Search

In this paper, we present our novel approach to recommender systems based on a neuro-fuzzy approach. The neuro-fuzzy approach allows for deciding to recommend or not to recommend processed items for a user. By using it, we can understand the decision through analyzing rules of decision paths. Our method gives a possibility to learn and simulate users decisions based on their actions in our test environment. Finally, a rank list of top-rated items is delivered to the user based on simulated rank for each of them. We develop our AI framework to perform tests with the use of CUDA technology. Additionally, we develop a user interface in the form of a web application. It gives the possibility to perform simulations of real users. To compare our approach with a deep learning based method, we perform tests on the MovieLens 20M Dataset. It should be noted that the architecture of the data module of our system allowed for reasonably easy integration with MovieLens data.

In this paper radar technology developments in C band at PIT-RADWAR S.A. are presented. Research and development activities performed between 1990 and 2014 are briefly discussed and resulting technologies are presented and described.

Urban areas constitute complex environments for radars. This paper deals with the problem of radar track formation for flying targets in low-level airspace over urban environment, particularly for artillery rockets and mortars. The presented experiments address the problem of sensitivity of two track formation algorithms, based on multisensor versions of the multiple hypothesis tracking approach (MHT) and the Hough transform, to radar performance degradation caused by urban environment. Simulation result show superiority of the MHT track initiator for virtually all performed tests. Moreover, multisensor detection can significantly reduce number of false alarms at the expense of only slight delay of track detection.

The paper presents the new software library supporting development of the fault-robust applications. The main goals of the proposed software hardening mechanisms are: usage simplicity for the programmer, independence from the development tool, effectiveness in terms of fault coverage, low static and dynamic overheads. The paper describes implemented software mechanisms and discusses their effectiveness verified with fault injection experiments.

In this paper a problem of detection of tactical ballistic missiles (TBM) by a network of long-range air-defence radars (ADR) is addressed. Multi-radar detection capacity of TBM is evaluated using modelling and simulation techniques. The outcome of the study is shown in the form of the estimates of the signal-to-noise ratio (SNR), as would be observed at the outputs of the matched filters of the radars.

The present paper describes a microstrip patch antenna array to be used in the mobile terminal of a mobile communication system at 2 GHz. The array can be used in two frequency sub-bands has an almost omnidirectional radiation pattern and provides a vertical plane shaped beam.