32results about How to "Computationally" patented technology

Methods are disclosed for performing proper word alignment that satisfy constraints of coverage and transitive closure. Initially, a translation matrix which defines word association measures between source and target words of a corpus of bilingual translations of source and target sentences is computed. Subsequently, in a first method, the association measures in the translation matrix are factorized and orthogonalized to produce cepts for the source and target words, which resulting matrix factors may then be, optionally, multiplied to produce an alignment matrix. In a second method, the association measures in the translation matrix are thresholded, and then closed by transitivity, to produce an alignment matrix, which may then be, optionally, factorized to produce cepts. The resulting cepts or alignment matrices may then be used by any number of natural language applications for identifying words that are properly aligned.

A device for classifying of supraventricular tachyarrhythmia (SVT) from ventricular tachyarrhythmia (VT) comprising means for providing a template signal and a test signal originated from an electrogram, the template signal and the test signal comprising samples, means for transforming at least the test signal resulting in a representation of the test signal where the sample values of the signal take integers, means for determining a correlation between the template signal and the test signal and means for classifying of SVT from ventricular VT based on the correlation.

A spatiotemporal system and method for parking occupancy detection. The system can generally include suitable image acquisition, processing, transmission and data storage devices configured to carry out the method which includes generating and processing spatiotemporal images to detect the presence of an object in a region of interest, such as a vehicle in a parking stall.

The present invention relates to a speech procession systems comprising a frame handler unit (100) for dividing the incoming speech signal into frames and subframes of samples, a short-term analyzer (200) connected to the frame handler unit (100) for calculating short-term characteristics of the frames of the input speech signal, a short-term redundancy removing unit (250) connected to the short-term analyzer (200) for eliminating short-term characteristics of the frames of the input speech signal and creating noise shaped speech signal, a long-term analyzer (300) connected to the short-term redundancy removing unit (250) for calculating and predicting long-term characteristics of the noise shaped speech signal, a long-term redundancy removing unit (350) connected to the long-term analyzer (300) for eliminating long-term characteristics of the noise shaped speech signal or eliminating short-term and long-term characteristics of the frames of the speech input signal, and in such a way creating a target vector, an excitation pulse search unit (500) connected to the short-term analyzer (200) and the long-term redundancy removing unit (350) for generating sequences of pulses which are to simulate the target vector, wherein every pulse is of variable position, sign and amplitude. Furthermore, the present invention relates to a method of speech processing comprising the steps of dividing the incoming speech signal into frames and subframes, calculating short-term characteristics of the frames of the input speech signal, eliminating short-term characteristics of the frames of the input speech signal and creating noise shaped speech signal, calculating and predicting long-term characteristics of the noise shaped speech signal, eliminating long-term characteristics of the noise shaped speech signal or eliminating short-term and long-term characteristics of the frames of the speech input signal, and in such a way creating a target vector, and generating sequences of pulses of variable position, sign and amplitude which are to simulate the target vector by passing a synthesis filter.

An imaging device comprises a number of light sources, a camera, a processor and a platen. As an object is moved over the platen each of the light sources illuminates the platen sequentially, with the principal axis of illumination of each light source intersecting the plane of the platen at a different place. The camera captures a series of images of the object, each captured image corresponding to the illumination of the platen by a different light source. The processor then generates a composite image from the series of images that compensates for the reflection of light from the platen associated with the principal axis of illumination.

Methods, systems, and computer readable media are provided for identification of heart sound components in an audio signal of heart sounds. Time domain kurtosis and frequency domain kurtosis are used to distinguish peaks corresponding to the primary heart sounds, S₁ and S₂, from murmur peaks. Timing based error correction may also be used to verify that appropriate peaks corresponding to the primary heart sounds are identified.

A method of operating a wind turbine. The wind turbine is operated over an operating period in accordance with a control strategy. A sensor signal is received over the operating period from a sensor measuring an operational parameter of the turbine. A model is used to obtain a modelled fatigue value based on the sensor signal. The modelled fatigue value provides an estimate of fatigue loading applied to a component of the turbine over the operating period. The control strategy is modified based on the modelled fatigue value.

A timing-driven cloning method iteratively partitions sinks of the net into different sets of clusters and for each set computes a figure of merit for a cloned gate location which optimizes timing based on linear delay, that is, a delay proportional to the distance between the cloned gate location and the sinks. The set having the highest figure of merit is selected as the best solution. The original gate may also be moved to a timing-optimized location. The sinks are advantageously partitioned using boundaries of Voronoi polygons defined by a diamond region surrounding the original gate, or vice versa. The figure of merit may be for example worst slack, a sum of slacks at the sinks in the second cluster, or a linear combination of worst slack and sum of the slacks.

A visual image processing method is based on received spatial field information (302) from a spatial field sensor (116). A data store (804) is accessed, which contains a sensor map data structure (206) comprising a set of predefined regions (208) within a spatial field corresponding with the information received via the sensor input. Each predefined region is associated in the data structure with one or more of a set of stimuli (204) applicable to a biological visual system, and each stimulus corresponds with a visual percept (210). The spatial field information associated with each region is processed to generate stimulus control information which is applied to select, from within the sensor map data structure, stimuli from the set of stimuli for application to the biological visual system. Output stimulus signals (310) are generated, which are suitable for application to the biological visual system based upon the selected stimuli. Flexible mappings are thus provided between visual percepts, stimuli which may be applied (e.g. via a prosthetic implant) in order to generate the percepts, and associations between those stimuli and regions of the spatial field corresponding with the visual percepts.

A method for operating a navigation system of an ego vehicle includes: obtaining information about vehicles in a region proximate the ego vehicle; determining trajectories of the vehicles proximate the ego vehicle based on the obtained information; comparing the trajectories of the vehicles proximate the ego vehicle with a selected route path of the ego vehicle; and based on a determination that at least one vehicle proximate the ego vehicle was driving, is currently driving, or will be driving along the selected route pate, generating and outputting an instruction to a driver of the ego vehicle to follow the at least one vehicle.

A control system and a method for estimating a risk exposure of an automated driving system (ADS) of a vehicle. Obtaining an actuation capability of the vehicle, wherein the obtained actuation capability includes an uncertainty estimation for the actuation capability. Obtaining a location of free-space areas in the surrounding environment of the vehicle, wherein the obtained location of free-space areas comprises an uncertainty estimation for the estimated location of free-space areas. Forming a risk map of the surrounding environment of the vehicle based on the obtained actuation capability and the obtained location of free-space areas, wherein the risk map includes a risk parameter for each of a plurality of area segments included in the surrounding environment of the vehicle. Determining a total risk value of the ADS based on the risk parameters of a set of area segments intersected by at least one planned path of the ADS.

An image processing system for recognizing image features in three dimensional images, which can be medical images, uses a mask generator for generating masks that are used by a candidate searcher to search for candidate images in the three dimensional image. The candidate searcher applies the mask to a section of a foreground region of the image to determine the presence of a structure/object by counting the number of intersections between the mask and the section of the foreground region.

The present invention concerns a method of segmenting a media item comprising media elements. The method comprises: selecting a first seed media element for a first cluster of media elements, referred to hereinafter as a first adaptel; selecting a second seed media element, different from the first seed media element, for a second cluster of media elements, different from the media elements of the first adaptel, the second cluster being referred to hereinafter as a second adaptel; successively forming the first and second adaptels, starting from the first and second seed media elements, respectively, by allocating a first plurality of the media elements to the first adaptel, and then allocating a second plurality of the media elements to the second adaptel; and reallocating at least one media element of the first adaptel to the second adaptel if a dissimilarity measure between the at least one media element and the second adaptel is smaller than the dissimilarity measure between the at least one media element and the first adaptel. The second seed media element is selected from a set of the media elements neighboring the first adaptel.

An MR imaging method with an imaging workflow is provided. Within the scope of the MR imaging method, at least one breath-holding command is output to a patient. An MR imaging is performed with an MR imaging method that may be used with free breathing. A breathing movement of the patient is detected based on measured data acquired when performing the MR imaging method. A time relationship is determined between the breathing movement of the patient and the breath-holding command. The imaging workflow is modified as a function of the determined time relationship. A breathing monitoring device and a magnetic resonance imaging system are also provided.

In a method for motion estimation using adaptive patterns in a video sequence compression system, an initial search pattern located at a center of a search window in a block of a video frame is determined. A location of a minimum block distortion measure (BDM) is searched in the initial search pattern. A horizontal search pattern for functioning on the search window is determined in the horizontal direction to search a location of a minimum BDM in the horizontal search pattern. A vertical search pattern for operating on the search window is determined in the vertical direction to search a location of a minimum BDM in the vertical search pattern. The location of the minimum BDM in each pattern is designated to be a motion vector. A search pattern to be used in a subsequent searching stage is determined based on the location of the minimum BDM in each pattern.