Abstract: According to one embodiment, a method, computer system, and computer program product for adaptive surrogate modeling is provided. The embodiment may include capturing a plurality of system information for a smart Internet of Things (IoT) device. The embodiment may also include calculating a lifespan value of the smart IoT device based on the plurality of captured system information. The embodiment may further include, in response to the calculated lifespan value being below a threshold and a surrogate model fitting one or more parameters of the smart IoT device not existing, creating the surrogate model for the smart IoT device. The embodiment may also include deploying the created surrogate model to the smart IoT device through an update transmission.

Abstract: A method, computer system, and a computer program product for dynamic role assignment is provided. The present invention may include identifying a crisis event based on data collected by one or more internet-connected sensors. The present invention may then include selecting an incident plan based on the identified crisis event. The present invention may then include communicating an incident role to a registered device of a crowd member.

Abstract: A computer completes a data image analysis task. The computer receives a machine learning (ML) model trained for use with image data content characterized by first context. The computer receives an evaluation image dataset having evaluation image data content characterized by a second context. The computer receives a request to complete an image data analysis task for the evaluation image dataset using the ML model. The computer compares the contexts to determine whether the contexts are similar and whether the evaluation image dataset is compatible with the ML model. If the evaluation dataset is incompatible with the ML model, the computer uses the generative model to generate a ML model compatible synthetic image dataset based on the evaluation dataset. The computer applies the ML model to the synthetic image dataset to provide an answer for the data image analysis task; the computer delivers the answer to a user interface.

Abstract: One or more processors may detect that an extreme event that occurred in a first region. One or more processors may determine that the extreme event creates a drift in a probability distribution that is an output of a model associated with the first region. One or more processors may retrain the model associated with the first region using data associated with the extreme event. One or more processors may identify a second region similar to the first region according to a defined correlation threshold. One or more processors may generate data representing potential extreme scenarios for the second region based on the detected extreme event in the first region. One or more processors may retrain a model associated with the second region based on the generated data representing potential extreme scenarios.

Abstract: A method for calculating sales trend of a product at a store shelf based on crowdsourcing, includes receiving, by a retail store server, availability data of a product measured on a shelf in the retail store from a portable device, where the availability data is in the form of a picture acquired of the product on the shelf, identifying products on the shelf using tags attached to the shelves, calculating sales velocity and sales trends of the product from the identified products, and transmitting the sales velocity and sales trend of the product to one or more third parties' systems in a supply chain of said retail store. Products and their locations on retail store shelves have been cataloged in a product database.

Abstract: A method and system of generating a documentation includes monitoring user actions regarding a model development, wherein the user actions are captured in a source code development environment. Semantic meaning is provided for each user action captured in the source code development environment. A degree of impact of each user action is determined in connection with the model. Actions having a degree of impact in the development of the model that is above a predetermined threshold are identified as impactful actions. An interactive knowledge graph is identified based on the user actions, semantic meaning of each action, and the determined degree of impact of each user action. The interactive knowledge graph is provided to be displayed in a navigable way.

Abstract: A computer completes a data image analysis task. The computer receives a machine learning (ML) model trained for use with image data content characterized by first context. The computer receives an evaluation image dataset having evaluation image data content characterized by a second context. The computer receives a request to complete an image data analysis task for the evaluation image dataset using the ML model. The computer compares the contexts to determine whether the contexts are similar and whether the evaluation image dataset is compatible with the ML model. If the evaluation dataset is incompatible with the ML model, the computer uses the generative model to generate a ML model compatible synthetic image dataset based on the evaluation dataset. The computer applies the ML model to the synthetic image dataset to provide an answer for the data image analysis task; the computer delivers the answer to a user interface.

Abstract: Data associated with a region, acquired by a robot may be passed to a previously trained classifier. The classifier outputs a classification label L, and a confidence score C. Responsive to determining that the confidence score C is below a threshold T, the acquired data can be added to a training data set associated with the classifier, and the classifier retrained using the training data set which include at least information from the acquired data. Responsive to determining that the confidence score C is below the threshold T, at least one candidate region having characteristic similarity to the region can be identified. Responsive to determining that the confidence score C is not below the threshold T, at least one candidate region having a different characteristic from the region can be identified. The robot may be caused to acquire data associated with the candidate region.

Abstract: A technique relates to tracking a foodstuff. A device images human consumable code formed on the foodstuff, the human consumable code being part of the foodstuff, the foodstuff being unpackaged. A coding associated with the human consumable code is determined. Product information of the foodstuff is retrieved from a computer system by using the coding. The product information of the foodstuff is provided on the device.

Abstract: A method for transporting data from a source location to a destination location includes receiving the data from at least one sender at the source location, the sender specifying at least one recipient at the destination location; splitting the data into a plurality of portions; and finding one or more couriers who will travel from the source location to the destination location. The method also includes: while at least a given courier is at the source location, sending at least one of the plurality of portions to a mobile device of at least the given courier; once the given courier travels to the destination location, receiving the at least one of the portions from the mobile device of the given courier; and once the plurality of portions of the data have been received at the destination location, sending the data set to the at least one recipient.

Abstract: A method for coordinating activities includes monitoring physiologic signals and movement signals from a plurality of individuals, and learning at least one baseline for each of the plurality of individuals from the physiologic stress signals and the movement signals. The method further includes comparing the individual's physiologic signals to their baseline, determining a current activity for each individual, and learning correlations between current activities and sequences of activities and estimated divergences of the physiologic signals from baseline. The method also includes determining prospective activities for each individual, identifying at least one prospective shared activity among two or more individuals, estimating prospective divergences of the physiologic signals associated with the prospective shared activity, and mitigating the prospective divergences of the physiologic signals by controlling the scheduling component to adjust a schedule of the at least one prospective shared activity.

Abstract: A technique relates to a manufacturing process. A computer system receives a material identification of a resource being manufactured, and receives images captured of units of the resource, the resource having been cut into the units. Features are determined for each of the units from the images. Feature vectors are created on a one-to-one basis for each of the units. A blockchain is formed using the feature vectors associated with each of the units, the blockchain having the material identification of the resource and a certificate identifying the units. A feasibility of the certificate for the units of the resource is validated via the blockchain.

Abstract: Data associated with a region, acquired by a robot may be passed to a previously trained classifier. The classifier outputs a classification label L, and a confidence score C. Responsive to determining that the confidence score C is below a threshold T, the acquired data can be added to a training data set associated with the classifier, and the classifier retrained using the training data set which include at least information from the acquired data. Responsive to determining that the confidence score C is below the threshold T, at least one candidate region having characteristic similarity to the region can be identified. Responsive to determining that the confidence score C is not below the threshold T, at least one candidate region having a different characteristic from the region can be identified. The robot may be caused to acquire data associated with the candidate region.

Abstract: A method for processing an attempted payment made using a mobile device includes receiving information about the attempted payment, receiving data indicative of a behavior of a user of the mobile device at the time of the attempted payment, computing a likelihood that the attempted payment is fraudulent, based on a comparison of the behavior of the user to an historical behavior pattern of the user, and sending an instruction indicating how to proceed with the attempted payment, based on the likelihood.

Abstract: A method of determining occupancy of a vehicle along a route is determined by processing data generated by two different smartphones reported to be travelling in the same vehicle. An app executing within each smartphone. Information that has been transmitted from the two smartphones includes a unique identification of the mobile computing device and a unique identification of a person associated with the mobile computing device. Sensor data is also received, which corresponds to a local ambient environment inside the vehicle of the mobile computing device generating the data. The sensor data does not include location data or data entered by a user. The received data is used to determine if both mobile computing devices were actually present during the portions of the route, by comparing the data from each device.

Abstract: A technique relates to tracking a foodstuff. A device images human consumable code formed on the foodstuff, the human consumable code being part of the foodstuff, the foodstuff being unpackaged. A coding associated with the human consumable code is determined. Product information of the foodstuff is retrieved from a computer system by using the coding. The product information of the foodstuff is provided on the device.

Abstract: A technique relates to a manufacturing process. A computer system receives a material identification of a resource being manufactured, and receives images captured of units of the resource, the resource having been cut into the units. Features are determined for each of the units from the images. Feature vectors are created on a one-to-one basis for each of the units. A blockchain is formed using the feature vectors associated with each of the units, the blockchain having the material identification of the resource and a certificate identifying the units. A feasibility of the certificate for the units of the resource is validated via the blockchain.

Abstract: A method, computer system, and a computer program product for dynamic role assignment is provided. The present invention may include identifying a crisis event based on data collected by one or more internet-connected sensors. The present invention may then include selecting an incident plan based on the identified crisis event. The present invention may then include communicating an incident role to a registered device of a crowd member.

Abstract: A system for automatically generating an athletic training schedule includes a wearable device having one or more sensors for determining a quantity of athletic training performed by a user wearing the wearable device and an athletic performance of the user. A processor is configured to receive the quantity of athletic training performed and the athletic performance data from the wearable device, and to estimate a relationship between the quantity of athletic training performed and the athletic performance. A selection of a competitive target is received. A performance level of the selected competitive target is estimated. A minimum level of training needed to meet or exceed the estimated performance level is determined based on the estimated relationship between the quantity of athletic training performed and the athletic performance. The athletic training schedule is automatically generated based on the determined minimum level of training.

Abstract: A method for transporting data from a source location to a destination location includes receiving the data from at least one sender at the source location, the sender specifying at least one recipient at the destination location; splitting the data into a plurality of portions; and finding one or more couriers who will travel from the source location to the destination location. The method also includes: while at least a given courier is at the source location, sending at least one of the plurality of portions to a mobile device of at least the given courier; once the given courier travels to the destination location, receiving the at least one of the portions from the mobile device of the given courier; and once the plurality of portions of the data have been received at the destination location, sending the data set to the at least one recipient.