International Business Machines Corporation

Jimeng Sun

Fei Wang

Shahram Ebadollahi

Jianying Hu

Hanghang Tong

David Haim Gotz

Spyridon Papadimitriou

U Kang

Philip Shilung Yu

Ching-Yung Lin

Nan Cao

Yuan-Chi Chang

George Andrei Mihaila

Ioana Roxana Stanoi

Pei-Yun S Hsueh

Feifei Li

Ravindranath Konuru

Kun-Lung Wu

Lei Shi

Mithkal M Smadi

Aliza Rivka Heching

Abhijit Bose

Judah M Diament

Shixia Liu

Robert K Sorrentino

Wei Hong Qian

Martin S Kohn

Steve Demuth

Jiayu Zhou

Chandra Kumar Velpuri

Noah Lee

Spyridon Papadimitrion

Systems and methods for individual risk factor identification include identifying common risk factors for one or more risk targets from population data. Individuals are stratified into clusters based upon the common risk factors. A discriminability of each of the common risk factors is determined, using a processor, for a target cluster using individual data of the target cluster to provide re-ranked common risk factors as individual risk factors for the target cluster, such that the discriminability is a measure of how a risk factor discriminates its cluster from other clusters.

Identifying group and individual-level risk factors via risk-driven patient stratification

A system and method for providing a temporally dynamic model parameter include building a model parameter by minimizing a loss function based on patient measurements taken at a plurality of time points. Temporally related values of the model parameter are identified, using a processor, having a same type of patient measurement taken at different time points. At least one value of the model parameter and temporally related values of the at least one value are selected to provide a temporally dynamic model parameter.

Dynamic identification of the biomarkers leveraging the dynamics of the biomarker

A method for determining a similarity between a plurality of graphs includes inferring a low-rank representation of a first graph, inferring a low-rank representation of a second graph, wherein the low-rank representations of the first and second graphs are stored in memory, estimating a left interaction between the first and second graphs, estimating a middle interaction between the first and second graphs, estimating a right interaction between the first and second graphs, wherein the estimations are based on the low-rank representations of the first and second graphs stored in memory, and aggregating the left interaction, the middle interaction and the right interaction into a kernel, wherein the kernel is indicative of the similarity between the first and second graphs.

Determining a similarity between graphs

A method for determining a correspondence between a first node set of a first graph and a second node set of a second graph includes building a feature representation for each of the first graph and the second graph, and inferring the correspondence between the first node set and the second node set based on the feature representations.

Determining soft graph correspondence between node sets based on feature representations

Common sub-process patterns in a plurality of deployed process models may be discovered, and performance measures associated with the sub-process patterns may be computed based on runtime events of the deployed process models. Positive or negative performance patterns among sub-process patterns may be identified and used for creating new process models or improving existing process models.

Measuring process model performance and enforcing process performance policy

A system and method for a composite distance metric leveraging multiple expert judgments includes inputting a data distribution of multiple expert judgments stored on a computer readable storage medium. Base distance metrics are converted into neighborhoods for comparison, wherein each base distance metric represents an expert and each neighborhood represents an individual similarity measure of the expert. The neighborhoods are combined to leverage the local discriminalities of all base distance metrics by applying at least one iterative process to output a composite distance metric.

System and method for composite distance metric leveraging multiple expert judgments

Methods and apparatus are provided for multi-faceted visualization of rich text corpora. A data set comprising a plurality of entities, facets and relations is visualized by generating a visualization of a plurality of the facets in the data set, wherein the visualization indicates connections along the plurality of the facets in a single view using multi-faceted edges. The entities are instances of a particular concept, the facets are classes of entities and the relations are connections between pairs of the entities. A compound node comprises a representation of a primary entity, surrounded by representations of one or more secondary entities connected by one or more external relations. The internal relations can be represented as edges connecting two facet nodes from different compound nodes and a number of crossings of the edges can be reduced by adjusting a position order of facet nodes. The compound nodes can optionally be rotated based on, for example, a global spring force model to reduce an average length of one or more of the edges and/or to allow edge bundling.

Multi-faceted visualization of rich text corpora

Visualization techniques are provided for a clustered multidimensional dataset. A data set is visualized by obtaining a clustering of a multidimensional dataset comprising a plurality of entities, wherein the entities are instances of a particular concept and wherein each entity comprises a plurality of features; and generating an icon for at least one of the entities, the icon having a plurality of regions, wherein each region corresponds to one of the features of the at least one entity, and wherein a size of each region is based on a value of the corresponding feature. Each icon can convey statistical measures. A stabilized Voronoi-based icon layout algorithm is optionally employed. Icons can be embedded in a visualization of the multidimensional dataset. A hierarchical encoding scheme can be employed to encode a data cluster into the icon, such as a hierarchy of cluster, feature type and entity.

Visual analysis of multidimensional clusters

Dynamically aggregating data is provided. A server device receives a subscriber request for a report based on a subset of metadata contained in a data dimensions catalog. The server device analyzes data aggregation requirements from a plurality of data sources for the report based on the subset of metadata defined in the subscriber request. The server device generates a data access plan for movement of data from the plurality of data sources based on the data aggregation requirements for the report. Then, the server device executes the data access plan to fetch the data from the plurality of data sources based on the data aggregation requirements for the report.

Dynamic data aggregation from a plurality of data sources

The invention provides a method and system for visualization of a data set, the method comprises: dividing the data set into a plurality of information layers based on different information dimensions; and visually processing the plurality of information layers based on different information dimensions, respectively, in order to present respective views of the plurality of information layers. In the present invention, by visualizing the data set through presenting different overviews of the data set from different information dimensions, respectively, the presentation of comprehensive information of the data set to a data set analyst is ensured while distortion of presented contents as well as visual clutter are prevented.

Method and system for visualization of data set

A system and method for a composite distance metric leveraging multiple expert judgments includes inputting a data distribution of multiple expert judgments stored on a computer readable storage medium. Base distance metrics are converted into neighborhoods for comparison, wherein each base distance metric represents an expert. The neighborhoods are combined to leverage the local discriminalities of all base distance metrics by applying at least one iterative process to output a composite distance metric.

Computer-implemented methods, systems, and articles of manufacture for determining the importance of a data item. A method includes: (a) receiving a node graph; (b) approximating a number of neighbor nodes of a node; and (c) calculating a average shortest path length of the node to the remaining nodes using the approximation step, where this calculation demonstrates the importance of a data item represented by the node. Another method includes: (a) receiving a node graph; (b) building a decomposed line graph of the node graph; (c) calculating stationary probabilities of incident edges of a node graph node in the decomposed line graph, and (d) calculating a summation of the stationary probabilities of the incident edges associated with the node, where the summation demonstrates the importance of a data item represented by the node. Both methods have at least one step carried out using a computer device.

Determining the importance of data items and their characteristics using centrality measures

A method, system and computer program product for managing and querying a graph. The method includes the steps of: receiving a graph; partitioning the graph into homogeneous blocks; compressing the homogeneous blocks; and storing the compressed homogeneous blocks in files where at least one of the steps is carried out using a computer device.

Method and system for managing and querying large graphs

Methods and systems for event pattern mining are shown that include representing longitudinal event data in a measurable geometric space as a temporal event matrix representation (TEMR) using spatial temporal shapes, wherein event data is organized into hierarchical categories of event type and performing temporal event pattern mining with a processor by locating visual event patterns among the spatial temporal shapes of said TEMR using a constraint sparse coding framework.

Growing community of inventors

White Plains, NY, United States of America

Jimeng Sun