International Business Machines Corporation

Kyndryl, Inc.

Roxana Monge Nunez

Edgar Adolfo Zamora Duran

Franz Friedrich Liebinger Portela

Maja Vukovic

Juan G Rodriguez

Sarbajit Kumar Rakshit

Clifford A Pickover

Shikhar Kwatra

Itzhack Goldberg

Cesar Augusto Rodriguez Bravo

Michael Bar-Joshua

Franz F Liebinger

Michael S Gordon

Jinho Hwang

Jeronimo Irazabal

Yanil Zeledon

Effron Esseiva

Juan Gabriel Rodriguez Arguedas

Valentina Salapura

Craig M Trim

Peeyush Jaiswal

Mauro Marzorati

Komminist S Weldemariam

Priyansh Jaiswal

Luis Carlos Cruz Huertas

Chen Lin

Girmaw Abebe Tadesse

Raghuram Srinivasan

Jose Cano Zapata

Ivonne Rocio Cuervo Fajardo

Luis G Solano Enriquez

Ana Isabel Montero Soto

Franklin Gerardo Fernandez Arias

Priscilla Mariel Guzman Angulo

Juan G Rodriguez Arguedas

Sheyla V Vargas

Yered Andres Cespedes Corrales

Radha Radha Mohan De

Juan G Rodriquez Arguedas

Barun Das

Joseph M Phillips, Jr

An example operation may include one or more of computing historical patterns related to fraudulent attempts from a transaction log, predicting future fraud attempts from public data, correlating the historical patterns and the predicted future fraud attempts, modifying one or more first endorsement policies based on the correlations, preventing modifying one or more second endorsement policies, the one or more second endorsement policies providing read-only access, and adding the modified one or more first endorsement policies to a smart contract.

Smart contract endorsement architecture

Controlling autonomous vehicle (AV) functions includes receiving occupant identification data from device(s) of an AV and identifying occupant(s) of the AV based on the received occupant identification data, determining a respective prioritization level for each occupant of the occupant(s), the prioritization level for each occupant dictating priority of the AV in performing commands provided to the AV by that occupant to control AV functions, receiving, from an occupant, input of a command for performance by the AV to control a function of the AV, determining whether to perform the command to control the function of the AV based on the prioritization level for the occupant, and performing processing based on the determining whether to perform the command.

Controlling autonomous vehicle functions

Approaches presented herein enable delivery of real-time internet of things (IoT) feedback to optimize a public speaking performance. More specifically, a set of data representing a speaking performance of a user is captured and analyzed to generate a speaking performance profile of the user. This profile is compared to a reference speaking performance profile and, based on the comparison, a set of performance improvement strategies for the user is generated. A performance improvement strategy is selected from the set of performance improvement strategies based on an identification of an availability of a set of IoT devices for delivery of at least one of the strategies. Instructions are then communicated, responsive to the captured speaking performance associated with the user, to an available IoT device to deliver the selected performance improvement strategy to the user through an output user interface of the available IoT device during the speaking performance.

Internet of things public speaking coach

An example operation may include one or more of computing historical patterns related to fraudulent attempts from a transaction log, predicting future fraud attempts from public data, correlating the historical patterns and the predicted future fraud attempts, modifying one or more endorsement policies based on the correlations, and adding the modified one or more endorsement policies to a smart contract.

Auto-evolving database endorsement policies

Methods and systems are disclosed for encoding and decoding data from genetic traits. In one embodiment, the invention provides a method of encoding data from genetic traits. The method comprises encoding genetic traits information, including using quantum dot wavelengths to identify distinct genetic traits, and using numbers of the quantum dots to represent probabilities associated with the traits. In an embodiment, the invention provides a genetic characteristics decoding system for decoding genetic information encoded using quantum dots in a carrier. The decoding system comprises a light source for charging the quantum dots in the carrier; a scanner for scanning the carrier to retrieve information from the charged quantum dots; and a processing system for processing the retrieved information to determine quantum dot wavelengths to identify distinct genetic traits, and to determine numbers of the quantum dots to identify probabilities associated with the genetic traits.

Encoding data from genetic traits relevant to illness diagnosis and heritage

Predicting infection risk by generating a first temporal graph of a first set of disease progression data, generating a second temporal graph of a second set of disease progression data, combining a first temporal graph node embedding and a second temporal graph node embedding, and generating a predicted infection risk according to the first temporal graph node embedding and the second temporal graph node embedding.

Predicting infection risk using heterogeneous temporal graphs

Techniques for autonomously tracking and/or predicting an alert event are provided. In one example, a system can comprise a memory that stores computer executable components. The system can also comprise a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory. The computer executable components can comprise a schedule component that determines plan information for a hub of a plurality of hubs, and the hub can be coupled to a device. The computer executable components can further comprise a tracking component that identifies a deviation from the plan information by the hub. Additionally, the computer executable components can comprise a prediction component that determines a probability that the deviation will result in an alert event.

Predictive analytics and device tracking to facilitate minimization of alert events

A computing device controls a physical locking device. The computing device determines that an authorized user has requested an unlocking of a physical security device included in a first computing device. The computing device sends a signal to a mobile computing device of the user that is in communication with the first computing device. The computing device unlocks the physical security device included in the first computing device via the mobile computing device based on the signal.

Cognitive security system

The disclosure describes techniques for generating device recommendations. The techniques include registering a plurality of Internet of Things (IoT) devices in a social IoT network, where each device performs one or more tasks and the one or more tasks include a first task. The techniques include periodically receiving, with the social IoT network, a work profile from one or more of the registered devices. The work profile includes device information associated with the one or more device tasks performed by the respective registered device. The techniques include grouping devices performing the first task into groups of similar devices, identifying, based on the device information in the work profile received from one or more of the registered devices, at least one device from the group of devices for which recommendations are to be provided, generating the recommendations for the identified device, and providing the recommendations for the identified device.

Device recommendations based on device interactions in network

A method, computer system, and a computer program product for managing and optimizing connectivity of a plurality of IoT devices based on cognitive learning is provided. The present invention may include identifying a user, wherein a plurality of user context data is stored in a user profile. The present invention may then include detecting a change in at least one current user context associated with the identified user. The present invention may also include performing a connectivity and management analysis on the detected change in the at least one current user context. The present invention may then include generating at least one optimal plan for the plurality of IoT devices associated with the identified user based on the performed connectivity and management analysis. The preset invention may further include performing at least one action based on the generated at least one optimal plan.

Cognitive engine for multiple internet of things devices

A set of gesture commands are learned. Each gesture in the set of gesture commands controls a function of one or more computing devices. A first gesture received from a user is identified. A determination is made whether at least one computing device associated with the identified gesture is active. In response to determining that at least one computing device associated with the identified gesture is active, a determination is made whether the user associated with the identified gesture is recognized. In response to determining that the user associated with the identified gesture is recognized, an action to perform on at least one computing device associated with the identified gesture is determined. The determined action is implemented.

Gesture control of internet of things devices

Approaches presented herein enable delivery of real-time internet of things (IoT) feedback to optimize a group discussion. More specifically, a set of data representing a discussion between users is captured and analyzed to generate a discussion profile that includes participation of the users. This profile is compared to a reference profile and, based on the comparison, a set of discussion participation improvement strategies for a user is generated. A strategy is selected from the set of discussion participation improvement strategies based on an identification of an availability of a set of IoT devices for delivery of the strategy. Instructions are then communicated, responsive to the captured discussion between the users, to an available IoT device to deliver the selected discussion participation improvement strategy to the user through an output user interface of the available IoT device during the discussion.

Internet of things group discussion coach

Method of collision avoidance which includes: sensing parameters by a first vehicle with respect to relative movements of the first vehicle and a second vehicle; responsive to determining by the first vehicle, based on the sensed parameters, of an impending collision with the second vehicle, communicating, by the first vehicle, a query to the second vehicle as to if the second vehicle can perform a corrective action to avoid a collision with the first vehicle; and performing, by the first vehicle and independent of any corrective action performed by the second vehicle, a corrective action to avoid a collision with the second vehicle.

Vehicle collision avoidance

A method for enhancing speech performance includes communicating, via an input/output (I/O) device, speech data of a patient with speech problems, segmenting the speech data, generating one or more feature vectors based on at least the segmented speech data, determining whether the one or more feature vectors match with one or more recognition objects pre-trained using clinical data of one or more other patients, determining a speech disorder based on a matched result between the one or more feature vectors and the one or more recognition objects, and communicating, via the I/O device, one or more ameliorative actions for mitigating the determined speech disorder.

System for enhancing speech performance via pattern detection and learning

An approach is provided for authenticating a payment card. Information is read from the payment card being used for a purchase. The information includes an identifier and data on a chip, in braille cells, and in markings in the payment card. A hash read from the chip, the identifier, and security codes derived from the braille cells and the markings are sent to a payment system. A hash of an (n+1)-th block of a blockchain is received and recorded in the chip in response to validations of the hash as matching a hash of an n-th block of the blockchain, the identifier, and the first and second security codes, and a generation of the hash of the (n+1)-th block. Data about the purchase and the hash of the (n+1)-th block are sent to the payment system.

Growing community of inventors

San Jose, Costa Rica

Roxana Monge Nunez