CUSTOMER
AT & T
We are supporting an experimental trial of a new wireless access technology based on 4G/LTE which brought us to integrate NM2Suite into the SmarTIE platform. Thanks to the deployment of our platform the traffic of 100 customers will be monitored and classified, while active measurements will be periodically performed to assess the real performance perceived by the users.
CUSTOMER
European Space Agency
We conducted an experimental study to determine the most efficient combination of transport- and application-layer protocols to use for transferring experimental data from globally distributed Ground Stations to ESOC via Internet. Our results will help in designing how to efficiently transfer large volumes of experimental data expected from future space missions starting from Euclid, which will begin in 2020.
CUSTOMER
European Space Agency
We conducted an experimental study to determine the most efficient combination of transport- and application-layer protocols to use for transferring experimental data from globally distributed Ground Stations to ESOC via Internet. Our results will help in designing how to efficiently transfer large volumes of experimental data expected from future space missions starting from Euclid, which will begin in 2020.
CUSTOMER
Eutelsat
Starting from late 2016 Eutelsat is using our DITGBox product to evaluate and to demonstrate the performance of KA-SAT satellite access networks. We continuously support them to let the product satisfy the specific requirements of their network scenarios and to make their demonstrations more effective.
CUSTOMER
Huawei
Starting from late 2016 we are conducting a research project focused on the classification of mobile and encrypted traffic. The project has two main objectives: (1) finding an efficient way to automate the generation of realistic annotated traffic traces (ground truth) from mobile apps; (2) designing novel approaches to classify in real time mobile apps traffic with high accuracy in real world scenarios (thousands of existing apps, frequent version updates, new apps released every day). The project is heavily focused on machine learning approaches for classification (supervised, semi-supervised, and non-supervised) and combination (hard and soft combiners), including those resulted very effective in other application domains (e.g., Deep Learning, Extreme Learning Machines).
CUSTOMER
Huawei
Starting from late 2016 we are conducting a research project focused on the classification of mobile and encrypted traffic. The project has two main objectives: (1) finding an efficient way to automate the generation of realistic annotated traffic traces (ground truth) from mobile apps; (2) designing novel approaches to classify in real time mobile apps traffic with high accuracy in real world scenarios (thousands of existing apps, frequent version updates, new apps released every day). The project is heavily focused on machine learning approaches for classification (supervised, semi-supervised, and non-supervised) and combination (hard and soft combiners), including those resulted very effective in other application domains (e.g., Deep Learning, Extreme Learning Machines).
