International Business Machines Corporation

Utopus Insights, Inc.

Universiti Brunei Darussalam

Sambaran Bandyopadhyay

Vijay Arya

Srikanth Govindaraj Tamilselvam

Ramasuri Narayanam

Ruhi Sharma Mittal

Utkarsh Milind Desai

Lokesh Nagalapatti

Rajendu Mitra

Rama C Kota

Vijay Ekambaram

Saravanan Sadacharam

Ashok Pon Kumar Sree Prakash

Mohit Jain

Sampath Dechu

Sachin Gupta

Ramachandra Kota

Tanuja Ganu

Zainul Mohammed Charbiwala

Alex Mathai

Pg Dr M Iskandar Pg Hj Petra

Akash Kumar Panda

Methods, systems, and computer program products for automatically detecting outliers in federated data are provided herein. A computer-implemented method includes obtaining local outlier-related data from multiple client systems within a federated learning environment; detecting one or more federated learning environment-level outliers from at least a portion of the multiple client systems by processing at least a portion of the obtained local outlier-related data using one or more artificial intelligence models; determining at least one calibration parameter for detecting federated learning environment-level outliers based at least in part on the one or more detected federated learning environment-level outliers; and outputting the at least one determined calibration parameter to at least a portion of the multiple client systems within the federated learning environment.

Automatically detecting outliers in federated data

Techniques for generating machine learning training data which corresponds to one or more downstream tasks are disclosed. In one example, a computer implemented method comprises generating one or more synthetic data instances for training a machine learning model, and determining a value of respective ones of the one or more synthetic data instances with respect to at least one task. One or more additional synthetic data instances for training the machine learning model are generated based at least in part on the values of the respective ones of the one or more synthetic data instances.

Generating task-specific training data

Methods, systems, and computer program products for constraints-based refactoring of monolith applications through attributed graph embeddings are provided herein. A computer-implemented method includes performing an analysis of source code of a monolith application to identify structural features and behavioral features; generating a graph structure representing the monolith application based on the identified structural features and the identified behavioral features, wherein the graph structure comprises: a plurality of nodes, each node corresponding to one of a plurality of software modules of the monolith application, and a plurality of edges between the plurality nodes, each edge representing a relationship of the corresponding nodes; automatically identifying constraints associated with the plurality of nodes in the graph structure based on the analysis of the source code; clustering the nodes using a convolutional neural network based the constraints; and outputting candidate microservices corresponding to respective ones of the clusters for refactoring the monolith application.

Constraints-based refactoring of monolith applications through attributed graph embeddings

One embodiment provides a method, including: receiving information describing an application to be split into a plurality of microservices; identifying, utilizing a microservices advisor application, application elements of the application; generating, utilizing the microservices advisor application and from the application elements, a heterogenous graph, wherein each node within the heterogenous graph represents an application element and wherein each edge within the heterogenous graph represents a relationship between two nodes connected by the edge; identifying, based upon user input identifying preferences of relationships between nodes, groups of nodes within the heterogenous graph sharing a common attribute; and providing, from the microservices advisor application, a recommendation, based upon the identified groups of nodes, for splitting the application into microservices, wherein the recommendation includes a number of microservices for the application and application elements that should be included within each of the microservices.

Heterogeneous graph generation for application microservices

A dynamic graph includes a plurality of nodes and edges at a plurality of time steps; each node corresponds to a geographic location in a first area where pest infestation information is available for a subset of locations. Each edge connects two of the nodes which are geographically proximate, has a direction based on wind direction, and has a weight based on relative wind speed. Assign node features based on weather data as well as labels corresponding to pest infestation severity. Train a graph convolutional network on the dynamic graph. Based on predicted future weather conditions for a second area different than the first area, use the trained graph convolutional network to predict, via inductive learning, pest infestation severity for future times for a new set of nodes corresponding to new geographic locations in the second area for which no pest infestation information is available.

System and method for predicting fall armyworm using weather and spatial dynamics

Methods, systems, and computer program products for dynamic pricing of energy consumed from a shared battery using real-time consumption data are provided herein. A computer-implemented method includes calculating wear cost arising from a battery shared by multiple users, wherein the wear cost is based on usage data of the battery; calculating a proportionality factor for each of the multiple users for the calculated wear cost, wherein the proportionality factor is based on individual usage of the battery; apportioning the calculated wear cost to each of the multiple users based on the user's proportionality factor; and determining a dynamic price for energy used by the battery for each of the multiple users, based on said apportioning.

Dynamic pricing of energy consumed from a shared battery using real-time consumption data

Methods, systems, and computer program products for prioritizing errors in connectivity models of distribution networks are provided herein. A computer-implemented method includes collecting geo-spatial data arising from each of multiple transformers and multiple customer meters within an electric power distribution network; collecting load data arising from each of the customer meters within the electric power distribution network; assigning one of the transformers to each of the customer meters that is not presently assigned to one of the transformers according to a connectivity model for the distribution network, wherein said assigning is based on the collected multiple items of geo-spatial data and the collected load data; computing an error probability attributable to each of the transformers and the customer meters assigned thereto within the electric power distribution network based on multiple variables; and modifying an existing field inspection schedule corresponding to the electric power distribution network based on said computing.

Identifying and prioritizing errors in connectivity models of distribution networks for efficient field inspections

Methods, systems, and computer program products for mapping wind turbines and predicting wake effects using satellite imagery data are provided herein. A computer-implemented method includes analyzing one or more satellite images depicting one or more portions of a pre-determined geographic area; detecting a group of one or more wind turbines in the pre-determined geographic area based on the analyzing step and one or more additional items of data; inferring geographic coordinates of each of the detected wind turbines; predicting a wake effect impacting one or more of the detected wind turbines based on the inferred geographic coordinates of each of the detected wind turbines and forecasted weather data; and outputting the predicted wake effect to at least one user.

Mapping wind turbines and predicting wake effects using satellite imagery data

Methods, systems, and computer program products for detecting losses in electrical networks are provided herein. A computer-implemented method includes computing a consumption estimation for each consumer associated with a network; determining a difference between (i) the consumption estimation and (ii) actual consumption for each consumer; clustering the consumers into a cluster based on a consumption pattern associated with each consumer; determining a level of deviation of (i) the consumption pattern associated with each consumer from (ii) a consumption pattern representative of the cluster; clustering the consumers into two or more clusters based on a consumption pattern during a first interval of time and during a second interval of time; determining, for each consumer, a level of evolution from (i) a first cluster during the first interval to (ii) a second cluster during the second interval; and identifying consumers associated with a given loss within the network.

Detecting non-technical losses in electrical networks based on multi-layered statistical techniques from smart meter data

A method of two-factor authentication for gaining access to an application using at least a first device and a second device registered to a user. The first and second devices each have a plurality of sensors for detecting activity modalities of the user on the first and the second devices and are in communication with a server computer. In the method, the server computer: receives credentials and detected activity modality for gaining access to the application from the first device; sends a request to the second device registered to the user for activity modality of the user; receives the detected activity modality from the second device; compares the detected activity modality of first device to the detected activity modality of the second device; and if the detected activity modalities of first device and the second device match, granting access to the user on the first device to the application.

Activity recognition to confirm secure authentication of a user

One embodiment provides a method for improving cartographic data using utility data, the method including: obtaining cartographic information; obtaining geo-location information associated with at least one utility asset; utilizing at least one processor to execute computer code that performs the steps of: generating, based on the geo-location information, a cartographic representation of the at least one utility asset; and modifying, based on the cartographic representation, the cartographic information. Other aspects are described and claimed.

Growing community of inventors

Bengaluru, India

Sambaran Bandyopadhyay