International Business Machines Corporation

Otis Smart

Sushain Pandit

Charles Daniel Wolfson

David Alec Selby

Brent P Gross

Harikumar Venkatesan

Smitkumar Narotambhai Marvaniya

Manikandan Padmanaban

Umamaheswari C Devi

Akil Khamisi Sutton

Ronald Bruce Baker

Linsong Chu

Sekou Lionel Remy

Myneeka Holloway

Suresh Kumar Jasrasaria

Corey A Stubbs

Charles Lynn

Lauren Quigley

Karthik Jayaraman

Zishan Sami

Computer-implemented methods selecting a cloud computing system for deployment of a workload are provided. Aspects include obtaining an input function that characterizes the workload and obtaining a plurality of performance models, wherein each of the plurality of performance models corresponds to one of a plurality of cloud computing systems including the cloud computing system. Aspects also include applying the input function into each of the plurality of performance models, calculating one or more of a gain, a phase shift, and a stability margin for each of the plurality of performance models, and selecting the cloud computing system from the plurality of cloud computing systems based at least in part on the one or more of the gain, the phase shift, and the stability margin.

Benchmarking and prediction of cloud system performance

A method for selective boundary detection includes identifying a plurality of boundaries for a plurality of subregions in a region of interest utilizing one or more multispectral images for the region of interest. The method further includes analyzing a plurality of adjacent fields to a first field in a first subregion out of the plurality of subregions utilizing a region identification criterion based on a plurality of attributes for the first field and the plurality of adjacent fields. The method further includes determining, based on the analyzing, the first region with the first field requires further analysis of multitemporal remote sensed data over a defined period of time.

Selective analysis for field boundary detection

Historical device positioning data captured from one or more devices over a period of time is received. The historical device positioning data includes historical latitude, longitude, and elevation data of the one or more devices. Building boundaries for a give building are identified based upon the historical latitude and longitude data. The historical device positioning data corresponding to locations within the building boundaries of the building is clustered using a machine learning-based clustering algorithm, resulting in clusters with corresponding cluster centroids. The cluster centroids are associated with respective floors within the building. A current floor of the building on which a specific device is located is determined by mapping current device positioning data of the specific device to the closest cluster centroid.

Spatial device clustering-based emergency response floor identification

A computer system merges location-based data sets. Each of a plurality of data sets are transformed into a standardized schema, including at least two data sets including information indicating a geographic location. The schemas of the plurality of data sets are combined by data set type to produce a resulting data set for each data set type. The schemas of a first and second data sets are joined to produce a merged data set using a machine learning model to identify corresponding rows of the schemas. The schema of the merged data set is joined with the schemas of the resulting data sets for the data set types to produce a new data set. A resulting merged data set in the standardized schema is produced. Embodiments of the present invention further include a method and program product for merging location-based data sets in substantially the same manner described above.

Processing multiple data sets to generate a merged location-based data set

Known geospatial device coordinates are clustered using a clustering algorithm into device clusters with cluster centroids. Each device cluster corresponds to a geographical location. Each cluster centroid is annotated with a regional floor-height value of the respective geographical location. Current device data of a device, including geographic location and elevation, are received. An approximate current floor upon which the first device is located is determined using the elevation of the first device and the annotated regional floor-height value of a closest cluster centroid, the closest cluster centroid determined based, at least in part, on the geographic location of the first device. An individual is directed to the device's geographic location and approximate current floor. The device clusters are re-computed based upon feedback from the individual regarding the device's actual floor.

First responder feedback-based emergency response floor identification

Known geospatial device coordinates are clustered using a machine learning-based clustering algorithm into device clusters with cluster centroids. Each device cluster corresponds to a geographical location. Each cluster centroid is annotated with a regional floor-height value of the respective geographical location. Current device data of a device, including latitude, longitude, and elevation, are received, and a geographic location of the device is determined using the latitude and longitude. An approximate current floor upon which the first device is located is determined by mapping the current device data of the first device to a closest cluster centroid, and calculating the approximate current floor using the elevation of the first device and the annotated regional floor-height value of the closest cluster centroid. An individual is directed to the device's geographic location and approximate current floor. The device clusters are re-computed based upon feedback from the individual regarding the device's actual floor.

Growing community of inventors

Duluth, GA, United States of America

Otis Smart