"Scientific research" Almanac

More titles

• 

  INFORMATION SECURITY OF HOSPITALS IN BULGARIA

  The relevance of this study is determined by the increasing requirements of and threats to the information security of healthcare facilities. The aim of the study is to investigate the state of information security of hospitals in Bulgaria and to define the concept of the model for information security. The following tasks are solved: studying the ... The relevance of this study is determined by the increasing requirements of and threats to the information security of healthcare facilities. The aim of the study is to investigate the state of information security of hospitals in Bulgaria and to define the concept of the model for information security. The following tasks are solved: studying the state of information security of hospitals in Bulgaria and opportunities for improvements; highlighting the good practices; analysing the capability of new technologies. On this basis, a concept for an information security model is developed, taking into account the features of Bulgarian hospitals. The research thesis, which is defended, is that threats and information security requirements have been steadily increasing. This requires precautionary measures and a high level of security and protection of data and services, as well as business continuity and is particular important to hospitals that collect, store and process personal data and health data of their patients. The information security level can be increased by applying an information security model. The studies have analysed the state of information security of medical establishments in Bulgaria and defined a concept for an information security model based on: good practices; following the recommendations for technical implementation required by the GDPR; accounting for the principle of protection levels.

• 

  CHARACTERISTICS OF FRAUD AND PERPETRATORS OF FRAUD

  The development of economic processes and activities raises the need for adequate knowledge and skills related to fraud detection. The relevance of the study is related to the continuous change and development of the means and approaches used by the control bodies, the emerging phenomena and processes requiring innovative thinking and the ... The development of economic processes and activities raises the need for adequate knowledge and skills related to fraud detection. The relevance of the study is related to the continuous change and development of the means and approaches used by the control bodies, the emerging phenomena and processes requiring innovative thinking and the developing technologies and software tools for financial fraud. The purpose of the research study is to identify the inherent characteristics of financial fraud and their perpetrators by analysing the regulations governing its manifestations and systematizing the types of financial fraud. The goal is achieved by performing the following tasks: defining the concept of "fraud"; outlining the main features of financial fraud; analysis of the legal framework; systematizing the types of financial fraud by certain indicators; examining the profile of the perpetrator of financial fraud. The thesis being defended is that financial fraud is a dynamic and complex phenomenon that requires adequate measures by the control and judicial authorities, taking into account the changes in the profile of the perpetrators and the methods of committing misconduct. As a result of the study, the legal regulation of financial fraud was systematized, criteria for their differentiation were drawn up and the characteristics and profile of the perpetrators of financial fraud were drawn up.

• 

  DEEP NEURAL NETWORKS FOR DETECTION OF CREDIT CARD FRAUD

  This publication presents research on the possibility of using Deep Neural Net-works (DNNs) for detection of credit card fraud. The research is based on an open da-taset and aims to determine how the varying number of hidden layers and other archi-tectural parameters (width of each layer, activation functions) affects training and predictive ... This publication presents research on the possibility of using Deep Neural Net-works (DNNs) for detection of credit card fraud. The research is based on an open da-taset and aims to determine how the varying number of hidden layers and other archi-tectural parameters (width of each layer, activation functions) affects training and predictive potential of the network. It also aims to determine how to use generative-adversarial approach efficiently in order to overcome the problem with the imbalance between legitimate and fraudulent transactions, which is crucial characteristic of the datasets related to detection of credit card fraud. The publication presents the results of various experiments, conducted to achieve the stated goals. A number of experiments have been carried out combining network training of various depth of the network and with different parameters of the learning process, for example, activation function and dropout values. The experiments focus on using generative-adversarial approach as a method for oversampling, in par-ticular. The results indicate that deep neural networks with moderate hidden layers, combined with methods for oversampling are performing much better in identifying fraudulent transactions than the classical neural networks, consisting of only one hid-den layer. The results also indicate that using generative-adversarial approach as a method for oversampling is comparable in efficiency to other widely used techniques.