-
公开(公告)号:GB2579976B
公开(公告)日:2022-03-16
申请号:GB202003640
申请日:2017-12-19
Applicant: IBM
Inventor: SEAN FUOCO , AARON BAUGHMAN , PALANI SAKTHI , CHENNAKESAVALU GOVINDASAMY , CHARLES BELLER
Abstract: A computer-implemented method comprising: receiving, by a computing device, biometrics data of a user via a user device as part of a request to access a secure device; applying, by the computing device, a non-invertible function to the biometrics data to scramble the biometrics data; determining, by the computing device, whether the scrambled biometrics data matches a pre-registered version of the scrambled biometrics data; and providing, by the computing device, an authentication message to the secure device requesting authentication of the user based on determining that the scrambled biometrics data matches the pre-registered version of the scrambled biometrics data, wherein the providing the authentication message provides a user of the user device with access to the secure device.
-
公开(公告)号:GB2589501B
公开(公告)日:2021-11-17
申请号:GB202100083
申请日:2019-06-11
Applicant: IBM
Inventor: TODD RUSSELL WHITMAN , NICHOLAS MCCRORY , DAVID BASTIAN , AARON BAUGHMAN
Abstract: Aspects of the present invention disclose a method, computer program product, and system for identifying a robotic. The method includes receiving an authentication request for an unknown robotic device asserting to be a first robotic device. The method further includes receiving a first identification dataset for the first robotic device. The method further includes issuing an identification action to the unknown robotic device. The method further includes generating a second identification dataset for the unknown robotic device based upon a response to the identification action received from the unknown robotic device. The method further includes in response to determining the first identification dataset matches the second identification dataset, determining that the unknown robotic device is the first robotic device. The method further includes authenticating the unknown robotic device in response to determining that the unknown robotic device is the first robotic device.
-
公开(公告)号:GB2587584B
公开(公告)日:2021-10-27
申请号:GB202100132
申请日:2019-06-13
Applicant: IBM
Inventor: TODD WHITMAN , AARON BAUGHMAN , DAVID BASTIAN , NICHOLAS MCCRORY
IPC: H04N19/20 , H04N19/149 , H04N21/433 , H04N21/435 , H04N21/439 , H04N21/4402
Abstract: A method and system for improving audio and video multimedia modification and presentation is provided. The method includes receiving an audio/video stream and analyzing objects of the audio/video stream for generating predictions with respect to the objects. Component analysis code is executed with respect to the audio/video stream and an object is removed from the audio/video stream resulting in a modified audio/video stream being generated thereby reducing hardware storage and transfer size requirements of the audio/video stream. The modified audio/video stream is presented to a user via a graphical user interface.
-
公开(公告)号:GB2589237A
公开(公告)日:2021-05-26
申请号:GB202019481
申请日:2019-05-24
Applicant: IBM
Inventor: GARY FRANCIS DIAMANTI , AARON BAUGHMAN , MAURO MARZORATI
IPC: G06N5/00
Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: identifying a training data set and defining a window for an initial beta value representing bias tolerated in formulating expectation conditional to each feature vector from the training data set. The conditional expectations are parallelly regularized by use of DNA computer. Amongst numerous combinations of candidate models, a best fit ensemble is produced as the machine learning model for predicting targeted outcomes based on inputs other than the training data set.
-
公开(公告)号:GB2584583A
公开(公告)日:2020-12-09
申请号:GB202015562
申请日:2019-03-06
Applicant: IBM
Inventor: AARON BAUGHMAN , STEPHEN HAMMER , MICAH FORSTER
Abstract: Simulating uncertainty in an artificial neural network is provided. Aleatoric uncertainty is simulated to measure what the artificial neural network does not understand from sensor data received from an object operating in a real-world environment by adding random values to edge weights between nodes in the artificial neural network during backpropagation of output data of the artificial neural network and measuring impact on the output data by the added random values to the edge weights between the nodes. Epistemic uncertainty is simulated to measure what the artificial neural network does not know by dropping out a selected node from each respective layer of the artificial neural network during forward propagation of the sensor data and measuring impact of dropped out nodes on the output data of the artificial neural network. An action corresponding to the object is performed based on the impact of simulating the aleatoric and epistemic uncertainty.
-
公开(公告)号:GB2599334A
公开(公告)日:2022-03-30
申请号:GB202200630
申请日:2020-06-12
Applicant: IBM
Inventor: CRAIG TRIM , MARY RUDDEN , AARON BAUGHMAN , STEFAN VAN DER STOCKT , BERNARD FREUND , AUGUSTINA RAGWITZ
Abstract: A transitive closure data structure is constructed for a pair of features represented in a vector space corresponding to an input dataset. The data structure includes a set of entries corresponding to a set of all possible paths between a first feature in the pair and a second feature in the pair in a graph of the vector space. The data structure is reduced by removing a subset of the set of entries such that only a single entry corresponding to a single path remains in the transitive closure data structure. A feature cross is formed from a cluster of features remaining in a reduced ontology graph resulting from the reducing the transitive closure data structure. A layer is configured in a neural network to represent the feature cross, which causes the neural network to produce a prediction that is within a defined accuracy relative to the dataset.
-
公开(公告)号:GB2579976A8
公开(公告)日:2022-01-19
申请号:GB202003640
申请日:2017-12-19
Applicant: IBM
Inventor: SEAN FUOCO , AARON BAUGHMAN , PALANI SAKTHI , CHENNAKESAVALU GOVINDASAMY , CHARLES BELLER
IPC: G06F21/32
Abstract: A computer-implemented method comprising: receiving, by a computing device, biometrics data of a user via a user device as part of a request to access a secure device; applying, by the computing device, a non-invertible function to the biometrics data to scramble the biometrics data; determining, by the computing device, whether the scrambled biometrics data matches a pre- registered version of the scrambled biometrics data; and providing, by the computing device, an authentication message to the secure device requesting authentication of the user based on determining that the scrambled biometrics data matches the pre- registered version of the scrambled biometrics data, wherein the providing the authentication message provides a user of the user device with access to the secure device.
-
公开(公告)号:GB2576463B
公开(公告)日:2021-10-20
申请号:GB201917684
申请日:2018-04-26
Applicant: IBM
Inventor: AARON BAUGHMAN , DIWESH PANDEY , JOHN PERRINO , TODD WHITMAN
Abstract: A determination can be made as to whether a user of an augmented reality device is within a threshold distance from a configurable physical apparatus including at least one display configured to emit light. Responsive to determining that the user is within the threshold distance from the configurable physical apparatus, a communication link can be established between the augmented reality device and a controller of the configurable physical apparatus. The controller can be initiated to change the configurable physical apparatus from a first configuration to a second configuration. In the first configuration the at least one display can visually depict textures causing the physical apparatus to look like a first type of ceiling or a first type of floor. In the second configuration the at least one display can visually depict textures causing the physical apparatus to look like a second type of ceiling or a second type of floor.
-
公开(公告)号:GB2573899B
公开(公告)日:2020-04-22
申请号:GB201910243
申请日:2018-01-04
Applicant: IBM
Inventor: MAURO MARZORATI , AARON BAUGHMAN , AHMED NASSAR , MICHAEL BARYLA
IPC: H04N21/262 , H04N21/258 , H04N21/266 , H04N21/435
Abstract: From a live streaming of a main content, an already streamed portion of the main content is analyzed to identify an occurrence of a climactic event in the main content. Based on the analysis, a set is constructed of feature values that are representative of the climactic event in the already streamed portion of the main content. A non-climactic period is forecasted during which a likelihood of an occurrence of any climactic event is below a threshold likelihood. A secondary content is inserted in the live streaming of the main content during the non-climactic period, such that a likelihood of the secondary content insertion interrupting the live streaming during a second climactic event is less than a second threshold of likelihood. The live streaming of the main content is continued after the secondary content is completely transmitted in the live streaming.
-
公开(公告)号:GB2576463A
公开(公告)日:2020-02-19
申请号:GB201917684
申请日:2018-04-26
Applicant: IBM
Inventor: AARON BAUGHMAN , DIWESH PANDEY , JOHN PERRINO , TODD WHITMAN
IPC: G06F3/01
Abstract: A determination can be made as to whether a user of an augmented reality device (110) is within a threshold distance from a configurable physical apparatus (130).Responsive to determining that the user is within the threshold distance from the configurable physical apparatus (130), a communication link can be established between the augmented reality device (110) and a controller (134) of the configurable physical apparatus (130). The augmented reality device (110) can initiate the controller (134) of the configurable physical apparatus to change the configurable physical apparatus (130) from a first configuration to a second configuration, wherein the second configuration accessibility of the configurable physical apparatus (130) to the user.
-
-
-
-
-
-
-
-
-