Patents Issued in November 17, 2016
-
Publication number: 20160335499Abstract: A solution is provided for temporally segmenting a video based on analysis of entities identified in the video frames of the video. The video is decoded into multiple video frames and multiple video frames are selected for annotation. The annotation process identifies entities present in a sample video frame and each identified entity has a timestamp and confidence score indicating the likelihood that the entity is accurately identified. For each identified entity, a time series comprising of timestamps and corresponding confidence scores is generated and smoothed to reduce annotation noise. One or more segments containing an entity over the length of the video are obtained by detecting boundaries of the segments in the time series of the entity. From the individual temporal segmentation for each identified entity in the video, an overall temporal segmentation for the video is generated, where the overall temporal segmentation reflects the semantics of the video.Type: ApplicationFiled: May 14, 2015Publication date: November 17, 2016Inventors: Min-hsuan Tsai, Sudheendra Vijayanarasimhan, Tomas Izo, Sanketh Shetty, Balakrishnan Varadarajan
-
Publication number: 20160335500Abstract: Method of and system for generating image metadata, comprising, at an electronic device: receiving an indication of text to be included in an image, the text comprising at least one character, each character being encoded according to a character encoding; generating the image based at least in part on the text, the image including an image representation of the text; generating the image metadata based at least in part on the text; and associating the image metadata with the image. Method of and system for generating video metadata. Method of and system for generating audio metadata.Type: ApplicationFiled: August 19, 2014Publication date: November 17, 2016Inventors: Lidia Vladimirovna POPELO, Dmitry Vladimirovich CHUPROV
-
Publication number: 20160335501Abstract: A surveillance device including a processing module, a lighting module, a movable module, a first camera module and a second camera module. The lighting module is coupled to the processing module to emit light and illuminate a surrounding environment. The movable module is coupled to the processing module. The first camera module is coupled to the processing module. The second camera module is coupled to the processing module, and is disposed on the movable module. When the processing module determines that the amount of light received by the first camera module is lower than a predetermined value, the processing module controls the lighting module to emit light. The processing module uses the movable module to control the second camera module to face towards a direction to the surrounding environment so that the second camera module acquires an image of the surrounding environment.Type: ApplicationFiled: May 15, 2015Publication date: November 17, 2016Inventor: SHENG-PIN HUANG
-
Publication number: 20160335502Abstract: A system and method are provided for tracking objects in a scene from a sequence of images captured by an imaging device. The method includes processing the sequence of images to generate sequential images at a plurality of hierarchical levels to generate a set of regions of interest; and, at each of the hierarchical levels: examining pairs of sequential images to link pixels into short tracklets; and grouping short tracklets that indicate similar motion patterns to generate representative tracklets. The representative tracklets are grouped to generate a tracking result for at least one object.Type: ApplicationFiled: May 15, 2015Publication date: November 17, 2016Inventors: Mehrsan Javan ROSHTKHARI, Martin D. LEVINE
-
Publication number: 20160335503Abstract: The present disclosure discloses an inspection method and device. The method comprises steps of acquiring a perspective image of an inspected object; processing the perspective image to obtain a region of interest; and automatically detecting the region of interest using a cigarette model, to determine whether the region of interest of the perspective image belongs to a cigarette. In the present disclosure, cigarette detection is implemented on a scanned image of goods, particularly a container, which can avoid the problem of detection vulnerability and poor effect of manual image judgment for the conventional manner, and is of significance in fighting against cigarette smuggling.Type: ApplicationFiled: November 11, 2014Publication date: November 17, 2016Inventors: Li ZHANG, Zhiqiang CHEN, Qiang LI, Jian ZHANG, Jianping GU, Jin CUI
-
Publication number: 20160335504Abstract: The subject of the invention is a method for detecting and classifying events of a scene by means of a single-pupil imaging system equipped with a VisNIR detector in the 0.6 ?m-1.Type: ApplicationFiled: February 5, 2015Publication date: November 17, 2016Inventors: Thierry MIDAVAINE, Olivier GARIN
-
Publication number: 20160335505Abstract: Systems and methods for cloud-based surveillance for an operation area are disclosed. At least two input capture devices, at least one safety control device and at least one user device are communicatively connected to a cloud-based analytics platform. The cloud-based analytics platform automatically generates 3-Dimensional (3D) surveillance data based on received 2-Dimensional (2D) video and/or image inputs and perform advanced analytics and activates the at least one safety control device based on analytics data from advanced analytics.Type: ApplicationFiled: July 27, 2016Publication date: November 17, 2016Applicant: Smartvue CorporationInventor: Martin A. Renkis
-
Publication number: 20160335506Abstract: Systems and methods for cloud-computing network with distributed input devices and a cloud-based analytics platform for automatically analyzing received 2-Dimensional (2D) video and/or image inputs for generating 3-Dimensional (3D) surveillance data and providing 3D display for a target surveillance area.Type: ApplicationFiled: July 27, 2016Publication date: November 17, 2016Applicant: Smartvue CorporationInventor: Martin A. Renkis
-
Publication number: 20160335507Abstract: A computer-implemented method and a system for vehicle localization. The method includes identifying expected lane lines based on a lane level map and a position of a vehicle and identifying observed lane lines based on images captured by an imaging device of the vehicle and the position of the vehicle. The method includes matching the expected lane lines to the observed lane lines and determining a likelihood score based on the matching. The method includes determining a best vehicle pose based on the likelihood score.Type: ApplicationFiled: May 13, 2015Publication date: November 17, 2016Inventors: Yuncong Chen, Aniket Murarka
-
Publication number: 20160335508Abstract: The present invention describes a vehicle detection system and method for detecting one or more vehicles in a dynamic varying region of interest, ROI. The system comprises a scene recognition module (101), a road topology estimation module (102), and a vehicle detecting module (103). The scene recognition module is configured for receiving either high exposure image or low exposure image for identifying condition of one or more scenes in a dynamically varying region of interest. The road topology estimation module configured for receiving either high exposure image or low exposure image for determining at least one of a curve, slope and vanishing point of a road in the dynamically varying region of interest. The vehicle detecting module is coupled with the scene recognition module and road topology module for detecting one or more vehicles on the road at night time.Type: ApplicationFiled: January 16, 2015Publication date: November 17, 2016Inventors: Snehal Gor, Darshan Kumar Beeruka
-
Publication number: 20160335509Abstract: A first terminal accompanying a subject moving entity transmits a first time-sequential data string, which represents a history of a first state quantity varying depending on a behavior of the subject moving entity, to a second terminal wirelessly. The second terminal stores a second time-sequential data string representing a history of a second state quantity of a moving entity detected by a moving entity detector in association with the moving entity detected. The received first time-sequential data string and the stored second time-sequential data string are referred to so as to identify the association between (i) the first terminal, which is equivalent to a transmission source of the first time-sequential data string, and (ii) an identified moving entity that is identified from the detected moving entity, to determine that the identified moving entity is associated with the first terminal.Type: ApplicationFiled: May 6, 2016Publication date: November 17, 2016Inventor: Tsuneo NAKATA
-
Publication number: 20160335510Abstract: A vision system of a vehicle includes a camera disposed at the vehicle and having a field of view exterior of the vehicle. A control has an image processor that is operable, via image processing of frames of image data captured by the camera, to detect an object present in the field of view of the camera. When the vehicle is moving, the control, responsive at least in part to vehicle motion information and image processing of frames of captured image data, determines motion of the detected object relative to the moving vehicle. The control determines the relative motion of the detected object by (i) determining corresponding object points in at least two frames of captured image data, (ii) estimating object motion trajectory of the detected object responsive to the determination of corresponding object points and (iii) determining the structure of the detected object along the estimated object motion trajectory.Type: ApplicationFiled: May 10, 2016Publication date: November 17, 2016Inventors: Nikhil Gupta, Liang Zhang
-
Publication number: 20160335511Abstract: Systems and methods are provided for authenticating a user of a computing device. The system comprises one or more memory devices storing instructions, and one or more processors configured to execute the instructions to provide, to a computing device associated with a user, an indication of a prescribed authentication parameter. The system also receives image data including an image of the user of the computing device captured using an image sensor of the computing device. The system determines an identity of the user based on an analysis of the received image data, determines whether the received image data includes a feature corresponding to the prescribed authentication parameter, and authenticates the user based at least in part on whether the received image data includes the feature corresponding to the prescribed authentication parameter.Type: ApplicationFiled: May 12, 2016Publication date: November 17, 2016Inventor: Colin Robert MACDONALD
-
Publication number: 20160335512Abstract: A user identification system includes an image recognition network to analyze image data and generate shape data based on the image data. The system also includes a generalist network to analyze the shape data and generate general category data based on the shape data. The system further includes a specialist network to compare the general category data with a characteristic to generate narrow category data. Moreover, the system includes a classifier layer including a plurality of nodes to represent a classification decision based on the narrow category data.Type: ApplicationFiled: May 9, 2016Publication date: November 17, 2016Inventor: Gary R. Bradski
-
Publication number: 20160335513Abstract: A managed notification system compares image(s) and/or indicia relating to the image(s) and where there is a match selectively provides a notification of the same.Type: ApplicationFiled: July 28, 2016Publication date: November 17, 2016Inventors: Joseph Ethan Rosenkrantz, Gifford Hesketh
-
Publication number: 20160335514Abstract: Improved thermoacoustic imaging is provided by ensuring directional uniformity of the microwave excitation provided to the target being imaged. This directional uniformity can be quantified in terms of the eccentricity e of the polarization ellipse of the microwave excitation. We have e?0.87, preferably e?0.71, and more preferably e?0.32. Optical excitation can be provided in addition to the microwave excitation. Excitation can be performed at multiple optical wavelengths and/or microwave frequencies to improve depth uniformity. In addition, the employment of excitation cells with optimized spacing and geometry provides the uniformity in another two degrees of freedom. One potential application is to detect blood vessel in user's finger for biometric authentication.Type: ApplicationFiled: July 29, 2016Publication date: November 17, 2016Inventors: Mohammad Amin Arbabian, Seyed Miaad Seyed Aliroteh, Hao Nan
-
Publication number: 20160335515Abstract: An image of a portion of a person's body is accessed, the image having been captured by an image capture device. Using the image, measurements of characteristics in the image are obtained, the characteristics in the image having been selected based on a statistical analysis of characteristics (i) in a plurality of first images taken directly of a person and (ii) in a plurality of second images taken of an image of a person. Based on a liveness function, a score for the image is determined using the obtained measurements of the characteristics in the image. A threshold value is accessed. The score of the image is compared to the accessed threshold value. Based on the comparison of the score of the image to the accessed threshold value, the image is determined to be have been taken by the image capture device imaging the portion of the person's body.Type: ApplicationFiled: July 26, 2016Publication date: November 17, 2016Inventors: Florian Juveneton, Alessio Cavallini
-
Publication number: 20160335516Abstract: Provided is an image processing apparatus including an acquisition section that acquires an object image which is an editing object, a feature quantity acquisition section that acquires a feature quantity of a reference image which is referred to when the object image is edited, a feature-reflected image generation section that reflects a feature of the reference image on the object image by using the feature quantity acquired by the feature quantity acquisition section, and generates a feature-reflected image which is the object image on which the feature is reflected, and a reflection degree changing section that changes a degree of reflection of the feature in the feature-reflected image by using an adjustment value which is input by a user.Type: ApplicationFiled: July 25, 2016Publication date: November 17, 2016Applicant: FUJI XEROX CO., LTD.Inventor: Takayuki YAMAMOTO
-
Publication number: 20160335517Abstract: An apparatus and method to detect a line segment or arc using Hough transform. A Hough transform unit performs contour extraction on brightness image data to generate contour image data, with pixels having a pixel value of 0 to 255, performs the Hough transform on points in the contour image data, and counts additional values represented by pixel values of points in the contour image data in a Hough table. The Hough transform unit performs contour extraction on first to third component data to generate first to third contour data with pixels having a pixel value of 0 to 255, performs the Hough transform on points in the first to third contour data, and counts additional values represented by pixel values of points in the first to third contour data in the Hough table. The detection unit comprehensively evaluates the counts to detect a line segment or arc.Type: ApplicationFiled: July 26, 2016Publication date: November 17, 2016Applicant: MegaChips CorporationInventor: Hiromu HASEGAWA
-
Publication number: 20160335518Abstract: The present invention concerns the recovery of fragmented files. In particular, the present invention concerns finding fragmentation points and continuation points of a fragmented JPEG image for purposes of reassembling the JPEG image. The continuation points are found by using a JPEG thumbnail image corresponding to the JPEG image to be reassembled.Type: ApplicationFiled: April 15, 2016Publication date: November 17, 2016Applicant: Micro Systemation ABInventor: Christopher Rossall
-
Publication number: 20160335519Abstract: Disclosed embodiments facilitate keypoint selection in part by assigning a similarity score to each candidate keypoint being considered for selection. The similarity score may be based on the maximum measured similarity of an image patch associated with a keypoint in relation to an image patch in a local image section in a region around the image patch. A subset of the candidate keypoints with the lowest similarity scores may be selected and used to detect and/or track objects in subsequent images and/or to determine camera pose.Type: ApplicationFiled: September 4, 2015Publication date: November 17, 2016Inventors: Daniel Wagner, Kiyoung Kim
-
Publication number: 20160335520Abstract: Improvements are disclosed for detecting counterfeit objects, based on comparison to digital fingerprints that describe features found in images of objects known to be counterfeit.Type: ApplicationFiled: July 12, 2016Publication date: November 17, 2016Applicant: Authentect, Inc.Inventors: David Justin Ross, Brian J. Elmenhurst, Mark Tocci, John Forbes, Heather Wheelock Ross
-
Publication number: 20160335521Abstract: The present invention relates to method and apparatus for generating, updating classifier, detecting objects, and image processing device. A method for generating a multi-class classifier, comprising the following steps: generating at least one one-class background classifier by using a one-class object classifier and background image regions obtained from a sequence of images; and assembling the one-class object classifier and the at least one one-class background classifier into a multi-class classifier.Type: ApplicationFiled: May 11, 2016Publication date: November 17, 2016Inventors: LONG JIANG, YONG JIANG, Wenwen ZHANG
-
Publication number: 20160335522Abstract: A method for visual recognition of an object in an electronic image includes extracting unique points of an object to be learned and/or a target object. The unique points are obtained by cross-correlating the image with a structure. Generally, the structure and/or the size of the structure may vary to detect extremum information associated with the learned object and/or target object. An icon corresponding to each of the unique points is extracted. The size of the icon corresponds to the scale of the unique point. After extraction of the various icons, an object becomes a collection of icons. Each of these icons is un-rotated and normalized or resized to a constant size so it can be compared with other icons. One of the unique properties of these icons is their stability over scale and angle. Thus, this invention allows the recognition of an image(s) or object(s) from large number of trained images or objects very quickly.Type: ApplicationFiled: June 6, 2014Publication date: November 17, 2016Inventor: Simon Melikian
-
Publication number: 20160335523Abstract: The invention relates to a method (100) for detecting incorrect associations between keypoints of a first image and keypoints of a second image, the method (100) comprising associating (101) every keypoint of the first image with every keypoint of the second image to obtain global associations, determining (103) similarity measures for pairs of initial associations, determining (105) similarity measures for pairs of global associations, determining (107) a first number of pairs of initial associations having a similarity measure within a predetermined range, determining (109) a second number of pairs of global associations having a similarity measure within the predetermined range, and comparing (111) the first number of pairs with the second number of pairs to detect the incorrect associations. The invention further relates to an apparatus for detecting incorrect associations between keypoints of a first image and keypoints of a second image.Type: ApplicationFiled: July 29, 2016Publication date: November 17, 2016Inventors: Nicola PIOTTO, Giovanni CORDARA
-
Publication number: 20160335524Abstract: A system for identifying in an image an object that is commonly found in a collection of images and for identifying a portion of an image that represents an object based on a consensus analysis of segmentations of the image. The system collects images of containers that contain objects for generating a collection of common objects within the containers. To process the images, the system generates a segmentation of each image. The image analysis system may also generate multiple segmentations for each image by introducing variations in the selection of voxels to be merged into a segment. The system then generates clusters of the segments based on similarity among the segments. Each cluster represents a common object found in the containers. Once the clustering is complete, the system may be used to identify common objects in images of new containers based on similarity between segments of images and the clusters.Type: ApplicationFiled: May 12, 2015Publication date: November 17, 2016Inventors: Peer-Timo Bremer, Hyojin Kim, Jayaraman J. Thiagarajan
-
Publication number: 20160335525Abstract: [PROBLEMS TO BE SOLVED] It is an object to provide a marker and a marker generating and detecting technology that can automatically design a diagrammatic marker that is not similar to any patterns to appear during the reproduction of background video images. [MEANS FOR SOLVING THE PROBLEMS] A marker generating system is characterized in having a special feature extracting means that extracts a portion, as a special feature, including a distinctive pattern in a video image not including a marker; a unique special feature selecting means that, based on the extracted special feature, selects a special feature of an image, as a unique special feature, that does not appear on the video image; and a marker generating means that generates a marker based on the unique special feature.Type: ApplicationFiled: December 19, 2013Publication date: November 17, 2016Applicant: NEC CorporationInventor: Noboru NAKAJIMA
-
Publication number: 20160335526Abstract: Examples disclosed herein relate to classifying paper based on three-dimensional characteristics of the paper. For example, a representation of the three-dimensional characteristics of the paper may be created, and statistical summary information related to the three-dimensional characteristics of the paper may be determined based on the representation. The paper may be classified based on the statistical summary information.Type: ApplicationFiled: January 6, 2014Publication date: November 17, 2016Inventors: Hossein Malekmohamadi, Guy Adams, Stephen Pollard, Steven J Simske, Khemraj Emirith, Melvyn Smith
-
Publication number: 20160335527Abstract: A recording device includes a recording unit that performs a recording operation, a first storage unit that stores a first template associated with a recording form, a second storage unit that store a second template corresponding to the first template, and a recording control unit that takes the second template corresponding to the designated first template from the second storage unit and gets the recording unit to perform the recording operation by using the second template when a recording instruction containing data designating the first template is input.Type: ApplicationFiled: July 25, 2016Publication date: November 17, 2016Applicant: Seiko Epson CorporationInventors: Susumu Shiohara, Toshifumi Yamaji
-
Publication number: 20160335528Abstract: To realize a dot pattern which can be read even by a frame buffer of which algorithm for search is simple and of which resolution is low without sacrificing an information dot for defining a direction of a block. There is provided a dot pattern, wherein a plurality of reference points is provided in an area of a block having a predetermined information dot arranged thereon; a plurality of virtual reference points to be defined is arranged from the reference points (for example, a central point of a grid area); an information dot is arranged, of which information is defined by a distance and a direction from the virtual reference point; and at least the information dot at the predetermined position is made into a direction dot showing the direction of the block by a direction from the virtual reference point.Type: ApplicationFiled: July 25, 2016Publication date: November 17, 2016Inventor: Kenji Yoshida
-
Publication number: 20160335529Abstract: A payment card (e.g., credit and/or debit card) is provided with a magnetic emulator operable of communicating information to a magnetic stripe reader. Information used in validating a financial transaction is encrypted based on time such that a validating server requires receipt of the appropriate encrypted information for a period of time to validate a transaction for that period of time. Such dynamic information may be communicated using such an emulator such that a card may be swiped through a magnetic stripe reader—yet communicate different information based on time. An emulator may receive information as well as communicate information to a variety of receivers (e.g., an RFID receiver).Type: ApplicationFiled: August 1, 2016Publication date: November 17, 2016Inventors: Jeffrey D. Mullen, David Lambeth, Bruce Cloutier
-
Publication number: 20160335530Abstract: A method and device for protecting sensitive information stored on a mobile device capable of wireless communication is described. The protection is provided by permitting wireless transmission of the sensitive information only if data received from an optical sensor or a magnetic sensor satisfies a predetermined requirement.Type: ApplicationFiled: May 13, 2016Publication date: November 17, 2016Inventors: Michael Lawrence Davis, Horst Arnold Mueller
-
Publication number: 20160335531Abstract: A dynamic code of a transaction device may be validated by a remote processor by comparing the dynamic code to a verification code generated using a timestamp and identification data received from the transaction device. A static code may replace the dynamic code for authorization processing. A remote verification processor may synchronize to the transaction device using the timestamp. A token may be associated to each communication interface of a multi-card transaction device. A display may be directly connected to driver circuit on a display board of a transaction card. A radio IC chip may be included in a powered card. A multi-card device may toggle a plurality of display screens to display transaction data.Type: ApplicationFiled: May 12, 2016Publication date: November 17, 2016Inventors: Jeffrey D. Mullen, Andrew Veter, Jason Dyro
-
Publication number: 20160335532Abstract: Disclosed are systems, methods, and non-transitory computer-readable storage media for utilizing a virtual assistant as part of a communication session. One or more of the participant users can select to utilize a virtual assistant to assist the participant users with tasks during the communication session. A user can use a communication application to enter a message directed to the virtual assistant. The virtual assistant can analyze the entered message and determine that the message was directed to the virtual assistant rather than to the other participants of the communication session. As a result, the message will not be transmitted to the other participants of the communication session and the virtual assistant will assist the user with the identified task. A virtual assistant can assist a user with a variety of different tasks.Type: ApplicationFiled: May 15, 2015Publication date: November 17, 2016Inventors: Mehul K. Sanghavi, Jeffrey P. Schwerdtfeger
-
Publication number: 20160335533Abstract: According to an embodiment, a processing network is configured to access a reputation system, provide a first user interface, provide a second user interface, receive a request from a user through the second user interface, retrieve user information from the reputation system, assign a plurality of human intelligence tasks based on the request, receive a plurality of results from the plurality of human intelligence tasks, confirm an identity and a status of the user based on the user information and the plurality of results, execute the request based on confirming the identity and the status of the user, and store evidence of execution of the request as an immutable data entry in a permanent database. The first user interface includes information from the reputation system, and the plurality of human intelligence tasks are assigned to a plurality of participants through the first user interface.Type: ApplicationFiled: February 24, 2016Publication date: November 17, 2016Inventors: Joshua P. Davis, Ronald Munoz
-
Publication number: 20160335534Abstract: Systems and methods for a sensor hub system that accurately and efficiently performs sensory analysis across a broad range of users and sensors and is capable of recognizing a broad set of sensor-based events of interest using flexible and modifiable neural networks are disclosed. The disclosed solution consumes orders of magnitude less power than typical application processors. In one embodiment, a scalable sensor hub system for detecting sensory events of interest comprises a neural network and one or more sensors. The neural network comprises one or more dedicated low-power processors and memory storing one or more neural network programs for execution by the one or more processors. The output of the one or more sensors is converted into a spike signal, and the neural network takes the spike signal as input and determines whether a sensory event of interest has occurred.Type: ApplicationFiled: May 13, 2016Publication date: November 17, 2016Inventors: Andrew Nere, Atif Hashmi, Michael Eyal, Mikko H. Lipasti, John F. Wakerly
-
Publication number: 20160335535Abstract: One embodiment of the invention provides a system for mapping a neural network onto a neurosynaptic substrate. The system comprises a reordering unit for reordering at least one dimension of an adjacency matrix representation of the neural network. The system further comprises a mapping unit for selecting a mapping method suitable for mapping at least one portion of the matrix representation onto the substrate, and mapping the at least one portion of the matrix representation onto the substrate utilizing the mapping method selected. The system further comprises a refinement unit for receiving user input regarding at least one criterion relating to accuracy or resource utilization of the substrate. The system further comprises an evaluating unit for evaluating each mapped portion against each criterion. Each mapped portion that fails to satisfy a criterion may be remapped to allow trades offs between accuracy and resource utilization of the substrate.Type: ApplicationFiled: March 18, 2015Publication date: November 17, 2016Inventors: Arnon Amir, Rathinakumar Appuswamy, Pallab Datta, Myron D. Flickner, Paul A. Merolla, Dharmendra S. Modha, Benjamin G. Shaw
-
Publication number: 20160335536Abstract: Generating loosely coupled parts by forming couplings between partial nodes in a hierarchical neural network in accordance with a check matrix of an error correcting code.Type: ApplicationFiled: February 10, 2014Publication date: November 17, 2016Applicant: Mitsubishi Electric CorporationInventors: Takashi YAMAZAKI, Wataru MATSUMOTO
-
Publication number: 20160335537Abstract: A method/apparatus/system for generating a request for improvement of a data object in a neural network is described herein. The neural network contains a plurality of data objects each made of an aggregation of content. The data objects of the neural network are interconnected based on one or several skill levels embodied in the content of the data objects via a plurality of connecting vectors. These connecting vectors can be generated and/or modified based on data collected from the iterative transversal of the connecting vectors by one or several users of the neural network.Type: ApplicationFiled: July 29, 2016Publication date: November 17, 2016Inventor: Perry M. Spagnola
-
Publication number: 20160335538Abstract: A method/apparatus/system for generating a request for improvement of a data object in a neural network is described herein. The neural network contains a plurality of data objects each made of an aggregation of content. The data objects of the neural network are interconnected based on one or several skill levels embodied in the content of the data objects via a plurality of connecting vectors. These connecting vectors can be generated and/or modified based on data collected from the iterative transversal of the connecting vectors by one or several users of the neural network.Type: ApplicationFiled: July 29, 2016Publication date: November 17, 2016Inventor: Perry M. Spagnola
-
Publication number: 20160335539Abstract: A method/apparatus/system for generating a request for improvement of a data object in a neural network is described herein. The neural network contains a plurality of data objects each made of an aggregation of content. The data objects of the neural network are interconnected based on one or several skill levels embodied in the content of the data objects via a plurality of connecting vectors. These connecting vectors can be generated and/or modified based on data collected from the iterative transversal of the connecting vectors by one or several users of the neural network.Type: ApplicationFiled: July 29, 2016Publication date: November 17, 2016Inventor: Perry M. Spagnola
-
Publication number: 20160335540Abstract: A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.Type: ApplicationFiled: July 28, 2016Publication date: November 17, 2016Inventors: Geoffrey E. Hinton, Alexander Krizhevsky, Ilya Sutskever, Nitish Srivastva
-
Publication number: 20160335541Abstract: A method/apparatus/system for generating a request for improvement of a data object in a neural network is described herein. The neural network contains a plurality of data objects each made of an aggregation of content. The data objects of the neural network are interconnected based on one or several skill levels embodied in the content of the data objects via a plurality of connecting vectors. These connecting vectors can be generated and/or modified based on data collected from the iterative transversal of the connecting vectors by one or several users of the neural network.Type: ApplicationFiled: July 29, 2016Publication date: November 17, 2016Inventor: Perry M. Spagnola
-
Publication number: 20160335542Abstract: A system, method, and computer-readable medium are disclosed for performing distributed analytics using a metadata encoded decision engine. More specifically, the operation of performing distributed analytics combines metadata encoding of input expectations for models with a multi-tier decision engine. In certain embodiments, the multi-tier decision engine provides arbitrary responses to input failures, including data dropping, routing to additional models, signaling, data conditioning, and even updating of the model parameters themselves. The combination of the processing model, the data input validation, and the decision engine improves the operation of a distributed data processing environment which is focused on predictive and reactive analysis of edge processing data.Type: ApplicationFiled: May 12, 2015Publication date: November 17, 2016Applicant: DELL SOFTWARE, INC.Inventors: Shree A. Dandekar, Mark W. Davis
-
Publication number: 20160335543Abstract: This invention provides a computer method and system for interactive administration of medical cannabinoid treatments. The invention also provides information on cannabinoid product availability and geographical information. Medical professionals, cannabis growers, cannabis manufacturers, and other stakeholders can use this computer method and system to study trends, efficacy, and other information pertinent to the medical cannabis market.Type: ApplicationFiled: May 12, 2016Publication date: November 17, 2016Inventors: Boris GOLDSTEIN, David GOLDSTEIN, Milla BAKHAREVA
-
Publication number: 20160335544Abstract: A method for generating a knowledge data model is provided. The method includes providing at least one initial set of semantic type entities of a specific semantic type. The initial set of semantic type entities is expanded using available mappings between entities of the initial set and entities of unspecified type to generate an extended set of semantic type entities. Entities of a same semantic type are clustered within the extended set of semantic type entities. The method maps semantic relations between entities of different semantic type to relations between corresponding clusters containing the entities to generate the knowledge data model.Type: ApplicationFiled: May 12, 2015Publication date: November 17, 2016Inventors: Claudia Bretschneider, Heiner Oberkampf, Sonja Zillner
-
Publication number: 20160335545Abstract: An information processing apparatus includes: a network information acquisition unit that acquires network information which includes target nodes and adjacent nodes; a classification ratio calculation unit that calculates a classification ratio, in which the target nodes are respectively classified as a plurality of communities corresponding to a predetermined number in the network information, so as to have correlation according to given resolutions with a classification ratio in which the adjacent nodes are respectively classified as the plurality of communities; a first type community generation unit that generates one or more first type communities; a classification ratio updating unit that updates the classification ratio relevant to the target nodes so as to have correlation with the classification ratio in which the adjacent nodes are respectively classified as the plurality of communities; and a second type community generation unit that generates one or more second type communities.Type: ApplicationFiled: October 21, 2015Publication date: November 17, 2016Inventors: Xule QIU, Hiroshi OKAMOTO
-
Publication number: 20160335546Abstract: The specification relates to a self-pipelining workflow management system. The system can receive a request to run a bioinformatics analysis and automatically create a workflow by accessing a knowledge structure. The knowledge structure can include a plurality of predicates describing computational relationships between at least one bioinformatics data file and at least two bioinformatics programs. The workflow contains a dynamic set of predicates specific to the request based upon initial input data, general request parameters and the knowledge structure. The workflow is initiated based on a first predicate of the dynamic set of predicates and after a new unprocessed input data is obtained, the dynamic set of predicates is updated. The workflow continues until no more predicates can be associated with the unprocessed input data or no more unprocessed data can be obtained.Type: ApplicationFiled: May 14, 2015Publication date: November 17, 2016Inventor: Andrey Ptitsyn
-
Publication number: 20160335547Abstract: An information processing device includes a processor configured to: acquire information of first status that represents a state of a first detection target; specify state transition in which the first status is changed based on the acquired information of the first status; acquire information of second status that represents a state of a second detection target; specify state transition in which the second status is changed based on the acquired information of the second status; specify a time point earlier than a first time point at which the state transition of the second status is specified as a second time point at which the state transition of the second status occurs; determine whether a combination of the second status and the first status at least at the second time point satisfies a predetermined condition; and perform predetermined processing according to a determination result indicating the condition is satisfied.Type: ApplicationFiled: April 4, 2016Publication date: November 17, 2016Applicant: FUJITSU LIMITEDInventor: Eiji HASEGAWA
-
Publication number: 20160335548Abstract: A method for predicting fault occurrence in a mechanical system and an electrical system. The method comprises: receiving a first dataset of mechanical system condition data, the first dataset being imbalanced by having more data points in a first category than in a second category; generating a plurality of chromosomes from the second category data points in the first dataset; the plurality of chromosomes including information to enable the creation of new datasets; generating a second dataset using the plurality of chromosomes and an evolutionary algorithm, the second dataset being less imbalanced than the first dataset; and predicting fault occurrence in the mechanical system using the second dataset and a machine learning algorithm.Type: ApplicationFiled: April 28, 2016Publication date: November 17, 2016Applicant: ROLLS-ROYCE plcInventors: Chi-Keong GOH, Lim PIN, Tan KAY CHEN