This paper presents a neural network model which was developed and trained to detect attacks on computer networks and to identify the differences indicating what distinguishes them from the regular network traffic. The influence of some parameters on the operation of the network was examined in order to select those characteristic for cyberattack. A certain number of models was tested for binary and multi-class classification. The accuracy of recognition by the network was evaluated for both the entire set and individual categories of the network traffic. The results obtained are promising based on comparison to those published in related work studies on intrusion detection systems.

Ubiquitous nature of information determines continuous decision making always based on its stream coming from the environment, not only in the human, but also in the animal world. Communication between the users of information system is a fundamental concept for acquiring, showing, spreading, sharing and constantly increasing the knowledge about the circumstances under which they are in need to make a move all alone as well as while working in groups. In this paper, we review information stream-based systems on amount of information acceptable to facilitate the process of decision making, also in multilingual settings. We analyze the information system objects and the resource management cycle. In addition, methodology of data mining in natural language is investigated. Multilingual information flow between the users is specific while analyzing from the contextual perspective, when the range of information system applications becomes extended to international cooperation.

The paper presents an approach to solve some problems arising in the management process of IT security. Our motivation of this research is to study in every detail the context of service oriented systems, which can be defined as considerable heterogeneous, dynamic and flexible configuration of the hardware and software system resources. The fundamental difference between security management systems with traditional centralized and monolithic architecture and service oriented systems is discussed. We propose a multilayered-reference model for service-oriented systems aimed predominantly at principal objectives related to IT based systems security working in dynamic environments. Likewise, considered are some dedicated to service-oriented environments key assumptions of a multi-agent system design with the aim at security analysis. The last part of the paper presents briefly the results of our analysis of IT security aspects, performed on the comparison basis of correlation between the events observed at the low and at high layers of our reference model.

Streaming information flow allows identification of linguistic similarities between language pairs in real time as it relies on pattern recognition of grammar rules, semantics and pronunciation especially when analyzing so called international terms, syntax of the language family as well as tenses transitivity between the languages. Overall, it provides a backbone translation knowledge for building automatic translation system that facilitates processing any of various abstract entities which combine to specify underlying phonological, morphological, semantic and syntactic properties of linguistic forms and that act as the targets of linguistic rules and operations in a source language following professional human translator. Streaming data flow is a process of mining source data into target language transformation during which any inference impedes the system effectiveness by producing incorrect translation. We address a research problem of exploring streaming data from source-target parallels for detection of linguistic similarities between languages originated from different groups.

eHealth services integrate Web Information Retrieval and Intelligent Medical Decision Support for health care professionals based on the range of possible symptoms which a patient reports. However, many symptoms like high temperature, fever, or headache, are ambiguous in terms of suggesting wide variety of possible patient's conditions to the GP, while other symptoms are mutually dependant, which again can be misleading to make an accurate diagnosis. On the other hand, doctor's up-to-date knowledge on the medicaments, drugs, active medical substances included, anticipated range of diseases relating to the symptoms reported, and the most reliable pharmaceutical manufacturers, are of the greatest importance to cure the illness successfully. This study proposes an approach to support so called standard medical procedure or clinical guidelines in treatment of each of the diseases by delivering such a knowledge to the physician and by individualizing the selection of drugs in respect to the patient's specific needs in order to avoid a potential drug interaction. We evaluate efficiency of a medical multilingual decision support system Diagnosia on the grounds of accessibility to such a knowledge depending on the EU language and we use Bayesian inference for generating the optimal decision on reaching a particular diagnosis accuracy. Our methodology is examined on the real data taken from the American service Prescriber Checkup and some other knowledge-based medical resources of nationally recognized rank. Our findings indicate that this approach outperforms not only traditional standard procedure of curing some commonly occurring illnesses, but also many commercial computer-assisted medical support diagnostic systems.

Classification is a data processing technique of a great significance both for native eHealth systems and web telemedicine solutions. In this sense, artificial neural networks have been widely applied in telerehabilitation as powerful tools to process information and acquire a new medical knowledge. But effective analysis of multidimensional heterogeneous medical data, still poses considerable difficulties. It was shown that processing too many data features simultaneously is costly and has some adverse effects on the resulting models classification properties. Therefore, there is a strong need to develop new techniques for selecting features from the very large data sets that include many irrelevant, or redundant features. This work addresses the context-related feature selection problem from medical data by proposing utility of Sigma-if neural network being an effective model of neurology patients's low-level distributed selective attention mechanisms. Our experiments indicate that a context-aware technique can reduce the average cost of medical data acquisition and data processing as well as it can decrease classification error probability resulting in increasing the overall eHealth systems reliability.

In more and more countries the number of citizens with double nationality is growing substantially. In their developing stage, current eHealth technologies are oriented towards helping the native patients rather than those speaking a foreign language that limits an access to the medical care. Nowadays, most people search the web for the medical symptoms of their disorders before going to the General Practitioner (GP), however multinational patients have limited chance to access eHealth care services not only owning to the lack of medical knowledge, but specifically due to their language barriers. In this study we investigate eHealth services on multilingual information access and online communication gap between the patients and the nurses or healthcare professionals.