Abstract: Route planning for an unmanned aerial vehicle (UAV) is disclosed. A map of a region is partitioned into geographic cells, data about flight conditions in each cell is aggregated, and a cost for each cell is calculated based on weighted flight condition factors. A plurality of flight paths from a first point to a second point are determined, and a cost for each flight path is determined by summing the cost of each cell traversed by the flight path. An optimal flight path is selected from the plurality of flight paths in dependence upon the total cost of each flight path. When new information is obtained that affects the cost of the cells the flight path, the cost of the current flight path is recalculated along with the costs of alternative flight paths to determine whether a route should be altered.

Abstract: Uses of artificial intelligence in battery technology including a method that includes receiving a trained model, receiving sensor data from at least one sensor associated with a battery, and executing the trained model by a processor. Executing the trained model includes providing the sensor data as input to the trained model to generate a model output. The method also includes sending, from the processor to a charge controller coupled to the battery, a control signal that is based on the model output and automatically, by the charge controller, initiating or terminating charging of the battery based on the control signal.

Abstract: A method includes receiving, at one or more processors of a vehicle, user speech input, the user speech input including a navigation command and a description of a photograph. The method also includes transmitting, via a local network, query data based on the user speech input to a portable computing device associated with the vehicle to initiate an image search based on the user speech input. The method further includes receiving, at the one or more processors of the vehicle from the portable computing device via the local network, location data indicating a location associated with the photograph and setting, by the one or more processors of the vehicle, a navigation waypoint based on the location data and based on the navigation command.

Abstract: Methods, systems, apparatuses, and computer program products for providing malware protection on a UAV are disclosed. In a particular embodiment, a method of providing malware protection on a UAV includes a malware defense controller initiating, on an unmanned aerial vehicle (UAV) in response to a malware defense event, a malware defense scan of at least one file stored on the UAV. In this embodiment, the malware defense controller also implements, in dependence upon a result of a malware detection analysis, a malware defense operation.

Abstract: In a particular embodiment, coordinating an aerial search among unmanned aerial vehicles is disclosed that includes receiving, by a server in a UAV transportation ecosystem, search area data, accessing, by the server, UAV parameters for a type of UAV, determining, by the server in dependence upon the search area data and the UAV parameters, a number of UAVs needed to complete a coordinated aerial search of a search area within a time limit, and partitioning, by the server, the search area into a plurality of partitions, wherein the number of partitions is equal to the number of UAVs.

Abstract: Controlling the operation of one or more components in an electric vehicle, including: receiving, from one or more vehicle operation sensors, operation data including sensor data corresponding to a condition of one or more components of the vehicle; determining, using a trained model, whether the one or more components of the vehicle are operating in an acceptable manner; and generating a control signal to adjust operation of the one or more components of the vehicle.

Abstract: A method includes selecting a subset of models from a plurality of models. The plurality of models is generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes performing at least one genetic operation of the genetic algorithm with respect to at least one model of the subset to generate a trainable model. The method includes determining a rate of improvement associated with prior backpropagation iterations. The method includes selecting, based on the rate of improvement, one of the trainable model or a prior trainable model as a selected trainable model. The method includes generating the trained model including training the selected trainable model. The method includes adding the trained model as input to a second epoch of the genetic algorithm that is subsequent to the first epoch.

Abstract: A method includes determining, based at least in part on parameters of a software defined radio (SDR), waveform data descriptive of an electromagnetic waveform. The method also includes generating feature data based on the waveform data. The method further includes providing the feature data as input to a first machine learning model to predict a future action of a device associated with at least a portion of the electromagnetic waveform and initiating a response action based on the predicted future action.

Abstract: Methods, systems, apparatuses, and computer program products for automated preflight evaluation of an unmanned aerial vehicle (UAV) configuration are disclosed. In a particular embodiment, automated preflight evaluation of an UAV configuration includes a preflight controller retrieving information about a UAV configuration selected to perform a mission in accordance with one or more mission parameters. In this embodiment, the preflight controller uses the retrieved information to assess an ability of the UAV configuration to perform the mission in accordance with the one or more mission parameters.

Abstract: Methods, systems, apparatuses, and computer program products for fulfilling a request associated with operational aspects of an unmanned aerial vehicle (UAV) mission are disclosed. In a particular embodiment, fulfilling a request associated with operational aspects of a UAV mission includes a fulfillment controller presenting to a first set of providers of a plurality of providers, a request for offers to perform a first set of operational aspects of a UAV mission. In this embodiment, the fulfillment controller also includes receiving from each provider of a second set of providers of the plurality of providers, an offer to perform a second set of operational aspects of the first set of operational aspects of the UAV mission. In addition, the fulfillment controller also selects from a first set of offers received from the second set of providers, a first offer to accept.

Abstract: A server includes: a specifying unit for specifying a live-stream to be preferentially recommended; an obtaining unit for obtaining, for the specified live-stream to be preferentially recommended, a number of users to whom the live-stream is recommended; a generating unit for generating a group of users by selecting a number of users corresponding to the obtained number of users to whom the live-stream is recommended; and a setting unit for setting a list of live-streams to be recommended to a user included in the generated group of users such that the live-stream to be preferentially recommended is presented in priority over other live-streams in the list on a terminal of the user.

Abstract: In a particular embodiment, decentralized oracles in an unmanned aerial vehicle (UAV) transportation ecosystem includes: receiving, by an oracle node of a plurality of oracle nodes, from a validating node of a plurality of validating nodes of a UAV transportation ecosystem, a request for data for fulfillment of a smart contract, wherein the plurality of oracle nodes are communicatively coupled via an overlay network implemented using a network communicatively coupling the plurality of validating nodes; generating, based on responses to the request from the plurality of oracle nodes, the data for fulfillment of the smart contract; and providing the data for fulfillment of the smart contract.

Abstract: A method includes selecting a subset of models from a plurality of models. The plurality of models is generated based on a genetic algorithm and corresponds to a first epoch of the genetic algorithm. Each of the plurality of models includes data representative of a neural network. The method includes performing at least one genetic operation of the genetic algorithm with respect to at least one model of the subset to generate a trainable model. The method includes determining a rate of improvement associated with prior backpropagation iterations. The method includes selecting, based on the rate of improvement, one of the trainable model or a prior trainable model as a selected trainable model. The method includes generating the trained model including training the selected trainable model. The method includes adding the trained model as input to a second epoch of the genetic algorithm that is subsequent to the first epoch.

Abstract: In a particular embodiment, blockchain-based hybrid authentication is disclosed that includes receiving, by a smart contract controller, an invocation of a smart contract and accessing, by the smart contract controller, one or more parameters associated with a client account. In this embodiment, the smart contract determines whether the one or more parameters fulfill the smart contract. In response to determining that the one or more parameters fulfill the smart contract, the smart contract provides an attestation of an identity associated with the client account.

Abstract: Embodiments of the invention provide a “tool-kit” of processing techniques which can be employed in different combinations depending on the circumstances. For example, flow speed can be found using eddy tracking techniques, or by using speed of sound measurements. Moreover, composition can be found by using speed of sound measurements and also by looking for turning points in the k-w curves, particularly in stratified multi-phase flows. Different combinations of the embodiments can therefore be put together to provide further embodiments, to meet particular flow sensing requirements, both on the surface and downhole. Once the flow speed is known, then at least in the case of a single phase flow, the flow speed can be multiplied by the interior cross-sectional area of the pipe to obtain the flow rate. The mass flow rate can then be obtained if the density of the fluid is known, once the composition has been determined.

Abstract: Methods, systems, apparatuses, and computer program products for geofence management with an unmanned aerial vehicle (UAV) are disclosed. In a particular embodiment, a method of geofence management with a UAV includes a geofence manager utilizing a first set of sensor data collected by a first set of in-flight UAVs of the UAV system to detect a first object. In this embodiment, the geofence manager also utilizes the first set of sensor data to determine a first location of the detected first object and determines whether the first location of the detected first object is within a geofence of an area.

Abstract: Methods, systems, apparatuses, and computer program products for displaying electromagnetic spectrum information for UAV navigation are disclosed. In a particular embodiment, a method of displaying electromagnetic spectrum information for UAV navigation includes an electromagnetic spectrum awareness controller, of a control device associated with a UAV, that generates a first map layer based on electromagnetic spectrum map data; and displays, on a display of the control device, the first map layer overlaid on a base image.

Abstract: The present invention provides a composition and a method for mitigating formation or activity of a corrosion-associated biofilm on metal surfaces of pipelines. The pipelines are first treated with pigs i.e. bi-di pigs for removing/disturbing biofilm, followed by microbial treatment i.e. application of microbecidal composition. The microbecidal composition comprising at least one alcohol, one corrosion inhibitor, one surfactant, one biocide and a lignin-based nanoparticle. The lignin-based nano particle is functionalized with amine functionalizing agent. The present composition and method is eco-friendly, as low concentration is sufficient and further, regular dosing is not required for MIC control.

Abstract: A method of behavior monitoring includes receiving, from a first sensor of a mobile sensor platform, first sensor data indicative of operation of a monitored device, wherein the monitored device is distinct from the mobile sensor platform; providing, as input to a trained behavior model associated with the monitored device, input data based at least in part on the first sensor data to generate behavior model output data; generating, based on the behavior model output data, a control command; and sending the control command to the mobile sensor platform or the monitored device.

Abstract: A method includes receiving input that identifies one or more data sources and determining, based on the input, a machine learning problem type of a plurality of machine learning problem types supported by an automated model building (AMB) engine. The method also includes generating an input data set of the AMB engine based on application of one or more rules to the one or more data sources. The method further includes, based on the input data set and the machine learning problem type, initiating execution of the AMB engine to generate a neural network configured to model at least a portion of the input data set.