Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

4208results about How to "Easy to train" patented technology

Feedback loop for spam prevention

The subject invention provides for a feedback loop system and method that facilitate classifying items in connection with spam prevention in server and / or client-based architectures. The invention makes uses of a machine-learning approach as applied to spam filters, and in particular, randomly samples incoming email messages so that examples of both legitimate and junk / spam mail are obtained to generate sets of training data. Users which are identified as spam-fighters are asked to vote on whether a selection of their incoming email messages is individually either legitimate mail or junk mail. A database stores the properties for each mail and voting transaction such as user information, message properties and content summary, and polling results for each message to generate training data for machine learning systems. The machine learning systems facilitate creating improved spam filter(s) that are trained to recognize both legitimate mail and spam mail and to distinguish between them.
Owner:MICROSOFT TECH LICENSING LLC

Unsupervised domain-adaptive brain tumor semantic segmentation method based on deep adversarial learning

The invention provides an unsupervised domain-adaptive brain tumor semantic segmentation method based on deep adversarial learning. The method comprises the steps of deep coding-decoding full-convolution network segmentation system model setup, domain discriminator network model setup, segmentation system pre-training and parameter optimization, adversarial training and target domain feature extractor parameter optimization and target domain MRI brain tumor automatic semantic segmentation. According to the method, high-level semantic features and low-level detailed features are utilized to jointly predict pixel tags by the adoption of a deep coding-decoding full-convolution network modeling segmentation system, a domain discriminator network is adopted to guide a segmentation model to learn domain-invariable features and a strong generalization segmentation function through adversarial learning, a data distribution difference between a source domain and a target domain is minimized indirectly, and a learned segmentation system has the same segmentation precision in the target domain as in the source domain. Therefore, the cross-domain generalization performance of the MRI brain tumor full-automatic semantic segmentation method is improved, and unsupervised cross-domain adaptive MRI brain tumor precise segmentation is realized.
Owner:CHONGQING UNIV OF TECH

Voiceprint identification method based on Gauss mixing model and system thereof

The invention provides a voiceprint identification method based on a Gauss mixing model and a system thereof. The method comprises the following steps: voice signal acquisition; voice signal pretreatment; voice signal characteristic parameter extraction: employing a Mel Frequency Cepstrum Coefficient (MFCC), wherein an order number of the MFCC usually is 12-16; model training: employing an EM algorithm to train a Gauss mixing model (GMM) for a voice signal characteristic parameter of a speaker, wherein a k-means algorithm is selected as a parameter initialization method of the model; voiceprint identification: comparing a collected voice signal characteristic parameter to be identified with an established speaker voice model, carrying out determination according to a maximum posterior probability method, and if a corresponding speaker model enables a speaker voice characteristic vector X to be identified to has maximum posterior probability, identifying the speaker. According to the method, the Gauss mixing model based on probability statistics is employed, characteristic distribution of the speaker in characteristic space can be reflected well, a probability density function is common, a parameter in the model is easy to estimate and train, and the method has good identification performance and anti-noise capability.
Owner:LIAONING UNIVERSITY OF TECHNOLOGY

Capsulectomy device and method therefore

InactiveUS6165190AEasy to useCost-effective in manufacture and operation and maintenanceEye surgerySurgeryHand heldEngineering
A surgical instrument for ophthalmic surgery, allowing the user to form a uniform circular incision of the anterior lens capsule of an eyeball, as part of an anterior capsulotomy. The capsulectomy device of the preferred embodiment of the present invention has first and second ends, with a rotor emanating from one end, the rotor having a cutting blade or bin situated at the distal end of the rotor, the rotor rotating in pivotal fashion up to 360 degrees, while simultaneously reciprocating the cutting blade at a consistent stroke so as to provide optimal incision edge and depth of the anterior lens capsule of the eyeball. The device is hand held and relatively compact, having provided therein a motor and gear reduction / transmission system for driving the rotor and providing the reciprocating action to the cutting blade or pin. The device further includes a power supply, which is illustrated as a separate component fed to the device via wire, as well as controls for initiating power, as well as varying the speed of the motor. Unlike the prior art systems, which generally have relied upon the skill of the surgeon to perform the radial incision by hand, the present system provides a relatively easy and uniform system for performing the radial incision which is believed to be safer, more uniform, and less time consuming than prior techniques.
Owner:NGUYEN NHAN

Experiential digitalized multi-screen seamless cross-media interactive opening teaching laboratory

ActiveCN104575142ASupports real-time processingRealize analysisElectrical appliancesPhysical spaceVirtual space
An experiential digitalized multi-screen seamless cross-media interactive opening teaching laboratory is integrated in testing, researching and analyzing. Experiment and data analysis are performed in a real teaching environment; under support of the multi-screen interactive technology, the laboratory comprises a laboratory functional partition, an operation support system, a data working system, an experiment information acquisition system and an audio and video input and output device; a screen jilting function among multiple mobile terminals is realized; the data working system comprises a server, a database, education resource cloud, a U-teaching system, a learning analysis and evaluation system, a mobile device, a cross-screen management module, a recording and broadcasting system and an Internet; learning space for cross-media interactive learning is provided, technologies of holographic imaging, multi-screen interaction, learning analysis and the like are integrated, and seamless fusion of the physical space and the virtual space is realized; seamless fusion of supporting technologies from formal learning to informal learning, multiple learning modes, cross-terminal, cross-media and the like is realized, and good learning experience is provided for learners.
Owner:SHANGHAI OPEN UNIVERSITY

Cascaded residual error neural network-based image denoising method

The invention discloses a cascaded residual error neural network-based image denoising method. The method comprises the following steps of building a cascaded residual error neural network model, wherein the cascaded residual error neural network model is formed by connecting a plurality of residual error units in series, and each residual error unit comprises a plurality of convolutional layers, active layers after the convolutional layers and unit jump connection units; selecting a training set, and setting training parameters of the cascaded residual error neural network model; training the cascaded residual error neural network model by taking a minimized loss function as a target according to the cascaded residual error neural network model and the training parameters of the cascaded residual error neural network model to form an image denoising neural network model; and inputting a to-be-processed image to the image denoising neural network model, and outputting a denoised image. According to the cascaded residual error neural network-based image denoising method disclosed by the invention, the learning ability of the neural network is greatly enhanced, accurate mapping from noisy images to clean images is established, and real-time denoising can be realized.
Owner:SHENZHEN INST OF FUTURE MEDIA TECH +1

Image denoising method based on generative adversarial networks

The invention provides an image denoising method based on generative adversarial networks, and belongs to the technical field of computer vision. The method comprises the following steps: (1) designing a neural network for estimation for noise intensity of an image containing noises; (2) using image blocks in an image library to add noises of the intensity according to the estimated noise intensity to use the same as samples of training the networks; (3) in network training, designing a new generation network and discrimination network, and adopting a form of fixing the generation network to train the discrimination network and fixing discrimination network parameters to train the generation network to enable the networks to carry out adversarial training; and (4) using the trained generation network as a denoising network, and selecting a network parameter according to a result, which is obtained by the noise recognition network, to denoise the image containing the noises. The methodhas the effects and the advantages that a visual effect of the denoised image is improved without the need for manual intervention for adjusting the parameter, and texture details of the image can bebetter restored.
Owner:DALIAN UNIV OF TECH

Human body gesture identification method based on depth convolution neural network

The invention discloses a human body gesture identification method based on a depth convolution neural network, belongs to the technical filed of mode identification and information processing, relates to behavior identification tasks in the aspect of computer vision, and in particular relates to a human body gesture estimation system research and implementation scheme based on the depth convolution neural network. The neural network comprises independent output layers and independent loss functions, wherein the independent output layers and the independent loss functions are designed for positioning human body joints. ILPN consists of an input layer, seven hidden layers and two independent output layers. The hidden layers from the first to the sixth are convolution layers, and are used for feature extraction. The seventh hidden layer (fc7) is a full connection layer. The output layers consist of two independent parts of fc8-x and fc8-y. The fc8-x is used for predicting the x coordinate of a joint. The fc8-y is used for predicting the y coordinate of the joint. When model training is carried out, each output is provided with an independent softmax loss function to guide the learning of a model. The human body gesture identification method has the advantages of simple and fast training, small computation amount and high accuracy.
Owner:UNIV OF ELECTRONICS SCI & TECH OF CHINA

Color-Coded Prosthetic Valve System and Methods for Using the Same

ActiveUS20120046738A1Facilitate trainingCorrectly identifyHeart valvesProsthesisBioprosthetic valve
A color-coded bioprosthetic valve system having a valve with an annular sewing ring, and a valve holder system with a holder sutured to the ring of the valve, a post operatively connected to the holder, and an adapter sutured to the post and having a color associated with the valve model and / or size. For example, the adapter may be blue to indicate that the valve of the system is a mitral valve of a particular type and / or size. The system may also include a flex handle that is configured to engage with the adapter. The handle has a color associated with the adapter such that a user is able to visually determine that the handle color matches the valve model. For example, the handle may have a grip that is colored blue to match the blue color of the adapter. Accordingly, the color-coded system enables users to confirm easily that the correct accessories such as the sizer or flex handle are being used with the correct valve.
Owner:EDWARDS LIFESCIENCES CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products