Papers by Domenico Rosaci
Improving Grid Nodes Coalitions by Using Reputation
Studies in computational intelligence, 2015
In this work we deal with the issue of improving the QoS provided by each node of a Grid Federati... more In this work we deal with the issue of improving the QoS provided by each node of a Grid Federation, by modelling it as a problem of “Grid formation”. In the proposed model each Grid node belonging to a computational Grid, is free to join with or leave a grid with the goal of improving its satisfaction. Contextually, each grid is free to search other nodes to join with it or to remove those nodes resulted ineffective. Software agents manage the node profiles and in our model a Grid agent has the role of handling the profile of the Grid.We introduce a distributed algorithm, called GF, to handle the node activity of joining to the grid, modelled as a matching problem. Some experiments shown the effectiveness of our approach.
Learning agents can autonomously improve both knowledge and performances by using learning strate... more Learning agents can autonomously improve both knowledge and performances by using learning strategies. Recently, a strategy based on a cloning process has been proposed to obtain more effective recommendations, generating advantages for the whole agent community through individual improvements. In particular, users can substitute unsatisfactory agents with others provided with a good reputation and associated with users having similar interests. This approach is able to support an evolutionary behaviour in the community that allows the better agents to predominate over the less productive agents. However, such an approach is user-centric requiring a user's request to clone an agent. Consequently, the approach slowly generates modifications in the agent population. To speed up this evolutive process, a proactive mechanism is proposed in this paper, where the system autonomously identifies for each user those agents that in the community have a good reputation and share the same interests. The user can check the clones of such suggested agents in order to evaluate their performances and to adopt them. The results of preliminary experiments show significant advantages introduced by the proposed approach.
Springer eBooks, Sep 6, 2008
The importance of mutual monitoring in recommender systems based on learning agents derives from ... more The importance of mutual monitoring in recommender systems based on learning agents derives from the consideration that a learning agent needs to interact with other agents in its environment in order to improve its individual performances. In this paper we present a novel framework, called EVA, that introduces a strategy to improve the performances of recommender agents based on a dynamic computation of the agent's reputation. Some preliminary experiments show that our approach, implemented on the top of some well-known recommender systems, introduces significant improvements in terms of effectiveness.
A multi-agent model for handling e-commerce activities
In this paper we propose a multi-agent model for han-dling e-commerce activities. In our model, a... more In this paper we propose a multi-agent model for han-dling e-commerce activities. In our model, an agent is present in each e-commerce site, managing the informa-tion stor ed ther ein. In addition, another agent is associated with each customer, handling her/his profile . ...
Lecture Notes in Computer Science, 2014
Information Sciences, Nov 1, 2017
In this work we investigate on the time-stability of the homogeneity -in terms of mutual users' s... more In this work we investigate on the time-stability of the homogeneity -in terms of mutual users' similarity within groups -into real Online Social Networks by taking into account users' behavioral information as personal interests. To this purpose, we introduce a conceptual framework to represents the time evolution of the group formation in an OSN. The framework includes a specific experimental approach that has been adopted along with a flexible, distributed algorithm (U2G) designed to drive group formation by weighting two different measures, mutual trust relationships and similarity, denoted by compactness. An experimental campaign has been carried out on datasets extracted from two social networks, CIAO and EPINIONS, and the results show that the time-stability of similarity measure for groups formed by the algorithm U2G based on the sole similarity criterion is lower than that of groups formed by considering similarity and trust together, even when the weight assigned to the trust component is small.
Springer eBooks, 2014
Recommender systems usually support B2C e-Commerce activities without to provide e-buyers with in... more Recommender systems usually support B2C e-Commerce activities without to provide e-buyers with information about the reputation of both products and interlocutors. To provide B2C traders with suggestions taking into account gossips, in this paper we present REBECCA, a fully decentralized trust-based B2C recommender system that also guarantees scalability and privacy. Some experiments show the advantages introduced by REBECCA in generating more effective suggestions.
Using Trust Measures to Optimize Neighbor Selection for Smart Blockchain Networks in the IoT
IEEE Internet of Things Journal, 2023
New Results in Image Compression through M.A.I.A. Neural Networks
Perspectives in neural computing, 1999
In this paper some results achieved in the image compression field by using neural networks are p... more In this paper some results achieved in the image compression field by using neural networks are presented. A particular kind of neural network has been used that allows compressing both sets of images and single images; furthermore, the compression can be effected with both Black and White and coloured images. The quality of the reconstructed image and the compression ratio are functions both of the error defined in the learning stage and the number of used images.
An agent-based approach for managing e-commerce activities
International Journal of Intelligent Systems, Apr 1, 2004
In this article, we propose an agent-based approach for managing e-commerce activities. In our ap... more In this article, we propose an agent-based approach for managing e-commerce activities. In our approach, an agent is present in each e-commerce site, managing the information stored there. In addition, another agent is associated with each customer, handling his/her ...
A reputation framework to share resources into IoT-based environments
Internet of Things (IoT) is an emerging paradigm for cooperation among physical objects provided ... more Internet of Things (IoT) is an emerging paradigm for cooperation among physical objects provided with computational and communication capabilities. The great amount of interactions occurring within the IoT environments expose IoT users and interconnected objects to security and privacy risks. Consequently, adding security and privacy into the IoT domain is fundamental for a wider IoT diffusion. In open and dynamic IoT environments such problems are more relevant for the greater possibility of anomalous behaviors and the adoption of approaches uniquely based on authentication methods could result infeasible and/or inadequate for creating an effective trustworthiness atmosphere. A possible solution, widely applied and investigated in different fields, is represented by trust- and reputation-based systems. To tackle the issues above we conceived a distributed reputation model along with a framework to manage information about IoT devices reputation. In particular, the model provides some countermeasures to detect malicious or cheating devices. To test the performance of our proposal, a set of experiments simulating the vehicular mobility on a basic urban network has been executed by providing promising results.
Computers and Electronics in Agriculture, Mar 1, 2020
Accurate predictions of surface runoff and soil erosion after wildfire help land managers adopt t... more Accurate predictions of surface runoff and soil erosion after wildfire help land managers adopt the most suitable actions to mitigate post-fire land degradation and rehabilitation planning. The use of the Artificial Neural Networks (ANNs) is advisable as hydrological prediction tool, given their lower requirement of input information compared to the traditional hydrological models. This study proposes an ANN model, purposely prepared for forest areas of the semi-arid Mediterranean environments. The ANN hydrological prediction capability in non-burned, burned by wildfire, and burned and then treated soils has been verified at the plot scale in pine forests of South-Eastern Spain. Runoff and soil loss were much higher than non-burned soils (assumed as control), but mulch application was effective to control runoff and soil erosion in burned plots. Moreover, logging did not affect the hydrological response of these soils. The model gave very accurate runoff and erosion predictions in burned and non-burned soils as well as for all soil treatments (mulching and/or logging or not), with only one exception (that is, in the condition with the combination of treatments which gave the worst performance, burning, mulching and logging), as shown by the exceptionally high model efficiency and coefficients of determination. Although further experimental tests are needed to validate the ANN applicability to the burned forests of the semi-arid conditions and other ecosystems, the use of ANN can be suggested to landscape planners as decision support system for the integrated assessment and management of forests.
Using Blockchain for Reputation-Based Cooperation in Federated IoT Domains
Studies in computational intelligence, Oct 2, 2019
The convergence of Internet of Things and Multi-Agent Systems also relies on the association of s... more The convergence of Internet of Things and Multi-Agent Systems also relies on the association of software agents with IoT devices to benefit from their social attitude to cooperate for services. In this context, the selection of reliable partners for cooperation can be a very difficult task if IoT devices migrate across different domains. To this purpose, we introduce the Reputation Capital model and an algorithm to form agents groups in each IoT federated domain, on the basis of the reputation capital of each agent, to realize a competitive framework. A further essential contribution consists of adopting the blockchain technology to certify the reputation capital of each agent in each federated environment. To verify that the individual reputation capital of devices and, consequently, the overall reputation capital of the IoT community can benefit from the adoption of the proposed approach, we performed some experiments. The results of these experiments witnessed that, under certain conditions, almost all the misleading agents were detected. Moreover, the simulations also have shown that, by adopting our reputation model, malicious actors always pay for services significantly more than honest devices.
Lecture Notes in Computer Science, 2007
Agent-based Web recommender systems are applications capable to generate useful suggestions for v... more Agent-based Web recommender systems are applications capable to generate useful suggestions for visitors of Web sites. This task is generally carried out by exploiting the interaction between two agents, one that supports the human user and the other that manages the Web site. However, in the case of large agent communities and in presence of a high number of Web sites these tasks are often too heavy for the agents, even more if they run on devices having limited resources. In order to address this issue, we propose a new multi-agent architecture, called MARS, where each user's device is provided with a device agent, that autonomously collects information about the local user's behaviour. A single profile agent, associated with the user, periodically collects such information coming from the different user's devices to construct a global user profile. In order to generate recommendations, the recommender agent autonomously pre-computes data provided by the profile agents. This recommendation process is performed with the contribution of a site agent which indicates the recommendations to device agents that visit the Web site. This way, the site agent has the only task of suitably presenting the site content. We performed an experimental campaign on real data that shows the system works more effectively and more efficiently than other well-known agent-based recommenders.
Recommendation of reliable users, social networks and high-quality resources in a Social Internetworking System
Ai Communications, 2011
Social Internetworking Systems are a significantly emerging new reality; they group together some... more Social Internetworking Systems are a significantly emerging new reality; they group together some social networks and allow their users to share resources, to acquire opinions and, more in general, to interact, even if these users belong to different social networks and, ...
Agent-based recommender systems are tools able to assist users' choices with suggestions coming c... more Agent-based recommender systems are tools able to assist users' choices with suggestions coming closest to their orientations. In this context, it is relevant to identify those users that are the most similar to the target user in order to require them suitable suggestions. However, particularly when we deal with video contents for e-Learning, it should be appropriate also to consider (i) recommendations coming from those students resulted the most effective in suggesting video and (ii) the effects of the device currently exploited. To address such issues in a multimedia scenario, we propose a multi-agent trust based recommender architecture, called ELSA, appositely conceived to this aim. Some preliminary performed simulations permitted to evaluate our proposal with respect to the other considered agentbased RSs.
The formation and evolution of interest groups in Online Social Networks is driven by both the us... more The formation and evolution of interest groups in Online Social Networks is driven by both the users' preferences and the choices of the groups' administrators. In this context, the notion of homogeneity of a social group is crucial: it accounts for determining the mutual similarity among the members of a group and it's often regarded as fundamental to determine the satisfaction of group members. In this paper we propose a group homogeneity measure that takes into account behavioral information of users, and an algorithm to optimize such a measure in a social network scenario by matching users and groups profiles. We provide an advantageous formulation of such framework by means of a fully-distributed multi-agent system. Experiments on simulated social network data clearly highlight the performance improvement brought by our approach.
Deriving “Sub-source” Similarities from Heterogeneous, Semi-structured Information Sources
Lecture Notes in Computer Science, 2001
In this paper we propose a semi-automatic technique for deriving the similarity degree between tw... more In this paper we propose a semi-automatic technique for deriving the similarity degree between two portions of heterogeneous, semistructured information sources (hereafter, sub-sources). The proposed technique consists of two phases: the first one selects the most ...
In this paper we present an XML-based multi-agent system, called Multi Agent System for Traders (... more In this paper we present an XML-based multi-agent system, called Multi Agent System for Traders (MAST), that completely supports Business-to-Customer E-commerce activities, including advertisements and payments. MAST helps both customers and merchants in their tasks with a homogeneous and personalized approach. In particular, E-payments in MAST are implemented under the availability of financial institutions. This avoids exchanging of sensible customers' information and reinforces the confidence between customers and merchants. A complete prototype of MAST has been implemented in the JADE framework, and it has been exploited for realizing some experiments, in order to evaluate its performances.
A Hopfield-Like Neural Network in the Simulation of Traffic Flows in a Transportation Network
Uploads
Papers by Domenico Rosaci