International Business Machines Corporation

Ying Li

Sharathchandra UmapathiRao Pankanti

Norman C Haas

Wei Yan

Chitra Dorai

Vijay Narayanan

Cyril Cabral, Jr

Richard Thomas Goodwin

An L Steegen

Arun Hampapur

Jianying Hu

Robert Evan Strom

Diane Catherine Boyd

Anda C Mocuta

Ta-Hsin Li

Xin Zhou

Krishna Chaitanya Ratakonda

Youngja Park

Rakesh Mohan

Ping Zhang

Clifford A Pickover

Bruce Bennett Doris

Valentina Salapura

Erik Rueger

Rogerio Schmidt Feris

Mukesh Kumar Mohania

Yun-Yu Wang

Roman Vaculin

Paul Charles Jamison

Kwong Hon Wong

Minkyong Kim

Maheswaran Surendra

Rong Liu

Kenney Ng

Sharathchandra Umapathirao Pankanti

Charles A Otto

Pu Huang

Anh Quy Lu

Hoang Trinh

Chuan Yang Wang

Jian Lu

Victor Ku

Richard D Kaplan

Richard B Segal

Jakub Tadeusz Kedzierski

Kaan Kudsi Katircioglu

Woo-Hyeong Lee

Ricky S Amos

Jie Wang

Axel Martens

Zhaonan Sun

Robert Stephen Olyha, Jr

Jonathan H Connell

T K Balachandran

Lisa A Smith

Yuichi Fujiki

Maheswaren Surendra

Danish Contractor

Ole Asmussen

Anshul Sheopuri

Bikram Sengupta

Robert Beiderbeck

Wesley M Gifford

Pavankumar Murali

Markus Schäfer

Yu Cheng

Sheng Hui Zhan

Balamanohar Paluri

Mohamed Ghalwash

Matous Havlena

Prasanna Chandrasekharan Nair

Vibha Anand

Soumya Ghosh

Harummiati Gandasasmita

Shen H Zhan

Yuichi Fujiji

Weiguang Guan

Techniques for generating an ontology based on biomarker information associated with persons to facilitate improving clinical predictions relating to medical conditions are presented. An ontology generator component (OGC) can extract clinical features associated with patients and their associated times from medical records or databases to develop clinical profiles associated with the patients and relating to a medical condition. OGC can develop an ontology relating to the medical condition, including progression and severity of biomarkers associated with the medical condition, based on the clinical profiles and domain knowledge information relating to the medical condition. OGC can determine global features relating to progression and severity associated with the medical condition based on the ontology. At a forecasting point, the global features can be extracted from the ontology and applied to a prediction model to enhance prediction of onset of, or progression of, the medical condition for a patient.

Generating ontology based on biomarkers

A processor may provide a machine learning model. The machine learning model may have an input and an output. The processor may receive input data. The input data may include log data of a queried storage medium and a queried media drive. The processor may provide the input data to the input of the machine learning model. The processor may determine, from the output of the machine learning model, a predicted failure cause category and a predicted failure probability assigned to the predicted failure cause category. The processor may provide a first prediction to a user.

Storage mounting event failure prediction

Methods, systems, and computer program products for cognitive content mapping and collating are provided herein. A computer-implemented method includes identifying resources relevant to an existing course; partitioning, based on pre-determined partitioning parameters, (i) the existing course into multiple portions and (ii) the resources into multiple portions; detecting content coverage gaps in the existing course by semantically comparing (i) the multiple portions of the existing course with (ii) the multiple portions of the resources; retrieving, based on the detected content coverage gaps, at least one of the multiple portions of the resources; and generating an updated version of the existing course by incorporating the at least one retrieved portion of the resources into the existing course.

Cognitive content mapping and collating

A system (or method) for generation and employment of disease progression model(s) that facilitates identifying and indexing discriminative features for disease progression in observational data. The disease progression prediction system comprises a processor that executes computer executable components stored in memory. A receiving component receives and learns observational patient data. A model generation component builds a preliminary disease progression model. An identification component identifies discriminative clinical features for different disease stages. A ranking component ranks discriminative powers of clinical features for respective pairs of disease stages; wherein the model generation component employs the ranked features to generate a final disease progression model.

Identifying and indexing discriminative features for disease progression in observational data

A method and system for improving a network search query is provided. The method includes receiving a natural language Internet search request and executing a real time search with respect to a database associated with an Internet based search for specified digital information. Categories associated with the natural language Internet search request are identified and associated intent information is received. Digital attributes data identified during the real time search are identified and an associated concept is extracted. The associated concept is mapped to the digital attributes and search based software code is generated and executed. Resulting relevant results are presented and the database is configured such that the relevant results are stored within a logical partition of the database.

Network search mapping and execution

Predicting beneficial drug combinations mitigating adverse drug reactions identifies drug combinations and associated target adverse drug reaction from a spontaneous reporting system containing case reports of drugs and associated adverse drug reactions. Each drug combination comprises a first drug and a second drug, and a propensity score is computed for each drug in each group. This propensity score expresses a probability of being exposed to a given drug based on other co-prescribed drugs and reported indications, which reflect patient characteristics. Associations are computed for each drug as well as drug interaction. Among the associations, the sum of the associations of the second drug and the interaction effect represents the predicted beneficial score expressing whether the second drug alters the chance of developing the target adverse drug reaction for patients on the first drug. The interaction effect is referred to as predicted interaction score, and represents antagonistic or synergistic drug interactions.

Data-driven prediction of drug combinations that mitigate adverse drug reactions

A method and system for improving a network search query is provided. The method includes executing a real time search with respect to a database associated with an Internet based search for specified digital information. Digital attributes of digital data identified during the real time search are identified and keywords associated with the digital attributes are ranked. In response, search based software code associated with an Internet search for the digital information is generated and associated real time user interactions are recorded. The search based software code is modified resulting in generation of modified search based software code. The modified search based software code is executed and relevant results associated with the Internet based search are presented via a GUI. The database is configured such that the modified search is stored within a logical partition of the database.

Network search query

A method for validating a remote user's identity comprises retrieving a user's photo and a user's signature from a digital associated identification card; requesting a real-time photo set, wherein the real-time photo set includes a first photo and a second photo; requesting a real-time written signature with the requested real-time photo set; signature matching the real-time written signature against the user's signature of the digital associated identification card; background matching a background in the first photo of the real-time photo set against a background in the second photo of the real-time photo set; user matching an image of the user from the first photo against the user's photo from the digital associated identification card; and validating the user's identity in response to determining that the signature matching satisfies a first threshold, the background matching satisfies a second threshold, and the user matching satisfies a third threshold.

Remote user identity validation with threshold-based matching

A user trajectory graph may be constructed based on spatio-temporal data. A mobility pattern may be extracted from the user trajectory graph. Users may be clustered into groups, wherein the users in a same group possess similar feature values in the mobility pattern, and the users in different groups have different feature values, to identify personas and location sets. A distribution model may be constructed that models user timing and location preference, wherein an outcome indicates a preference for a particular time bin on a particular day for a particular location.

Automatic extraction of user mobility behaviors and interaction preferences using spatio-temporal data

A method for targeting marketing for user conversion includes receiving a list of users. Data pertaining to the users is received. A conversion likelihood score representing an estimation of how likely the user would be to converted from a trial user to a paid user is determined for each user. A similarity score representing how similar the users of the pair are to one another is determined for each possible pair of users. A graph in which each node thereof represents each user and edges between the nodes have edge weights representing the determined similarity scores is constructed. Each node is associated with a value representing its conversion likelihood score. A marketing potential score is calculated for each user using both the node-associated-values and the edge weights of the graph. A set of target users having highest marketing potential scores is constructed.

Targeted marketing for user conversion

A method includes obtaining from an online social media site a plurality of instances of images of objects associated with a person; analyzing with a data processor the plurality of instances of the images with a plurality of predetermined style classifiers to obtain a score for each image for each style classifier; and determining with the data processor, based on the obtained scores, a likely preference of the person for a particular style of object. The plurality of instances of images of objects associated with the person can be images that were posted, shared or pinned by person, and images that the person expressed a preference for. In a non-limiting embodiment the object is clothing, and the style can include a fashion style or fashion genre including color preferences. A system and a computer program product to perform the method are also disclosed.

System and method for creating a preference profile from shared images

Growing community of inventors

Mohegan Lake, NY, United States of America

Ying Li