International Business Machines Corporation

David Alec Selby

Mark Steven Ramsey

Charles Daniel Wolfson

Stephen James Todd

Sushain Pandit

Brent P Gross

Otis Smart

Milind Chitgupakar

Harikumar Venkatesan

Kevin Christopher Brown

Vincent Philip Thomas

Charles J Schott

Vince P Thomas

Yan Moyaux

James R Anderson

Hamish C Hunt

Corey A Stubbs

Andrew Martin Lawrence

Gary F Anderson

In an approach for determining the date of planting of a crop growing in an agricultural field, a processor receives an aerial image of one or more agricultural fields in a pre-determined geographical region. A processor selects a plurality of points from the aerial image. A processor calculates a Vegetation Index of one or more crops growing at the plurality of points selected. A processor compares the Vegetation Index calculated for the one or more crops growing at the plurality of points selected to the Vegetation Index known for a plurality of historical reference signatures. A processor generates an actual signature. A processor cross-correlates the actual signature against the plurality of historical reference signatures to measure a degree of similarity. A processor identifies the one or more crops growing in the one or more agricultural fields in the pre-determined geographical region from the cross-correlation.

Agricultural crop estimated date of planting

In an approach for identifying a crop using satellite observation data and crop rotation data, a processor receives an aerial image of one or more agricultural fields in a pre-determined geographical region from an optical satellite. A processor selects a plurality of points from the aerial image. A processor clips the aerial image into one or more smaller images to generate one or more observed signatures. A processor determines there is a change in a spatial distribution of one or more crops. A processor generates an actual signature from the one or more observed signatures. A processor cross-correlates the actual signature against a plurality of historical reference signatures to determine a degree of similarity. A processor ranks one or more results of the cross-correlation. A processor identifies the one or more crops. A processor calculates a first estimate of an amount of the one or more crops.

Agricultural crop identification using satellite and crop rotation

A method of predicting crop yield includes generating, via a processor, a plurality of vectors representative of growing conditions for a current time period and a plurality of vectors representative of growing conditions for a previous time period. The processor compares the plurality of vectors for the current time to the vectors of the previous time periods for corresponding growing conditions and determines which previous vectors are closest to the current vectors. The plurality of previous time periods are each associated with crop yields. Thus, the processor can determine a crop yield for the current time period for a selected crop producing field and crop type based on crop yields for the closest previous time periods.

Crop monitoring to determine and control crop yield

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

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

Using a location sensor, a location including a latitude and a longitude of a device is determined. Using an air pressure sensor, a first elevation of a device is determined. Using the location, a corresponding street address is determined. Using the street address and the first elevation, a floor number is determined. The street address and the floor number are reported to an emergency response system.

Enhanced elevation detection for emergency response systems

At an emergency response system, a first location including a latitude and a longitude at which a first device is located is received. At an emergency response system, an air pressure reading measured by the first device is received. Using the air pressure reading and a mean sea-level barometric measurement, a first elevation of a device is computed. Using the first location, a corresponding street address is computed. Using the street address and the first elevation, a floor number is computed. The street address and the floor number are transmitted to a second device.

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.

A processor-implemented method, system, and/or computer program product detects illicit activities in micro-commerce transactions. An historic transaction pattern of known legitimate past micro-commerce transactions by a cohort is identified. A current transaction pattern for a current set of multiple micro-commerce transactions is also identified. The current transaction pattern and the historic transaction pattern are compared. In response to determining that the current transaction pattern deviates from the historic transaction pattern beyond a predetermined level, a determination is made that the current set of multiple micro-commerce transactions are being used for money laundering.

Identifying money laundering in micro-commerce

The present invention applies gaming theory and well-understood sales processes and techniques to allow the operator of an interactive sales medium to control what is displayed to a user of the medium in a manner that signals their intentions (e.g., looking for a lower price, looking for a particular incentive, etc.) so that the 'strategies' being used by the consumer can be identified and exploited to lead the consumer to a desired end choice. In particular, upon identification of the strategies being used by the consumer, incentives (e.g., gradually increasing rewards and/or decreasing 'punishments') are presented to the consumer in such a way that the margins achieved by an eventual sale are slowly decreased with each presentation of the incentives to the consumer. Since the presentation of each incentive increases the likelihood the consumer will make a purchase, margins are maximized for the seller.

Incentive-based website architecture

Traditional methods of prediction of the likelihood of churning in a given market such as wireless telecommunications are improved by inclusion of social network analysis to predict churning by members of a population in response to churning by any given individual member of that population. A sphere of influence of individual members of the population on other members of the population are modeled and analyzed through a plurality of degrees of separation and quantitatively evaluated by a number of relational algebraic joins in which at least one such join includes weights to assert a diminishing influence with number of degrees of separation.

Social network analysis for churn prediction

A marketing method and system. The method includes receiving by a computing system total population data. A peer group is selected from the total population data. The peer group is associated with a first marketing action. A list of attributes characterizing the peer group is generated. The attributes are associated with the marketing action, demographic data, and additional purchasing habits of the peer group. A target group of individuals of the total population data is selected. The attributes are associated with the individuals of the target group. Scores associated with the individuals of the target group are generated. The individuals of the target group are ranked based on said scores. A ranking list based is generated. The ranking list includes the individuals of the target group in a ranked order. The ranking list is stored.

Target marketing

The invention provides a method, system, and program product for increasing the effectiveness of a customer contact strategy. In one embodiment, the method includes assigning a value to each of a plurality of customer events; assigning each of the plurality of promotion events to a 'bucket' having a predefined range of values, based on a value of each promotion event; and selecting a customer event from the bucket having the highest range of values.

Growing community of inventors

Nr Fareham, United Kingdom

David Alec Selby