Abstract: A system for broad area geospatial object detection includes a processor configured to retrieve training data including a first plurality of orthorectified geospatial training images each including at least one labeled instance of the object of interest, and a second plurality of orthorectified geospatial images each including at least one labeled instance of the object of interest and/or at least one unlabeled instance of the object of interest, and apply at least one type of image correction to the training data. The processor is also configured to train a plurality of machine learning classifier elements, based on the first plurality of orthorectified geospatial training images and subsequently based on the second plurality of orthorectified geospatial images, each of the plurality of machine learning classifier elements being defined by a machine learning protocol parameterized based on one or more visually unique features of the object of interest.

Abstract: A system and a method generate a recommendation on a mobile device. The system and the method may use a time, a location, a venue and/or an event to generate the recommendation. Further, the system and the method may use an event database to determine current interests of the user. Still further, the system and the method for generating a recommendation on a mobile device may use a transactional history of the user and/or behavior of other users to generate the recommendation. The system and the method may recommend, for example, digital media, news and event information, editorial content and/or physical or digital merchandise. As a result, the system and the method may generate a recommendation that corresponds to the current interests of the user.

Abstract: An exemplary embodiment of the present disclosure provides a system comprising a pipette tip manipulable between a sample area and an active agent exposure zone and a controller configured to manipulate the pipette tip between the sample area and the active agent exposure zone, wherein when the pipette tip comprises at least a portion of a biological sample target, the controller is further configured to isolate at least a portion of the biological sample target from one or more biological sample targets. Also disclosed is a method for detecting an effect of an active agent on a cell, by forming a high-resistance seal between a cell and an apertured surface, isolating at least a portion of the cell, translocating the apertured surface in one or more translations within an x-plane, a y-plane, a z-plane, or combinations thereof, and exposing the portion of the cell to an active agent.

Abstract: Prioritizing a customer service agent's responses to customer messages. In one form, an expected response time target is determined based on a time interval between sending an agent response and receiving a customer response from a particular customer. In other forms, other objective factors, such as message intervals, customer properties, and message properties, are used to determine the expected response time target. In yet other forms, a customer conversation can be automatically closed if the customer does not respond within a predetermined maximum time interval.

Abstract: A hydrodynamic power generation assembly and method of use therefor for generating electrical power from the combination of kinetic energy, hydrostatic energy, and turbulent energy of water. The power generation assembly comprises a water accelerator assembly comprising a support structure which is at least partially buoyant and a baffle panel member (or an array of baffle panel members) having an opening, inter-panel spacing, or flow passageway around the baffle panel(s). A hydropower converter is supported from, by, or on the support structure and is operatively coupled to a generator. The hydropower converter is positioned behind baffle assembly. Water flowing through or around the baffle assembly has an increased velocity relative the ambient current and therefore is capable of generating more power relative to the ambient water where power generation assembly is deployed. Particular types of hydropower converters suitable for use with the invention are turbines and water wheels.

Abstract: Techniques for quantifying accuracy of a prediction model that has been trained on a data set parameterized by multiple features are provided. The model performs in accordance with a theoretical performance manifold over an intractable input space in connection with the features. A determination is made as to which of the features are strongly correlated with performance of the model. Based on the features determined to be strongly correlated with performance of the model, parameterized sub-models are created such that, in aggregate, they approximate the intractable input space. Prototype exemplars are generated for each of the created sub-models, with the prototype exemplars for each created sub-model being objects to which the model can be applied to result in a match with the respective sub-model. The accuracy of the model is quantified using the generated prototype exemplars. A recommendation engine is provided for when there are particular areas of interest.

Abstract: A system and a method generate a recommendation on a mobile device. The system and the method may use a time, a location, a venue and/or an event to generate the recommendation. Further, the system and the method may use an event database to determine current interests of the user. Still further, the system and the method for generating a recommendation on a mobile device may use a transactional history of the user and/or behavior of other users to generate the recommendation. The system and the method may recommend, for example, digital media, news and event information, editorial content and/or physical or digital merchandise. As a result, the system and the method may generate a recommendation that corresponds to the current interests of the user.

Abstract: Techniques for recommending a prediction model from among a number of different prediction models are provided. Each of these prediction models has been trained based on a respective training data set, and each performs in accordance with a respective theoretical performance manifold. An indication of a region definable in relation to the theoretical performance manifolds of the different prediction models is received as input. For each of the different prediction models, the indication of the region is linked to features parameterizing the respective performance manifold; and one or more portions of the respective performance manifold is/are identified based on the features determined by the linking, the portion(s) having a volume and a shape that collectively denote an expected performance of the respective model for the input. The expected performance of the prediction models for the input is compared. Based on the comparison, one or more of the models is/are suggested.

Abstract: Techniques for quantifying accuracy of a prediction model that has been trained on a data set parameterized by multiple features are provided. The model performs in accordance with a theoretical performance manifold over an intractable input space in connection with the features. A determination is made as to which of the features are strongly correlated with performance of the model. Based on the features determined to be strongly correlated with performance of the model, parameterized sub-models are created such that, in aggregate, they approximate the intractable input space. Prototype exemplars are generated for each of the created sub-models, with the prototype exemplars for each created sub-model being objects to which the model can be applied to result in a match with the respective sub-model. The accuracy of the model is quantified using the generated prototype exemplars. A recommendation engine is provided for when there are particular areas of interest.

Abstract: Techniques for recommending a prediction model from among a number of different prediction models are provided. Each of these prediction models has been trained based on a respective training data set, and each performs in accordance with a respective theoretical performance manifold. An indication of a region definable in relation to the theoretical performance manifolds of the different prediction models is received as input. For each of the different prediction models, the indication of the region is linked to features parameterizing the respective performance manifold; and one or more portions of the respective performance manifold is/are identified based on the features determined by the linking, the portion(s) having a volume and a shape that collectively denote an expected performance of the respective model for the input. The expected performance of the prediction models for the input is compared. Based on the comparison, one or more of the models is/are suggested.

Abstract: A method of cleaning a component within a turbine that includes disassembling the turbine engine to provide a flow path to an interior passageway of the component from an access point. The component has coked hydrocarbons formed thereon. The method further includes discharging a flow of cleaning solution towards the interior passageway from the access point, wherein the cleaning solution is configured to remove the coked hydrocarbons from the component.

Abstract: A system and a method generate a recommendation on a mobile device. The system and the method may use a time, a location, a venue and/or an event to generate the recommendation. Further, the system and the method may use an event database to determine current interests of the user. Still further, the system and the method for generating a recommendation on a mobile device may use a transactional history of the user and/or behavior of other users to generate the recommendation. The system and the method may recommend, for example, digital media, news and event information, editorial content and/or physical or digital merchandise. As a result, the system and the method may generate a recommendation that corresponds to the current interests of the user.

Abstract: A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.

Abstract: Disclosed are methods of treating a disorder or disease associated with myotonic dystrophy. Methods of treating a CNS dysfunction and/or cognitive impairment associated with myotonic dystrophy in a subject comprising administering a therapeutically effective amount of a GABAA receptor antagonist or inverse agonist to the subject are disclosed. Methods of treating a myotonic dystrophy associated disease or disorder caused by mis-splicing of GABRG2 in a subject comprising administering a therapeutically effective amount of a GABAA receptor antagonist or inverse agonist to the subject are disclosed. Methods of improving cognitive function or alertness in a subject having myotonic dystrophy comprising administering a therapeutically effective amount of a GABAA receptor antagonist or inverse agonist to the subject are disclosed.

Abstract: A spray coating system includes a spraying robot sized to fit within a conduit. The spraying robot includes arms that extend outward and retract inward to maintain contact with an interior surface of the conduit. The spraying robot is configured to be coupled with hoses that separately supply different fluids to the spraying robot. The spraying robot includes a spray head from which a compound formed from the fluids is sprayed onto the interior surface of the conduit. The spraying robot is configured to be pulled through the conduit and/or self-propel in the conduit to spray the compound onto the interior surface of the conduit and form a coating thereon.

Abstract: A system for simplified generation of systems for analysis of satellite images to geolocate one or more objects of interest. A plurality of training images labeled for a study object or objects with irrelevant features loaded into a preexisting feature identification subsystem causes automated generation of models for the study object. This model is used to parameterize pre-engineered machine learning elements that are running a preprogrammed machine learning protocol. Training images with the study are used to train object recognition filters. This filter is used to identify the study object in unanalyzed images. The system reports results in a requestor's preferred format.

Abstract: A system and a method generate a recommendation on a mobile device. The system and the method may use a time, a location, a venue and/or an event to generate the recommendation. Further, the system and the method may use an event database to determine current interests of the user. Still further, the system and the method for generating a recommendation on a mobile device may use a transactional history of the user and/or behavior of other users to generate the recommendation. The system and the method may recommend, for example, digital media, news and event information, editorial content and/or physical or digital merchandise. As a result, the system and the method may generate a recommendation that corresponds to the current interests of the user.

Abstract: A hydrodynamic power generation assembly and method of use therefor for generating electrical power from the combination of kinetic energy, hydrostatic energy, and turbulent energy of water. The power generation assembly comprises a water accelerator assembly comprising a support structure which is at least partially buoyant and a baffle panel member (or an array of baffle panel members) having an opening, inter-panel spacing, or flow passageway around the baffle panel(s). A hydropower converter is supported from, by, or on the support structure and is operatively coupled to a generator. The hydropower converter is positioned behind baffle assembly. Water flowing through or around the baffle assembly has an increased velocity relative the ambient current and therefore is capable of generating more power relative to the ambient water where power generation assembly is deployed. Particular types of hydropower converters suitable for use with the invention are turbines and water wheels.

Abstract: A system and a method generate a recommendation on a mobile device. The system and the method may use a time, a location, a venue and/or an event to generate the recommendation. Further, the system and the method may use an event database to determine current interests of the user. Still further, the system and the method for generating a recommendation on a mobile device may use a transactional history of the user and/or behavior of other users to generate the recommendation. The system and the method may recommend, for example, digital media, news and event information, editorial content and/or physical or digital merchandise. As a result, the system and the method may generate a recommendation that corresponds to the current interests of the user.

Abstract: A hydrodynamic power generation assembly and method of use therefor for generating electrical power from the combination of kinetic energy, hydrostatic energy, and turbulent energy of water. The power generation assembly comprises a water accelerator assembly comprising a support structure which is at least partially buoyant and a baffle panel member (or an array of baffle panel members) having an opening, inter-panel spacing, or flow passageway around the baffle panel(s). A hydropower converter is supported from, by, or on the support structure and is operatively coupled to a generator. The hydropower converter is positioned behind baffle assembly. Water flowing through or around the baffle assembly has an increased velocity relative the ambient current and therefore is capable of generating more power relative to the ambient water where power generation assembly is deployed. Particular types of hydropower converters suitable for use with the invention are turbines and water wheels.