-
A Framework for Parallel Assessment of Reputation Management Systems. V. Agate, A. De Paola, S. Gaglio, G. Lo Re, M. Morana. In Proceedings of the 17th International Conference on Computer Systems and Technologies. CompSysTech 16
Abstract
| PDF
| BibTeX
| Full Text
Several distributed applications running over the Internet use Reputation Management Systems (RMSs) to guarantee reliable interactions among unknown agents. Because of the heterogeneity of the existing RMSs, their assessment in terms of correctness and resistance to security attacks is not a trivial task. This work addresses this issue by presenting a novel parallel simulator aimed to support researchers in evaluating the performances of a RMS since the design phase. Preliminary results obtained by simulating two different attacks confirm the suitability of the proposed framework to evaluate different RMSs.
-
SESAMO: An Integrated Framework for Gathering, Managing and Sharing Environmental Data. V. Agate, C. Crapanzano, A. De Paola, S. Gaglio, G. La Loggia. In Proceedings of the 17th International Conference on Computer Systems and Technologies. CompSysTech 16
Abstract
| PDF
| BibTeX
| Full Text
ICT systems are widely adopted for environmental management, but existing solutions address limited tasks and compose a plethora of heterogeneous tools, which impose a great additional effort on the operators. This work presents SESAMO, a novel framework to provide the operators with a unique tool for gathering, managing and merging environmental and territorial data. SESAMO uses WSNs for providing pervasive monitoring of environmental phenomena and exploits a multi-tier infrastructure in order to integrate data coming from heterogeneous information sources.
-
A Simulation Framework for Evaluating Distributed Reputation Management Systems. V. Agate, A. De Paola, G. Lo Re, M. Morana. In Proceedings of the 13th International Conference on Distributed Computing and Artificial Intelligence
Abstract
| PDF
| BibTeX
| Full Text
In distributed environments, where interactions involve unknown entities, intelligent techniques for estimating agents? reputation are required. Reputation Management Systems (RMSs) aim to detect malicious behaviors that may affect the integrity of the virtual community. However, these systems are highly dependent of the application domain they address; hence the evaluation of different RMSs in terms of correctness and resistance to security attacks is frequently a tricky task. In this work we present a simulation framework to support researchers in the assessment of a RMS. The simulator is organized in two logic layers where network nodes are mapped to system processes that implement the interactions between the agents. Message Passing Interface (MPI) is used to enable communication among different distributed processes and provide the synchronization within the framework. A case study addressing the simulation of two different attacks to a RMS is also presented.
-
Bio-inspired Sensory Data Aggregation. A. De Paola, M. Morana. In Biologically Inspired Cognitive Architectures, 2012, pp. 367-368.
Abstract
| PDF
| BibTeX
| Full Text
The Ambient Intelligence (AmI) research field focuses on the design of systems capable of adapting the surrounding environmental conditions so that they can match the users needs, whether those are consciously expressed or not. In order to achieve this goal, an AmI system has to be endowed with sensory capabilities in order to monitor environment conditions and users' behavior and with cognitive capabilities in order to obtain a full context awareness. Amy systems have to distinguish between ambiguous situations, to learn from the past experience by exploiting feedback from the users and from the environment, and to react to external stimuli by modifying both its internal state and the external state.
-
A decisional multi-agent framework for automatic supply chain arrangement. L. Greco, L. Lo Presti, A. Augello, G. Lo Re, M. La Cascia, S. Gaglio. In New Challenges in Distributed Information Filtering and Retrieval. 2013, pp. 215-232
Abstract
| PDF
| BibTeX
| Full Text
In this work, a multi-agent system (MAS) for supply chain dynamic configuration is proposed. The brain of each agent is composed of a Bayesian Decision Network (BDN); this choice allows the agent for taking the best decisions estimating benefits and potential risks of different strategies, analyzing and managing uncertain information about the collaborating companies. Each agent collects information about customer's orders and current market prices, and analyzes previous experiences of collaborations with trading partners. The agent therefore performs a probabilistic inferential reasoning to filter information modeled in its knowledge base in order to achieve the best performance in the supply chain organization.
-
Mimicking biological mechanisms for sensory information fusion. A. De Paola, M. La Cascia, G. Lo Re, M. Morana, M. Ortolani. In Journal of Biologically Inspired Cognitive Architectures, vol. 3, 2013, pp. 27-38.
Abstract
| PDF
| BibTeX
| Full Text
Current Artificial Intelligence systems are bound to become increasingly interconnected to their surrounding environment in the view of the newly rising Ambient Intelligence (AmI) perspective. In this paper, we present a comprehensive AmI framework for performing fusion of raw data, perceived by sensors of different nature, in order to extract higher-level information according to a model structured so as to resemble the perceptual signal processing occurring in the human nervous system. Following the guidelines of the greater BICA challenge, we selected the specific task of user presence detection in a locality of the system as a representative application clarifying the potentialities of cognitive models. Specifically, our contribution lies in the definition of a suitable model for knowledge representation and management; our goal is to make the artificial system able to understand the environment in which it acts, analogously to the way the human brain acts. In our system, the fusion of several information flows is performed by a Hidden Markov Model that allows to deal with heterogeneous data, potentially affected by a non-negligible degree of uncertainty, also taking into account the history of past perceptions. Sensory data are provided to the inference engine by a sensor network acting as a 'peripheral nervous system' which performs a preliminary processing, thus mimicking a mechanism present in the human beings. Our cognitive approach to information fusion is not limited to the specific case study, but it can be easily generalizable to any context characterized by a striking heterogeneity in the sensory system. Promising results have been obtained during the assessment of the information fusion model which performed very satisfactorily in terms of specificity and sensitivity.
-
A Distributed Bayesian Approach to Fault Detection in Sensor Networks. G. Lo Re, F. Milazzo, M. Ortolani. In Proceedings of the IEEE Global Telecommunications Conference (GlobeCom), 2012, pp. 634-639
Abstract
| PDF
| BibTeX
| Full Text
Sensor networks are widely used in industrial and academic applications as the pervasive sensing module of an intelligent system. Sensor nodes may occasionally produce incorrect measurements due to battery depletion, dust on the sensor, manumissions and other causes. The aim of this paper is to develop a distributed Bayesian fault detection algorithm that classifies measurements coming from the network as corrupted or not. The computational complexity is polynomial so the algorithm scales well with the size of the network. We tested the approach on a synthetic dataset and obtained significant results in terms of correctly labeled measurements.
-
An execution, monitoring and replanning approach for optimal energy management in microgrids E.Riva Sanseverino, M.L. Di Silvestre, M.G. Ippolito, A. De Paola, G. Lo Re. In Energy, vol. 36, Issue 5, pp. 3429-3436
Abstract
| PDF
| BibTeX
| Full Text
This work develops a new approach for optimal energy management of electrical distribution 'smart-grids'. Optimality aims at improving sustainability through the minimization of carbon emissions and at reducing production costs and maximizing quality. Input data are the forecasted loads and productions from renewable generation units, output data are a set of control actions for the actuators. The considered electrical distribution system includes storage units that must be considered over a 24 h time interval, to consider an entire charge and discharge cycle. The objectives for the optimal management of distributed (renewables and not) generation are technical, economical and environmental. It is thus required to solve a multi-objective optimization problem over a 24 h time interval considering the uncertainty associated to weather conditions and loads profiles. The novelty of the proposed approach resides in considering the optimal scheduling of generation units an automatic planning process in a dynamic, non-deterministic and not fully observable environment, as it is, getting closer to actual conditions. The system proposed here is a planning and execution scheduler which allows the central controller to monitor the execution of a scheduling plan, interrupt the monitoring to input new information and repair the plan under execution every time interval.
-
A knowledge management and decision support model for enterprises. P. Ribino, A. Augello, G. Lo Re, S. Gaglio. In Advances in Decision Sciences, vol. 2011, Article ID 425820, 16 pages, 2011
Abstract
| PDF
| BibTeX
| Full Text
We propose a novel knowledge management system (KMS) for enterprises. Our system exploits two different approaches for knowledge representation and reasoning: a document-based approach based on data-driven creation of a semantic space and an ontology-based model. Furthermore, we provide an expert system capable of supporting the enterprise decisional processes and a semantic engine which performs intelligent search on the enterprise knowledge bases. The decision support process exploits the Bayesian networks model to improve business planning process when performed under uncertainty.
-
A methodology for graphical modeling of business rules. D. Di Bona, G. Lo Re, G. Aiello, A. Tamburo, M. Alessi. In Proceedings of the Fifth UKSim European Symposium on Computer Modeling and Simulation (EMS), 2011 , pp. 102-106
Abstract
| PDF
| BibTeX
| Full Text
This work proposes a novel methodology based on the Business Process Modeling Notation (BPMN) standard capable of graphically modeling business rules. A set of new representation patterns allows business analysts to map processes described through BPMN into conditions and actions of business rules. Our approach exploits Domain Specific Language techniques in order to make the methodology independent from the programming language supported by the specific rule engine. Moreover, this work proposes a web graphical editor, instantiated on a specific sample scenario, where the selected rule engine is Drools, one of the most used open source products. The developed editor allows business analysts to graphically define business rules and to automatically generate executable code compliant with the selected rule engine. The case study and the resulting benchmarking show the effectiveness of the proposed methodology.
-
Multi-sensor fusion through adaptive bayesian networks. A. De Paola, S. Gaglio, G. Lo Re, M. Ortolani. In AI*IA 2011: Artificial Intelligence Around Man and Beyond, 2011, pp. 360-371
Abstract
| PDF
| BibTeX
| Full Text
Common sensory devices for measuring environmental data are typically heterogeneous, and present strict energy constraints; moreover, they are likely affected by noise, and their behavior may vary across time. Bayesian Networks constitute a suitable tool for pre-processing such data before performing more refined artificial reasoning; the approach proposed here aims at obtaining the best trade-off between performance and cost, by adapting the operating mode of the underlying sensory devices. Moreover, self-configuration of the nodes providing the evidence to the Bayesian network is carried out by means of an on-line multi-objective optimization
-
Reputation management for distributed service-oriented architectures. C. Crapanzano, F. Milazzo, A. De Paola, G. Lo Re. In Proceedings of the Fourth IEEE International Conference on Self-Adaptive and Self-Organizing Systems Workshop (SASOW), 2010 , pp. 160-165
Abstract
| PDF
| BibTeX
| Full Text
Nowadays, several network applications require that consumer nodes acquire distributed services from unknown service providers on the Internet. The main goal of consumer nodes is the selection of the best services among the huge multitude provided by the network. As basic criteria for this choice, service cost and Quality-of-Service (QoS) can be considered, provided that the underlying Service-Oriented Architecture (SOA) be augmented in order to support the declaration of this information. The correct behavior of such new SOA platforms, however, will depend on the presence of some mechanisms that allow consumer nodes to evaluate trustworthiness of service providers. This work proposes a new methodology for discouraging antisocial behaviors of malicious service providers that declare QoS higher than the real one. The architecture is fully distributed over the network and emulates a decentralized hierarchical trusting authority capable of managing reputation values and of providing correct QoS assessments.
-
A knowledge management system using Bayesian networks. P. Ribino, A. Oliveri, G. Lo Re, S. Gaglio. In AI*IA 2009: Emergent Perspectives in Artificial Intelligence, 2009, pp. 446-455
Abstract
| PDF
| BibTeX
| Full Text
In today's world, decision support and knowledge management processes are strategic and interdependent activities in many organizations. The companies' interest on a correct knowledge management is grown, more than interest on the mere knowledge itself. This paper proposes a Knowledge Management System based on Bayesian networks. The system has been tested collecting and using data coming from projects and processes typical of ICT companies, and provides a Document Management System and a Decision Support system to share documents and to plan how to best use firms' knowledge.
-
A knowledge management system based on ontologies. P. Ribino, A. Oliveri, G. Lo Re, S. Gaglio. In Proceedings of International Conference on New Trends in Information and Service Science, 2009, pp. 1025-1033
Abstract
| PDF
| BibTeX
| Full Text
Recently the companies' interest on a correct knowledge management is grown, more than interest on the mere knowledge itself. In the last few years, several projects have been carried out, with the aim of the development of innovative systems capable of collecting and sharing information. This paper proposes a Knowledge Management System, whose main feature is an ontological knowledge representation. The ontological representation of data allows of specializing the reasoning capabilities and of providing ad hoc behaviors. The system has been tested collecting and using data coming from projects and processes typical of ICT companies, and provides a Document Management System and an Expert System to share documents and to plan how-to best use firms' knowledge
-
Kromos: Ontology based information management for ICT societies. A. Oliveri, P. Ribino, S. Gaglio, G. Lo Re, T. Portuesi, A. La Corte, F. Trapani. In Proceedings of the 4th International Conference on Software and Data Technologies
vol. 2, 2009, pp. 318-325
Abstract
| PDF
| BibTeX
| Full Text
Over the last few years, several projects for the development of innovative systems capable of collecting and sharing information have been carried out, following the increasing companies' interest on a correct knowledge management. ICT companies' managers have realized that knowledge and its management, more than the mere data, constitute fundamental part of their activities. This paper proposes a Knowledge Management System whose main feature is an underlying ontological knowledge representation. This data representation allows the specialization of the reasoning capabilities and the provision of ad hoc behaviors. The system has been designed for the management of projects and processes and has been tested using data coming from projects and processes typical of government ICT companies, providing a Document Management System and an Expert System to share documents and to plan how to best use firms' knowledge.
-
A Networking Framework for Multi-Robot Coordination. A. Chella, G. Lo Re, I. Macaluso, M. Ortolani, D. Peri. In Recent Advances in Multi-Robot Systems, 2008, pp. 1-14
Abstract
| PDF
| BibTeX
| Full Text
-
Reputation management in distributed systems. A. De Paola, A. Tamburo. In Proceedings of the 3rd International Symposium on Communications, Control and Signal Processing, 2008. ISCCSP 2008, pp. 666-670
Abstract
| PDF
| BibTeX
| Full Text
Several distributed applications, implemented over today's Internet, are based on the assumption that participating agents collaborate in order to achieve their own goal. However, when these applications are modelled as unstructured distributed systems, the greater autonomy and decentralization encourage antisocial behaviours, which are likely to cause performance degradation for the whole system. This paper presents a fully distributed reputation management system that allows the evaluation of agent reputation in unstructured environments without any centralized coordination. The proposed approach is based on game theory and is capable of capturing the highly dynamic nature of the involved communities. As a representative example of an unstructured environment, peer-to-peer (P2P) networks are considered. Those dynamic communities are affected by several antisocial behaviours, such as free riding. Since this phenomenon typically causes and exacerbates an unbalanced and unfair use of system resources, it has been considered as the case study in our work. The proposed solution exploits peer reputations in order to define an incentive system, whose main goal is the dissuasion from free riding.
-
An efficient distributed algorithm for generating and updating multicast trees L. Gatani, G. Lo Re, S. Gaglio. In Parallel Computing, 2006, vol. 32, issue 11-12, pp. 777-793
Abstract
| PDF
| BibTeX
| Full Text
As group applications are becoming widespread, efficient network utilization becomes a growing concern. Multicast transmission represents a necessary lower network service for the wide diffusion of new multimedia network applications. Multicast transmission may use network resources more efficiently than multiple point-to-point messages; however, creating optimal multicast trees (Steiner Tree Problem in networks) is prohibitively expensive. This paper proposes a distributed algorithm for the heuristic solution of the Steiner Tree Problem, allowing the construction of effective distribution trees using a coordination protocol among the network nodes. Furthermore, we propose a novel distributed technique for dynamically updating the multicast tree. The approach proposed has been implemented and extensively tested both in simulation, and on experimental networks. Performance evaluation indicates that the distributed algorithm performs as well as the centralized version, providing good levels of convergence time and communication complexity.
-
A monitoring framework exploiting the synergy between actual and virtual wireless sensors L. Gatani, G. Lo Re, M. Ortolani, F. Sorbello. In Proceedings of the 2006 International Conference Workshops on Parallel Processing, 2006, pp. 361-367
Abstract
| PDF
| BibTeX
| Full Text
This paper describes a framework that allows realistic monitoring of a wireless sensor network in order to assess its behavior before actually deploying all the nodes. Designing a wireless sensor network for a specific application typically involves a preliminary phase of simulations that rely on specialized software, whose behavior does not necessarily reproduce what will be experienced by an actual network. On the other hand, delaying the test phase until deployment may not be advisable due to unreasonable costs. This paper suggests the adoption of a hybrid approach that involves coupling an actual wireless sensor network composed of a minimal set of actual nodes with a simulated one; we describe a software platform that, by exploiting currently available wireless sensor networks technologies, implements a superimposed communication control network thus making this approach feasible. In order to demonstrate the advantages deriving from such approach, our framework will be validated on a specific scenario dealing with geophysical monitoring for avalanches prevention.
-
A logical architecture for active network management S. Gaglio, L. Gatani, G. Lo Re, A. Urso. In Journal of Network and Systems Management, 2006, vol. 14, issue 1, pp. 127-146
Abstract
| PDF
| BibTeX
| Full Text
This paper focuses on improving network management by exploiting the potential of 'doing' of the Active Networks technology, together with the potential of 'planning,' which is typical of the artificial intelligent systems. We propose a distributed multiagent architecture for Active Network management, which exploits the dynamic reasoning capabilities of the Situation Calculus in order to emulate the reactive behavior of a human expert to fault situations. The information related to network events is generated by programmable sensors deployed across the network. A logical entity collects this information, in order to merge it with general domain knowledge, with a view to identifying the root causes of faults, and to deciding on reparative actions. The logical inference system has been devised to carry out automated isolation, diagnosis, and even repair of network anomalies, thus enhancing the reliability, performance, and security of the network. Experimental results illustrate the Reasoner capability of correctly recognizing fault situations and undertaking management actions.
-
An integrated architecture for surveillance and monitoring in an archaeological site E. Ardizzone, M. La Cascia, G. Lo Re, M. Ortolani. In Proceedings of the third ACM international workshop on Video surveillance and sensor networks, 2005, pp. 79-86
Abstract
| PDF
| BibTeX
| Full Text
This paper describes an on-going work aimed at designing and deploying a system for the surveillance and monitoring of an archaeological site, namely the 'Valley of the Temples' in Agrigento, Italy. Given the relevance of the site from an artistical and historical point of view, it is important to protect the monuments from malicious or simply incautious behavior; however, the vastity of the area to be monitored and the vague definition of its boundaries make it unpractical to provide extensive coverage through traditional sensors or similar devices. We describe the design of an architecture for the surveillance of the site and for the monitoring of the visitors' behavior consisting in an integrated framework of networked sensors and cameras. Information will be collected by a minimal set of cameras deployed only at critical spots and coupled with higher-performance wireless sensor nodes. Both sets of devices will be supported by more densely deployed lower-cost wireless sensor so that the system will fulfill the concurrent goals of being minimally intrusive and remaining both responsive and efficient. Sensed data will be processed locally whenever possible and convenient, or otherwise sent to a central intelligent unit that will perform further and more sophisticated analyses using a reasoning system, will infer a higher level representation of the outdoor environment, and finally will be able to fine-tune the action of remote devices.
-
The Random Neural Network Model for the On-Line Multicast Problem G. Aiello, S. Gaglio, G. Lo Re, P. Storniolo, A. Urso. In Biological and Artificial Intelligence Environments, 2005, pp. 157-164
Abstract
| PDF
| BibTeX
| Full Text
In this paper we propose the adoption of the Random Neural Network Model for the solution of the dynamic version of the Steiner Tree Problem in Networks (SPN). The Random Neural Network (RNN) is adopted as a heuristic capable of improving solutions achieved by previously proposed dynamic algorithms. We adapt the RNN model in order to map the network characteristics during a multicast transmission. The proposed methodology is validated by means of extensive experiments.
-
A dynamic distributed algorithm for multicast path setup L. Gatani, G. Lo Re, S. Gaglio. In Euro-Par 2005 Parallel Processing, 2005, pp. 595-605
Abstract
| PDF
| BibTeX
| Full Text
In the past few years, there has been a considerable work on multicast route selection techniques, with the aim to design scalable protocols which can guarantee an efficient use of network resources. Steiner tree-based multicast algorithms produce optimal trees, but they are prohibitively expensive. For this reason, heuristic methods are generally employed. Conventional centralized Steiner heuristics provide effective solutions, but they are unpractical for large networks, since they require a complete knowledge of the network topology. In this paper, we propose a new distributed approach that is efficient and suitable for real network adoption. Performance evaluation indicates that it outperforms the state-of-the-art distributed algorithms for multicast tree setup, providing good levels of competitiveness, convergence time, and communication complexity. Furthermore, we propose a novel distributed technique for dynamically updating the multicast tree.
-
An efficient distributed algorithm for generating multicast distribution trees L. Gatani, G. Lo Re, S. Gaglio. In Proceedings of the International Conference Workshops on Parallel Processing, 2005. ICPP 2005 Workshops, pp. 477-484
Abstract
| PDF
| BibTeX
| Full Text
Multicast transmission may use network resources more efficiently than multiple point-to-point messages; however, creating optimal multicast trees (Steiner Tree Problem in Networks) is prohibitively expensive. For this reason, heuristic methods are generally employed. Conventional centralized Steiner heuristics provide effective solutions, but they are unpractical for large networks, since they require complete knowledge of the network topology. This paper proposes a distributed algorithm for the heuristic solution of the Steiner Tree Problem. The algorithm allows the construction of effective distribution trees using a coordination protocol among the network nodes. The algorithm has been implemented and extensively tested both in simulation, and on experimental networks. Performance evaluation indicates that our algorithm performs as well as the centralized version, providing good levels of convergence time and communication complexity. Moreover, the proposed approach outperforms the state-of-the-art distributed algorithms for multicast tree setup.
-
An efficient distributed approach for dynamic multicast trees L. Gatani, G. Lo Re. In Proceedings of the 3rd International Conference on Information Technology: Research and Education, 2005. ITRE 2005, pp. 188-194
Abstract
| PDF
| BibTeX
| Full Text
In this paper we present a distributed algorithm for constructing efficient multicast trees in large networks. The algorithm allows the set up of effective distribution trees using a coordination protocol among the network nodes. The algorithm has been implemented and extensively tested both in simulation, and on experimental networks. Performance evaluation indicates that our approach outperforms the state-of-the-art distributed algorithms for multicast tree setup, providing good levels of convergence time and communication complexity. Furthermore, we introduce a distributed technique for dynamically updating the multicast tree. The approach monitors the accumulated damage as nodes join or leave, and it triggers a "stirring" process that locally rearranges the tree, when its degradation exceeds a given threshold.
-
Rule based reasoning for network management A. De Paola, S. Fiduccia, S. Gaglio, L. Gatani, G. Lo Re, A. Pizzitola, M. Ortolani, P. Storniolo, A. Urso. In Proceedings of the Seventh International Workshop on Computer Architecture for Machine Perception, 2005, pp. 25-30
Abstract
| PDF
| BibTeX
| Full Text
This paper focuses on improving network management by the adoption of artificial intelligence techniques. We propose a distributed multi-agent architecture for network management, where a logical reasoner acts as a managing entity capable of directing, coordinating, and triggering monitoring and management actions in the proposed architecture. The logical inference system has been devised to enable automated isolation, diagnosis, and to repair network anomalies, thus enhancing the reliability, performance, and security of the network. The measurements of network events are captured by programmable sensors deployed on the network devices and are collected by the network management entity where they are merged with general domain knowledge, with a view to identifying the root causes of anomalies, and to decide on reparative actions. The relevant results inferred by the logical reasoner and the significant events occurred on the network are stored both in a global DB and in local distributed DBs, in order to enable successive analyses of network events. In order to illustrate the advantages and potential benefits deriving from the reasoning capabilities of our management system, the results of preliminaries experiments are analyzed.