Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: The present invention relates to a cheerleading training system. The cheerleading training system uses sensors implemented on training gloves to measure pressures imposed on cheerleaders' hands, as well as the acceleration of the cheerleaders' hands. Each training glove may have a microprocessor that contains target measurements that are compared to the pressure and acceleration measurements obtained by the sensors of the training gloves. Each training glove may have at least one LED and/or a buzzer that provide feedback to the cheerleaders depending on whether the measured pressures and accelerations meet the target measurements. This allows the cheerleaders to adjust their technique, and thereby perform a cheerleading stunt more safely. The pressure and acceleration measurements may also be transmitted to a coach's device via a transmitter.

Abstract: Systems and methods for dynamic demand sensing in a supply chain in which constantly-updated data is used to select a machine learning model or retrain a pre-selected machine learning model, for forecasting sales of a product at a specific location. The updated data includes product information and geographic information.

Abstract: Systems and methods for dynamic demand sensing in a supply chain in which constantly-updated data is used to select a machine learning model or retrain a pre-selected machine learning model, for forecasting sales of a product at a specific location. The updated data includes product information and geographic information. Also disclosed are systems and methods relating to demand forecasting and readjusting forecasts based on forecast error.

Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: Embodiments of the present invention comprise a 4-wheeled resistance training device in the form of a box, wherein a user may add weights to the inside or to the top of the box to increase the resistance provided to the user. The wheels may be connected to the box by one or more threaded axles, each threaded axle existing as two or more parts. Rotation of the threaded axles may power a generator, which may power a light system comprising one or more lights. The light system may provide visual feedback to a user by changing the color and/or intensity of the one or more lights depending on multiple factors. Further embodiments of the invention may comprise a battery for storing energy generated by the generator. Embodiments of the invention may also comprise the ability to store data about a user's workout.

Abstract: Embodiments of the present invention comprise a 4-wheeled resistance training device in the form of a box, wherein a user may add weights to the inside or to the top of the box to increase the resistance provided to the user. The wheels may be connected to the box by one or more threaded axles, each threaded axle existing as two or more parts. Rotation of the threaded axles may power a generator, which may power a light system comprising one or more lights. The light system may provide visual feedback to a user by changing the color and/or intensity of the one or more lights depending on multiple factors. Further embodiments of the invention may comprise a battery for storing energy generated by the generator. Embodiments of the invention may also comprise the ability to store data about a user's workout.

Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: Systems and methods for dynamic demand sensing in a supply chain in which constantly-updated data is used to select a machine learning model or retrain a pre-selected machine learning model, for forecasting sales of a product at a specific location. The updated data includes product information and geographic information.

Abstract: The innovation is directed to a method for treating a CCR5 and/or CCR2 mediated disease such as nonalcoholic steatohepatitis (NASH) comprising administering an effective amount of a C—C Chemokine receptor 5 (CCR5) antagonist (e.g., maraviroc or vicriviroc or cenicriviroc) and/or an effective amount of a C—C Chemokine receptor 2 (CCR2) antagonist, or a CCR5/CCR2 antagonist together with an effective amount of farnesoid X receptor (FXR) agonist (e.g., obeticholic acid (OCA)). An “effective amount” can be a regular clinical dose of either agent alone or a reduced dose of the FXR receptor agonist and/or the CCR5/CCR2 antagonist. The combination is effective to treat NASH with (1) enhanced efficacy and (2) substantial reduction of side effects, particularly those associated with administration of OCA or its analogues, namely less effect on liver enzyme elevation, and less severity and frequency of pruritus (3). The fixed dose combination provides for better efficacy and safety profile.

Abstract: Systems and methods for dynamic demand sensing in a supply chain in which constantly-updated data is used to select a machine learning model or retrain a pre-selected machine learning model, for forecasting sales of a product at a specific location. The updated data includes product information and geographic information.

Abstract: Systems and methods for features engineering, in which internal and external signals are received and fused. The fusing is based on meta-data of each of the one or more internal signals and each of the one or more external signals. A set of features is generated based on one or more valid combinations that match a transformation input, the transformation forming part of library of transformations. Finally, a set of one or more features is selected from the plurality of features, based on a predictive strength of each feature. The set of selected features can be used to train and select a machine learning model.

Abstract: A system and method for gas pump or carwash environments which allows new applications to be added to established systems, having a computing system, software techniques, and hardware or software communications interfaces. Various embodiments include methods of separation and interception and the software techniques. One implementation includes separating a first application from an equipped device by interposing a bridge; intercepting, with the bridge, downstream communications to the equipped device from the first application; using the bridge, accepting downstream communications to the equipped device from a second application; with the bridge, locking communications with the equipped device to one of the first application and the second application; and unlocking the communications with the equipped device in response to receiving a status from the equipped device.

Abstract: The innovation is directed to a method for treating a CCR5 and/or CCR2 mediated disease such as nonalcoholic steatohepatitis (NASH) comprising administering an effective amount of a C-C Chemokine receptor 5 (CCR5) antagonist (e.g., maraviroc or vicriviroc or cenicriviroc) and/or an effective amount of a C-C Chemokine receptor 2 (CCR2) antagonist, or a CCR5/CCR2 antagonist together with an effective amount of farnesoid X receptor (FXR) agonist (e.g., obeticholic acid (OCA)). An “effective amount” can be a regular clinical dose of either agent alone or a reduced dose of the FXR receptor agonist and/or the CCR5/CCR2 antagonist. The combination is effective to treat NASH with (1) enhanced efficacy and (2) substantial reduction of side effects, particularly those associated with administration of OCA or its analogues, namely less effect on liver enzyme elevation, and less severity and frequency of pruritus (3). The fixed dose combination provides for better efficacy and safety profile.

Abstract: A system and method for gas pump or carwash environments which allows new applications to be added to established systems, having a computing system, software techniques, and hardware or software communications interfaces. Various embodiments include methods of separation and interception and the software techniques. One implementation includes separating a first application from an equipped device by interposing a bridge; intercepting, with the bridge, downstream communications to the equipped device from the first application; using the bridge, accepting downstream communications to the equipped device from a second application; with the bridge, locking communications with the equipped device to one of the first application and the second application; and unlocking the communications with the equipped device in response to receiving a status from the equipped device.