Abstract: An edge computing platform with machine learning capability is provided between a local network with a plurality of sensors and a remote network. A machine learning model is created and trained in the remote network using aggregated sensor data and deployed to the edge platform. Before being deployed, the model is edge-converted (“edge-ified”) to run optimally with the constrained resources of the edge device and with the same or better level of accuracy. The “edge-ified” model is adapted to operate on continuous streams of sensor data in real-time and produce inferences. The inferences can be used to determine actions to take in the local network without communication to the remote network. A closed-loop arrangement between the edge platform and remote network provides for periodically evaluating and iteratively updating the edge-based model.

Abstract: A set of processes enable supervised learning of a machine learning model without human intervention by producing the positive and negative examples at-will in a deployed environment. A technique implements a series of events that replaces the need for human intervention to generate labeled data for supervised learning. This enables automatic retraining of the model in a deployed environment without the need for human labeled data, supporting audio and video data.

Abstract: A method for enabling intelligence at the edge. Features include: triggering by sensor data in a software layer hosted on either a gateway device or an embedded system. Software layer is connected to a local-area network. A repository of services, applications, and data processing engines is made accessible by the software layer. Matching the sensor data with semantic descriptions of occurrence of specific conditions through an expression language made available by the software layer. Automatic discovery of pattern events by continuously executing expressions. Intelligently composing services and applications across the gateway device and embedded systems across the network managed by the software layer for chaining applications and analytics expressions. Optimizing the layout of the applications and analytics based on resource availability. Monitoring the health of the software layer. Storing of raw sensor data or results of expressions in a local time-series database or cloud storage.

Abstract: An edge computing platform with machine learning capability is provided between a local network with a plurality of sensors and a remote network. A machine learning model is created and trained in the remote network using aggregated sensor data and deployed to the edge platform. Before being deployed, the model is edge-converted (“edge-ified”) to run optimally with the constrained resources of the edge device and with the same or better level of accuracy. The “edge-ified” model is adapted to operate on continuous streams of sensor data in real-time and produce inferences. The inferences can be used to determine actions to take in the local network without communication to the remote network. A closed-loop arrangement between the edge platform and remote network provides for periodically evaluating and iteratively updating the edge-based model.

Abstract: A method for enabling intelligence at the edge. Features include: triggering by sensor data in a software layer hosted on either a gateway device or an embedded system. Software layer is connected to a local-area network. A repository of services, applications, and data processing engines is made accessible by the software layer. Matching the sensor data with semantic descriptions of occurrence of specific conditions through an expression language made available by the software layer. Automatic discovery of pattern events by continuously executing expressions. Intelligently composing services and applications across the gateway device and embedded systems across the network managed by the software layer for chaining applications and analytics expressions. Optimizing the layout of the applications and analytics based on resource availability. Monitoring the health of the software layer. Storing of raw sensor data or results of expressions in a local time-series database or cloud storage.

Abstract: A method for enabling intelligence at the edge. Features include: triggering by sensor data in a software layer hosted on either a gateway device or an embedded system. Software layer is connected to a local-area network. A repository of services, applications, and data processing engines is made accessible by the software layer. Matching the sensor data with semantic descriptions of occurrence of specific conditions through an expression language made available by the software layer. Automatic discovery of pattern events by continuously executing expressions. Intelligently composing services and applications across the gateway device and embedded systems across the network managed by the software layer for chaining applications and analytics expressions. Optimizing the layout of the applications and analytics based on resource availability. Monitoring the health of the software layer. Storing of raw sensor data or results of expressions in a local time-series database or cloud storage.

Abstract: A method for enabling intelligence at the edge. Features include: triggering by sensor data in a software layer hosted on either a gateway device or an embedded system. Software layer is connected to a local-area network. A repository of services, applications, and data processing engines is made accessible by the software layer. Matching the sensor data with semantic descriptions of occurrence of specific conditions through an expression language made available by the software layer. Automatic discovery of pattern events by continuously executing expressions. Intelligently composing services and applications across the gateway device and embedded systems across the network managed by the software layer for chaining applications and analytics expressions. Optimizing the layout of the applications and analytics based on resource availability. Monitoring the health of the software layer. Storing of raw sensor data or results of expressions in a local time-series database or cloud storage.