Abstract: Methods and apparatuses for implementing customized anomaly detection. A time-series data including a plurality of data points is obtained. Anomaly detection is performed to the time-series data with an anomaly detection model. A feedback associated with an anomaly detection result of at least one data point in the time-series data is received. The anomaly detection model is updated based at least on the feedback through reinforcement learning.

Abstract: A server, user terminal, system, method and computer-program product for performing a data transfer to upload a data file from the user terminal to the server or download a data file from the server to the user terminal, via a connection over a network. The method comprises evaluating a size of the data file to be uploaded or downloaded, determining a measure of a current workload of the server, and estimating a bandwidth of at least part of the connection. A time-out window is derived during which the transfer of the data file is allowed to be performed, wherein the deriving of the time out window is performed based the data file size, server workload and bandwidth. The data transfer is enabled during the time-out window, but timed out when the time-out window expires.