Patents by Inventor Daniel Marcus

Daniel Marcus has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Publication number: 20210134441
    Abstract: A patient's image data and associated metadata describing the image data and characteristics of the patient are received and stored in a memory area. Information that describes one or more imaging analysis services and associated service criteria is accessed and compared to the metadata. Based on matches between the image metadata and service criteria, services are selected and executed, producing an output. Iterative rounds of service matching based on the metadata and the output of previous services and service execution proceed. The output of the services is associated with the image data and metadata, stored in the memory area, and made available to the user. A data repository, including the original images, metadata, and service output is accessible via the services for use in comparative analyses. Such services can utilize the repository to dynamically update indices and algorithms used in the comparative analyses.
    Type: Application
    Filed: November 4, 2020
    Publication date: May 6, 2021
    Applicant: Washington University
    Inventor: Daniel Marcus
  • Patent number: 10984429
    Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.
    Type: Grant
    Filed: June 18, 2019
    Date of Patent: April 20, 2021
    Assignee: SDL Inc.
    Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
  • Publication number: 20200311573
    Abstract: A device may receive historical cloud data associated with resources of a cloud computing environment, and may receive historical customer data associated with requested resource usage by customers of the cloud computing environment. The device may determine a usage growth profile based on the historical cloud data and the historical customer data, and may determine, based on the historical cloud data and the historical customer data, usage deviation data indicating deviations between actual and planned resource usage. The device may train a model, with the usage growth profile and the usage deviation data, to generate a trained model, and may receive a request for new resource usage by a customer associated with the cloud computing environment. The device may process the request for the new resource usage, with the trained model, to generate projected resource usage data, and may perform actions based on the projected resource usage data.
    Type: Application
    Filed: August 26, 2019
    Publication date: October 1, 2020
    Inventors: Vijay DESAI, Kun QIU, Suraj THULKAR, Laser Seymour KAPLAN, Daniel Marcus LOMBARDO
  • Publication number: 20200311603
    Abstract: A device receives historical data associated with multiple cloud computing environments, trains one or more machine learning models, with the historical data, to generate trained machine learning models that generate outputs, and trains a model with the outputs to generate a trained model. The device receives particular data, associated with a cloud computing environment, that includes data identifying usage of resources associated with the cloud computing environment, and processes the particular data, with the trained machine learning models, to generate anomaly scores indicating anomalous usage of the resources associated with the cloud computing environment. The device processes the one or more anomaly scores, with the trained model, to generate a final anomaly score indicating anomalous usage of at least one of the resources associated with the cloud computing environment, and performs one or more actions based on the final anomaly score.
    Type: Application
    Filed: August 26, 2019
    Publication date: October 1, 2020
    Inventors: Kun QIU, Vijay DESAI, Laser Seymour KAPLAN, Durga KALYAN GANJAPU, Daniel Marcus LOMBARDO
  • Publication number: 20190303952
    Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.
    Type: Application
    Filed: June 18, 2019
    Publication date: October 3, 2019
    Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
  • Patent number: 10417646
    Abstract: A prediction of the cost associated with translating textual content in a source language can be determined. A first quantity estimation of first textual content may be determined. The first textual content is to be translated via human translation. A second quantity estimation of second textual content may also be determined. The second textual content is to be translated via machine translation. An indication of a target language is obtained, wherein the source language and the target language form a language pair. The prediction of the cost associated with translating the first textual content and the second textual content from the source language to the target language is then determined. The prediction is based at least in part on the first quantity estimation, the second quantity estimation, and the language pair.
    Type: Grant
    Filed: March 9, 2010
    Date of Patent: September 17, 2019
    Assignee: SDL Inc.
    Inventors: Radu Soricut, Narayanaswamy Viswanathan, Daniel Marcu
  • Patent number: 10402498
    Abstract: The present invention provides a method that includes receiving a result word set in a target language representing a translation of a test word set in a source language. When the result word set is not in a set of acceptable translations, the method includes measuring a minimum number of edits to transform the result word set into a transform word set. The transform word set is in the set of acceptable translations. A system is provided that includes a receiver to receive a result word set and a counter to measure a minimum number of edits to transform the result word set into a transform word set. A method is provided that includes automatically determining a translation ability of a human translator based on a test result. The method also includes adjusting the translation ability of the human translator based on historical data of translations performed by the human translator.
    Type: Grant
    Filed: October 16, 2018
    Date of Patent: September 3, 2019
    Assignee: SDL Inc.
    Inventors: Daniel Marcu, Markus Dreyer
  • Patent number: 10348888
    Abstract: Methods and systems for optimizing a call queue at a dispatch center. One system includes an electronic computing device including an electronic processor configured to define an incident based on a first call received from a first communication device, wherein the incident includes an incident location, receive, from a second communication device operated by a caller, a second call, perform an analysis of a metadata of the second call, determine a caller identification based on the metadata of the second call when the electronic processor determines, based on the analysis, that either (1) a call traffic level, following the first call, exceeds a call traffic threshold, or (2) a location of the second communication device is proximate to a location of the incident, and direct the second call to either a primary call handling workstation or a secondary call handling workstation based on the caller identification.
    Type: Grant
    Filed: August 3, 2018
    Date of Patent: July 9, 2019
    Assignee: MOTOROLA SOLUTIONS, INC.
    Inventors: Scott Arnold, Julianne Folden, Daniel Marcus, Lisa Vailencour
  • Patent number: 10319252
    Abstract: A learning system for a text-to-text application such as a machine translation system. The system has questions, and a matrix of correct answers to those questions. Any of the many different correct answers within the matrix can be considered as perfectly correct answers to the question. The system operates by displaying a question, which may be a phrase to be translated, and obtaining an answer to the question from the user. The answer is compared against the matrix and scored. Feedback may also be provided to the user.
    Type: Grant
    Filed: November 9, 2005
    Date of Patent: June 11, 2019
    Assignee: SDL Inc.
    Inventors: Michel Galley, Kevin Knight, Daniel Marcu
  • Patent number: 10261994
    Abstract: The present invention provides a method that includes receiving a result word set in a target language representing a translation of a test word set in a source language. When the result word set is not in a set of acceptable translations, the method includes measuring a minimum number of edits to transform the result word set into a transform word set. The transform word set is in the set of acceptable translations. A system is provided that includes a receiver to receive a result word set and a counter to measure a minimum number of edits to transform the result word set into a transform word set. A method is provided that includes automatically determining a translation ability of a human translator based on a test result. The method also includes adjusting the translation ability of the human translator based on historical data of translations performed by the human translator.
    Type: Grant
    Filed: May 25, 2012
    Date of Patent: April 16, 2019
    Assignee: SDL Inc.
    Inventors: Daniel Marcu, Markus Dreyer
  • Publication number: 20190042566
    Abstract: The present invention provides a method that includes receiving a result word set in a target language representing a translation of a test word set in a source language. When the result word set is not in a set of acceptable translations, the method includes measuring a minimum number of edits to transform the result word set into a transform word set. The transform word set is in the set of acceptable translations. A system is provided that includes a receiver to receive a result word set and a counter to measure a minimum number of edits to transform the result word set into a transform word set. A method is provided that includes automatically determining a translation ability of a human translator based on a test result. The method also includes adjusting the translation ability of the human translator based on historical data of translations performed by the human translator.
    Type: Application
    Filed: October 16, 2018
    Publication date: February 7, 2019
    Inventors: Daniel Marcu, Markus Dreyer
  • Publication number: 20180105094
    Abstract: A clamping apparatus that securely creates an anchoring point along the side rails of the pickup bed to efficiently fasten a securing strap or rope includes a pickup bed rail clamp, a T-head tie down, and a strap receiving bracket. An upper jaw and a lower jaw of the pickup bed rail clamp secure the clamping apparatus to the pickup bed through a fastener of the pickup bed rail clamp. The strap receiving bracket is terminally connected to the upper jaw and designed to receive a hook of the securing strap or a knot of the securing rope. The T-head tie down is connected to the upper jaw and the strap receiving bracket. a first V-shaped notch, a second V-shaped notch, and a U-shaped notch of the T-head tie down provide multiple placements for the securing strap or rope to loop around thus secure a load within the pickup bed.
    Type: Application
    Filed: October 13, 2017
    Publication date: April 19, 2018
    Inventors: Daniel Marcus Cain, Tanna Kay Cain
  • Publication number: 20170309191
    Abstract: A method is provided for limiting access to airspace by drones. The method includes receiving position information from a user associated with a property identified by the position information. The method also includes assembling the position information with other position information to compile a comprehensive configurable flight zone database. The method further includes pushing the configurable flight zone database to at least one drone. The drone accesses the configurable flight zone database to determine if movement is allowed, and the drone is programmed to not fly into areas identified in the configurable flight zone database. In the method, the drone may be further programmed to prohibit directing a camera into the areas identified in the configurable flight zone database.
    Type: Application
    Filed: July 7, 2017
    Publication date: October 26, 2017
    Inventor: Benjamin Daniel MARCUS
  • Patent number: 9728089
    Abstract: A method is provided for limiting access to airspace by drones. The method includes receiving position information from a user associated with a property identified by the position information. The method also includes assembling the position information with other position information to compile a comprehensive configurable flight zone database. The method further includes pushing the configurable flight zone database to at least one drone. The drone accesses the configurable flight zone database to determine if movement is allowed, and the drone is programmed to not fly into areas identified in the configurable flight zone database. In the method, the drone may be further programmed to prohibit directing a camera into the areas identified in the configurable flight zone database.
    Type: Grant
    Filed: December 30, 2015
    Date of Patent: August 8, 2017
    Assignee: AirMap, Inc.
    Inventor: Benjamin Daniel Marcus
  • Patent number: 9694155
    Abstract: A method to induce an immediate psychosomatic change in a patient optimal for a particular medical procedure, is provided. The method uses a brain-computer interface integrating a loop of biofeedback and neurofeedback components, interactive, immersive, 3D virtual reality (VR) modules utilizing hypnotic or guided-response, learning, placebo and experience-ratification principles. The method will differentiate between low and high hypnotizable patients as well their specific abilities and limitations by their distinct brain patterns and will deliver VR output content appropriate for the current and targeted psychosomatic state of the patient, needs, and stage of a particular medical procedure thus being applicable to any medical patient regardless of abilities. The device will continuously measure the patient's physiological markers and will customize the intensity, order, timing, and content of the output “dose.
    Type: Grant
    Filed: December 17, 2014
    Date of Patent: July 4, 2017
    Inventors: Juliana Stoianova Panova, Joel Daniel Marcus, Tayana Borisova Panova
  • Publication number: 20160189549
    Abstract: A method is provided for limiting access to airspace by drones. The method includes receiving position information from a user associated with a property identified by the position information. The method also includes assembling the position information with other position information to compile a comprehensive configurable flight zone database. The method further includes pushing the configurable flight zone database to at least one drone. The drone accesses the configurable flight zone database to determine if movement is allowed, and the drone is programmed to not fly into areas identified in the configurable flight zone database. In the method, the drone may be further programmed to prohibit directing a camera into the areas identified in the configurable flight zone database.
    Type: Application
    Filed: December 30, 2015
    Publication date: June 30, 2016
    Inventor: Benjamin Daniel Marcus
  • Patent number: 9152622
    Abstract: Personalizing machine translation via online adaptation is described herein. According to some embodiments, methods for providing personalized machine translations may include receiving translator feedback regarding machine translations generated by a machine translation system for a translator, determining translator feedback that improves translations generated by the machine translation system, and incorporating the determined translator feedback into the translation methodology of the machine translation system to personalize the translation methodology.
    Type: Grant
    Filed: November 26, 2012
    Date of Patent: October 6, 2015
    Assignee: Language Weaver, Inc.
    Inventors: Daniel Marcu, Jonathan May
  • Publication number: 20150174362
    Abstract: Despite the significantly researched curative properties and health benefits of psychosomatic approaches such as clinical hypnosis and bio- and neurofeedback, they are still broadly underused in medical settings. The delivery of efficient holistic treatment requires organically uniting the mind and body treatment approaches in a well-calibrated, reliable and intensive treatment. We propose a method for reliably achieving the necessary psychosomatic state that is optimal for the specific current needs of medical patients via a medical device utilizing brain-computer interface that integrates immersive, interactive virtual reality with bio- and neurofeedback, and hypnotic or guided-response modules. The method will solve the practical limitations in the utilization of the aforementioned psychosomatic approaches, augmenting their efficacy and permitting their reliable and measurable integration in a medical treatment, optimizing it in terms of efficacy, time, and cost.
    Type: Application
    Filed: December 17, 2014
    Publication date: June 25, 2015
    Inventors: Juliana Stoianova Panova, Joel Daniel Marcus, Tayana Borisova Panova
  • Patent number: 8990064
    Abstract: A document containing text in a source language may be translated into a target language based on content associated with that document, in conjunction with the present technology. An indication to perform an optimal translation of a document into a target language may be received via a user interface. The document may then be accessed by a computing device. The optimal translation is executed by a preferred translation engine of a plurality of available translation engines. The preferred translation engine is the most likely to produce the most accurate translation of the document among the plurality of available translation engines. Additionally, the preferred translation engine may be identified based on content associated with the document. The document is translated into the target language using the preferred translation engine to obtain a translated document, which may then be outputted by a computing device.
    Type: Grant
    Filed: July 28, 2009
    Date of Patent: March 24, 2015
    Assignee: Language Weaver, Inc.
    Inventors: Daniel Marcu, Radu Soricut, Narayanaswamy Viswanathan
  • Patent number: 8943080
    Abstract: Systems, computer programs, and methods for identifying parallel documents and/or fragments in a bilingual collection are provided. The method for identifying parallel sub-sentential fragments in a bilingual collection comprises translating a source document from a bilingual collection. The method further includes querying a target library associated with the bilingual collection using the translated source document, and identifying one or more target documents based on the query. Subsequently, a source sentence associated with the source document is aligned to one or more target sentences associated with the one or more target documents. Finally, the method includes determining whether a source fragment associated with the source sentence comprises a parallel translation of a target fragment associated with the one or more target sentences.
    Type: Grant
    Filed: December 5, 2006
    Date of Patent: January 27, 2015
    Assignee: University of Southern California
    Inventors: Daniel Marcu, Dragos Stefan Munteanu