Matrix factorization has proven to be one of the most accurate recommendation approaches. However, it faces one major shortcoming: the latent features that result from the factorization are not directly interpretable. Providing interpretation for these features is important not only to help explain the recommendations presented to users, but also to understand the underlying relations between the users and the items. This paper consists of 2 contributions. First, we propose to automatically interpret features as users, referred to as representative users. This interpretation relies on the study of the matrices that result from the factorization and on their link with the original rating matrix. Such an interpretation is not only performed automatically, as it does not require any human expertise, but it also helps to explain the recommendations. The second proposition of this paper is to exploit this interpretation to alleviate the content-less new item cold-start problem. The experiments conducted on several benchmark datasets confirm that the features discovered by a NonNegative Matrix Factorization can be interpreted as users and that representative users are a reliable source of information that allows to accurately estimate ratings on new items. They are thus a promising way to solve the new item cold-start problem.
Background. Numerical simulation and experimental research have been used as powerful tools to understand and predict the behavior and mechanics of the operation of natural heart valves and their prostheses in natural and pathological conditions. Such studies help to evaluate the effectiveness of the valves, their design and the results of surgical procedures, to diagnose healthy and impaired function of the heart valves. There is an actual problem in creating more reliable methods and tools for the operation diagnostics of mechanical heart valves. Objective. The aim of the research is to investigate the effect of fluid viscosity on the hydroacoustic characteristics of jets that flow from a semi-closed and open mechanical bileaflet heart valve. To study the possibility of using hydroacoustic measuring instruments as diagnostic equipment for determining the working conditions of the bileaflet prosthetic heart valve. Methods. The experimental research was carried out by means of hydroacoustic measurements of the hydrodynamic noise in the near wake of the side and central jets of the glycerin solution and the pure water flow downstream of the prosthetic bileaflet heart valve. Results. The effect of fluid viscosity on the hydroacoustic characteristics of the jets that flow from a semi-closed and open mechanical bileaflet heart valve has been experimentally determined. Integral and spectral characteristics of the hydrodynamic noise of jets of the glycerin solution and the pure water flow downstream of the bileaflet mitral heart valve for different fluid rate were detected. Conclusions. In the stream conditions of pure water, the integral characteristics of the pressure field are lower than in stream conditions of the aqueous glycerin solution. As the glycerin concentration in the solution increases, increase average pressures and especially RMS pressure fluctuations. The spectral levels of the hydrodynamic noise in the near wake of the side jet of the glycerin solution are lower than for water flow in the frequency ranges from 1 to 7-8 Hz and from 100 to 1000 Hz for fluid rate 5 l/min. For higher fluid rates, the spectral components of the hydrodynamic noise in the near wake of the side jet of the glycerin solution of the semi-closed mitral valve are higher than that for the pure water. The greatest difference (1.5-1.8 times) in the spectral levels is observed in the frequency range from 10 to 100 Hz for the fluid rate 15 l/min.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.