Abstract: A computing system configured to execute a predictive program is provided. The predictive program, in a run-time phase, receives a current value for a remotely sourced forecast as run-time input into an artificial intelligence model. The artificial intelligence model has been trained on training data including a time series of locally sourced measurements for a parameter and a time series of remotely sourced forecast data for the parameter. The predictive program outputs a predicted forecast offset between the current value of a remotely sourced forecast and a future locally sourced measurement for the parameter. The predictive program outputs from the artificial intelligence model a predicted forecast offset based on the run-time input.

Abstract: An imaging system that includes a camera mounted on an aerial platform, for example a balloon, allows a user to increase the longevity of the camera's battery by remote control. A user may capture imagery at a time scale of interest and desired power consumption by adjusting parameters for image capture by the camera. A user may adjust a time to capture an image, a time to capture a video, or a number of cycles per time period to capture one or more images as the aerial platform moves in a region of interest to change power consumption for imaging. The system also provides imaging alignment to account for unwanted movement of the aerial platform when moved in the region of interest. Additionally, a mounting device is provided that is simple and inexpensive, and that allows a camera to remain positioned in a desired position relative to the ground.

Abstract: The disclosure herein describes transmitting data from a satellite using a primary ground station and a set of secondary ground stations. An orbit of the satellite is determined over a schedule period and a subset of secondary ground stations is identified based on the determined orbit of the satellite, wherein secondary ground stations are configured to receive from the satellite and not transmit to the satellite. A transmission schedule associated with the satellite is then generated. For each secondary ground station of the subset, a time interval during which the satellite is within communication range is determined, an expected transmission rate is estimated, and the time interval and the expected transmission rate are included in the transmission schedule. The transmission schedule is provided to the satellite via the primary ground station, whereby the satellite is configured to transmit data to the subset of ground stations based on the transmission schedule.

Abstract: Solutions for performing on-platform analytics for collected images include: enriching, on-board an orbital platform, collected images using a packaged analytics component; based at least on content of the collected images, selecting a set of the collected images to transmit to a ground station; and transmitting the selected set of the collected images to the ground station. Other solutions include: packaging an analytics component for on-platform execution by a platform in orbit; transmitting, from a ground station to the platform, at least one update selected from the list consisting of: an analytics algorithm update, a machine learning (ML) model, and ML training data; and executing the analytics component with the update. Other solutions include: performing intelligent compression on collected images, wherein the intelligent compression process determines data to transmit to a ground station, based at least on content of the collected images; and transmitting the data to the ground station.

Abstract: The minimization of the amount of power consumed by an electronic device in acquiring or maintaining network connectivity with a network may extend the battery life of the electronic device. When the electronic device has established a communication connection with a wireless access point, the electronic device cycles a network interface controller of the electronic device between a power on state and a power off state without terminating the communication connection. Accordingly, the electronic device powers on a main processor of the electronic device when the network interface controller detects a beacon during the power on state that indicates the wireless access point has a buffered data frame for the electronic device.

Abstract: Examples disclosed herein are related to using a machine learning model to generate image data. One example provides a system, comprising one or more processors, and storage comprising instructions executable by the one or more processors to obtain image data comprising an image with unoccluded features, apply a mask to the unoccluded features in the image to form partial observation training data comprising a masked region that obscures at least a portion of the unoccluded features, and train a machine learning model comprising a generator and a discriminator at least in part by generating image data for the masked region and comparing the image data generated for the masked region to the image with unoccluded features.

Abstract: A computing device is provided, including a logic subsystem with one or more processors, and memory storing instructions executable by the logic subsystem. These instructions are executed to obtain one or more source images, segment the one or more source images to generate a plurality of segments, determine a priority order for the plurality of segments, and transmit the plurality of segments to a remote computing device in the priority order. The plurality of segments are spatial components generated by spatial decomposition of the one or more source images and/or frequency components that are generated by frequency decomposition of the one or more source images. A remote computing device may receive these components in priority order, and perform certain algorithms on individual components without waiting for the entire image to upload.

Abstract: A secure wireless IoT platform configured to provide secure channel hopping for transmitting or receiving messages over a television whitespace spectrum. The platform includes a client device and a base station in communication with a gateway device which provides internet access. A secret key is determined based on the transmission loss associated with the transmission and potentially a new parameter. A next hopping channel is determined in a safe manner to ensure secure communications between the multiple devices.

Abstract: A method can include receiving sensor data from at least three different types of sensor situated in the geographic area, the types of sensors including an air temperature sensor, relative humidity sensor, dewpoint sensor, soil moisture sensor, soil temperature sensor, average wind speed sensor, maximum wind speed sensor, and a rainfall sensor, producing a feature vector including a time series of values corresponding to the received sensor data, and using a neural network, estimating the physical characteristics, the physical characteristics including at least one of (a) a leaf wetness, (b) a solar radiation, (c) an evapotranspiration, (d) a future soil moisture, and (e) a future soil temperature.

Abstract: Systems, methods, and computer-executable instructions for scheduling neural network workloads on an edge device. A performance model for each neural network model is received. Parameters for each neural network workload is determined based on an associated performance model. Processing core assignments are determined from a plurality of processing cores for each neural network workload based on the corresponding performance model and processing core utilization. Image streams are received and associated with a neural network workload. Each neural network workload is scheduled to run on the processing cores based on the processing core assignments.

Abstract: Techniques for dynamically changing internal state of a battery are described herein. Generally, different battery configurations are described that enable transitions between different battery power states, such as to accommodate different battery charge and/or discharge scenarios.

Abstract: Various methods and systems for implementing resource management for an infrastructure are provided. Resource management includes datacenter byproduct management interfaces, datacenter power management, datacenter operations optimization and infrastructure resource management. Resource management facilitates using and distributing physical resources, including incidental physical resources that are generated during operation of an infrastructure, based on a threshold reserve of the physical resource associated with the operating the infrastructure. Resource management can include controlling an amount of the physical resource that is generated and an amount the physical resource that is reserved. The threshold reserve in combination with the control over generating and reserving the physical resource help identify an allocable amount of the physical resource. Physical resources of an infrastructure are quantified to support resource management.

Abstract: Techniques for dynamically changing internal state of a battery are described herein. Generally, different battery configurations are described that enable transitions between different battery power states, such as to accommodate different battery charge and/or discharge scenarios.

Abstract: Techniques for ability enhancement are described. In some embodiments, devices and systems located in a transportation network share threat information with one another, in order to enhance a user's ability to operate or function in a transportation-related context. In one embodiment, a process in a vehicle receives threat information from a remote device, the threat information based on information about objects or conditions proximate to the remote device. The process then determines that the threat information is relevant to the safe operation of the vehicle. Then, the process modifies operation of the vehicle based on the threat information, such as by presenting a message to the operator of the vehicle and/or controlling the vehicle itself.

Abstract: Solutions for performing on-platform analytics for collected images include: enriching, on-board an orbital platform, collected images using a packaged analytics component; based at least on content of the collected images, selecting a set of the collected images to transmit to a ground station; and transmitting the selected set of the collected images to the ground station. Other solutions include: packaging an analytics component for on-platform execution by a platform in orbit; transmitting, from a ground station to the platform, at least one update selected from the list consisting of: an analytics algorithm update, a machine learning (ML) model, and ML training data; and executing the analytics component with the update. Other solutions include: performing intelligent compression on collected images, wherein the intelligent compression process determines data to transmit to a ground station, based at least on content of the collected images; and transmitting the data to the ground station.

Abstract: Solutions for performing on-platform analytics for collected images include: enriching, on-board an orbital platform, collected images using a packaged analytics component; based at least on content of the collected images, selecting a set of the collected images to transmit to a ground station; and transmitting the selected set of the collected images to the ground station. Other solutions include: packaging an analytics component for on-platform execution by a platform in orbit; transmitting, from a ground station to the platform, at least one update selected from the list consisting of: an analytics algorithm update, a machine learning (ML) model, and ML training data; and executing the analytics component with the update. Other solutions include: performing intelligent compression on collected images, wherein the intelligent compression process determines data to transmit to a ground station, based at least on content of the collected images; and transmitting the data to the ground station.

Abstract: A base station utilizes duty cycle requirements of each of multiple base station components to efficiently consume power. The base station may include a synchronization module that allows the base station to send collected data from a cache to a gateway, which then, sends it up to the cloud. The base station may also include a sensor connectivity module that establishes a connection between the base station and data collecting devices deployed to collect data for storage in the cache. A base station controller serves as the cache for the data collected by the sensor module and sends the data to the gateway for synchronization in the cloud using the synchronization module. A base station controller determines/coordinates the duty cycle of the sensor connectivity module and synchronization module in a power efficient way depending on the current power available to the base station, network needs, and the weather conditions.

Abstract: A soil measurement system is provided, comprising a soil surveying device, a radio receiver, a plurality of subterranean antennas, and a processor. The soil surveying device comprises a wireless radio transmitter configured to emit a wireless signal at a predetermined bandwidth in a predetermined spectrum. The plurality of subterranean antennas are in an array electronically connected to the radio receiver and configured to be mounted in a subterranean environment at different depths in the subterranean environment. Each of the plurality of subterranean antennas is configured to receive the wireless signal at a respective point in time. The processor is configured to determine a relative time of flight of the received wireless signal between the plurality of antennas at the respective point in time, and estimate a soil permittivity based on the determined relative time of flight. The measurement system may be applied to materials other than soil, in some examples.

Abstract: In embodiments of battery-backed RAM for wearable devices, a mobile device, such as a mobile phone, tablet computer, or other portable device is implemented for wireless connection with a wearable device, such as a smartwatch, exercise tracking device, glasses device, or other wearable device that implements computing technology. The wearable device can store data in battery-backed RAM in the wearable device, and the mobile device can back-up the data with battery-backed RAM in the mobile device when the data is received from the wearable device. A wireless connection can be established for wireless data communication between the wearable device and the mobile device. A data manager can detect a low battery condition of the wearable device, which initiates the data being transferred from the wearable device to the mobile device via the wireless connection.

Abstract: A method can include generating a feature vector based on image data and soil data, the image data of an image of the geographical region produced by an aerial vehicle, the image data representative of an attribute of the attributes of the soil or foliage, and the soil data indicating physical characteristics of soil of cells within the geographical region, producing a matrix including entries indicating how similar the cells are in terms of the image data and the soil data based on the feature vector, and producing based on the matrix, data indicating a cluster of clusters to which each cell of the cells belongs, each cell more similar to other cells of the cluster to which they belong than cells of other clusters, each cluster indicating a location at which to situate a sensor of the sensors to monitor the attribute.