Abstract: In various example embodiments, a system and method are provided for protection customer data collected at sensor nodes within a networked system. A key recovery module determines the encrypted sensor data in a request was encrypted with a certified public key associated with a first customer key-pair. The first customer key-pair represents a recovered private key. The key recovery module determines the private key associated with the first customer key-pair is encrypted with the private key associated with a second customer key-pair. The private key associated with the first customer key-pair is decrypted by using the private key associated with the second customer key-pair. The encrypted sensor data in the request is decrypted using the decrypted private key associated with the first customer key-pair.

Abstract: In various example embodiments, a system and method are provided for a service data platform. The service data platform includes an application management API configured to receive software uploaded by a third party using a management application API. The service data platform also includes a plurality of graph servers configured to identify a group of lighting nodes to distribute the uploaded software and determine the uploaded software is safe for deployment to the identified group of lighting nodes. The service data platform further includes a device manager configured to distribute, using an administrative API, the uploaded software to the identified group of lighting nodes.

Abstract: Systems and methods for probabilistic semantic sensing in a sensory network are disclosed. The system receives raw sensor data from a plurality of sensors and generates semantic data including sensed events. The system correlates the semantic data based on classifiers to generate aggregations of semantic data. Further, the system analyzes the aggregations of semantic data with a probabilistic engine to produce a corresponding plurality of derived events each of which includes a derived probability. The system generates a first derived event, including a first derived probability, that is generated based on a plurality of probabilities that respectively represent a confidence of an associated semantic datum to enable at least one application to perform a service based on the plurality of derived events.

Abstract: Methods, devices, systems, and non-transitory process-readable storage media for controlling lighting nodes of a lighting system associated with a lighting infrastructure based on composited lighting models. An embodiment method performed by a processor of a computing device may include operations for obtaining a plurality of lighting model outputs generated by lighting control algorithms that utilize sensor data obtained from one or more sensor nodes within the lighting infrastructure, combining the plurality of lighting model outputs in an additive fashion to generate a composited lighting model, calculating lighting parameters for a lighting node within the lighting infrastructure based on the composited lighting model and other factors, and generating a lighting control command for configuring the lighting node within the lighting infrastructure using the calculated lighting parameters.