International Business Machines Corporation

David Bacarella

Sumit Patel

Nicholas Todd Lawrence

James H Barnebee, Iv

Ying Chen

Aaron Michael Cohen

Ravi Mani

Lawrence Candes

Stephan Joseph Roorda

Arunava Majumdar

Ginés Carrascal De Las Heras

Pattern recognition by receiving a set multi-variable data records, each record including a plurality of variables, representing at least two of the plurality of variables as geometric shapes, defining a boundary enclosing the geometric shapes, configuring at least one geometric shape to move within the boundary, capturing a location of each of the geometric shapes within the boundary as a system state, one or more times, combining one or more system states as a system signature, providing a model trained to recognize patterns in system signatures, and recognizing a pattern in the system signature.

Multi-variable pattern recognition for predictive deep learning models

A computer-implemented method includes: receiving, by a computing device, data corresponding to a dynamic speckle spectrum image associated with a biological sample; comparing, by the computing device, the dynamic speckle spectrum image with a plurality of training images; classifying, by the computing device, a contaminant present in the biological sample, based on the comparing; and providing, by the computing device, information regarding the classification of the contaminant.

Testing a biological sample based on sample spectrography and machine learning techniques

A system, computer program product, and method are provided to automate a framework for knowledge graph based persistence of data, and to resolve temporal changes and uncertainties in the knowledge graph. Natural language understanding, together with one or more machine learning models (MLMs), is used to extract data from unstructured information, including entities and entity relationships. The extracted data is populated into a knowledge graph. As the KG is subject to change, the KG is used to create new and retrain existing machine learning models (MLMs). Weighting is applied to the populated data in the form of veracity value. Blockchain technology is applied to the populated data to ensure reliability of the data and to provide auditability to assess changes to the data.

Machine learning model modification and natural language processing

Machine learning to integrate knowledge and augment natural language processing

Machine learning modification and natural language processing

A system, computer program product, and method are provided to automate a framework for knowledge graph based persistence of data, and to resolve temporal changes and uncertainties in the knowledge graph. Natural language understanding, together with one or more machine learning models (MLMs), is used to extract data and a data relationship from structured and/or unstructured data, create an entry in the KG and selectively store the extracted data and data relationship in the KG, assign a veracity value to the stored data, create an asset value entry in a corresponding BC ledger, and store a BC identifier with the KG entry.

Machine learning to integrate knowledge and natural language processing

A power service receives, from one or more battery enabled mobile devices, battery usage information for one or more locations within an area. A power service identifies, from the battery usage information, one or more battery usage impact factors that are location based that consume additional battery power for the area. A power service predicts, based on the one or more battery usage impact factors for the area a predicted battery consumption factor in the area. A power service updates one or more user schedules of users with one or more events scheduled in the area with an alert identifying the predicted battery consumption factor in the area.

Optimizing scheduled charging of battery enabled devices based on a predicted battery consumption factor for an area

A power service receives one or more types of individual current usage from one or more battery enabled devices. The power service receives a user schedule of predicted usage for the one or more battery enabled devices. The power service analyzes the one or more types of current usage and the predicted usage to identify a separate recommended charging time and charging location for each of the one or more battery enabled devices. The power service updates the user schedule to specify at least one event for scheduling each separate recommended charging time and charging location for each of the one or more battery enabled devices.

Scheduling optimized charging of battery enabled devices based on power usage impact data received from multiple sources

A power service receives, from battery enabled devices, battery charging information for multiple locations, wherein the battery charging information specifies the type of power source a device is being charged from and an amount of time charged. The power service analyzes the battery charging information for the locations to identify moving charging locations that change location. The power service filters the locations to identify locations where the type of power source is a power outlet. The power service filters the locations against a security map to identify a first selection of locations that are publicly accessible and a second selection of locations that require a security authorization. The power service generates a base map of the selection of locations. The power service specifies the base map for each user based on a schedule of the user identifying predicted locations and whether each particular user has a required security authorization.

Specifying a map of available locations for recharging battery enabled devices based on a schedule of predicted locations for a user

A power service receives a user schedule of one or more events each specifying predicted usage and predicted location for one or more battery enabled mobile devices. The power service accesses one or more battery usage impact factors for each predicted location. The power service analyzes the predicted usage and predicted location for each of the one or more events and the one or more battery usage impact factors to predict at least one recommended charging time and charging location for each of the one or more battery enabled mobile devices. The power service updates the user schedule to specify at least one charging event for each at least one recommended charging time and charging location.

Growing community of inventors

Naperville, IL, United States of America

David Bacarella