Abstract: The present disclosure relates to methods and systems for providing inferences using machine learning systems. The methods and systems receive a load forecast for processing requests by a machine learning model and split the machine learning model into a plurality machine learning model portions based on the load forecast. The methods and systems determine a batch size for the requests for the machine learning model portions. The methods and systems use one or more available resources to execute the plurality of machine learning model portions to process the requests and generate inferences for the requests.

Abstract: Systems and methods are provided for merging models for use in an edge server under the multi-access edge computing environment. In particular, a model merger selects a layer of a model based on a level of memory consumption in the edge server and determines sharable layers based on common properties of the selected layer. The model merger generates a merged model by generating a single instantiation of a layer that corresponds to the sharable layers. A model trainer trains the merged model based on training data for the respective models to attain a level of accuracy of data analytics above a predetermined threshold. The disclosed technology further refreshes the merged model upon observing a level of data drift that exceeds a predetermined threshold. The refreshing of the merged model includes detaching and/or splitting consolidated sharable layers of sub-models in the merged model.

Abstract: Described is a technology by which driver safety technology such as collision detection is implemented via mobile device (e.g., smartphone) sensors and a cloud service that processes data received from vehicles associated with the devices. Trajectory-related data is received at the cloud service and used to predict collisions between vehicles and/or lane departures of vehicles. To operate the service in real-time with low latency, also described is dividing driving areas into grids, e.g., based upon traffic density, having parallel grid servers each responsible for only vehicles in or approaching its own grid, and other parallel/distributed mechanisms of the cloud service.

Abstract: Described is a technology by which driver safety technology such as collision detection is implemented via mobile device (e.g., smartphone) sensors and a cloud service that processes data received from vehicles associated with the devices. Trajectory-related data is received at the cloud service and used to predict collisions between vehicles and/or lane departures of vehicles. To operate the service in real-time with low latency, also described is dividing driving areas into grids, e.g., based upon traffic density, having parallel grid servers each responsible for only vehicles in or approaching its own grid, and other parallel/distributed mechanisms of the cloud service.

Abstract: Described is a technology by which driver safety technology such as collision detection is implemented via mobile device (e.g., smartphone) sensors and a cloud service that processes data received from vehicles associated with the devices. Trajectory-related data is received at the cloud service and used to predict collisions between vehicles and/or lane departures of vehicles. To operate the service in real-time with low latency, also described is dividing driving areas into grids, e.g., based upon traffic density, having parallel grid servers each responsible for only vehicles in or approaching its own grid, and other parallel/distributed mechanisms of the cloud service.

Abstract: A method is provided in one example embodiment and includes providing an Internet Protocol (IP) address based on an authentication request associated with a device, the authentication request being associated with a Wi-Fi protocol. The method also includes identifying a Wi-Fi event associated with the IP address, and mapping the Wi-Fi event to a WiMax event. Further, the method includes providing a WiMax message, which is based on the Wi-Fi event, to a network element. In other embodiments, the mapping further includes converting the Wi-Fi event to the WiMax message such that the WiMax message is presented to the network element in a WiMax format. The same IP address can be used for both the Wi-Fi event and the WiMax message.

Abstract: One or more techniques and/or systems are disclosed for predicting when a signal handoff may occur from a current base station to a neighboring base station for a mobile device. An indication of signal strength between the mobile device and the current base station and an indication of signal strength between the mobile device and a (e.g., closest) neighboring base station can be monitored by the mobile device. A difference between these signal strength indications can be determined and compared against a threshold (e.g., based upon historical signal handoffs) to predict when and/or where a signal handoff may occur. The predicted signal handoff may be determined by the mobile device and a corresponding notification can be provided so that appropriate action may be taken (e.g., a user may not initiate a call and/or an application may not attempt to communicate data).

Abstract: The simultaneous localization and RF modeling technique pertains to a method of providing simultaneous localization and radio frequency (RF) modeling. In one embodiment, the technique operates in a space with wireless local area network coverage (or other RF transmitters). Users carrying Wi-Fi-enabled devices traverse this space while the mobile devices record the Received Signal Strength (RSS) measurements corresponding to access points (APs) in view at various unknown locations and report these RSS measurements, as well as nay other available location fix to a localization server. A RF modeling algorithm runs on the server and is used to estimate the location of the APs using the recorded RSSI measurements and any other available location information. All of the observations are constrained by the physics of wireless propagation. The technique models these constraints and uses a genetic algorithm to solve them, thereby providing an absolute location of the mobile device.

Abstract: The simultaneous localization and RF modeling technique pertains to a method of providing simultaneous localization and radio frequency (RF) modeling. In one embodiment, the technique operates in a space with wireless local area network coverage (or other RF transmitters). Users carrying Wi-Fi-enabled devices traverse this space while the mobile devices record the Received Signal Strength (RSS) measurements corresponding to access points (APs) in view at various unknown locations and report these RSS measurements, as well as nay other available location fix to a localization server. A RF modeling algorithm runs on the server and is used to estimate the location of the APs using the recorded RSSI measurements and any other available location information. All of the observations are constrained by the physics of wireless propagation. The technique models these constraints and uses a genetic algorithm to solve them, thereby providing an absolute location of the mobile device.

Abstract: A method is provided in one example embodiment and includes providing an Internet Protocol (IP) address based on an authentication request associated with a device, the authentication request being associated with a Wi-Fi protocol. The method also includes identifying a Wi-Fi event associated with the IP address, and mapping the Wi-Fi event to a WiMax event. Further, the method includes providing a WiMax message, which is based on the Wi-Fi event, to a network element. In other embodiments, the mapping further includes converting the Wi-Fi event to the WiMax message such that the WiMax message is presented to the network element in a WiMax format. The same IP address can be used for both the Wi-Fi event and the WiMax message.