International Business Machines Corporation

Nationaluniversity of Ireland, Maynooth

Faisal Ghaffar

Hitham Ahmed Assem Aly Salama

Teodora Sandra Buda

Ahmad Abdul Wakeel

Lei Xu

Bora Caglayan

Al Chakra

Robert Huntington Grant

Kevin C Carr

Kelley Anders

Patrick Joseph O'Sullivan

Mark Patrick Delaney

David W Malone

Andres Omar Portillo Dominguez

Peter Keane

Shane Brady

Magdalena Kacmajor

According to an embodiment of the present invention, an approach accurately detects anomalies or outliers of a time-series dataset. A method for identifying whether a particular data element of the time-series dataset is an outlier comprises predicting a value for that particular data element and obtaining a threshold value that defines, relative to the predicted value, whether an actual value of the data element is an outlier. In an aspect of a present invention embodiment, the threshold value is generated based on historic error values associated with data elements temporally preceding the particular data element of the time-series dataset.

Anomaly detection

An embodiment for contextualizing abnormal events which employ location-based social networks, LBSN, data to determine events that may be linked to the abnormal events is provided. The embodiment may include detecting an occurrence of an abnormal event within a geographic region, wherein the abnormal event occurs at an occurrence time. The embodiment may also include obtaining location-based social networks, LBSN, data relating to the geographic region for a time period including the occurrence time. The embodiment may further include analyzing the obtained LBSN data, wherein the analyzation determines a linked event within the geographic region for the time period. The embodiment may also include associating the linked event with the abnormal event.

Abnormal event analysis

An augmented connection graph can be created based on a task to be performed by a fog computing node by augmenting a connection graph representing plurality of IoT devices and connections among them. The augmenting can include adding to the connection graph data type nodes representing types of data processed by the fog computing node and adding connections between the data type nodes and IoT devices that generate the type of data represented by the respective data type nodes. A connection can be added between each pair of the IoT devices that are not currently connected and for which a level of correlation between the pair of IoT devices at least equals a threshold value. Based on the augmented connection graph, at least one of the IoT devices to assign to the fog computing node can be determined and assigned to the fog computing node.

Coordinated device grouping in fog computing

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

Aspects of the invention include systems and methods for real-time feedback for online collaboration communication quality. A non-limiting example computer-implemented method includes monitoring a conference between a plurality of participants, wherein each participant accesses the conference via a respective Voice over Internet Protocol (VoIP) device. The method further includes detecting, by a processor, an indication, by a scoring system that monitors the conference, of a degradation of sound quality of at least one VoIP device being used to access the conference. The processor engages in verifying the indication of the degradation by analyzing a peer-to-peer test between the VoIP device that has an indication of a degradation of sound quality and a VoIP device that does not have an indication of a degradation of sound quality. The process engages in determining a corrective measure based on the indication of the degradation of sound quality and the peer-to-peer test

Real-time feedback for online collaboration communication quality

An example implementation for social networking service content sharing provides a computer-implemented method that includes analyzing content to be shared on a social networking service, the content being directed to a plurality of potential recipients. The method further includes analyzing the plurality of potential recipients to calculate a plurality of probability scores for each of the plurality of potential recipients. The method further includes calculating a recipient score for each of the plurality of potential recipients based at least in part on the plurality of probability scores for each of the plurality of potential recipients. The method further includes generating a metadata table for the plurality of potential recipients based at least in part on the recipient score for each of the plurality of potential recipients and designating a subset of the plurality of potential recipients to receive the content based at least in part on the metadata table.

Social networking service content sharing

According to one or more embodiments of the present invention, a computer-implemented method includes creating a baseline online behavior profile of a user at a time tbased on a usage of a social network by the user. The method further includes continuously monitoring an online behavior profile of the user on the social network and in response to detecting a deviation between the online behavior profile and the baseline online behavior profile, creating a changed online behavior profile of the user at a time t, t&#x3e;t. The method further includes extracting keywords from a plurality of online posts associated with the user, the online posts being from time tuntil time t. The method further includes determining an event associated with the extracted keywords. The method further includes in response to the event being of a predetermined type, sending a notification to another user.

Cognitive monitoring of online user profiles to detect changes in online behavior

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

A system and method for filtering search results to exclude technically incompatible devices with a user's existing IoT network includes analyzing the search query to determine an objective of a user, calculating a relevance score for each IoT device, profiling an existing IoT network associated with the user, determining a compatibility of each IoT device with the existing IoT network, combining the relevance score and an ease of incorporation score to determine a total score, and filtering the search results for the IoT devices according to the total score, such that an optimal device is displayed at a top of the search results from the search engine on a webpage among other IoT devices that are above a minimum ease of incorporation score and removing other IoT devices from the search results displayed on the webpage that are below the minimum ease of incorporation score.

Search engine filter based on user IoT network

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 method, computer system, and a computer program product for improving social media network actions is provided. The present invention may include determining a proposed action by a user and predicting a predicted influence score for the proposed action. The present invention may include identifying a prior related action in the user's social media network. The present invention may include retrieving a previously calculated average influence score for the type and user of the prior related action and applying a decay profile to the average influence score from the time of the action to a current time. The present invention may include comparing the predicted influence score with the decayed average influence score at the current time. The present invention may include posting the proposed action on the social media network at a time when the predicted influence score is greater than the decayed average influence score.

Timing social media network actions

A data congestion control can operate in a hierarchical sensor network. A first data rate of data received from a set of devices is determined to compare unfavorably to a congestion threshold. A most favorable negotiation score of a set of negotiation scores corresponding to the set of devices is determined. A proposed reduced transmission rate that is less than a current transmission rate of the device and that compares favorably a boundary conditions of the device is determined. A transmission rate reduction request is generated for transmission to the one of the set of devices that indicates the proposed reduced transmission rate. An updated data rate of the data received from the set of devices is determined, and a difference between the updated data rate and the first aggregated data rate corresponds to a reduction of rate of transmission by the device.

Growing community of inventors

Dunboyne, Ireland

Faisal Ghaffar