International Business Machines Corporation

University College Dublin

Lei Xu

Hitham Ahmed Assem Aly Salama

Teodora Sandra Buda

Patrick Joseph O'Sullivan

Faisal Ghaffar

Bora Caglayan

Diaa Eldin Ali Mohamed Mahmoud Ali

Leandro Almeida

Philip Perry

Christina Thorpe

An embodiment includes a method for use in managing a cluster comprising a plurality of computers, each computer comprising at least one hardware processor coupled to at least one memory. The method comprises a computer-implemented manager: collecting access pattern data for the plurality of computers; based at least in part on the access pattern data, determining that at least a first one of the plurality of computers is overutilized; and responsive to determining that the first computer is overutilized, moving stored data from the first computer to at least a second one of the plurality of computers.

Managing heterogeneous cluster environment

Techniques that facilitate machine learning optimization are provided. In one example, a system includes a computational resource component, a batch interval component, and a machine learning component. The computational resource component collects computational resource data associated with a group of computing devices that performs a machine learning process. The batch interval component determines, based on the computational resource data, batch interval data indicative of a time interval to collect data for the machine learning process. The machine learning component provides the batch interval data to the group of computing devices to facilitate execution of the machine learning process based on the batch interval data.

Machine learning optimization framework

An embodiment includes a method for use in managing a system comprising one or more computers, each computer comprising at least one hardware processor coupled to at least one memory, the method comprising a computer-implemented manager: generating a potential configuration for hardware resources of the system; determining whether the potential configuration satisfies accuracy and time constraints for a selected machine learning model; if the potential configuration satisfies the constraints, indicating the potential configuration to be the optimal configuration for the system; and if the potential configuration does not satisfy the constraints, adapting the potential configuration to satisfy the constraints. The adapting may comprise repeating the generating and determining steps. The adapting may be based at least in part on the hardware resources and the selected machine learning model.

Adaptive configuration of a heterogeneous cluster environment

Embodiments for detecting data anomalies by a processor. A machine learning model may be trained according to collected scores and anomaly labels of a plurality of anomaly detection operations applied to one or more data sets such that the collected scores and labels identify a degree of accuracy of estimating anomalies for each of the plurality of anomaly detection operations. An anomaly may be detected in an unstructured data set by applying the trained machine learning model on an unstructured data set.

Detecting data anomalies

Embodiments for data replication in a distributed file system environment by a processor. Data replication of one or more files that are more frequently used as compared to other files in a plurality of files may be increased according to hot data detected from one or more queries to a distributed file system.

Data replication in a distributed file system

A system and method for recognizing recurrent crowd mobility patterns in a defined geographical area are presented. A crowded area may be determined for a selected geographical region at predefined time intervals based on spatial distribution of a plurality of users collected from a social media network. A crowd footprint may be generated according to the crowded areas determined at the predefined time intervals. Recurrent crowd mobility patterns may be detected according to the crowd footprint.

Recognizing recurrent crowd mobility patterns

Detecting data anomalies by receiving a first data set related to a first variable metric, determining data anomaly detection scores for data points of the first data set according to a plurality of data anomaly detection techniques, generating an adaptive ground-truth window according to the data anomaly detection scores, assigning a weighting value to each data point within the adaptive ground-truth window, training a machine learning system using the set of data anomaly detection scores and weighting values, and providing a trained machine learning system for evaluating a second data set.

Adaptive window based anomaly detection

A conference call management method, system, and computer program product include inferring an Internet Protocol (IP) address of a new user requesting to join a call including at least one other user, inferring a codec to stream an emulated network pattern for the call if the new user were to join the call, measuring a call quality perceived by the at least one other user in the call while the emulated codec is run on the call, and measuring an impact on the call quality in a case that the new user joins the call based on the perceived call quality and the network pattern.

Growing community of inventors

Dublin, Ireland

Lei Xu