Yiouli Kritikou

An overview of learning mechanisms for cognitive systems

Cognitive systems were first introduced by Mitola and in the last decade they have proved to be beneficial in self-management functionalities of future generation networks. The advantages and the way that networks gain benefits from cognitive systems is analysed in this article. Moreover, since such systems are closely related to machine learning, the focus of this article is also placed on machine learning techniques applied both in the network and the user devices side. In particular, celebrating 10 years of cognitive systems, this survey-oriented article presents an extended state-of-the-art of machine learning applied to cognitive systems as coming from the recent research and an overview of three different learning capabilities of both the network and the user device.

Knowledge Management Toolbox: Machine Learning for Cognitive Radio Networks

Learning mechanisms are essential for the attainment of experience and knowledge in cognitive radio (CR) systems, exposed to high dynamics with often unpredictable states [1]. These mechanisms can be associated with user and device profiles, context, and decisions. The focus learning user preferences is the dynamic inference and estimation of current and future user preferences. The acquisition and learning of context information encompasses mechanisms for the system to perceive its current status and conditions in its present environment, as well as estimating (and forecasting) the capabilities of available network configurations. Finally, learning related to decisions addresses the building of knowledge with respect to the efficiency of solutions that can be applied to specific situations encountered. Based on knowledge obtained through learning, decision-making mechanisms can become faster, since the CR system can learn and immediately apply solutions that have been identified as being efficient in the past. Moreover, knowledge obtained through learning mechanisms may be shared among nodes of a system. Thus, more reliable and more optimal decisions can be made by exploiting knowledge obtained through learning mechanisms.

Introducing cognition in the management of equipment in the future wireless world

A key topic in the field of future wireless B3G/4G networks is related to mechanisms for the efficient complementary use of the different technologies. The goal is to exploit the multiplicity of the available access standards to the benefit of end-users, operators and manufacturers. The concept of future wireless B3G/4G introduces the idea of diverse, heterogeneous Radio Access Technologies (RATs) able to converge into one composite radio environment, where the user is ldquoalways best connectedrdquo, while the most appropriate technology is selected and applied seamlessly. Cognitive and reconfigurable wireless networks have appeared as a complementary concept to B3G networks. Cognitive systems determine their behaviour, goals, principles, experience and knowledge, reactively or proactively and acting in response to external triggers. The focus of this paper is more on the end-user side. In this sense, the paper presents a Cognitive Terminal Management System (CTMS) that comprises mechanisms for retrieving and managing user information using concepts from Bayesian statistics. The use of Bayesian Networks for the prediction of future user preferences is also addressed in terms of appropriate modelling of the user profile.

Technical challenges for merging opportunistic networks with respective cognitive management systems in the Future Internet

The dawn of the Future Internet (FI) era poses new requirements to modern communication networks namely, the demand for new applications/ services, the support for diversified services, the expanded use of wireless access and the need for increased efficiency in resource provisioning and utilization. In this paper we propose a solution to address these requirements. In particular, the proposed solution is based on (i) opportunistic networks, which can be seen as operator-governed, temporary and probably infrastructure-less extensions of the infrastructure-based network, (ii) cognitive systems both for managing the opportunistic networks and for coordinating with the infrastructure, and (iii) control channels for the cooperation of the cognitive management systems. We advocate that the adoption of such a solution will bring about enhanced wireless service provision and extended access capabilities for the Future Internet, through higher resource utilization, lower costs, and management decisions with a larger “green” footprint.

Role of neighbour discovery in distributed learning and knowledge sharing algorithms for cognitive wireless networks

This work investigates the impact of neighbour discovery on distributed learning schemes applied on optimal network selection based on the acquisition by the selecting device of context information on the capabilities and status of surrounding networks. The work introduces the problem of neighbour discovery in multiple channel and cognitive networks, and identifies the trade-offs between neighbour discovery performance and overall network performance. Next, an optimal network selection algorithm based on distributed learning is introduced, and key parameters and components relevant to its operation are presented, focusing in particular on the common control channel required to exchange the context information. Finally, the paper discusses the relation between neighbour discovery and the distributed learning process at the basis of the context information acquisition; a model for mapping the learning process on a neighbour discovery problem is proposed, and the potential impact of neighbour discovery failures on the performance of the optimal network selection scheme is discussed.

Cognitive Management of Devices in the Wireless World

The success of mobile networks has been driven by the services offered, i.e. voice in second generation and multimedia services in third generation networks. Similarly, a key issue for the success of future generation networks is considered to be the provision of enhanced, always available, personalised services. At the same time, the complexity and heterogeneity of the infrastructure of mobile network operators increases as Radio Access Technologies continue to evolve and new ones emerge. All these issues call for self-management and learning capabilities in future generation network systems. Cognitive, reconfigurable systems encompassing self-management and learning capabilities have been devised as a solution in this direction. Cognitive systems determine their behaviour, in a self-managed way. This is done reactively or proactively, based on goals, policies, knowledge and experience obtained through learning. This paper focuses on the user device and presents a Cognitive Device Management System that comprises mechanisms for dynamically selecting the optimal device configuration, taking into account user preferences, device environment characteristics (context), policies, and knowledge established through machine learning functionality.

Introducing Cognition in Web-Based, Learning Management Systems for Vocabulary Teaching

Nowadays, connectivity is practically imposed for everyone, as it is used for professional interactions, information retrieval, or just for entertainment. Thus, the importance of communicating, along with the need of people to interact through various foreign languages, increases rapidly, so as to enable ubiquitous connectivity and continuous updating. The increase of the vocabulary in a foreign language is often provided as a service in the context of web-based systems and can be significantly facilitated through considering the various ways that knowledge can be perceived and interpreted by each person. The goal of this paper is to consider such factors in designing a “cognitive, web-based, foreign language learning management system”. The system proposed is capable of monitoring the user’s activity and adapting accordingly, so as to improve the learning process as a whole. This is achieved by exploiting Bayesian Networks’ concepts, in order to monitor past preferences, acquire knowledge and estimate the likelihood of future preferences. The paper presents the related work in the field and the influences in the current work, the system’s basic requirements and structure, the methodology for introducing cognition in such a system and indicative simulation results that showcase the system’s effectiveness.

Evaluation of the Potentials of the Business Case of Deploying Reconfigurable Segments in Wireless B3G Infrastructures

The B3G concept can be realized in two complementary ways. The first solution is the integration of the diverse radio access technologies into one composite radio environment. The alternative solution is provided by the concept of reconfigurable (adaptive) networks. Composite radio networks, sometimes also referred to as cooperative networks, jointly handle a difficult condition. Reconfigurable networks on the other hand, support B3G Systems by providing technologies that enable network elements and terminals to dynamically adapt to the environment requirements and conditions, in principle, by means of self-management. This paper provides proof on the business advantages of reconfigurable networks. In this context the paper performs an evaluation of the investment in both composite radio and reconfigurable networks, presenting a methodology that can be used for the financial assessment of such networks by applying investment appraisal techniques. Concrete results for both cases are presented and analyzed. The analysis clearly proves that reconfigurable networks can provide significant business benefits for network operators.

Management Architecture for the Provision of e-Services in Cognitive Environments

—The following paper discusses on the evolution of cognitive networks in conjunction with the development of advanced e-services, making a brief description of their role in modern society. E-services are delivered through a specific model, which is described in detail, and find several applications in peoples’ everyday activities. E-learning has proven to be a very important application of e-services, since the number of users that adopt it in their lives increases everyday. Thus, this paper presents the architecture of an e-learning platform, as well as the principles of the learning theories that influence the content’s structure. In this work, the e-learning content is formed for use by adult learners. Finally, the need for adaptation to each user’s specific demands and preferences, concerning both the content and the technical features of the platform, is discussed, providing further information on the way this personalization can take place, so as the maximum performance of users can be achieved. Index Terms —adaptation, cognitive networks, e-services, e-learning, user profile

User Modeling in the Context of Cognitive Service Delivery: Application to Learning Management Systems

—A contemporary trend in the field of telecommunications is the development of a constantly increasing number of services available to users through computer networks. These services are being used in order to facilitate users’ everyday life and save them time and effort. The following paper discusses on the service delivery and the way it can be adapted to each user’s specific needs, in the context of cognitive networks and service provisioning. An example of such a service is being examined, namely a Learning Management System and specifically User Model entity, which is responsible for storing user’s preferences. In support of this vision, a paradigm of Bayesian Networks’ application is presented, aiming at predicting user’s preferences in a Learning Management System, by managing a specific set of parameters that affect it and providing the information to configure the learning content to be delivered, accordingly. For the confirmation of this Model’s validity a set of indicative results are also presented at the end of this paper. Index Terms‐E‐learning, Learning Management System, Service Provisioning, User model