Examples of methods for model prediction are described herein. In some examples, a method includes predicting a compensated model. In some examples, the compensated model is predicted based on a three-dimensional (3D) object model. In some examples, a method includes predicting a deformed model. In some examples, the deformed mode is predicted based on the compensated model.

Abstract: An image processing system acquires a first three-dimensional model of an object. The image processing system includes a processor and storage medium encoded with instructions executable by the processor. The instructions include instructions to define a material potential function for a material. The material potential function is a function of a three-dimensional origin point of the material in the object, a three-dimensional propagation limit of the material in the object, and a three-dimensional propagation function of the material in the object. The instructions include instructions to generate a second three-dimensional model of the object based in part on the material potential function and the first model. The second model illustrates propagation of the material through an interior volume of the object at a unit level. A controller generates control signals based on the second model, and a fluid ejection engine performs an additive manufacturing process based on the control signals.

Abstract: Examples of methods for object deformation determination are described herein. In some examples, a method includes aligning a first bounding box of a three-dimensional (3D) object model with a second bounding box of a scan. In some examples, the method includes determining a deformation between the 3D object model and the scan based on the alignment.

Abstract: A fan and an electronic device are provided. The fan includes a hub, an outer frame surrounding the hub, and a plurality of blades connected between the hub and the outer frame. The outer frame includes a first side facing an air inlet of the fan, a second side facing an air outlet of the fan, and an inner wall between the first side and the second side. Each of the plurality of blades includes a first end connected to the hub and a second end connected to the outer frame. The second end includes a first region and a second region, the second region is connected to the inner wall. The first region extends from the second region and is disposed above the first side. A first notch is defined among the first regions of two adjacent blades and the first side.

Abstract: Examples of methods for registering objects are described herein. In some examples, a method includes determining a set of overlap scores based on a set of orientations between a first bounding box of a three-dimensional (3D) object model and a second bounding box of a 3D scan of an object. In some examples, the method includes registering the 3D scan with the 3D object model based on the set of overlap scores.

Abstract: The present invention relates to phenyl amino pyrimidine compounds which are inhibitors of protein kinases including JAK kinases. In particular the compounds are selective for JAK2 kinases. The kinase inhibitors can be used in the treatment of kinase associated diseases such as immunological and inflammatory diseases including organ transplants; hyperproliferative diseases including cancer and myeloproliferative diseases; viral diseases; metabolic diseases; and vascular diseases.