Abstract: A system comprising a ground-based station comprising a first data store, where the first data store stores operational characteristics of a space-based station, where the space-based station comprises a second data store that mirrors the first data store at a first time. The ground-based station is configured to generate first log data based on a determined type of activity performed by the user at a second time. The system further comprises a user device located on the space-based station and configured to determine a second type of activity performed by the user at the space-based station at the second time; generate second log data based on the determined second type of activity performed by the user; process a synchronization request received from the ground-based station; identify a conflict between the first and second data logs; and in response to identifying the conflict, select one of the data logs are accurate.

Abstract: This invention comprises a system for tracking users' position along a multitude of routes. One or more sensors placed along a known route are activated by a user, further transmitting user and/or sensor identification information to a server. As a user proceeds along the route, they activate subsequent sensors, allowing a server to track the user's position and perform other useful calculations. The system optionally includes relay sensors, which aid in wireless sensor-to-server communications over longer distances. Numerous other embodiments are provided capable of monitoring different types of routes in various circumstances.

Abstract: Embodiments are directed towards classifying data using machine learning that may be incrementally refined based on expert input. Data provided to a deep learning model that may be trained based on a plurality of classifiers and sets of training data and/or testing data. If the number of classification errors exceeds a defined threshold classifiers may be modified based on data corresponding to observed classification errors. A fast learning model may be trained based on the modified classifiers, the data, and the data corresponding to the observed classification errors. And, another confidence value may be generated and associated with the classification of the data by the fast learning model. Report information may be generated based on a comparison result of the confidence value associated with the fast learning model and the confidence value associated with the deep learning model.

Abstract: Embodiments are directed towards classifying data using machine learning that may be incrementally refined based on expert input. Data provided to a deep learning model that may be trained based on a plurality of classifiers and sets of training data and/or testing data. If the number of classification errors exceeds a defined threshold classifiers may be modified based on data corresponding to observed classification errors. A fast learning model may be trained based on the modified classifiers, the data, and the data corresponding to the observed classification errors. And, another confidence value may be generated and associated with the classification of the data by the fast learning model. Report information may be generated based on a comparison result of the confidence value associated with the fast learning model and the confidence value associated with the deep learning model.