International Business Machines Corporation

Globalfoundries Inc.

Umamaheswari C Devi

Malolan Chetlur

Shivkumar Kalyanaraman

Ravindranath Kokku

Amith Singhee

Mukundan Madhavan

Robert Bruce Nicholson

Sumedh Wasudeo Sathaye

Smitkumar Narotambhai Marvaniya

Jagabondhu Hazra

Partha Dutta

Parul Gupta

Vinay Kumar Kolar

Kedar Kulkarni

Ramana V Polavarapu

Nicholas Ettlinger

Jacob T Griffith

Benjamin Grisz

John Michael Ganci, Jr

Dinesh C Verma

Ravi Kothari

Ashok Pon Kumar Sree Prakash

Mathieu Sinn

John Michael Tracey

Shantanu Ravindra Godbole

Manikandan Padmanaban

Raghavendra Singh

Abhishek Malvankar

Nilanjan Banerjee

Amar Prakash Azad

Mudit Verma

Subhrajit Bhattacharya

Vincent Lonij

Otis Smart

Kunal Korgaonkar

Zishan Sami

One embodiment provides a method, including: training a machine-learning model to produce customized farming practices specific to a farm to increase crop yield; wherein the training includes obtaining, from remote sensed data, (i) information corresponding to a crop of each of a plurality of farms and (ii) information corresponding to farming practices of each of the plurality of farms; wherein the training further includes detecting, from the remote sensed data, geographical features and farming characteristics of each of the plurality of farms; wherein the machine-learning model identifies from relationships between (iii) crop information and farming practices and (iv) geographical features and farming characteristics; and discovering, for a specific farm in an identified geographical location, utilizing the trained machine-learning model, and from farm-specific remote-sensed data, farming practices.

Discovering farming practices

An artificial intelligence (AI) platform to support optimization of workload scheduling in a distributed computing environment. Unstructured data corresponding to one or more application artifacts related to a workload in the distributed computing environment is leveraged. NLP is applied to the unstructured data to identify one or more host requirements corresponding to the application artifacts. One or more hosts in the computing environment compatible with the identified host requirements are selectively identified and compatibility between the application artifacts and the identified hosts is assessed. The workload is selectively scheduled responsive to the selective host identification based on the assessed compatibility. The scheduled workload is selectively executed on at least one of the selectively identified hosts responsive to the assessment workload compatibility.

Optimization of workload scheduling in a distributed shared resource environment

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

The present invention provides a method, system, and computer program product of modeling and calculating aggregate power of a set of renewable energy source stations using power output from representative renewable energy source stations. In an embodiment, the present invention includes receiving location, power output time series, and weather time series data of renewable energy source stations in a geographic region and aggregate power output time series data for the geographic region, for each cluster of stations, normalizing the aggregate power value to a representative renewable energy source station, learning a regression model, and de-normalizing a normalized aggregate output power model with respect to a maximum possible power value, and applying a combined model to the received data and power output of representative renewable energy source stations for a particular day, resulting in a total aggregate power value of the renewable energy source stations for the particular day.

Modeling and calculating normalized aggregate power of renewable energy source stations

Embodiments of the present invention disclose a method, a computer program product, and a computer system for predictive maintenance of refrigeration cases. A computer collects a temperature time series for a refrigeration case and, based on the temperature time series, learns a refrigeration case signature for both non-frost and defrost cycles. The computer generates features based on the refrigeration case signature and compares the refrigeration case signature to real time, or observed, temperatures and features using a rule-based and/or machine learning framework. Based on determining that the real time data varies beyond a threshold from the refrigeration case signature, the computer identifies a failure symptom of the refrigeration case and diagnoses a root cause of the symptom or failure. In addition, the computer may activate an alarm and open a work order corresponding to the root cause of the symptom or failure.

Predictive maintenance of refrigeration cases

Methods, systems, and computer program products for leveraging shared work to enhance job performance across analytics platforms are provided herein. A computer-implemented method includes comparing one or more task characteristics of multiple tasks across multiple jobs to be executed within a given environment, wherein each of the multiple jobs comprises one or more tasks; identifying, based on said comparing, one or more of the multiple tasks that can be shared by two or more of the multiple jobs; scheduling the multiple jobs for execution within the given environment, wherein said scheduling is based on (i) the identified tasks that can be shared by two or more of the multiple jobs, and (ii) one or more performance metrics of the given environment; and allocating resources to the multiple jobs based on said scheduling.

Leveraging shared work to enhance job performance across analytics platforms

One embodiment provides a method of identifying a location of a target object within a plurality of images, the method including: utilizing at least one processor to execute computer code that performs the steps of: receiving a plurality of images; receiving position information indicating a central location, wherein the central location comprises a location that the plurality of images were taken; receiving direction information indicating a position of a target object with respect to the central location, wherein one of the plurality of images contains the target object; and determining, using the position information and the direction information, a target location, wherein the target location comprises a location of the target object. Other aspects are described and claimed.

Verification of business processes using spatio-temporal data

One embodiment provides a method including: utilizing at least one processor to execute computer code that performs the steps of: receiving at least one location map comprising a plurality of possible routes; identifying at least one location area configuration, wherein the location area configuration identifies a location, relative to the at least one location map, of at least one location area boundary segment; computing a utility of the at least one location area configuration, wherein the utility comprises an identification of any usefulness of identifying a route comprising at least one identified sub-route and wherein the at least one sub-route is identified using the at least one location area boundary segment; identifying at least one prominent location area boundary segment, wherein a prominent location area boundary segment comprises a location area boundary segment having a computed utility exceeding a predetermined threshold; and generating a location area map comprising a plurality of identified prominent location area boundary segments, wherein the location area map defines boundaries of a location area. Other variants and embodiments are broadly contemplated herein.

Generation of location area boundaries

Methods and arrangements for managing variable-priority flows in a network. Requests for transmission of digital content are received from client devices, each request being associated with a priority, the requests including at least one lower-priority delayable request and at least one higher-priority request. A usable bandwidth for delivery of the requested digital content through the network is estimated and, within the estimated usable bandwidth, there is controlled at least one flow associated with the at least one lower-priority request in the presence of at least one flow for the at least one higher-priority request. Other variants and embodiments are broadly contemplated herein.

Executing variable-priority jobs using multiple statistical thresholds in cellular networks

Systems and methods for estimating bandwidth. A first probe flow is sent into cellular traffic, and a first bandwidth quantity achieved by the first probe flow is measured. A second probe flow is sent into the cellular traffic, and a second bandwidth quantity achieved by the first probe flow while the second probe flow is in the cellular traffic is measured. The first bandwidth quantity and the second bandwidth quantity are compared, and at least one result from the comparing is determined.

Estimating available bandwidth in cellular networks

Systems and methods for managed service delivery at the edge in 4G wireless networks for: dynamic QoS (Quality of Service) provisioning and prioritization of sessions based on the task (current, future) of the workflow instance; predicting the current and future network requirements based on the current and future tasks of all business process sessions and prepare session QoS accordingly; providing an audit trail of business process execution; and reporting on business process execution.

Systems and methods for managed service delivery in 4G wireless networks

Systems and associated methods for estimating wireless workloads are described herein. Systems and methods provide for generating an estimate of a wireless workload's processing requirements from the combined knowledge of system specific values, such as system parameters, platform details, and implementation details. Systems and methods for estimating wireless workloads may be utilized in various wireless protocols, including, 3G, WiMax, LTE, WiFi, femtocells, and point-to-point wireless links. The estimated workloads may be used for scheduling wireless workloads in a shared computing environment.

Estimating processing workloads

Methods, systems, and articles of manufacture for dynamically delayed delivery of content in a network are provided herein. A method includes receiving, from a user device coupled to a network, a request for a content from the network; estimating a measure of available bandwidth on the network for delivery of the requested content at each of multiple periods of time; generating multiple schedules for the delivery of the requested content, wherein each of the multiple schedules is based on (i) the measure of available bandwidth on the network at one of the multiple periods of time and (ii) a predefined set of scheduling rules associated with the user device and the network; and delivering the requested content to the user device according to a schedule selected from the multiple schedules.

Dynamically delayed delivery of content in a network

Estimating available bandwith in cellular networks

Growing community of inventors

Domlur, India

Umamaheswari C Devi