Current computer vision systems, especially those using machine learning techniques are data-hungry and frequently only perform well when dealing with patterns they have seen before. As an alternative, cognitive systems have become a focus of attention for applications that involve complex visual scenes, and in which conditions may vary. In theory, cognitive applications uses current machine learning algorithms, such as deep learning,...

Sformułowano problem sterowania jakością wody w sieciach wodociągowych i następnie zaproponowano podejście do projektowania sterowania stężeniem chloru w takich sieciach, bazujący na estymacji parametrów oraz sterowaniu adaptacyjnym. Podejście wykorzystuje założenie, że w sieci wodociągowej istnieją punkty wstrzykiwania chloru. Zależność typu wejście-wyjście pomiędzy stężeniem chloru w węźle dozowania i monitorowania jest modelowana...

The problem of active feedback control of a narrowband acoustic noise in the presence of impulsive disturbances is considered. It is shown that, when integrated with appropriately designed outlier detector, the proposed earlier feedback control algorithm called SONIC is capable of isolating and rejecting noise pulses. According to our tests this guarantees stable and reliable operation of the closed-loop noise cancelling...

A feedback controller is proposed for cancellation of magnetic resonance imaging (MRI) noise. The design of the controller takes into account specific features of the MRI noise signal. Simulation results show that a considerable rejection rate of the MRI noise can be obtained.

The problem of active control of narrowband acoustic noise is considered. It is shown that the proposed earlier feedback control algorithm called SONIC (self-optimizing narrowband interference canceller), based on minimization of the L2-norm performance measure, can be re-derived using the L1 approach. The resulting robust SONIC algorithm is more robust to heavy-tailed measurement noise, such as the αlpha-stable noise, than the...