• Machine learning is used to effectively detect anomalies in nuclear power plants. Deep neural networks are trained using simulated data the frequency domain. Training generated by CORE SIM+ neutronic modelling tool. Domain adaptation methods align and real plant data. Unsupervised self-supervised anomalies’ types locations. Learning this paper for noise-diagnostics defined reactor cores solel...

Inversion of electromagnetic data finds applications in many areas geophysics. The inverse problem is commonly solved with either deterministic optimization methods (such as the nonlinear conjugate gradient or Gauss-Newton) which are prone to getting trapped a local minimum, probabilistic very computationally demanding. A recently emerging alternative employ deep neural networks for predicting ...

This study introduces a challenge faced by CNN in the task of traffic sign detection: how to achieve robustness distributional shift. At present, all kinds models rely on strong data augmentation methods enrich samples and robustness, such as Mosaic Mixup. In this study, we note that these do not have similar effects combating noise. We explore performance strategies against disturbance differe...

In this paper we propose a new space diversity scheme for broadband PLC systems using orthogonal space-time block coding (OSTBC) transmission combined with single-carrier frequency-domain equalization (SC-FDE). To apply this diversity technique to PLC channels, we first propose a new technique for combining SC-FDE with OSTBCs applicable to all dispersive multipath channels impaired by impulsive...