International Business Machines Corporation

Timothy Michael Lynar

John Michael Wagner

James R Kozloski

Kent C Steer

Suraj Pandey

Rahil Garnavi

Stefan Von Cavallar

Olivia Jayne Smith

Jorge Andres Moros Ortiz

Clifford A Pickover

Aaron K Baughman

Julian De Hoog

Ziyuan Wang

Cristian Vecchiola

Christian Vecchiola

Mark Carl Hampton

Arun Vishwanath

Christopher John Butler

Ramachandra Rao Kolluri

Frank Suits

Fatemeh Jalali

Adam Eberbach

Dileban Karunamoorthy

Khoi-Nguyen Dao Tran

Roslyn I Hickson

Kent C B Steer

Annalisa Jean Swan

Adam H E Eberbach

Yaniv Shmuel Bernstein

Jorge A M Ortiz

Mark D Nelson

Gandhi Sivakumar

Sergiy Zhuk

Suman Sedai

Shaila Pervin

Mani Abedini

Stephen Michael Moore

Andrew John Bernoth

Josh Andres

Ross Warren Judd

Melanie E Roberts

Hamideh Anjomshoa

Khalid Abdulla

Adam Joseph Makarucha

Jasbir K Dhaliwal

Gandhi Slvakumar

Christopher I E Mesiku

A risk management method, system, and non-transitory computer readable medium, include a data analyzing circuit configured to analyze user data, site data, and equipment data to map prior behavior types to an event on a site, a relationship determining circuit configured to determine a relationship between the mapped data and the event based on behaviors exhibited by the user and an impact on a performance factor and a risk factor, and a reinforcement learning circuit configured to use reinforcement learning to learn the performance factor to the risk factor ratio to optimize an overall site productivity.

Risk optimization through reinforcement learning

A method, computer system, and a computer program product for payload stabilization is provided. The present invention may include, in response to receiving at least one sensor data associated with a suspended payload, detecting an unstable movement in the suspended payload during a transport of the suspended payload. The present invention may also include implementing at least one sail coupled to the suspended payload to stabilize the detected unstable movement of the suspended payload.

Crane payload stabilization

A state of a driver operating a vehicle based at least on a rest pattern of the driver and a driver safety score and vehicle characteristic associated with the vehicle are determined. A risk of a planned route is received based on environment information. A safety risk for at least one location along the planned route is determined based on the received risk. Based on the safety risk, a use of available driver attention determined based on the state of the driver, possible modification of the planned route and vehicle state may be planned that minimize the safety risk. It may be determined that the driver is approaching a location along the planned route having a safety risk. Responsive to determining that the driver is approaching a location along the planned route having a safety risk, alert may be caused to be sent to the driver.

Vehicle driver and autonomous system collaboration

A hardware processor may be coupled to a communication network and receive charging requests and discharging requests from a plurality of prosumer facilities via the communication network. One or more energy storage systems may be coupled to an energy grid and able to charge from and discharge to the energy grid, and may communicate with the hardware processor via the communication network. Based on the charging requests and discharging requests, an energy schedule may be generated. The energy schedule may include a first set of the prosumer facilities from which charge requests are accepted, and a second set of prosumer facilities from which discharge requests are accepted. One or several energy storage systems may be controlled or triggered to charge or discharge repeatedly via the energy grid according to an updated energy schedule (e.g., regularly updated).

Virtualization of large-scale energy storage

A method, a computer program product, and a computer system warn workers of a hazardous condition on a worksite. The method includes determining at least one outcome involving a worker and at least one worksite object based on conditions of the worksite. The method includes predicting whether a select one of the at least one outcome presents a hazardous condition to the worker. As a result of predicting that the select outcome presents the hazardous condition, the method includes transmitting a signal to a device associated with the worker. The signal triggers a warning to be received by the worker where the device is in a proximity of the worker.

Predictive warning system

A technique relates to communication resource allocation. A computer system monitors a communication between a conversational entity communication channel and a user device. A type of the communication associated with the user device is determined based on the communication. A replacement communication channel to replace the conversational entity communication channel is determined, in response to the type of the communication. The replacement communication channel is coupled to the user device in place of the conversational entity communication channel.

Communication resource allocation

An information processing system, computer readable storage medium, and methods for analyzing the airflow related health of a person. A method includes obtaining an audio sample of a person's verbal communication, obtaining geographic information of the person, querying a remote server based on the geographic information, and obtaining additional information from the remote server, the additional information being related to the geographic information, and extracting contours of amplitude change from the at least one audio sample over a period of time, the contours of amplitude change corresponding to changes in an airflow profile of the person. The method further includes correlating the contours of amplitude change with periodic episodes typical of airflow related health problems, and determining, based at least on the additional information, whether the contours of amplitude change result from at least one local environmental factor related to the geographic information.

System and method to measure, analyze, and model pulmonary function and disease utilizing temporal, spatial, and contextual data

A system for allocating tasks within a moving multi-hop mesh network includes a processor operatively coupled to memory. The processor is configured to implement the steps of: sending a bid request from a first network node to two or more other network nodes for computing a task, wherein the first network node has a first geographical location relative to a first geographical location of the two or more other network nodes; in response to the first network node receiving a bid from at least two of the two or more other network nodes for computing the task; predicting a second geographical location for each of the at least two of the two or more other network nodes relative to a second geographical location of the first network node based on the time when the task will be completed; predicting a total task completion time for the at least two of the two or more other network nodes; comparing the total task completion time predicted for the at least two of the two or more other network nodes to generate a winning bid; and allocating the task to the winning bid.

Dynamic task allocation and node reconfiguration in mesh network

A computer-implemented method for implementing an overlay network on peer-to-peer network to enable resource allocation that accounts for attributes and statuses of one or more nodes therein is provided. The computer-implemented method includes registering one or more nodes with the overlay network and executing overlay registration routing of the one or more nodes by building a routing table to cause node types to know about each other. Overlay sorting is executed between the node types based on corresponding characteristics.

Peer-to-peer network for internet of things resource allocation operation

Embodiments of the invention are directed to a locally powered smart device. A non-limiting example of the locally powered smart device includes a sensor, an energy storage communicatively coupled to the sensor, a processor communicatively coupled to the sensor and the energy storage. The processor is configured to control the sensor and the energy storage to perform multiple iterations of a tamper mitigation process, wherein each of the multiple iterations of the tamper mitigation process includes an authentication process that includes the transmission of authentication communications between the sensor and the energy storage. The processor is further configured to initiate an anti-tampering protocol based at least in part on a determination that the authentication process was unsuccessful.

Tamper mitigation scheme for locally powered smart devices

A method, computer program product, and a system where a processor(s), obtains pre-recorded visual data from a given location, captured by an image capture device at a visual input location at the given location. The processor(s) determines a position of the image capture device utilized to capture the visual data. The processor(s) obtains known landmarks from data related to the given location. The processor(s) analyzes the visual data to identify a portion of the known landmarks in the visual data, where the analyzing generates matched landmarks. The processor(s) determines a spatial orientation and positioning of the visual input location with respect to the matched landmarks, at the given location. The processor(s) generates an encryption key, utilizing the spatial orientation and the positioning of the visual input location with respect to the matched landmarks. The processor(s) encrypts a message with the encryption key, generating an encrypted message.

Location specific identity verification system

Segmentation and classification of documents in a mixed security environment includes receiving a document including a plurality of subcomponents. A security classification level of each of the plurality of subcomponents is determined using a first classification model. The security classification level of each subcomponent includes one of a first classification level and a second classification level. A first subcomponent having the first classification level is routed to a first environment having a first security level. A second subcomponent having the second classification level is routed to a second environment having a second security level. A pointer for the second subcomponent is determined in which the pointer references a portion of the first subcomponent.

Segmenting, redacting, and transporting secure documents in a mixed security environment

An example operation may include one or more of collecting a set of driving data, estimating, from the set of driving data, one or more states that are predictive of an elevated driving risk of an adverse event endangering at least one of a driver, a vehicle's occupants or a vehicle's cargo, determining, from the one or more estimated states, an existence of an elevated driving risk, and alerting at least one of the vehicle, driver or the vehicle's occupants to the existence of the elevated driving risk.

Driving state within a driving environment that includes autonomous and semi-autonomous vehicles

Embodiments are directed to a computer-implemented method of displaying a presentation. The method includes analyzing a set of media files that include the presentation. Thereafter, each media file is displayed in a predetermined order. Upon the detection of an audience viewing the media files, the displaying of the media files is adjusted based on characteristics of the audience.

Dynamically altering presentations to maintain or increase viewer attention

A method and system are provided. The method includes performing, by at least a computer processing system having a hardware processor, a particulate mapping process to predict particulate exposure at a target location based on an estimated particulate source, an estimated particulate source output, and a fine-grained weather forecast for the target location. The performing step includes estimating the target location using a fine-grained weather hindcast and inverse modelling. The performing step further includes generating observations of particulate exposure for one or more specific particulates, using a set of particulate sensors.

Personalized particulate matter exposure management using fine-grained weather modeling and optimal control theory

Growing community of inventors

Kew, Australia

Timothy Michael Lynar