Abstract: For reconstruction in medical imaging, such as reconstruction in MR imaging, a high-resolution image is reconstructed using a generator of a progressive generative adversarial network (PGAN or progressive GAN). In machine training the network, both the generator and discriminator of the GAN are grown progressively: starting from a low resolution, new layers are added that model finer details as training progresses. The resulting generator may be better able to handle high-resolution information than a generator of a GAN.

Abstract: For reconstruction in medical imaging, such as reconstruction in MR imaging, a high-resolution image is reconstructed using a generator of a progressive generative adversarial network (PGAN or progressive GAN). In machine training the network, both the generator and discriminator of the GAN are grown progressively: starting from a low resolution, new layers are added that model finer details as training progresses. The resulting generator may be better able to handle high-resolution information than a generator of a GAN.

Abstract: Ensuring the security of a data transmission by verifying an identity of a user, comprising: a prior step of enrolling a terminal of the user, comprising: an association of a authentic identity data item of the user and a data item of a terminal available to the user and communicating via a network, the association being stored with data for contacting the terminal via the network, and a determination of an identity derived from at least said information, stored in the memory of the terminal, in correspondence with a data item specific to the user, for the purposes of a later strong authentication based on both the data item specific to the user and on the derived identity, as well as a current step of verifying the user identity.

Abstract: Ensuring the security of a data transmission by verifying an identity of a user, comprising: a prior step of enrolling a terminal of the user, comprising: an association of a authentic identity data item of the user and a data item of a terminal available to the user and communicating via a network, the association being stored with data for contacting the terminal via the network, and a determination of an identity derived from at least said information, stored in the memory of the terminal, in correspondence with a data item specific to the user, for the purposes of a later strong authentication based on both the data item specific to the user and on the derived identity, as well as a current step of verifying the user identity.

Abstract: The invention relates to a method for detecting impacts on areas to be monitored on a running vehicle (2), created by objects projected due to its velocity, wherein vibration sensors (11a-11d) are arranged in direct contact with areas to be monitored on said running vehicle (2) and the signals from the vibration sensors (11a-11d) are analyzed to detect impacts. The invention also relates to an impact detection system on areas to be monitored on a running vehicle (2).