Moodle is a widely deployed distance learning platform that provides numerous opportunities to enhance the learning process. Moodle’s importance in maintaining the continuity of education in states of emergency and other circumstances has been particularly demonstrated in the context of the COVID-19 virus’ rapid spread. However, there is a problem with personalizing the learning and monitoring of students’ work. There is room for upgrading the system by applying data mining and different machine-learning methods. The multi-agent Observer system proposed in our paper supports students engaged in learning by monitoring their work and making suggestions based on the prediction of their final course success, using indicators of engagement and machine-learning algorithms. A novelty is that Observer collects data independently of the Moodle database, autonomously creates a training set, and learns from gathered data. Since the data are anonymized, researchers and lecturers can freely use them for purposes broader than that specified for Observer. The paper shows how the methodology, technologies, and techniques used in Observer provide an autonomous system of personalized assistance for students within Moodle platforms.

This paper describes one of the non-linear (and non-stationary) stochastic models, the GSB (Gaussian, or Generalized, Split-BREAK) process, which is used in the analysis of time series with pronounced and accentuated fluctuations. In the beginning, the stochastic structure of the GSB process and its important distributional and asymptotic properties are given. To that end, a method based on characteristic functions (CFs) was used. Various procedures for the estimation of model parameters, asymptotic properties, and numerical simulations of the obtained estimators are also investigated. Finally, as an illustration of the practical application of the GSB process, an analysis is presented of the dynamics and stochastic distribution of the infected and immunized population in relation to the disease COVID-19 in the territory of the Republic of Serbia.

One of the key problems in the application of multicriteria analysis methods is identifying the importance of the model criteria. The relevance and validity of the decisions are directly conditioned by the relevance of a given set of criteria used for evaluating alternatives, and the correct determination of the weights of these criteria. Several methodologies have been developed to calculate the importance of each criterion for a given problem. All methodologies are classified into two main groups: subjective and objective. In this paper, we present a new procedure to integrate two recognized methods for determining the weights of factors—the analytic hierarchy method as a subjective method and entropy as an objective method. We apply our methodology to a contemporary local economic problem in Serbia—the process of certifying cities and municipalities as favorable to business. We also discuss its implementation in a software tool on a local government website.

Complex real problems increasingly require intelligent systems that combine knowledge, techniques and methodologies from various sources. Intelligent systems based on artificial intelligence techniques that are associated with the behavior of people can perform the processes of learning, reasoning and solving all kinds of problems. Such systems, which automatically can perform tasks set by the user or other software, today thankfully called intelligent agents. Independent, intelligent agents on the Internet can be very successful to perform some search work on behalf of and for the needs of different users. For efficient collection, manipulation and management of data, such software can be very interesting from the standpoint of intelligent data analysis in many areas the police. Analysis of the data collected by an intelligent agent (a software robot-bot) can be successfully utilized, among many jobs in the police, and in the field of crime and in particular manifestation of cyber­crime, traffic safety, emergencies, etc. To make the collection and analysis of data from criminal activities on the Internet effective, it is necessary to examine the existing artificial intelligence techniques to be used for the conclusion of the intelligent agents. On the other hand, using of methods of artificial intelligence in finding data along with intelligent data analysis (data mining) should be used, which has found wide use in the area of business, economics, mechanics, medicine, genetics, transport etc.

This paper describes the enhanced LIRE (LInked RElations) architecture for creating relations between datasets available on open government portals. The architecture is improved to be applicable on different open government data platforms using minimal configuration at the Data processing layer. We evaluated the applicability of enhanced LIRE, its advantages and disadvantages, which resulted in necessary recommendations for the publication of dataset's metadata to obtain better associations between datasets. Moreover, we introduced a LINDAT indicator that reflects the percentage of linked data in the total possible number of linked data on open government data portals.

An Entity-Relationship (E-R) diagram is a graphical representation of interest in a specific domain of knowledge about any information system. It is a data modeling technique that can help defining business processes and plays a central role in software engineering process. Extracting conceptual models from natural language requirements can help identify dependencies, redundancies, and conflicts between requirements generated from lengthy textual specifications. The automatic generation of different software diagram from natural language requirements such as English is highly challenging, with advancements in artificial intelligence. In this paper, a semi-automated approach for the design of E-R model from the short requirements written in a Serbian natural language using morphological analysis is presented. Presented rules are heuristics and were founded suitable for conceptual model creation in the phase of requirements analysis. At the end, examples obtained by using basic learning resources are presented.