International Business Machines Corporation

International Business Corporation

Mudhakar Srivatsa

Raghu Kiran Ganti

Dakshi Agrawal

Dinesh C Verma

Joshua M Rosenkranz

Ramya Raghavendra

Saritha Arunkumar

Vasileios Pappas

Supriyo Chakraborty

Linsong Chu

Pranita Sharad Dewan

Shreeranjani Srirangamsridharan

Mathews Thomas

Bong Jun Ko

Stephen D Pipes

Utpal Mangla

Petros Zerfos

Franck Vinh Le

Nirmit V Desai

Satishkumar Sadagopan

Arun Kwangil Iyengar

Sihyung Lee

Yeon-Sup Lim

Kisung Lee

Murthy V Devarakonda

Ravindranath Kokku

Sameh W Asaad

Chatschik Bisdikian

Palanivel Andiappan Kodeswaran

Bruce Oliver Anthony, Jr

Sayandeep Sen

Nithya Rajamani

Shiqiang Wang

Thai V Le

Liang Ma

Joseph W Ziskin

Roger Moussalli

Michael G Hill

Omer Tripp

Kai Liu

Erich Miles Nahum

Sheng Huang

Shubhadip Ray

Jeffrey James Jonas

Swati Rallapalli

Norbert Herman

Xiao Yan Chen

Ting He

Jian Yin

Jae-Wook Ahn

Alina Beygelzimer

Gerald Coon

Shen Li

Mahmood Saajan Ashek

Ho Y Wong

Jingjing Wang

Satish Sadagopan

Wei Gao

Dajung Lee

Seema Nagar

Robert Bruce Nicholson

Seraphin Bernard Calo

Praveen Jayachandran

Anastasios Kementsietsidis

Enara C Vijil

Murtaza Zafer

Vijay Arya

Thai Franck Le

Amitkumar Manoharrao Paradkar

Catherine Helen Crawford

Jonathan Ian Settle

Matthew Edward Duggan

Kristian Jon Stewart

Nizar Lethif

Shahrokh Daijavad

Thiago Bianchi

Pooja Aggarwal

Chander Govindarajan

Michele Merler

Dipyaman Banerjee

Carlos Henrique Andrade Costa

Venkateswara Reddy Madduri

Rohan R Arora

William Cornejo

Xuan-Hong Dang

Venkat Raghavan

Achille Fokoue

Janusz Marecki

Kavya Govindarajan

Priyanka Prakash Naik

Chaitanya Kumar

Tuan Minh Hoang Trong

Dipanwita Guhathakurta

Mohammad Siddiqui

Venkatesh Ashok Rao Rao

Dean Steuer

Laura Wynter

Ramey Ghabros

Somesh Jha

Mojdeh Sayari Nejad

A system, computer program product, and method are provided for distributed data workflow semantics. A pipeline, such as a machine learning pipeline, is represented in a data flow graph (DFG) with nodes and edges. The represented nodes are configured to be annotated with an operational semantic. On order of execution of the pipeline is discovered through the node annotation(s) represented in the annotated DFG, and execution of the pipeline is based on the discovered order. A control signal formatted based on the executed pipeline is configured to dynamically and selectively control an operatively coupled physical hardware device.

Annotation of a machine learning pipeline with operational semantics

The present inventive concept provides for a method of unmanned machine synchronization using robotic sensing. The method includes generating at least one physical signal in the vicinity of at least one unmanned machine. The at least one generated physical signal is received by the at least one unmanned machine. At least one task is performed by the at least one unmanned machine based on the at least one received generated physical signal.

Unmanned machine synchronization using robotic sensing

A method, computer system, and a computer program product is provided for establishing a dynamically adaptive network firewall. A firewall model is established that identifies resources that can be used and a plurality of nodes that connect to one another to form a network. A set of external rules and policies are provided to each resource. The firewall implemented using the firewall model upon receiving of incoming data and upon traffic flow. The firewall expands or contracts the network by adding or removing resources according to work that needs to be performed. The work includes both tasks to be completed and efforts that has to be taken by the firewall to ensure security by preventing unauthorized access into the network.

Polymorphic dynamic firewall

A computer-implemented method, a computer system and a computer program product route meeting sessions through a venue based on device availability. The method includes identifying a plurality of sessions in a venue network, where each session in the plurality of sessions comprises session data that is associated with a network slice. The network slice includes connection requirements. The method also includes receiving a connection request from a user, where the connection request includes a session in the plurality of sessions. The method further includes determining an available device to receive the session data, where the available device satisfies the connection requirements of the network slice. Lastly, the method includes associating the available device with the network slice, where the session data is transmitted to the available device.

Flexible orchestration of session content in venue networks

In an approach to identifying occluded objects, a computer retrieves a first image that includes an object at least partially occluded by one or more occlusions. A computer removes the one or more occlusions from the first image to create a partial object in a second image. A computer runs a detection model with the second image to predict one or more identifications of a symbol represented by the partial object. A computer determines top predictions of the one or more identifications of the symbol by the detection model. A computer identifies at least one geometric property associated with the one or more identifications of the symbol included in the one or more top predictions. A computer applies the at least one geometric property to the partial object. A computer determines a probability of the one or more top predictions correctly identifying the symbol represented by the partial object.

Identifying occluded objects in engineering drawings

Provided are a computer-implemented method, a computer program product, and a computer system for drone deployment for distributed asset maintenance and repair. Embodiments identify a fix for a problem at an asset and identify a drone to perform the fix. Embodiments generate an initial flight plan that describes a drone flight path for the drone, and embodiments generate an updated flight plan for the drone by updating the drone flight path using real-time air traffic data, real-time road traffic data, and real-time drone flight path conditions obtained from one or more edge devices. Embodiments generate an overall flight plan for the drone and one or more other drones using a predicted cost and a predicted period of time for the updated drone flight path. Embodiments send a drone flight path from the overall flight plan to the drone with instructions to fix the problem.

Drone deployment for distributed asset maintenance and repair

A system and method are provided for discovering k-nearest-neighbors to a given point within a certain distance d. The method includes constructing an index of geometries using geohashes of geometries as an indexing key to obtain an indexed set of geometries, and calculating a geohash representation of the given point with a resolution equal to a magnitude value of d. The method includes searching for a closest-prefix geometry from the indexed set using the geohash representation of the given point, and identifying geometries from the indexed set having a same prefix as the closest-prefix geometry. The method further includes calculating distances between the given point and the geometries identified from the indexed set having the same prefix as the closest-prefix geometry, and determining k geometries with respective shortest distances less than d from the geometries identified from the indexed set having the same prefix as the closest-prefix geometry.

Fast and accurate geomapping

Embodiments for providing rare topic detection using hierarchical topic modeling by a processor. A hierarchical topic model may be learned from one or more data sources. One or more dominant words in a selected cluster may be iteratively removed using the hierarchical topic model. The dominant words may relate to one or more primary topics of the cluster. The learned hierarchical topic model may be seeded with one or more words, n-grams, phrases, text snippets, or a combination thereof to evolve the hierarchical topic model and the removed dominant words are reinstated upon completion of the seeding.

Rare topic detection using hierarchical clustering

Embodiments related to using a foundational model for network packet traces. A technique includes receiving network traffic of a network and extracting features from the network traffic, the features having a function related to communications in the network. The technique includes generating tokens from the features, each of the features corresponding to a respective one of the tokens, training a machine learning model by inputting the tokens, the machine learning model being trained to output contextual embeddings for the tokens, and using the contextual embeddings to determine an anomaly in the network traffic.

Foundational model for network packet traces

Aspects of the present disclosure relate to annotating or tagging customer data. In some embodiments, the annotating can include summarizing touchpoints into k-hot encoding feature vectors, mapping the feature vectors onto an embedding layer, predicting a hierarchical data sequence using the embedding layer and the feature vectors, extracting the feature vectors that are most influential in predicting the embedding layer, and outputting the touchpoints associated with the most influential feature vectors.

Annotating customer data

A computer implemented method determines a placement of an application being added to a network. The method includes determining a logical-physical mapping for the application. Sub-graphs in the logical-physical mapping are identified. A stored application in a catalog of applications previously used in the network is located. The stored application includes one of the sub-graphs in the logical-physical mapping. An experiment is generated, performed by a computing device running a neural network model, using the sub-graphs. The experiment includes inducing a physical node mapping for the sub-graph. A cost function associated with a placement of the application being added to the network to one or more physical nodes in the induced physical node mapping is determined.

Generative experiments for application deployment in 5G networks

A method for determining a correlation of one or more events occurring in a plurality of nodes of a network includes accessing, by a computing device, address information associated with each of the plurality of nodes on the network. The computing device can further access one or more event IDs associated with one or more events occurring on the plurality of nodes. The computing device can further create an association the one or more events occurring on the plurality of nodes with related events occurring on others of the plurality of nodes, the association including the address information.

Topology-homogeneity for enriching event patterns in artificial intelligence operations

An embodiment includes detecting a set of anomalies recorded during a first predefined window of time in log entries for a computer environment. The embodiment also includes generating cluster data representative of a cluster of anomalies from among the set of anomalies, where the cluster is formed using a lattice clustering algorithm that spatially distinguishes the cluster of anomalies from other anomalies in the set of anomalies. The embodiment also includes composing an explanation using log templates generated from log entries associated with the cluster of anomalies.

Generating incident explanations using spatio-temporal log clustering

Data associated with performances of microservices functioning in a distributed computing environment is clustered by executing an unsupervised machine learning algorithm. A representative data is selected from a cluster, selecting performed for a plurality of the clusters. Based on time series data of the representative data associated with the plurality of the clusters, causal extraction is performed. Based on the causal extraction and the plurality of the clusters, a causal graph is constructed. The causal graph is embedded into vector space. Based on the embedded vector space, an artificial neural network model can be trained for managing the distributed computing environment.

Unsupervised learning to simplify distributed systems management

Aspects of the invention include techniques for decomposing trend and seasonality components in a forecast of parametric time series data. A non-limiting example method includes receiving time series data that includes a plurality of values taken over a first period of time. A forecast is generated using the time series data. The forecast can include one or more predicted values over a second period of time. The forecast is decomposed into N components and 2coalitions are defined for the N components. A coalition value is determined for each coalition of the 2coalitions.

Trend and seasonality decomposition

Growing community of inventors

White Plains, NY, United States of America

Mudhakar Srivatsa