ABSTRACT. This paper presents a multi-agent system that facilitates the remote monitoring of the elderly patients which are susceptible to mental disorder disease. In order to find early signs of health condition depreciation we have assessed four of the most common mental disorder diseases to find which kind of sensors can detect specific symptoms with the main purpose of creating an early warning system. The diagnosis component is based on an ontology that defines the relations between sensors, symptoms and diseases. Based on these relationships a specialized agent can inform the medical personnel about the detected symptoms.

ABSTRACT. This paper presents results of the analysis of a tourism information Web site (AmFostAcolo.ro) by using Complex Networks (CN) analytics. The work presented in this paper complements our previous results on data extraction and modelling of tourism information using Complex Networks. We analyze the properties of this network including nodes distribution and communities in order to investigate the social phenomena hidden behind this data set. Temporal analysis methods are employed for examining the evolution of the user community of this Web site. The results obtained prove the natural development of this system, as well as the usefulness of the CN analytics applied to this specific scenario.

ABSTRACT. By modelling a software project as a complex system, its internal structure can be analysed in order to asses its design quality. However, as a software system is being developed, the quality of its internal structure is evolving too, not always for the better. Flaws in the internal structure are usually indicators of code that is hard to understand, maintain and, in many cases, they are pointers of accumulated technical debt. While there are already methods and tools that enable design flaw detection, they only look at a snapshot of the code, they do not analyse how the design flaw evolved over time. We propose an approach which enhances design flaw detection with history information, in order to: (i) find patterns in the evolution of a design flaw, which could then be used to predict future activity, (ii) improve detection by eliminating false negatives, (iii) improve recommendation system to provide better refactoring advices and a better ranking of design flaws, in order to address the most critical first.

ABSTRACT. Stock market prediction is influenced by many internal and external factors. One of these factors are the news articles and financial reports related to each listed company. This paper describes a system that is able to extract relevant information from this type of textual documents, correlate them with the stock price movement and determine whether or not a new released news can and in which proportion will influence the market behavior. Predefined ontologies are used for classifying the news articles and automated ontology extraction for classifying concepts and super - concepts, on an attempt to make a semantic mining of the text news. The system is based on a Multi-Agent Architecture that will investigate, extract and correlate the textual data message with the price evolution in order to better determine buy/sell moments, the trend direction and optimize an investment portfolio. In order to validate our model a prototype was developed and applied to the Bucharest Stock Exchange Market listed companies.