Abstract: Disclosed is a technique that can be performed by a server computer system. The technique can include obtaining data from each of multiple endpoint devices to form global data. The global data can be generated by the endpoint devices in accordance with local instructions in each of the endpoint devices. The technique further includes generating global instructions based on the global data and sending the global instructions to a particular endpoint device. The global instructions configure the particular endpoint device to perform a data analytic operation that analyzes events. The events can include raw data generated by a sensor of the particular endpoint device.

Abstract: Disclosed is a technique that can be performed by an electronic device. The electronic device can generate time-stamped events, extract training data from the time-stamped events, and send the training data over a network to a remote computer. The electronic device can receive model data generated by the remote computer from the training data by use of a machine learning process, update a local model of the electronic device based on the received model data, and generate an output by processing locally sourced data of the electronic device with the updated local model.

Abstract: An example method of updating a client dashboarding component of an asset monitoring and reporting system comprises: identifying an update of a client dashboarding component of an asset monitoring and reporting system (AMRS), the client dashboarding component comprising one or more dynamic elements, each dynamic element associated with an asset node; receiving one or more search queries, each search query corresponding to a dynamic element of the one or more dynamic elements; modifying one or more dynamic elements of the client dashboarding component in accordance with the one or more search queries; and updating the client dashboarding component to reflect metric values associated with the modified dynamic elements.

Abstract: Disclosed is a technique that can be performed by a server computer system. The technique can include executing a machine learning process to generate a machine learning model based on global data collected from one or more electronic devices, wherein the machine learning model is described by model data. The technique can further include encapsulating the model data in a markup language document. The technique can further include sending, over a network, the markup language document to at least one electronic device of the one or more electronic devices to cause the at least one electronic device to update a local device machine learning model.

Abstract: An asset monitoring and reporting system (AMRS) implements decoupled update cycle and disparate search frequency dispatch for dynamic elements of an asset monitoring and reporting system. The AMRS identifies occurrence of an update to a visualization of a client dashboarding component of an AMRS, the visualization comprising dynamic elements and corresponding dynamic element searches that are each associated with a search query to be submitted for execution to obtain a value of a metric of an asset node associated with a respective dynamic element. The AMRS further sends a request indicative of the dynamic elements to a server component of the AMRS, receives dynamic element objects for the dynamic elements, the dynamic element objects specifying search queries corresponding to the dynamic elements, modifies dynamic element searches of the dashboarding component in accordance with the search queries, and stores a definition of the visualization as control information.

Abstract: Disclosed is a technique that can be performed by a server computer system. The technique can include executing a machine learning process to generate a machine learning model based on global data collected from one or more electronic devices, wherein the machine learning model is described by model data. The technique can further include encapsulating the model data in a markup language document. The technique can further include sending, over a network, the markup language document to at least one electronic device of the one or more electronic devices to cause the at least one electronic device to update a local device machine learning model.

Abstract: Disclosed is a technique that can be performed by an electronic device. The electronic device can generate time-stamped events, extract training data from the time-stamped events, and sending the training data over a network to a remote computer. The electronic device can receive model data generated by the remote computer from the training data by use of a machine learning process, update a local model of the electronic device based on the received model data, and generate an output by processing locally sourced data of the electronic device with the updated local model.

Abstract: Apparatuses and methods are disclosed that may allow a wireless device to dynamically select a bandwidth for MU-MIMO communications. A wireless device may transmit, on each of a plurality of wireless channels, a clear-to-send-to-self (CTS2S) frame that reserves medium access on a number of wireless channels and/or confirms the continued availability of the wireless channels. The bandwidth for a subsequent sounding operation may be based on the bandwidth used to transmit the CTS2S frames. Thereafter, the wireless device may transmit one or more MU-MIMO data frames to a number of other wireless devices using the selected bandwidth.

Abstract: Disclosed is a technique that can be performed by a server computer system. The technique can include executing a machine learning process to generate a machine learning model based on global data collected from one or more electronic devices, wherein the machine learning model is described by model data. The technique can further include encapsulating the model data in a markup language document. The technique can further include sending, over a network, the markup language document to at least one electronic device of the one or more electronic devices to cause the at least one electronic device to update a local device machine learning model.

Abstract: Apparatuses and methods are disclosed that may allow a wireless device to dynamically select a bandwidth for MU-MIMO communications. A wireless device may transmit, on each of a plurality of wireless channels, a clear-to-send-to-self (CTS2S) frame that reserves medium access on a number of wireless channels and/or confirms the continued availability of the wireless channels. The bandwidth for a subsequent sounding operation may be based on the bandwidth used to transmit the CTS2S frames. Thereafter, the wireless device may transmit one or more MU-MIMO data frames to a number of other wireless devices using the selected bandwidth.

Abstract: Methods, systems, and devices are described for adapting blind reception duration for range and congestion. A wireless station may measure channel conditions (e.g., range to an access point (AP) and channel congestion), and adjust one or more sleep timers based on the conditions. The sleep timers may each be associated with a window for reception of an expected transmission. If the transmission is not received in the window, the station may enter a sleep state to conserve power. In one example, a beacon miss timer is adjusted, and the expected wireless transmission is a delivery traffic indication message (DTIM). In another example, a content after beacon (CAB) timer is adjusted and the expected wireless transmission is the CAB. In some cases, the station may measure a delay for a number of beacons and determine the adjustment based on the delays.

Abstract: Methods, systems, and devices are described for adapting blind reception duration for range and congestion. A wireless station may measure channel conditions (e.g., range to an access point (AP) and channel congestion), and adjust one or more sleep timers based on the conditions. The sleep timers may each be associated with a window for reception of an expected transmission. If the transmission is not received in the window, the station may enter a sleep state to conserve power. In one example, a beacon miss timer is adjusted, and the expected wireless transmission is a delivery traffic indication message (DTIM). In another example, a content after beacon (CAB) timer is adjusted and the expected wireless transmission is the CAB. In some cases, the station may measure a delay for a number of beacons and determine the adjustment based on the delays.

Abstract: Power saving for wireless communication devices by adjusting the amount of time, after a last transmission/reception of data, that the device remains in an awake mode listening for more data before the device enters a sleep mode. This time period may be referred to as inactivity time interval or inactivity timeout (ITO). The described features may be employed to improve power savings by taking metrics of channel congestion into account for determining the ITO. The appropriate ITO may be determined to be commensurate with ongoing transmission and/or reception activity. Because error may occur in estimating channel congestion and/or transmission/reception activity, latency bounds based on estimation errors may be managed by classifying the operational mode into multiple regions and employing techniques for mitigating error in congestion estimation based at least in part on the operational mode.

Abstract: Power saving for wireless communication devices by adjusting the amount of time, after a last transmission/reception of data, that the device remains in an awake mode listening for more data before the device enters a sleep mode. This time period may be referred to as inactivity time interval or inactivity timeout (ITO). The described features may be employed to improve power savings by taking metrics of channel congestion into account for determining the ITO. The appropriate ITO may be determined to be commensurate with ongoing transmission and/or reception activity. Because error may occur in estimating channel congestion and/or transmission/reception activity, latency bounds based on estimation errors may be managed by classifying the operational mode into multiple regions and employing techniques for mitigating error in congestion estimation based at least in part on the operational mode.