Abstract: Machine learning is used to train a network to estimate a three-dimensional (3D) body surface and body regions of a patient from surface images of the patient. The estimated 3D body surface of the patient is used to determine an isocenter of the patient. The estimated body regions are used to generate heatmaps representing visible body region boundaries and unseen body region boundaries of the patient. The estimation of 3D body surfaces, the determined patient isocenter, and the estimated body region boundaries may assist in planning a medical scan, including automatic patient positioning.

Abstract: There is a need for solutions that perform preprocessing and/or searching of documents with semantic intelligence. This need can be addressed by, for example, by performing pre-processing of each document of a plurality of documents to generate an indexed representation for the document by identifying sentences in the document; determining, for each n-gram of one or more n-grams associated with the document, one or more n-gram semantic scores based semantic proximity indicators for the n-gram; determining, based at least in part on each one or more n-gram semantic scores, one or more sentence semantic labels for each sentence in the document; and determining the indexed representation for the document based at least in part on the one or more sentence semantic labels for the document; performing the search query based each indexed representation associated with a document; and transmitting the result to a computing device associated with the search query.

Abstract: Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.

Abstract: In one aspect, there is provided a method for software testing. In one aspect, there is provided a method. The method may include executing a test script including at least one test instruction requiring an input at a user interface element displayed on a screen of a device under test; determining, based on a machine learning model, a candidate location on the screen of the device under test, the candidate location representing a candidate portion of the screen having the user interface element for the required input associated with the at least one test instruction; recognizing, based on optical character recognition, one or more characters in the determined candidate location; selecting, based on the recognized characters, the determined candidate location as the user interface element having the required input; and executing an inserted value at the determined candidate location to test a result of the test script execution.

Abstract: A rotating detonation combustor includes an annular combustion passage that is non-circular. Specifically, the present rotating detonation combustor includes a forward wall, a radially inner wall, and a radially outer wall. The radially inner wall and the radially outer wall extend downstream from the forward wall around a longitudinal axis of the combustor, thus defining an annular passage between the radially inner wall and the radially outer wall. An air inlet and a fuel inlet are disposed proximate to the forward wall and in fluid communication with the annular passage. The cross-section of the annular passage, which can be elliptical or polygonal, is defined by arcuate and/or straight sides of the inner and outer walls.

Abstract: The present disclosure is directed to a rotating detonation combustor that includes a forward wall, a radially inner wall, and a radially outer wall. The forward wall is disposed at an inlet end of the rotating detonation combustor. The radially inner wall surrounds a longitudinal axis and extends downstream from the forward wall to an outlet end of the rotating detonation combustor. The radially outer wall extends downstream from the forward wall to the outlet end and surrounds the radially inner wall to define at least one annular plenum between the radially inner wall and the radially outer wall. At least one partition is proximate to the inlet end and defines at least two mixing zones. A plurality of oxidizer inlets and a plurality of fuel inlets are disposed at the inlet end in fluid communication with the at least two mixing zones.

Abstract: The present disclosure involves systems, software, and computer implemented methods for automatically detecting user interface elements. One example method includes accessing master frame information for a user interface of an application. The master frame information includes first captured user interface information captured during a first execution of a scenario for the application. A subsequent execution of the scenario is performed, including capturing second captured user interface information. A determination is made that the subsequent execution of the scenario has not passed successfully, due to a non-functional error. A determination is made that the non-functional error is based on a failure to locate a user interface element specified in the master frame. A recovery strategy is performed, using the first captured user interface information and the second captured user interface information, to automatically locate the user interface element.

Abstract: A cloud network may include a distributed security switch (DSS). The DSS may be to receive configuration information from the hypervisor. The configuration information may include a set of access mode attributes and a security policy. The DSS may be to determine that a packet is to be directed from a source virtual machine to a target virtual machine. The DSS may be to identify an egress interface of the source virtual machine and an ingress interface of the target virtual machine. The egress interface may be associated with a first access mode attribute and the ingress interface being associated with a second access mode attribute. The DSS may be to selectively route the packet, using the shared memory, based on the first access mode attribute, the second access mode attribute, and the security policy.

Abstract: A computer process including receiving first patient bone data of a patient leg and foot in a first pose, the first pose comprising a position and orientation of the patient leg relative to the patient foot as defined in the first patient bone data. The computer process may further include receiving second patient bone data of the patient leg and foot in a second pose, the second pose comprising a position and orientation of the patient leg relative to the patient foot as defined in the second patient bone data. The computer process may further include generating a 3D bone model of the patient leg and foot. Finally, the computer process may include modifying the 3D bone model of the patient leg and foot such that the plurality of 3D bone models are reoriented into a third pose that matches the second pose.

Abstract: This disclosure relates to methods, non-transitory computer readable media, and systems that use a design-component-neural network to categorize a design component from an interface-design file as a platform widget corresponding to a particular computing platform. Having categorized the design component as a platform widget, in certain implementations, the disclosed systems compare and validate properties of the design component against user-interface guidelines for the particular computing platform. Upon determining that the design component does not comply with a user-interface guideline, the systems can provide and implement options to modify the design component to comply with the user-interface guideline.

Abstract: An exhaust system for a work vehicle includes a mixer that includes a nozzle configured to receive a first exhaust flow along a lateral axis through a plurality of openings in a peripheral wall of the nozzle. The nozzle also receives a diesel exhaust fluid along a longitudinal axis through a longitudinal inlet. Further, the nozzle is configured to mix the first exhaust flow and the diesel exhaust fluid to form an exhaust solution. In addition, the mixer includes a conduit configured to receive the exhaust solution along the longitudinal axis. Moreover, the conduit has an opening configured to receive a portion of the nozzle, and the conduit is configured to receive a second exhaust flow through a gap formed between the nozzle and the conduit at the opening, and the opening is positioned downstream of the plurality of openings.

Abstract: A method to secure an adjacent pair of turf members to a ground surface is provided. The method includes disposing a joint strip on the ground surface, disposing a first turf member on the joint strip, inserting a first set of primary fasteners through the first turf member, joint strip and ground surface, inserting a first set of secondary fasteners through the first turf member, joint strip and ground surface, disposing a second turf member on the joint strip to permit a side edge of the second turf member to align with the side edge of the first turf member along a seam line, inserting a second set of primary fasteners through the second turf member, joint strip and ground surface, and inserting a second set of secondary fasteners through the second turf member, joint strip and ground surface.

Abstract: Disclosed is a system and method for optimizing cooling efficiency of a data center is disclosed. The system may comprise an importing module, a Computational fluid dynamics (CFD) modeling module, a scope determination module, a metrics computation module, an identification module and a recommendation module. The importing module may be configured to import data associated to the data center. The CFD modeling module may be configured to leverage an external CFD Analysis tool in order to develop a CFD model of the data center. The scope determination module may be configured to determine a scope for optimizing the cooling efficiency of the data center. The metrics computation module may be configured to compute metrics based upon the data. The identification module may be configured to identify inefficiency and a cause producing the inefficiency. The recommendation module may be configured to facilitate optimizing cooling efficiency of the data center.

Abstract: Disclosed are a pedestrian detection method of a vehicle and a pedestrian detection system thereof. The pedestrian detection method includes transmitting and receiving a radar signal to and from an object in front of a vehicle to sense the object; capturing an exterior image of the vehicle; calculating a distance between the vehicle and the sensed object, detecting the sensed object in the captured image, and setting a region of interest (ROI) including the sensed object; and detecting a pedestrian in the ROI.

Abstract: Solid dispersions of lurasidone or a pharmaceutically acceptable salt thereof are described, as well as pharmaceutical formulations thereof, and methods for making such formulations. Preferably, the solid dispersions are prepared by hot-melt extrusion or spray-drying, and comprise lurasidone with a pharmaceutically acceptable carrier (e.g., hydroxypropyl methyl cellulose acetate succinate (HPMC-AS), polyvinyl pyrrolidine vinyl acetate (PVP/VA) copolymer, hydroxypropyl methylcellulose phthalate (HPMCP), or mixtures thereof). The pharmaceutical composition may be orally administered to a patient in either the fed or fasted state, with a decrease or elimination of the food effect. Preferably, following oral administration of the pharmaceutical compositions, there is no substantial difference in the pharmacokinetic parameters (e.g., Tmax, Cmax, AUC0-t and/or AUC0-infinity) of lurasidone, regardless of whether the pharmaceutical compositions are administered to a subject in the fed or fasted state.

Abstract: One illustrative MPT device disclosed herein includes an active region and an inactive region, isolation material positioned between the active region and the inactive region, the isolation material electrically isolating the active region from the inactive region, and an FG MTP cell formed in the active region. In this example, the FG MTP cell includes a floating gate, wherein first, second and third portions of the floating gate are positioned above the active region, the inactive region and the isolation material, respectively, and a control gate positioned above at least a portion of the inactive region, wherein the control gate is positioned above an upper surface and adjacent opposing sidewall surfaces of at least a part of the second portion of the floating gate.

Abstract: Techniques are disclosed for address manipulation using indices and tags. A first index is generated from bits of a processor program counter, where the first index is used to access a branch predictor bimodal table. A first branch prediction is provided from the bimodal table, based on the first index. The first branch prediction is matched against N tables, where the tables contain prior branch histories, and where: the branch history in table T(N) is of greater length than the branch history of table T(N?1), and the branch history in table T(N?1) is of greater length than the branch history of table T(N?2). A processor address is manipulated using a greatest length of hits of branch prediction matches from the N tables, based on one or more hits occurring. The branch predictor address is manipulated using the first branch prediction from the bimodal table, based on zero hits occurring.

Abstract: Solid dispersions of lurasidone or a pharmaceutically acceptable salt thereof are described, as well as pharmaceutical formulations thereof, and methods for making such formulations. Preferably, the solid dispersions are prepared by hot-melt extrusion or spray-drying, and comprise lurasidone with a pharmaceutically acceptable carrier (e.g., hydroxypropyl methyl cellulose acetate succinate (HPMC-AS), polyvinyl pyrrolidine vinyl acetate (PVP/VA) copolymer, hydroxypropyl methylcellulose phthalate (HPMCP), or mixtures thereof). The pharmaceutical composition may be orally administered to a patient in either the fed or fasted state, with a decrease or elimination of the food effect. Preferably, following oral administration of the pharmaceutical compositions, there is no substantial difference in the pharmacokinetic parameters (e.g., Tmax, Cmax, AUC0-t and/or AUC0-infinity) of lurasidone, regardless of whether the pharmaceutical compositions are administered to a subject in the fed or fasted state.

Abstract: An apparatus is provided which comprises: a first circuitry to provide an estimate of a distance of a user from the apparatus; and a second circuitry to select a display resolution for displaying on a display panel of the apparatus, based at least in part on the estimate of the distance of the user from the apparatus.

Abstract: A method and apparatus for operating a plasma processing chamber includes performing a plasma process at a process pressure and a pressure power to generate a plasma. A first ramping-down stage starts in which the process power and the process pressure are ramped down substantially simultaneously to an intermediate power level and an intermediate pressure level, respectively. The intermediate power level and intermediate pressure level are preselected so as to raise a plasma sheath boundary above a threshold height from a surface of a substrate. A purge gas is flowed from a showerhead assembly at a sufficiently high rate to sweep away contaminant particles trapped in the plasma such that one or more contaminant particles move outwardly of an edge of the substrate. A second ramping-down stage starts where the intermediate power level and the intermediate pressure level decline to a zero level and a base pressure, respectively.