Due to the factors that affect the results of work on a daily basis, higher education institutions, through their quality assurance systems, or their planning, must assess risks. In doing so, they must take into account all issues of the internal and external context as well as the needs and expectations of all stakeholders in higher education. The paper explains in an appropriate way the concept of risk as well as all the elements that determine it and their classification in the field of higher education. Subsequently, a possible approach to risk management is discussed, with an emphasis on clarifying the principles and the risk management process itself. Finally, the basics of practical application in risk identification, analysis, evaluation and treatment are outlined.

The advancement of technology in the field of artificial intelligence and neural networks allows us to improve speed and efficiency in the diagnosis of various types of problems. In the last few years, the rise in the field of convolutional neural networks has been particularly noticeable, showing promising results in problems related to image processing and computer vision. Given that humans have limited ability to detect patterns in individual images, accurate diagnosis can be a problem for even medical professionals. In order to minimize the number of errors and unintended consequences, computer programs based on neural networks and deep learning principles are increasingly used as assistant tools in medicine. The aim of this study was to develop a model of an intelligent system that receives x-ray image of the lungs as an input parameter and, based on the processed image, returns the possibility of pneumonia as an output. The implementation of this functionality was implemented through transfer learning methodology based on already defined convolution neural network architectures.

No abstract

SAŽETAK: S obzirom na obveze poslodavca koje proizlaze iz Zakona o zaštiti na radu, a s ciljem unapređenja sigurnosti i zaštite zdravlja radnika, u ovome radu prezentirani su rezultati na osnovi reguliranog postupka ispitivanja radnog okoliša administrativnih radnih mjesta i mogućnost primjene umjetne inteligencije s metodom neizrazite (fuzzy) logike. U radu su odabrana dva fizikalna čimbenika ispitivanja radnog okoliša, električno osvjetljenje i brzina strujanja zraka, na kojima se prezentira cijeli postupak obrade prikupljenih rezultata ispitivanja kroz neizrazitu logiku. Mogućnosti metode neizrazite logike koja se koristi u ovome radu nalazi primjenu kod ispitivanja radnog okoliša, kako po pojedinim radnim mjestima tako i za kompletnu tvrtku. Na taj način prikupljeni i obrađeni rezultati ispitivanja radnog okoliša pomažu u određivanju tendencije rezultata i mogu poslužiti kao orijentacija i pomoć u izradi plana mjera za smanjenje rizika i poboljšanje sustava zaštite zdravlja i sigurnosti na radu u pojedinom poslovnom sustavu.