Patents by Inventor Stefan Von Cavallar
Stefan Von Cavallar 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: 20230334180Abstract: A method, a structure, and a computer system for privacy-preserving motion analysis. Embodiments may include identifying one or more joints of a user based on collected data and generating one or more 3D representations of the one or more joints of the user. Embodiments may further include anonymizing the one or more 3D representations, classifying one or more actions of the user based on the one or more 3D representations, wherein the classifying outputs an action score, and exporting at least one of the one or more actions and the action score.Type: ApplicationFiled: June 29, 2023Publication date: October 19, 2023Inventors: TIAN HAO, Umar Asif, Stefan Harrer, Jianbin Tang, Stefan von Cavallar, Deval Samirbhai Mehta, JEFFREY L. ROGERS, Erhan Bilal, Stefan Renard Maetschke
-
Patent number: 11751800Abstract: A method, a computer program product, and a computer system determine abnormal motion from a patient. The method includes receiving sensory data of the patient and a location in which the patient is present. The sensory data includes video data over a period of time the patient is being monitored. The method includes generating contextual information based on the sensory data. The contextual information is indicative of surroundings of the patient and characteristics of the location. The method includes generating motion information based on the sensory data. The motion information is indicative of movement of the patient in the location. The method includes generating contextual motion data by incorporating the contextual information with the motion information. The method includes determining the abnormal motion based on the contextual motion data.Type: GrantFiled: October 22, 2020Date of Patent: September 12, 2023Assignee: International Business Machines CorporationInventors: Umar Asif, Stefan von Cavallar, Jianbin Tang, Stefan Harrer
-
Patent number: 11734453Abstract: A method, a structure, and a computer system for privacy-preserving motion analysis. Embodiments may include collecting data corresponding to a user with one or more sensors and identifying one or more joints of the user based on the data. Embodiments may additionally include generating one or more 3D representations of the one or more joints of the user and anonymizing the one or more 3D representations by applying thereto a joint-centering and a random shuffling. Embodiments may further include classifying one or more actions of the user based on analysing the one or more 3D representations, and exporting at least one of the data and the one or more actions.Type: GrantFiled: February 22, 2021Date of Patent: August 22, 2023Assignee: International Business Machines CorporationInventors: Tian Hao, Umar Asif, Stefan Harrer, Jianbin Tang, Stefan von Cavallar, Deval Samirbhai Mehta, Jeffrey L. Rogers, Erhan Bilal, Stefan Renard Maetschke
-
Publication number: 20220280098Abstract: The exemplary embodiments disclose a system and method, a computer program product, and a computer system for assessing one or more Parkinson's disease symptoms. The exemplary embodiments may include collecting data of a user's motion, extracting one or more features from the collected data, and assessing one or more Parkinson's disease symptoms of the user based on applying one or more models to the data.Type: ApplicationFiled: March 2, 2021Publication date: September 8, 2022Inventors: Tian Hao, Jeffrey L. Rogers, Umar Asif, Erhan Bilal, Deval Samirbhai Mehta, Stefan Harrer, Jianbin Tang, Stefan von Cavallar, Paolo Fraccaro
-
Publication number: 20220269824Abstract: A method, a structure, and a computer system for privacy-preserving motion analysis. Embodiments may include collecting data corresponding to a user with one or more sensors and identifying one or more joints of the user based on the data. Embodiments may additionally include generating one or more 3D representations of the one or more joints of the user and anonymizing the one or more 3D representations by applying thereto a joint-centering and a random shuffling. Embodiments may further include classifying one or more actions of the user based on analysing the one or more 3D representations, and exporting at least one of the data and the one or more actions.Type: ApplicationFiled: February 22, 2021Publication date: August 25, 2022Inventors: TIAN HAO, Umar Asif, Stefan Harrer, Jianbin Tang, Stefan von Cavallar, Deval Samirbhai Mehta, JEFFREY L. ROGERS, Erhan Bilal, Stefan Renard Maetschke
-
Publication number: 20220125370Abstract: A method, a computer program product, and a computer system determine abnormal motion from a patient. The method includes receiving sensory data of the patient and a location in which the patient is present. The sensory data includes video data over a period of time the patient is being monitored. The method includes generating contextual information based on the sensory data. The contextual information is indicative of surroundings of the patient and characteristics of the location. The method includes generating motion information based on the sensory data. The motion information is indicative of movement of the patient in the location. The method includes generating contextual motion data by incorporating the contextual information with the motion information. The method includes determining the abnormal motion based on the contextual motion data.Type: ApplicationFiled: October 22, 2020Publication date: April 28, 2022Inventors: Umar Asif, Stefan von Cavallar, Jianbin Tang, Stefan Harrer
-
Publication number: 20220101185Abstract: A machine learning model can be updated based on collected data (i.e., initially unlabeled data). The unlabeled data can be labeled based on comparisons to labeled data. The newly labeled data, referred to as “weak labeled data” (as it was labeled without direct input of a professional) can then be used as training data in order to retrain the machine learning model.Type: ApplicationFiled: September 29, 2020Publication date: March 31, 2022Inventors: Umar Asif, Stefan von Cavallar, Jianbin Tang, Stefan Harrer
-
Publication number: 20220101184Abstract: A machine learning model can be optimized for deployment on a device based on hardware specifications of the device. An existing model is acquired and pruned to reduce hardware resource consumption of the model. The pruned model is then trained based on training data. The pruned model is also trained based on a collection of “teacher” models. Performance of the trained model is then evaluated and compared to performance requirements, which can be based on the hardware specifications of a device.Type: ApplicationFiled: September 29, 2020Publication date: March 31, 2022Inventors: Umar Asif, Stefan von Cavallar, Jianbin Tang, Stefan Harrer
-
Patent number: 11074351Abstract: A method, computer program product, and a system where a processor(s), obtains pre-recorded visual data from a given location, captured by an image capture device at a visual input location at the given location. The processor(s) determines a position of the image capture device utilized to capture the visual data. The processor(s) obtains known landmarks from data related to the given location. The processor(s) analyzes the visual data to identify a portion of the known landmarks in the visual data, where the analyzing generates matched landmarks. The processor(s) determines a spatial orientation and positioning of the visual input location with respect to the matched landmarks, at the given location. The processor(s) generates an encryption key, utilizing the spatial orientation and the positioning of the visual input location with respect to the matched landmarks. The processor(s) encrypts a message with the encryption key, generating an encrypted message.Type: GrantFiled: August 21, 2018Date of Patent: July 27, 2021Assignee: International Business Machines CorporationInventors: Mark Carl Hampton, Timothy M. Lynar, John M. Wagner, Stefan von Cavallar
-
Patent number: 11061912Abstract: A method includes building a well-being profile for a given user based on data obtained from one or more sources associated with the given user. One or more personalized incentives for the given user are identified based on the well-being profile. A personalized route is generated based on the one or more identified personalized incentives, with the personalized route being designed to improve a well-being of the given user. A notification is transmitted to a given client device associated with the given user over a network, with the notification causing the given client device to display the personalized route.Type: GrantFiled: October 26, 2016Date of Patent: July 13, 2021Assignee: International Business Machines CorporationInventors: Lenin Mehedy, Stefan von Cavallar, Nicholas I. Waywood
-
Patent number: 10983032Abstract: An apparatus for automatically separating and collecting a fluid stream into multiple portions, including a tubing to receive the fluid stream, a plurality of valves attached to the tubing in spaced relation along the length of the tubing and a plurality fluid collection containers attached to the valves. A controller controls the activation of the plurality of valves to collect and separate portions of the fluid stream in the plurality of the fluid collection containers. A flow meter detects the flow of the fluid stream in the tubing and measures a flow rate of the fluid stream. The controller activates the valves based on the detection of the fluid and the flow rate. The controller also activates the valves based on the timing of the fluid stream. The controller also monitors the flow rate over time and activates the valves in sequence based on the flow rate.Type: GrantFiled: November 13, 2018Date of Patent: April 20, 2021Assignee: International Business Machines CorporationInventors: Stefan von Cavallar, Kerry J. Halupka, Rahil Garnavi, Rajib Chakravorty, Suman Sedai
-
Patent number: 10979472Abstract: Embodiments are directed to a computer-implemented method of displaying a presentation. The method includes analyzing a set of media files that include the presentation. Thereafter, each media file is displayed in a predetermined order. Upon the detection of an audience viewing the media files, the displaying of the media files is adjusted based on characteristics of the audience.Type: GrantFiled: September 29, 2016Date of Patent: April 13, 2021Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Stefan von Cavallar, Timothy M. Lynar, John M. Wagner
-
Patent number: 10789604Abstract: A reality augmenting computer-implemented method, system, and computer program product, includes detecting a consumer and at least one of a product and a location, determining a current sensory state of the consumer, calculating a desired sensory state to achieve a target mood based on a correlation between the target mood and a user model, and executing an action according to the desired sensory state by a wearable to change the current sensory state of the consumer to the target mood.Type: GrantFiled: August 26, 2016Date of Patent: September 29, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Stefan Von Cavallar, Timothy Michael Lynar, Jorge Andres Moros Ortiz, John Michael Wagner
-
Patent number: 10785546Abstract: A computer-implemented method includes determining a characteristic of a target audience for a viewing of a visual media, extracting a frame of the visual media from an electronic signal, identifying an object that is visible in the frame of the visual media, and digitally inserting an item of advertising content into the frame of the visual media, in a region of the object, wherein a selection of the item of advertising content has been optimized for at least the characteristic of the audience.Type: GrantFiled: May 1, 2017Date of Patent: September 22, 2020Assignee: International Business Machines CorporationInventors: Timothy Lynar, Stefan von Cavallar, John Wagner
-
Patent number: 10719075Abstract: The present invention provides a method, a system, and a computer program product of directive controlled vehicles. In an exemplary embodiment, the system includes a plurality of computing systems comprising at least two vehicles, a directive source to transmit a directive to at least one of the plurality of computing systems, and a command source to issue at least one command to at least one vehicle of the at least two vehicles, wherein the at least one command controls a movement pattern and an operation of the at least one vehicle of the at least two vehicles based on the directive.Type: GrantFiled: September 25, 2017Date of Patent: July 21, 2020Assignee: International Business Machines CorporationInventors: Stefan von Cavallar, Timothy M. Lynar
-
Patent number: 10704994Abstract: An apparatus for the collection of multiple samples of a fluid stream. The apparatus includes a plurality fluid collection containers arranged to receive separate portions of the fluid stream in a temporal sequence and a sealing mechanism provided on each fluid collection container configured to close the fluid collection containers when filled by a portion of the fluid stream and to cause the fluid stream to flow to the next fluid collection container in the sequence. The fluid collection containers separately collect at least a beginning portion of the fluid stream, a mid-portion of the fluid stream and an end-portion of the fluid stream. Each of the fluid collection containers may be detachably connected to tubing held in a housing having a sloped upper surface for receiving the fluid stream and an inlet for directing the fluid stream to the tubing. The housing may be a fluid collection cup.Type: GrantFiled: November 13, 2018Date of Patent: July 7, 2020Assignee: International Business Machines CorporationInventors: Kerry J. Halupka, Stefan von Cavallar, Rajib Chakravorty, Suman Sedai, Rahil Garnavi
-
Patent number: 10692112Abstract: A display control method, system, and non-transitory computer readable medium for a digital billboard display, include an attribute identification circuit configured to identify attributes of each user of a group of users viewing the digital billboard display, a content determining circuit configured to determine a content type to be displayed on the digital billboard based on an aggregation of all of the attributes of the group of users identified by the attribute identification circuit, and a display augmenting circuit configured to deliver the content type to the digital billboard display.Type: GrantFiled: June 28, 2016Date of Patent: June 23, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Stefan von Cavallar, Timothy Michael Lynar, Jorge Andres Moros Ortiz, John Michael Wagner
-
Publication number: 20200150000Abstract: An apparatus for the collection of multiple samples of a fluid stream. The apparatus includes a plurality fluid collection containers arranged to receive separate portions of the fluid stream in a temporal sequence and a sealing mechanism provided on each fluid collection container configured to close the fluid collection containers when filled by a portion of the fluid stream and to cause the fluid stream to flow to the next fluid collection container in the sequence. The fluid collection containers separately collect at least a beginning portion of the fluid stream, a mid-portion of the fluid stream and an end-portion of the fluid stream. Each of the fluid collection containers may be detachably connected to tubing held in a housing having a sloped upper surface for receiving the fluid stream and an inlet for directing the fluid stream to the tubing. The housing may be a fluid collection cup.Type: ApplicationFiled: November 13, 2018Publication date: May 14, 2020Inventors: Kerry J. Halupka, Stefan von Cavallar, Rajib Chakravorty, Suman Sedai, Rahil Garnavi
-
Publication number: 20200150001Abstract: An apparatus for automatically separating and collecting a fluid stream into multiple portions, including a tubing to receive the fluid stream, a plurality of valves attached to the tubing in spaced relation along the length of the tubing and a plurality fluid collection containers attached to the valves. A controller controls the activation of the plurality of valves to collect and separate portions of the fluid stream in the plurality of the fluid collection containers. A flow meter detects the flow of the fluid stream in the tubing and measures a flow rate of the fluid stream. The controller activates the valves based on the detection of the fluid and the flow rate. The controller also activates the valves based on the timing of the fluid stream. The controller also monitors the flow rate over time and activates the valves in sequence based on the flow rate.Type: ApplicationFiled: November 13, 2018Publication date: May 14, 2020Inventors: Stefan von Cavallar, Kerry J. Halupka, Rahil Garnavi, Rajib Chakravorty, Suman Sedai
-
Patent number: 10650918Abstract: A computer-implemented method for determining routes includes receiving a user's location and health measures, for a plurality of users, analyzing the plurality of users and their corresponding locations to determine health behaviors at a given location and time, receiving a request from a user for a route, developing a route to the user's destination from a current location to obtain a target health behavior within a given threshold or constraint based on the plurality of user's healthy behaviors, and presenting the a route on a computing device.Type: GrantFiled: June 1, 2017Date of Patent: May 12, 2020Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Paul R. Bastide, Isabell Filiz Kiral-Kornek, Dwarikanath Mahapatra, Susmita Saha, Arun Vishwanath, Stefan Von Cavallar