Abstract: A customized video stream is provided. A second content is searched for that includes the plurality of entities, and a plurality of user data associated with the social media account. A hierarchy of additional content is generated based, at least in part, on the second content that is associated with the plurality of entities, and the user data associated with the social media account, wherein the hierarchy of additional content contains a plurality of second content. A customized video stream is generated based, at least in part, on the video stream and the hierarchy of additional content. The customized video stream is populated on a display screen of the user device, wherein the video stream is displayed on the display screen of the user device, and the hierarchy of additional content is displayed in a portion of the display screen and displayed concurrently with the video stream.

Abstract: Provided is a method, a system, and a program product for determining a policy using semi-supervised reinforcement learning. The method includes observing a state of an environment by a learning agent. The method also includes taking an action by the learning agent. The method further includes observing a new state of the environment and calculating a reward for the action taken by the learning agent. The method also includes determining whether a policy related to the learning agent should be changed. The determination is conducted by a teaching agent that inputs the state of the environment and the reward as features. The method can also include changing the policy related to the learning agent upon a determination that a label outputted by the teaching agent exceeds a reward threshold.

Abstract: A system for executing a video summary is provided. One or more video segments for a video based on one or more digital media is generated. A video summary is generated based on a user request.

Abstract: Techniques for padding audiovisual clips (for example, audiovisual clips of sporting events) for the purpose of causing the clip to have a predetermined duration so that the padded clip can be evaluated for viewer interest by a machine learning (ML) algorithm. The unpadded clip is padded with audiovisual segment(s) that will cause the padded clip to have a level of viewer interest that it would have if the unpadded clip had been longer. In some embodiments the padded segments are synthetic images generated by a generative adversarial network such that the synthetic images would have the same level of viewer interest (as adjudged by an ML algorithm) as if the unpadded clip had been shot to be longer.

Abstract: Distributing computation workload among computing nodes of differing computing paradigms is provided. Compute gravity of each computing node in a cloud computing paradigm and each computing node in a client network computing paradigm within an Internet of Systems is calculated. Each component part of an algorithm is distributed to an appropriate computing node of the cloud computing paradigm and client network computing paradigm based on calculated compute gravity of each respective computing node within the Internet of Systems. Computation workload of each component part of the algorithm is distributed to a respective computing node of the cloud computing paradigm and the client network computing paradigm having a corresponding component part of the algorithm for processing.

Abstract: Fair deep reinforcement learning is provided. A microstate of an environment and reaction of items in a plurality of microstates within the environment are observed after an agent performs an action in the environment. Semi-supervised training is utilized to determine bias weights corresponding to the action for the microstate of the environment and the reaction of the items in the plurality of microstates within the environment. The bias weights from the semi-supervised training are merged with non-bias weights using an artificial neural network. Over time, it is determined where bias is occurring in the semi-supervised training based on merging the bias weights with the non-bias weights in the artificial neural network. A deep reinforcement learning model that decreases reliance on the bias weights is generated based on determined bias to increase fairness.

Abstract: A computer-implemented method includes: receiving, by a computer device, sensor data for a plurality of UAVs in a fleet of UAVs; applying, by the computer device, logistic regression to the sensor data; predicting, by the computer device, a probability of malfunction of each UAV in the fleet of UAVs based on the applying; combining, by the computer device, the probability of malfunction of each UAV with a pre-existing malfunction data set to produce an intermediate malfunction data set; generating, by the computer device, additional cases of predicted UAV malfunctions with a GAN, the GAN using the intermediate malfunction data set as initial training data for the GAN; combining, by the computer device, the additional cases with the intermediate malfunction data set to produce a combined malfunction data set; and comparing, by the computer device, the sensor data for a first UAV of the UAVs to the combined malfunction data set.

Abstract: Advising on computer software upgrade decisions for enterprise software by analyzing respective vendor information correlated to influences from user data including periodically checking for vendor software updates for selected software programs. A plurality of factors are assessed for software update risks, and the factors include dimensions of importance of each of the factors. Opinion and comments from users on public websites are collected regarding the software and the software updates. Each of the dimensions for each of one or more factors for a selected software program are weighted. The weighting is based on an importance for each of the dimensions for a respective user. A risk score is calculated based on the assessed software update risk for each dimension which includes the weighting of each of the dimensions, and a notification is sent to a user recommending the software upgrade or not based on the risk score.

Abstract: Techniques for tailoring sampling rates for data from interactive digital properties on a feature-by-feature basis and collecting the data using the tailored sampling rates. Each feature may have an independent sampling rate irrespective of sampling rates assigned to other features. The independent sampling rates are determined based on at least one factor of predictive feature usage information based on historical feature usage information, predetermined rules, and current usage velocity of the feature. In some embodiments the independent sampling rate is influenced by the usage of an allocated resource provided to the digital property relative to a total allocation of that resource for a given time period. In some embodiments, the allocated resource is server calls to a digital data analytics server for the purposes of providing feature usage information from the interactive digital property for the performance of digital data analytics.

Abstract: Technology for generating camera viewfinder displays for camera people video recording/broadcasting live events such as sporting events, where the viewfinder displays include overlays that include: (i) priority values for objects shown on and/or off the live event view shown in viewfinder display; (ii) identifications of objects that are outside the viewfinder display; and/or (iii) direction to the locations of objects that are outside the viewfinder display. In response to these indications in the overlay, the cameraperson may move the camera to better capture a high priority object and/or capture an object that was outside the viewfinder display.

Abstract: Optimizing market assets using tensor optimization across cloud and edge resources by generating a tensor space associated with market assets, calculating matrices associated with the tensor space according to market asset correlations, determining market asset allocation opportunities, and suggesting market asset allocations according to a user risk assessment.

Abstract: Systems and methods for customizing digital content based on consumer context data are disclosed. In embodiments, a computer-implemented method, comprises: determining, by a computing device, a goodness of fit of one or more digital content segments for a digital product based on asset success metrics indicating a trend in consumer consumption of content; identifying, by the computing device, a select digital content segment from the one or more digital content segments based on the goodness of fit; and incorporating, by the computing device, the select digital content segment into the digital product.

Abstract: A method for voice signal fatigue compensation, that includes sampling, using an audio signal capturing apparatus, a segment of a voice signal in a normal time series to form a normal series sample, generating, using a processor and a memory, from the normal series sample, a reversed series sample, and constructing, by executing using the processor and the memory a time-series mixing component, a first synthesized segment by mixing the normal series sample and the reversed series sample, the first synthesized segment including a compensation for an instance of micro fatigue in the segment of the voice signal. The method also includes forming a fatigue-compensated voice segment from the first synthesized segment, and outputting, as a fatigue-compensated voice segment, the first synthesized segment.

Abstract: A method for voice signal fatigue compensation, that includes sampling, using an audio signal capturing apparatus, a segment of a voice signal in a normal time series to form a normal series sample, generating, using a processor and a memory, from the normal series sample, a reversed series sample, and constructing, by executing using the processor and the memory a time-series mixing component, a first synthesized segment by mixing the normal series sample and the reversed series sample, the first synthesized segment including a compensation for an instance of micro fatigue in the segment of the voice signal. The method also includes forming a fatigue-compensated voice segment from the first synthesized segment, and outputting, as a fatigue-compensated voice segment, the first synthesized segment.

Abstract: Distributing computation workload among computing nodes of differing computing paradigms is provided. Compute gravity of each computing node in a cloud computing paradigm and each computing node in a client network computing paradigm within an Internet of Systems is calculated. Each component part of an algorithm is distributed to an appropriate computing node of the cloud computing paradigm and client network computing paradigm based on calculated compute gravity of each respective computing node within the Internet of Systems. Computation workload of each component part of the algorithm is distributed to a respective computing node of the cloud computing paradigm and the client network computing paradigm having a corresponding component part of the algorithm for processing.

Abstract: A computer-implemented method includes: receiving, by a computer device, sensor data for a plurality of UAVs in a fleet of UAVs; applying, by the computer device, logistic regression to the sensor data; predicting, by the computer device, a probability of malfunction of each UAV in the fleet of UAVs based on the applying; combining, by the computer device, the probability of malfunction of each UAV with a pre-existing malfunction data set to produce an intermediate malfunction data set; generating, by the computer device, additional cases of predicted UAV malfunctions with a GAN, the GAN using the intermediate malfunction data set as initial training data for the GAN; combining, by the computer device, the additional cases with the intermediate malfunction data set to produce a combined malfunction data set; and comparing, by the computer device, the sensor data for a first UAV of the UAVs to the combined malfunction data set.

Abstract: A system for executing a video summary is provided. One or more video segments for a video based on one or more digital media is generated. A video summary is generated based on a user request.

Abstract: Advising on computer software upgrade decisions for enterprise software by analyzing respective vendor information correlated to influences from user data including periodically checking for vendor software updates for selected software programs. A plurality of factors are assessed for software update risks, and the factors include dimensions of importance of each of the factors. Opinion and comments from users on public websites are collected regarding the software and the software updates. Each of the dimensions for each of one or more factors for a selected software program are weighted. The weighting is based on an importance for each of the dimensions for a respective user. A risk score is calculated based on the assessed software update risk for each dimension which includes the weighting of each of the dimensions, and a notification is sent to a user recommending the software upgrade or not based on the risk score.

Abstract: An adjustment specification specifies the adjustment to be made to a multimedia content, including a time characteristic. The multimedia content is matched within a tolerance to a set of comparable multimedia contents having a characteristic corresponding to the adjustment specification. An embedding model is configured and trained. Using the trained embedding model and the set of comparable multimedia contents, a set of styles is generated. Using a frame adjustment model and a style in the set of styles, a video frame of the multimedia content is adjusted. Using an audio adjustment model and the trained embedding model, an audio portion of the multimedia content is adjusted. The video frame of the multimedia content and the audio portion of the multimedia content are synchronized, producing an adjusted multimedia content adjusted according to the adjustment characteristic.

Abstract: Provided is a method, a system, and a program product for determining a policy using semi-supervised reinforcement learning. The method includes observing a state of an environment by a learning agent. The method also includes taking an action by the learning agent. The method further includes observing a new state of the environment and calculating a reward for the action taken by the learning agent. The method also includes determining whether a policy related to the learning agent should be changed. The determination is conducted by a teaching agent that inputs the state of the environment and the reward as features. The method can also include changing the policy related to the learning agent upon a determination that a label outputted by the teaching agent exceeds a reward threshold.