Abstract: In one embodiment, the method includes obtaining a plurality of sensor data items, each specifying a set of values determined from at least one sensor; and training, based on the plurality of sensor data items, a machine learning model including a data adaptation part configured for determining a modified sensor data item based on an input sensor data item, an encoder configured for determining encoded features based on the modified sensor data item, a decoder configured for determining a decoded sensor data item based on the encoded features, representing an estimation of the input sensor data item, and a classifier configured for determining a class associated with the input sensor data item. The training the machine learning model includes updating parameters of the data adaptation part based on the input sensor data item and the corresponding decoded sensor data item, while maintaining the encoder, the decoder and the classifier frozen.

Abstract: In one embodiment, the method includes obtaining a plurality of sensor data items, each specifying a set of values determined from at least one sensor; and training, based on the plurality of sensor data items, a machine learning model configured for classifying sensor data items. The machine learning model includes a data adaptation part configured for determining a modified sensor data item based on an input sensor data item, an encoder configured for determining encoded features based on the modified sensor data item, a decoder configured for determining a decoded sensor data item based on the encoded features, representing an estimation of the input sensor data item, and a classifier configured for determining a class associated with the input sensor data item.

Abstract: A method in a telecommunications network, the network including at least one service area, the method comprising: at the network, distributing a mobile edge computing server within a corresponding one of the service areas; at the mobile edge computing server, distributing at least one access point within the corresponding service area; and at the mobile edge computing server, determining a mobile edge computing area within the corresponding service area; wherein at least one of the access points is located within a corresponding one of the mobile edge computing areas.

Abstract: In one embodiment, the method includes obtaining a plurality of sensor data items, each specifying a set of values determined from at least one sensor; and training, based on the plurality of sensor data items, a machine learning model configured for classifying sensor data items. The machine learning model includes a data adaptation part configured for determining a modified sensor data item based on an input sensor data item, an encoder configured for determining encoded features based on the modified sensor data item, a decoder configured for determining a decoded sensor data item based on the encoded features, representing an estimation of the input sensor data item, and a classifier configured for determining a class associated with the input sensor data item.

Abstract: A method in a telecommunications network, the network including at least one service area, the method comprising: at the network, distributing a mobile edge computing server within a corresponding one of the service areas; at the mobile edge computing server, distributing at least one access point within the corresponding service area; and at the mobile edge computing server, determining a mobile edge computing area within the corresponding service area; wherein at least one of the access points is located within a corresponding one of the mobile edge computing areas.