272 results about "Computational Technique" patented technology

Arrangements involving portable devices (e.g., smartphones and tablet computers) are disclosed. One arrangement enables a content creator to select software with which that creator's content should be rendered—assuring continuity between artistic intention and delivery. Another utilizes a device camera to identify nearby subjects, and take actions based thereon. Others rely on near field chip (RFID) identification of objects, or on identification of audio streams (e.g., music, voice). Some technologies concern improvements to the user interfaces associated with such devices. Others involve use of these devices in connection with shopping, text entry, sign language interpretation, and vision-based discovery. Still other improvements are architectural in nature, e.g., relating to evidence-based state machines, and blackboard systems. Yet other technologies concern use of linked data in portable devices—some of which exploit GPU capabilities. Still other technologies concern computational photography. A great variety of other features and arrangements are also detailed.

A computational technique to construct a 3-D valve leaflet geometry. The invention pertains to methodology to construct a 3-D heart valve leaflet geometry using finite element analysis (FEA) to simulate the manual assembly process or, in other words, provide a virtual assembly process as an input to a subsequent simulated valve testing step. The simulated valves may be subjected to simulated cyclic valve opening and closings and the stress levels induced therein monitored. Simulated valve designs with lower principal stresses can then be selected for prototyping. Proposed valves can be subjected to cyclic fatigue stress testing under simulated physiologic conditions to study valve durability.

The objective of the invention is a bi-level method for modeling geometric tolerances compatible with the ANSI/ASME tolerance standard. At the local level, the model represents each tolerance-zone for a plane or an axis (line) as a tolerance map, and it includes the computational techniques that relate interdependencies between these regions and subregions within them. The model includes formulations for variations in size, form, orientation, position, and runout, and combinations of these, because all of these variations can be modeled using points, lines, and planes. Since variations in simple profiles that are formed from lines and circular arcs also can be described by such combinations, they too are includable in the formulation. The primary method is to overlay the geometry of tolerance-zones onto some traditional modes for representing planes, lines, and points. At the global level, the model inter-relates all frames of reference on a part or an assembly.

The invention involves generating and presenting, typically electronically, a number of design alternatives to persons who are participating in the design, selection, or market research exercise. The participants (referred to as “selectors”) transmit data indicative of their preferences among or between the presented design alternatives, and that data is used to derive a new generation of design alternatives or proposals. The new designs are generated through the use of a computer program exploiting a genetic or evolutionary computational technique. The process is repeated, typically for many iterations or cycles.

A method and system for computer aided design (CAD) is disclosed for designing geometric objects. The present invention interpolates and/or blends between such geometric objects sufficiently fast so that real time deformation of such objects occurs while deformation data is being input. Thus, a user designing with the present invention obtains immediate feedback to input modifications without separately entering a command for performing such deformations. The present invention utilizes novel computational techniques for blending between geometric objects, wherein weighted sums of points on the geometric objects are used in deriving a new blended geometric object. The present invention is particularly useful for designing the shape of surfaces. Thus, the present invention is applicable to various design domains such as the design of, e.g., bottles, vehicles, and watercraft. Additionally, the present invention provides for efficient animation via repeatedly modifying surfaces of an animated object such as a representation of a face.

The present invention discloses methods and apparatus for developing, analyzing, investigating, and advising healthcare and well-being related decisions. In particular, the present invention relates to the architecture of systems in either stand-alone or distributed/collaborative/pervasive settings, the components of the systems and their underlying processes and couplings, the computational techniques built into the methods, input data sources integrated into and output results produced and distributed by the systems, as well as the apparatus for carrying out the corresponding user interaction, data access and collection, data integration and processing, data-driven inferences and simulation, intelligent computations, decision analytics, and decision support to generating solutions to various healthcare analytics and decision-making problems. This invention also relates to two working illustrations of the methods and apparatus that present the embodiment illustrations of the present invention.

Systems and method of the present disclosure are directed to a strategy assessment tool that facilitates developing a financial strategy, testing the financial strategy on historical data, and applying the strategy in real time to activate trades. The strategy assessment tool can retrieve, obtain, or otherwise identify financial data related financial instruments. The tool can store the financial data in a database or data structure such that the tool can efficient analyze the data using one or more financial strategies running on multiple threads of a GPU.

The invention provides a multi-screen parallel massive information display system. An integral splicing wall is divided by the system with four screens as a unit, each four screens are controlled by an accessory node controller, and the accessory node controllers are connected with a master node controller through a high-speed internet. Under unified allocation and organization of the master node controller, external massive data (including analog video signals, digital signals of a computer and the like) are transmitted to the high-speed internet after quantization and digital processing and finally transmitted to the accessory node controllers, and images are parallelly rendered to a video memory by the accessory node controllers and displayed on a high-definition splicing display screen. The system comprehensively applies the CPU (central processing unit)+CPU parallel processing technology, the cloud computing technology and the high-speed network technology, so that the massive data which cannot be processed and displayed by a traditional system are quickly displayed in real time.

A system is disclosed in which human genomes are stored in databases or in a cloud based computer system, which is secure and private and then downloaded to personal devices for possible peer-to-peer interactions for health care applications, as well as for social and other applications. The use of the system is directed to fully sequenced genomes and includes protocols that are constructed to mimic in vitro biological tests to conduct genomic analysis instead of generic computational techniques, which tend to be impractical as they require performance of online computation over the entire genome. Three specific examples of protocols or techniques for privacy-preserving testing on fully sequenced genomes included are: 1) privacy-preserving genetic paternity testing, 2) privacy-preserving personalized medicine testing, and 3) privacy-preserving genetic compatibility testing.

The techniques and structures described herein generally relate to sampling from an available probability distribution to create a desirable probability distribution. This resultant distribution can be used for computing values used in computational techniques including: Importance Sampling and Markov chain Monte Carlo systems.

The invention relates to an image data expansion method for deep learning model training and learning, and belongs to the technical field of computer medical image calculation. The method comprises the following steps: firstly, judging a data type, and identifying CT or MRI image data; For the image data, judging whether an ROI (Region Of Interest) is defined or not, and selecting a correspondingmethod to complete the construction of an image data set in combination with the size of a tumor region; Training the image data set by adopting a basic image transformation method to obtain a preliminary training data set; And finally, carrying out data expansion on the preliminary training data set, carrying out deep training by adopting a network model, and finally, carrying out probability prediction. Based on artificial intelligence deep learning, a series of data expansion methods are applied to learning of deep model training in the field of medical image processing, the influence of medical image data heterogeneity on abnormal data is solved, computer-aided diagnosis is facilitated, and the diagnosis efficiency and accuracy are improved.

The invention discloses an imaging medical information sharing system based on an embedded type operation system and a cloud platform. The imaging medical information sharing system is characterized by comprising a medical imaging examination device, an information collection device, a printer and the cloud platform; the medical imaging examination device transmits medical imaging examination information to the printer through the information collection device; the information collection device is used for collecting medical imaging examination information from a port of the printer and uploads the information to the cloud platform; the information collection device comprises a registering module, a management module, a checklist obtaining module, a checklist applying module, an information downloading module, an authorization configuration module and a cloud platform association storage module. The system reads data of a general printing port and carries out transmission, storage, analysis and management through the cloud computing technology, and classified filing management, multifunctional retrieval analysis and large-range barrier-free data sharing of mass medical information can be achieved.

The invention discloses an image high dynamic range reconstruction method based on deep learning, and belongs to the field of computational photography and digital image processing. A mapping networkfrom a single LDR image to an HDR image is established by adopting a method based on deep learning. The method comprises the steps of generating LDR training data, HDR sample tags with aligned brightness units and mask images of high-brightness areas sequentially from a collected HDR data set; and then constructing and training a neural network to obtain a network model with an LDR-to-HDR mappingrelationship; and finally, directly inputting the LDR image into the network model by using the trained generative network model, thereby outputting the reconstructed HDR image. According to the method, the dynamic range of a real scene can be effectively reconstructed from a single common digital image, and the method can be used for HDR simulation effect display of the common digital image or providing a more realistic rendering effect for an image-based lighting technology.

The invention discloses a high-quality reconstruction method of a spectral imaging system based on a convolutional neural network, and belongs to the field of computational photography. The method isapplied to a snapshot spectral imaging system based on a coded aperture, spatial correlation and spectral correlation between images are considered in the reconstruction process of a hyperspectral image, residual error learning is used for accelerating the training speed and the convergence rate of a network, and a GPU is used for completing optimization solving of the whole network. Network parameters are updated by using a random gradient descent method; and block-by-block processing is performed to complete reconstruction of the hyperspectral image. According to the method, hyperspectral image reconstruction of the CASSI spectral imaging system can be completed in a high-quality mode, it is guaranteed that a reconstruction result has high spatial resolution and high spectral fidelity, meanwhile, the efficiency of hyperspectral image reconstruction is greatly improved, and the application range of hyperspectral images is expanded. The method can be applied to the fields of geologicalexploration, agricultural production, biomedicine and the like.

The invention discloses a power transformation equipment typical visual defect detection system and method based on edge cloud cooperation, and relates to the technical field of edge computing and cloud computing. The system comprises an inspection robot, a power transformation equipment image acquisition device, an edge computing platform, a cloud server platform, a communication device, an imagedata preprocessing module, a power transformation equipment typical visual defect detection module and a typical visual defect image data management module. The method comprises the steps of S1, acquiring power transformation equipment image data by the power transformation equipment image acquisition device and sending the power transformation equipment image data to an edge computing platform;through the inspection robot, the power transformation equipment image acquisition device, the edge computing platform, the cloud server platform, the communication device, the image data preprocessing module, the power transformation equipment typical visual defect detection module, the typical visual defect image data management module and the like, high power transformation equipment typical visual defect detection working efficiency is realized.

The invention discloses a reconstruction method of a snapshot spectral imaging system based on tensor low-rank constraint, and belongs to the field of computational photography. The method is appliedto two snapshot spectral imaging systems, namely, a coded aperture snapshot spectral imaging system and a dual-camera spectral system based on a panchromatic camera. The reconstruction method comprises the steps of firstly, constructing a three-dimensional tensor by using the non-local similarity of a hyperspectral image, then mining structural characteristics of the three-dimensional tensor by using a dimension-discriminative low-rank tensor regularization (DLTR) model, wherein the structural characteristics include the spatial self-similarity, the spectral correlation and the space-spectrumjoint correlation; and finally, alternately updating and iteratively solving so as to complete the high-precision hyperspectral image reconstruction. According to the invention, the high-dimensional physical characteristics of the hyperspectral image can be better transmitted, the internal structural characteristics of the hyperspectral image can be better mined, the reconstruction quality of thesnapshot spectral imaging system is greatly improved, and the method has the advantage of high reconstruction precision.

The invention discloses a high-quality imaging method of a spectral imaging system based on a convolutional neural network, and belongs to the field of computational photography. According to the invention, the hyperspectral image imaging process and the reconstruction process are considered together; in the reconstruction process, the spatial correlation and the spectral correlation between images are respectively considered, the residual error learning is used to accelerate the training speed and convergence speed of the network, the coding network is optimized while the network is reconstructed, and a GPU is used to complete the optimization solution of the whole network. A cuDNN library is used to accelerate the operation speed of the network. The method comprises updating network parameters by using a random gradient descent method; and performing block-by-block processing to complete reconstruction of the hyperspectral image. According to the method, the hyperspectral image reconstruction of the CASI spectral imaging system can be completed with high quality, the high spatial resolution and high spectral fidelity of a reconstruction result are ensured, meanwhile, the efficiency of hyperspectral image reconstruction is improved, and the application range of hyperspectral images is expanded. The method can be used in the fields of manned spaceflight, geological survey, agricultural production, biomedicine and the like.

The invention discloses a BIM-based concrete dam monitoring data intelligent management and real-time evaluation system, which comprises a database module, a building information module, a real-time evaluation module and a Web display platform, wherein the database module is used for collecting monitoring data and carrying out preliminary processing; the building information module is used for storing parameterized models of dam body terrain, important components and monitoring instruments, and is associated with the database; the real-time evaluation module is combined with a dam safety monitoring theory, an artificial intelligence technology and a high-performance computing technology, so that dam automatic monitoring data can be analyzed in real time; and the Web display platform has anengineering model quick display function, a monitoring information browsing function and an evaluation result output function. The BIM-based concrete dam monitoring data intelligent management and real-time evaluation system can assist a worker to efficiently complete the analysis and evaluation work of monitoring data, improves the informatization management level of a dam, and has important social and economic benefits.

In an authorization system, access is defined by rules, roles and active rules. These definitions are preprocessed to form a bit array for each of a plurality of roles representing the rules that apply to that role. Once a bit array is calculated or generated for a given user based on that user's roles, the user bit array can be cached so that it need not be regenerated for each time the user requests access to resources. The rules used can either be role-based rules or active rules.

The invention relates to the cross field of remote-sensing classification and a computer distributed computation technology and particularly relates to a multispectral remote-sensing image classification processing method based on Hadoop. Different points lie in that the method includes the following steps: step a): firstly carrying out construction of a classification model on a single task sub-tracker; step b): then using a heartbeat message communication mechanism of a distributed framework to send the classification model to different task trackers and the task trackers starting concurrently carrying out an image block classification task after receiving a classification model file; step c) at last reducing classification results of different sub-blocks into one complete classification result map. The multispectral remote-sensing image classification processing method based on the Hadoop improves significantly the classification speed during classification of mass remote-sensing image data.