Abstract: According to one embodiment, a method, computer system, and computer program product for navigating an autonomous vehicle is provided. The present invention may include measuring, in real time, movement patterns of air in the surroundings of the autonomous vehicle; analyzing the movement patterns to identify wind flow patterns, terrain, and passage in the surroundings; and navigating the autonomous vehicle based on the identified wind flow patterns, terrain, and passage.

Abstract: From a first set of natural language documents describing a demand for a movable physical item, a set of demand features is extracted. From a second set of natural language documents describing a supply of the movable physical item, a set of supply features is extracted. A correlation quantifying a relationship between the set of demand features and the set of supply features is computed. Using the correlation and the correlation trend, an attraction between the set of demand features and the set of supply features is modeled as a gravitational force. Using a routing determined according to the attraction, the movable physical item is caused to be transported.

Abstract: Pairing a user response and associated context with a neural network associated with a virtual assistant computer during a dynamic text conversation with an end user. The virtual assistant computer receives a detected user generated text input; determines context of the detected user generated text input; compares the context of the detected user generated text input by comparing a confidence score representing context of the user generated input to a classification associated with each of a plurality of existing nodes of a neural network. For confidence scores below a threshold relative to the classification associated with each of the existing nodes of the neural network, the virtual assistant computer creates a new node within the neural network and assigns the context of the user generated text to the new node.

Abstract: A computer-implemented method, system and computer program product for embedding contextual information in an image or video frames. A generative adversarial network (GAN) is trained to provide contextual information to be embedded in an image or video frames, where the contextual information includes text, sound and/or video frames that provides context to the image or video frames. After training the GAN, an image or video frames are received to be embedded with contextual information if necessary. Features are then extracted from the received image/video frames. An image(s) or video frame(s) are identified in a database using the GAN associated with features with a similarity to the extracted features of the received image/video frames that exceeds a threshold value. Such identified images and/or video frames are associated with “references” containing contextual information which are extracted. The received image/video frames are then augmented with the extracted references to provide context.

Abstract: By analyzing a natural language content concurrently with a presentation of the natural language content, a first language of the natural language content is detected. By analyzing the natural language content concurrently with the presentation of the natural language content, it is detected that a subset of the natural language content is expressed in a second language, wherein the second language is different from the first language, wherein a set of known languages comprises the first language, wherein the set of known languages excludes the second language. From the subset of the natural language content, a modified subset expressed in the first language is generated. The modified subset is inserted into the natural language content.

Abstract: According to one embodiment, a method, computer system, and computer program product for three-dimensional printing is provided. The embodiment may include analyzing data of a user. The data is collected while the user is performing an activity. The embodiment may include deriving a user behavior model (UBM) of the user based on the analysis of the data. The embodiment may include calculating a relative comfort coefficient (RCC) of the user for the activity based on attributes of the UBM. The embodiment may include predicting adjustments to the attributes of the UBM which result in the RCC exceeding a threshold value. The predicted adjustments are derived using a convolutional neural network classifier. The embodiment may include defining one or more parameters of a tangible component of an object utilized by the user when performing the activity based on the predicted adjustments.

Abstract: From a set of natural language text documents, a concept tree is constructed. For a node in the concept tree a polarity of the subset represented by the node is scored. A second set of natural language text documents is added to the subset, the adding resulting in a modified subset of natural language text documents having a polarity score within a predefined neutral polarity score range. From the modified subset, a bin of sentences is selected according to a sentence selection parameter, a sentence in the bin of sentences being extracted from a selected document in the modified subset. A sentence having a factuality score below a threshold factuality score is removed from the bin of sentences. From the filtered bin of sentences a new natural language text document corresponding to the filtered bin of sentences is generated using a transformer deep learning narration generation model.

Abstract: From a set of natural language text documents, a concept tree is constructed. For a node in the concept tree a polarity of the subset represented by the node is scored. A second set of natural language text documents is added to the subset, the adding resulting in a modified subset of natural language text documents having a polarity score within a predefined neutral polarity score range. From the modified subset, a bin of sentences is selected according to a sentence selection parameter, a sentence in the bin of sentences being extracted from a selected document in the modified subset. A sentence having a factuality score below a threshold factuality score is removed from the bin of sentences. From the filtered bin of sentences a new natural language text document corresponding to the filtered bin of sentences is generated using a transformer deep learning narration generation model.

Abstract: An embodiment calculates a point of view (POV) value for a subportion of an item of media content, including evaluating user inputs related to an automatically detected POV of the subportion of the item. The embodiment also calculates a non-factual cost for the subportion of the item indicative of an amount of the subportion of the item that lacks support in a fact-based corpora. The embodiment also performs a cascaded summarization process comprising generating a summary of the item using the subportion of the item and a summarization technique, analyzing the summary using a fact-checking algorithm to determine whether the summary satisfies a factual score threshold, and performing a next iteration of the cascaded summarization process while the summary fails to satisfy the factual score threshold. The embodiment also communicates a summary satisfying the factual score threshold to a user device.

Abstract: A method, computer program product and computer system to determine suspicious activity by users via in-game transactions is provided. A processor identifies a transaction involving a player character operated by a user within a game. A processor retrieves player data associated with the player character and item data associated with the items offered during the transaction involving the player character. A processor determines an optimal choice for the player character based on a comparison between the player data and the item data during the transaction. A processor, in response to the user selecting a suboptimal choice different from the optimal choice, adjusts at least one behavioral score of a profile associated with the user. A processor, in response to the at least one behavioral score being outside an expected range of the at least one behavioral score, restricts at least one aspect of an account associated with the player character.

Abstract: A computer-implemented method includes: presenting, by a computing device, a virtual event user interface to an attendee of a virtual event; obtaining, by the computing device, data about actions performed by the attendee within the virtual event; creating, by the computing device, a tensile sphere kernel that is specific to the attendee using the obtained data; creating, by the computing device, a mixed tensile sphere kernel using the tensile sphere kernel that is specific to the attendee and another tensile sphere kernel of another attendee; determining, by the computing device, an event recommendation of the virtual event using the mixed tensile sphere kernel; and presenting, by the computing device, the event recommendation to the attendee by changing the virtual event user interface to show the event recommendation.

Abstract: A relevant factoid(s) related to multimedia data is generated by splitting a multimedia item into a media component and a text component. Text information is retrieved relevant to text data from the text component using a query. The text information is summarized into a factoid. Source data is checked for an image based on the multimedia component. A current state image is generated from the image. The factoid and the current state image are combined into a combined factoid, and the combined factoid is stored for sending to a media outlet for presentation on a media format.

Abstract: Detecting spatial positioning between a user's hands and an object, using a wearable device, to provide feedback to a user. Motion data of a person's body motion while performing an action can be received at a computer. The motion data can include sensor data from sensors at a location where the sensors detect the person's body motion. The sensors can include a wearable device on the person's body. The computer can be used to model the person's body motion using the motion data. A set of parameters for acceptable motions is determined based on an action risk assessment of the action. Feedback can be initiated to the person, using the wearable device, based on the person's body motion exceeding a body motion threshold based on the set of parameters for the acceptable motions and the model.

Abstract: Using a sentiment analysis model, a reaction to a presentation of a first content is measured. Using the first content and the reaction, a content generation parameter is determined. Using a first content generation model and the content generation parameter, second content corresponding to the first content is generated. Using a second content generation model and the content generation parameter, third content corresponding to the first content is generated. The first content is adjusted by combining the first content with the second content and the third content, the adjusting resulting in an adjusted content.

Abstract: A live event virtual experience is provided. Emotions of virtual spectators to a current situation occurring in a live event at a physical venue are determined from received data regarding reactions of the virtual spectators to the live event using bias detection. A historical sound clip that matches the emotions of the virtual spectators to the current situation occurring in the live event is retrieved. The historical sound clip that matches the emotions of the virtual spectators to the current situation occurring in the live event is input into a machine learning model that performs inverse bias mitigation to amplify bias and applies in-process adversarial fairness debiasing. The historical sound clip after performing the inverse bias mitigation to amplify the bias and applying the in-process adversarial fairness debiasing is converted to a standardized historical sound segment length. A sound representation is generated from the standardized historical sound segment length.

Abstract: An autonomic function executing in an artificial intelligence environment determines that a fused model responsive to a new problem space has below a threshold level of accuracy in the new problem space. A spliced layer in the fused model is autonomically cloned, the spliced layer having been extracted from a second model and inserted at a location in the fused model. The cloned layer is autonomically inserted at a second location in the fused model. An automatically constructed vector transformation transforms an output vector of a previous layer in an immediately previous location in the model relative to the second location. The cloned layer is automatically fused in the fused model using the transformed output vector as input to the cloned layer, forming a deep fused model that has a revised accuracy that is higher than the accuracy relative to an ontology of the new problem space.

Abstract: A route from a first physical location to a second physical location is divided into a set of segments using a route optimization engine. Using a user response analysis model, a response to a physical environment associated with a segment in the set of segments is scored, the scoring resulting in a score. Using a content generation model and the score, the physical environment is augmented, the augmenting combining the physical environment and a generated environment.

Abstract: From a first sensor in a set of sensors, a set of sensor measurements corresponding to a wearer of a garment is collected. Using a model and the set of sensor measurements, a performance deviation index corresponding to the wearer is determined, the performance deviation index corresponding to a deviation from a baseline performance level of the wearer. Responsive to the performance deviation index being above a threshold, a characteristic of the garment is altered.

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 computer receives a multimedia data, where the multimedia data comprises a plurality of frames. The computer converts the multimedia data into a signal wave having a plurality of frequencies and a plurality of amplitudes. The computer determines a frame from the plurality of frames having a pronoun. The computer identifies a topic of the frame. The computer searches for a frame in a media repository having a highest correlation coefficient with the topic of the frame, where the frame from the media repository comprises a bag of objects and resolves the anaphora disambiguation by substituting the pronoun with an object from the bag of objects.