International Business Machines Corporation

University of Illinois

Deutschetelekom Ag

Petros Zerfos

Dakshi Agrawal

Dinesh C Verma

Syed Yousaf Shah

Mudhakar Srivatsa

Chatschik Bisdikian

Xuan-Hong Dang

Kang-Won Lee

Vadim Sheinin

Sihyung Lee

Joseph W Ziskin

Michael G Hill

Alberto Valdes Garcia

Jean-Olivier Plouchart

Raghu Kiran Ganti

Branimir Konstantinov Boguraev

Siddharth A Patwardhan

Dominic Peter Harries

Elahe Khorasani

Wendy Chong

Christopher R Gibson

Brent Paulovicks

Clifford A Pickover

Shivkumar Kalyanaraman

Seraphin Bernard Calo

Vasileios Pappas

Jing James Xu

Bong Jun Ko

Bei Chen

Ramya Raghavendra

Hani Talal Jamjoom

Ravi Kothari

Dakuo Wang

Si Er Han

Vijay Arya

Ji Hui Yang

Nancy Anne Greco

Joel W Branch

Xiping Wang

Peter Daniel Kirchner

Jun Wang

Horst Cornelius Samulowitz

Ting He

Jatinder Pal Singh

Wesley M Gifford

Parul Gupta

Dhavalkumar C Patel

Joshua M Rosenkranz

David Alvra Wood, Iii

Vinay Kumar Kolar

Saket Sathe

Gregory Bramble

Jorge Lobo

Raji Lakshmi Akella

Pablo Vidales

Haiyun Luo

Nathanael A Thompson

Long Vu

Vlivek V Shrivastava

Marcin Solarski

Milton Orlando Laverde Echeverria

Ashley Potter

Yunqi Guo

Providing time-series forecasting by receiving target variable data and exogenous variable data, training a plurality of time-series models according to the target variable data and the exogenous variable data, determining a historical error for each of the plurality of time series models, and providing a time-series forecasting model having a lowest historical error.

Time series forecasting with exogenous variable data

A system and method are provided for discovering k-nearest-neighbors to a given point within a certain distance d. The method includes constructing an index of geometries using geohashes of geometries as an indexing key to obtain an indexed set of geometries, and calculating a geohash representation of the given point with a resolution equal to a magnitude value of d. The method includes searching for a closest-prefix geometry from the indexed set using the geohash representation of the given point, and identifying geometries from the indexed set having a same prefix as the closest-prefix geometry. The method further includes calculating distances between the given point and the geometries identified from the indexed set having the same prefix as the closest-prefix geometry, and determining k geometries with respective shortest distances less than d from the geometries identified from the indexed set having the same prefix as the closest-prefix geometry.

Fast and accurate geomapping

Aspects of the invention include techniques for decomposing trend and seasonality components in a forecast of parametric time series data. A non-limiting example method includes receiving time series data that includes a plurality of values taken over a first period of time. A forecast is generated using the time series data. The forecast can include one or more predicted values over a second period of time. The forecast is decomposed into N components and 2coalitions are defined for the N components. A coalition value is determined for each coalition of the 2coalitions.

Trend and seasonality decomposition

To automate time series forecasting machine learning pipeline generation, a data allocation size of time series data may be determined based on one or more characteristics of a time series data set. The time series data may be allocated for use by candidate machine learning pipelines based on the data allocation size. Features for the time series data may be determined and cached by the candidate machine learning pipelines. Predictions of each of the candidate machine learning pipelines using at least the one or more features may be evaluated. A ranked list of machine learning pipelines may be automatically generated from the candidate machine learning pipelines for time series forecasting based upon evaluating predictions of each of the one or more candidate machine learning pipelines.

Automated time series forecasting pipeline generation

Embodiments relate to a system, program product, and method for employing deep learning techniques to fuse data across modalities. A multi-modal data set is received, including a first data set having a first modality and a second data set having a second modality, with the second modality being different from the first modality. The first and second data sets are processed, including encoding the first data set into one or more first vectors, and encoding the second data set into one or more second vectors. The processed multi-modal data set is analyzed, and the encoded features from the first and second modalities are iteratively and asynchronously fused. The fused modalities include combined vectors from the first and second data sets representing correlated temporal behavior. The fused vectors are then returned as output data.

Fusing multimodal data using recurrent neural networks

An assistive shopping cart system for guiding a user and monitoring the user's physical and cognitive conditions in a shopping environment is described. The assistive shopping cart system provides assistance and guidance to a user based on a user profile. The assistive shopping cart system routes the user through the shopping environment using a shopping route generated based on the user profile. The assistive shopping cart system also detects and tracks user physical and cognitive conditions and user actions in the shopping environment. The user actions are used to aid in the completion of a purchase/transaction and generate shopping notifications for the user and others to understand the process of the shopping experience.

Method, system, and medium for user guidance and condition detection in a shopping environment

Techniques regarding multivariate time series data analysis are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a time series analysis component that generates a machine learning model that discovers a dependency between multivariate time series data using an attention mechanism controlled by an uncertainty measure.

Determining multivariate time series data dependencies

Techniques are provided for the automated risk assessment of a document. In one embodiment, the techniques involve mapping, via a risk assessment engine, one or more sentences in a first document to one or more risk categories, identifying, via a classification engine, risk-associated language of the one or more sentences based on the one or more risk categories, mapping, via a risk assessment engine, the risk-associated language of the one or more sentences to one or more risk criterion of a risk criterion document, and generating, via a risk assessment engine, a first risk assessment based on the one or more risk criterion of the risk criterion document.

Automatic contract risk assessment based on sentence level risk criterion using machine learning

A computer-implemented method includes: receiving, using a processor, multiple data session records (DSRs); storing the multiple DSRs in a memory communicatively coupled to the processor; analyzing, using the processor, the stored multiple DSRs for temporal and spatial data; and determining, using the processor, quality degradation by using the temporal and spatial data for the stored multiple DSRs.

Detecting and diagnosing call quality degradation issues using data session record data

Methods and systems for tag-based identification include receiving a set of parameters at a user device from a remote server. A counterfeit-proof identification tag is read using a sensor in the user device using the set of parameters. Features of the counterfeit-proof identification tag are extracted in accordance with a feature extraction function, using a processor, to generate a tag bit sequence. A challenge function is applied to the extracted features to generate a result. The result is transmitted to the remote server to authenticate the counterfeit-proof identification tag. The counterfeit-proof identification tag is authenticated with a tag database at the remote server.

Consumer and business anti-counterfeiting services using identification tags

Methods and systems for tag-based identification include reading a counterfeit-proof identification tag using a sensor in a user device. Features of the identification tag are extracted in accordance with a feature extraction function, using a processor, to generate a tag bit sequence. A challenge function is applied to the extracted features to generate a result. The result is transmitted to a remote server to authenticate the identification tag.

Methods are provided for enabling secure big data analytics in the cloud. A method includes reading a secure file, by a Secure Distributed File System in a public cloud service provider. The reading step includes computing a hash of a name of the secure file to obtain a hashed file name, finding metadata for the secure file using the hashed file name, retrieving a sharing policy identifier from the metadata, and obtaining authorization from an external entity to decrypt the secure file. The reading step further includes extracting a security key and encrypted data file names from the metadata using the sharing policy identifier, requesting one or more encrypted data files that form the secure file from a node of the public cloud service provider, and at least one of decrypting and reconstructing plaintext data for the secure file from the one or more encrypted data files.

Enabling secure big data analytics in the cloud

A method, system and computer program product are disclosed for providing content to a communications device. In an embodiment of the invention, a communications network receives a first content portion from a content provider and sends the first content portion to the communications device. The communications network also sends a second content portion to the communications device, and this second content portion is customized for the user of the communications device based on selected information about the user that the communications network has. In one embodiment, the communications network uses the selected information about the user to customize the second content portion for the user, and sends the customized second content portion to the communications device. In an embodiment, the communications network sends the selected information to the content provider, and the content provider uses the selected information to customize the second content portion.

Information sharing for third party applications in cellular telecommunication infrastructures

A system and computer program product to externalize mobile device state migration (i.e., checkpointing) without being dependent upon any particular Edge Application (EdgeApp) proxy server or cellular network base station. In this manner, the Edge Application (EdgeApp) proxy server does not have to be aware of a migration process, yet will enable state information to be provided to other EdgeApp proxy/server nodes at the edge of the network (cell tower).

State migration of edge-of-network applications

Growing community of inventors

New York, NY, United States of America

Petros Zerfos