Search

The use of network technology to provide online courses is the latest trend in the training and development industry and has been defined as the “e-Learning revolution”. On the other hand, Online Social Networks (OSNs) represent today an effective possibility to have common and easy-to-use platforms for supporting e-Learning activities. However, as underlined by previous studies, many of the proposed e-Learning systems can result in confusion and decrease the learner’s interest. In this paper, we introduce the possibility to form e-Learning classes in the context of OSNs. At the best of our knowledge, any of the approaches proposed in the past considers the evolution of on-line classes as a problem of matching the individual users’ profiles with the profiles of the classes. In this paper, we propose an algorithm that exploits a multi-agent system to suitably distribute such a matching computation on all the user devices. The good effectiveness and the promising efficiency of our approach is shown by the experimental results obtained on simulated On-line Social Networks data.

Smart cities are built on top of heterogeneous IoT infrastructures, that can be viewed as communities of software agents (the intelligent objects) that interact with each other to realize complex activities. These agents operate on behalf of users that need services; for these reason agents are often in competition with each other. On the other hand, an agent can often benefit from collaborating with other agents in some circumstances, exchanging information and services. Under this viewpoint, the task of finding the best partners to collaborate is a key task for an agent. A general consensus exists about the benefits deriving by forming friendships and groups for mutual cooperation inside competitive Multi-Agent Systems (MASs). In this respect, the existing proposals are usually addressed to maximize the profit at the level of individual agent or group. Unfortunately, the most part of these approaches could advantage the most aggressive agents, also in presence of bad social behaviors. This is not a desired scenario in a smart city environment. A possible solution to this problem is that of promoting correct behaviors and meritocracy inside agent communities. To this aim, we propose to model the competitive MAS scenario in the framework of non cooperative games by assuming to represent (i) the trustworthiness of agents relationships by means of a trust model and (ii) the capability of a community to provide its members with a good environment by means of its social capital. As a result, a group formation algorithm capable to asymptotically maximize the social capital is proposed. This algorithm highlights two main features: (i) the computed solution is a Nash equilibrium in the considered game and (ii) the only rewarded agents are those having the most correct behaviors.

This paper deals with the principal aspects emerging from the application of trust techniques to the IoT domains with respect to the particular viewpoint of an IoT environment. We consider intelligent agents technology to add social behavior to the community of the smart objects, and we analyze the fundamental role of the concepts of trust and reputation in this perspective. Also, we analyze the existing architectures for IoT and explain how to integrate IoT with fog/edge computing. Besides discussing the main proposals present in the literature, the key contribution of this paper consists of providing a comparative study of the main current architectures for modeling trust in IoT environments. In this setting, we propose a comparison based on the important characteristics of the IoT layer and the architecture type. Such an analysis allows us to highlight both advantages and limitations of each approach, and to discuss the emerging research challenges.

In a massive IoT systems, large amount of data are collected and stored in clouds, edge devices, and terminals, but the data are mostly isolated. For many new demands of various intelligent applications, self-organized collaborated learning on those data to achieve group decisions has been a new trend. However, in order to reach the goal of group decisions, trust problems on data fusion and model fusion should be solved since the participants may not be trusted. We propose a consistent and trust fusion method with the consortium chain to reach a consensus, and complete the self-organized trusted decentralized collaborated learning. In each consensus process, consensus candidates check others’ trust levels to ensure that they tends to fuse consensus with users with high trust, where the trust levels are evaluated by scores according to their historical behaviors in the past consensus process and stored in the public ledger of blockchain. A trust rewards and punishments method is designed to realize trust incentive consensus, the candidates with higher trust levels have more rights and reputation in the consensus. Simulation results and security analysis show that the method can effectively defend malicious users and data, improve the trust perception performance of the whole federated learning network, and make the federated learning more trusted and stable.

The need of managing complex and interactive activities is becoming a key challenge in the “Internet of Things” (IoT) and leads to request large hardware and power resources. A possibility of facing such a problem is represented by the possibility of virtualizing physical IoT environments over the so called Cloud-of-Things (CoT), where each device is associated with one or more software agents working in the Cloud on its behalf. In this open and heterogeneous context, IoT devices obtain significant advantages by the social cooperation of software agents, and the selection of the most trustworthy partners for cooperating becomes a crucial issue, making necessary to use a suitable trust model. The cooperation activity can be further improved by clustering agents in different groups on the basis of trust measures, allowing each agent will to interact with the agents belonging to its own group. To this purpose, we designed an algorithm to form agent groups on the basis of information about reliability and reputation collected by the agents. In order to validate both the efficiency and effectiveness of our approach, we performed some experiments in a simulated scenario, which showed significant advantages introduces by the use of the trust measures.

Improvements in computational and network capabilities of mobile devices along with the wide spread of wireless networks for smart cities, allow users to make accessible temporarily unused communication resources for free or for a fee. Such interesting scenario introduces, however, some critical issues due to reliability of users sharing/consuming resources, which are a further concern with respect to those, strictly referred to the security. To tackle such problems, in this paper we propose a distributed multi-agent framework, exploiting reputation information, which considers Both the price paid by mobile users for resources and some countermeasures to detect malicious users, as confirmed by experimental results.

In this work we present an approach aimed at maximizing the global QoS perceived within a large-scale federation of computing infrastructures. This approach exploits the combina- tion of ( i ) a trust model for a network of software agents, designed to assist federated computing nodes, and ( ii ) a decentralized procedure which leads to the formation of coali- tions between them. The proposed solution is based on a generic SLA-based federated ar- chitecture and the concept of “Global Capital”which reflects the global QoS offered by the federation. Finally, a number of experimental trials prove that, by means of the proposed approach, the Global Capital improves.

In this work, we propose an algorithm, called E-Learning Ontology Enrichment (ELOE), to derive a global representation from the personal ontologies of different agents present in an e-Learning MAS. Using ELOE, each agent of a MAS-based e-Learning system can autonomously enrich his own ontology by using semantic negotiation and, at the same time, it can access to the global ontology to have a view of the terms used by all the other agents. Each term of the global ontology is associated with a set of meanings, and each meaning is associated with the set of agents that have used it. This way an agent, desiring to send a message to an interlocutor, is able of choosing from the global ontology the most suitable term with the most appropriate meaning. Only if the agent does not find in the global ontology the appropriate term, he will use a personal term that probably will lead to a new semantic negotiation process. This way, the use of the onerous task of the semantic negotiation will be limited to only the strictly necessary situations, and consequently the whole communication cost is decreased.

Thematic groups are gaining a lot of attention and high centrality in OSNs, as users share opinions and/or mutually collaborate for reaching their targets. Since users can be affiliated with groups belonging to different social networks, they can be supported by personal software agents able to perform activities aimed at supporting relationships and mutual cooperation among heterogeneous OSNs thematic groups. Basically software agents can encode users profiles with detailed information to be related with specific groups. This work discusses a multi-agent framework whose structure focuses on the role of software agents and the use of a common, shared dictionary for each group. Personal software agents are associated to OSN users to share knowledge for a specific theme for a number of groups related to that topic. Group agents are defined to support each group on each OSN by interacting with personal agents to manage group affiliation and enrich the common dictionaries of their own groups. The common dictionary of the group is a key element to provide knowledge sharing and interoperability between personal and group agents. In the proposed approach each user agent is able to personalize its own dictionary and enrich that of its own groups by means of selected categories.

In this work we deal with the issue of optimizing the global Quality of Service (QoS) of a Grid Federation by means of an aggregation model specifically designed for intelligent agents assisting Grid nodes. The proposed model relies on an algorithm, called FGF (Friendship and Group Formation), by which the nodes select their partners with the aim of maximizing the QoS they perceive when a computational task requires the collaboration of several Grid nodes. In the proposed solution, in order to assist the selection of the partners, a suitable trust model has been designed. Since jobs sent to Grid Federations hold complex requirements involving well defined resource sets, trust values are calculated for specific sets of resources. We also provide a theoretical foundation and some experiments to prove that, by means of the adoption of the FGF algorithm suitably supported by the proposed trust model, the Grid Capital (which respect the global QoS) of the Grid Federation is eventually improved.