-
1.发明公开公开(公告)号：US20230170057A1
公开(公告)日：2023-06-01
申请号：US17456966
申请日：2021-11-30
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： James R. Kozloski , Viatcheslav Gurev , Tim Rumbell
Abstract: A method, computer system, and a computer program product for model inversion is provided. The present invention may include training a generator of a generative adversarial network to sample a distribution of input parameters of a mechanistic model. The present invention may include generating a distribution of parameters for the mechanistic model. The present invention may include simulating the mechanistic model with the distribution of parameters.
-
公开(公告)号：US20230207085A1
公开(公告)日：2023-06-29
申请号：US17560814
申请日：2021-12-23
Applicant: International Business Machines Corporation
Inventor： James R. Kozloski , Tim Rumbell , VIATCHESLAV GUREV
Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include replicating, with patient parameters, a set of patient data of a patient and conditioning said patient parameters with at least one measure from said patient. The operations may include parameterizing a pharmacokinetic model with said patient parameters and sampling said patient parameters with a constrained optimization generative adversarial network. The operations may include calculating dosage data of a pharmaceutical with said patient parameters with said constrained optimization generative adversarial network and communicating said dosage data to a user.
-
公开(公告)号：US11133026B2
公开(公告)日：2021-09-28
申请号：US16239988
申请日：2019-01-04
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Michael S. Gordon , James Humble , Tim Rumbell , Ryan T. Gordon
Abstract: A natural language processing system for analyzing speech includes a computer processing device configured to receive recorded speech of a person. The computer processing device constructs a baseline speech model of the person, the baseline speech model of the person including a property of speech based on a personal attribute of the person, compares current recorded speech of the person to the baseline speech model of the person to determine a deviation of the property of speech therebetween, and determines if the deviation of the property of speech meets a threshold of the property of speech that is defined for a disorder.
-
公开(公告)号：US20190188650A1
公开(公告)日：2019-06-20
申请号：US15841764
申请日：2017-12-14
Applicant: International Business Machines Corporation
Inventor： James Humble , James R. Kozloski , Clifford A. Pickover , Tim Rumbell
CPC classification number: G06Q10/1097 , G06K9/00335 , G06Q10/063116
Abstract: A time-management planning method, system, and computer program product, includes determining at least one of a cognitive state and a contextual state of a user, compiling a specification of a cognitive goal associated with accomplishing a scheduled task for a period of time, and performing a planning action, via a time management software platform, to adjust the scheduled task based on the specification of the cognitive goal and the at least one of the cognitive state and the contextual state of the user.
-
公开(公告)号：US11227692B2
公开(公告)日：2022-01-18
申请号：US15856582
申请日：2017-12-28
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Tim Rumbell , James R. Kozloski
Abstract: One or more embodiments of the present invention include a computer-implemented method for generating neuronal models for personalized drug treatment selection for a patient. The method includes receiving allelic information for at least one neurophysiological coding region of a genome of the patient, and a physiological model of a disease associated with the genome. The method further includes determining a set of ion channels correlated with the allelic information, and receiving a set of phenotypic measurement ranges associated with the ion channels from the determined set. The method further includes performing a simulation to generate multiple neuronal models comprising the set of ion channels with parameter values within the corresponding phenotypic measurement ranges, and analyzing the generated neuronal models to identify components that affect the physiological model. The method further includes selecting a drug for the patient based at least in part on the identified components.
-
Patent Agency Ranking
6.发明申请公开(公告)号：US20200219529A1
公开(公告)日：2020-07-09
申请号：US16239988
申请日：2019-01-04
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Michael S. Gordon , James Humble , Tim Rumbell , Ryan T. Gordon
Abstract: A natural language processing system for analyzing speech includes a computer processing device configured to receive recorded speech of a person. The computer processing device constructs a baseline speech model of the person, the baseline speech model of the person including a property of speech based on a personal attribute of the person, compares current recorded speech of the person to the baseline speech model of the person to determine a deviation of the property of speech therebetween, and determines if the deviation of the property of speech meets a threshold of the property of speech that is defined for a disorder.
-
公开(公告)号：US20230207084A1
公开(公告)日：2023-06-29
申请号：US17560734
申请日：2021-12-23
Applicant: International Business Machines Corporation
Inventor： James R. Kozloski , Tim Rumbell , VIATCHESLAV GUREV
Abstract: A system may include a memory and a processor in communication with the memory. The processor may be configured to perform operations. The operations may include training a cr-GAN model with a first data set of a first pharmaceutical and a second data set of a second pharmaceutical. The operations may include conditioning the cr-GAN model with at least one conditional variable and generating, with the cr-GAN model, patient parameters. The operations may include replicating a set of patient data of a patient with the patient parameters and calculating dosage data with the patient parameters based on a therapeutic target. The operations may include displaying the dosage data to a user.
-
公开(公告)号：US11499627B2
公开(公告)日：2022-11-15
申请号：US16004526
申请日：2018-06-11
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： James Humble , James R. Kozloski , Clifford A. Pickover , Tim Rumbell
Abstract: Techniques related to vehicle operation. A processor determines that at least one condition is met related to a vehicle. In response to the at least one condition being met, the processor generates a natural language output having a query. The processor determines that an affirmative response to the query is received and causes a downshift of a transmission of the vehicle in response to the affirmative response.
-
公开(公告)号：US11093904B2
公开(公告)日：2021-08-17
申请号：US15841764
申请日：2017-12-14
Applicant: International Business Machines Corporation
Inventor： James Humble , James R. Kozloski , Clifford A. Pickover , Tim Rumbell
Abstract: A time-management planning method, system, and computer program product, includes determining at least one of a cognitive state and a contextual state of a user, compiling a specification of a cognitive goal associated with accomplishing a scheduled task for a period of time, and performing a planning action, via a time management software platform, to adjust the scheduled task based on the specification of the cognitive goal and the at least one of the cognitive state and the contextual state of the user.
-
公开(公告)号：US20190206573A1
公开(公告)日：2019-07-04
申请号：US15856582
申请日：2017-12-28
Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATION
Inventor： Tim Rumbell , James R. Kozloski
Abstract: One or more embodiments of the present invention include a computer-implemented method for generating neuronal models for personalized drug treatment selection for a patient. The method includes receiving allelic information for at least one neurophysiological coding region of a genome of the patient, and a physiological model of a disease associated with the genome. The method further includes determining a set of ion channels correlated with the allelic information, and receiving a set of phenotypic measurement ranges associated with the ion channels from the determined set. The method further includes performing a simulation to generate multiple neuronal models comprising the set of ion channels with parameter values within the corresponding phenotypic measurement ranges, and analyzing the generated neuronal models to identify components that affect the physiological model. The method further includes selecting a drug for the patient based at least in part on the identified components.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.017 seconds)
