Mario Veniero

Agent-based Cognitive approach to Airport Security Situation Awareness

Situation awareness is crucial factor in decision-making. It involves monitoring and identification of relationships among objects in collaborative dynamic environments. In the domain of Airport Security one of the main needs is to support the security operator to manage in real-time risk scenarios in the airside. This work relies on a cognitive approach to model the awareness ontology and introduces an agent-based architecture to address the problem. In particular, in order to model situation awareness the work instantiates the generic Situation Theory Ontology(STO) in the specific domain of airport security. Furthermore, some task-oriented agents allow to distribute the information in order to achieve better performances.

Towards an agent-based architecture for managing uncertainty in situation awareness

In computing, Ambient Intelligence (AmI) refers to electronic environments that are sensitive and responsive to the presence of people. The ambient intelligence paradigm is characterized by systems and technologies founded on a situational computing and, more generally, situation awareness substratum dealing with situational context representation and reasoning. At the same time, the global information infrastructure is becoming more and more pervasive and human computer interactions are performed in diverse situations, using a variety of mobile devices and across multiple communication channels. Nevertheless, recent advances in multi-sensors systems, multimodal access has yet to develop its full potential, due to imperfect observations, time-dependence of multimedia predicates, and to difficulties in conjoining facts coming from different modal streams. Hence, the knowledge upon which the context/situation aware paradigm is built is rather vague. To deal with this shortcoming, in this paper we propose a distributed architecture aimed at identifying and reasoning about the current situation of involved entities. Specifically, this work presents an hybrid architecture attaining a synergy among Agent Paradigm (AP), Situation Theory (ST) and semantic fuzzy modeling to efficiently support situation awareness in uncertain environments.

Applying cognitive situation awareness to collision avoidance for harbour last-mile area safety

Maneuvering ships in harbour areas is recognized as one of the most complex activity to be carried out Le (An automatic control system for ship harbour maneuvers using decoupling control. In: IEEE International Conference on Robotics and Automation, 2001. Proceedings 2001 ICRA 2:2108–2113, 2001) as a consequence of all information needs related to safety maintenance during guidance and control activities. By taking advantage of existing results, in this work we argue how situation awareness could be a leading and valuable technology to support decision making activities in this application. In particular, we propose the usage of a decentralized, autonomous, agent-based cognitive situation awareness framework, yet successfully experimented for airport safety monitoring and specifically modified to be applied to the maritime domain. The proposed framework exploits sensor network acquired streamed data management activities, together with semantic technologies and uncertainty management methods. The resulting architecture is aimed at monitoring ongoing situations and forecasting potential collisions, identifying involved entities and relations in order to improve the ability of maneuvering operators in assessing the current situations and their possible evolutions. Results and performances will be verified at the Port of Salerno, in order to show that information supporting inferred situations comply with real needs of decision making activities to prevent collisions during daily operations.

Searching optimal product bundles by means of GA-based Engine and Market Basket Analysis

The product bundling problem is a challenging task in the e-Commerce domain. We propose a generative engine in order to find the bundle of products that best satisfies user requirements and, at the same time, seller needs such as the minimization of the dead stocks and the maximization of net income. The proposed system named Intelligent Bundle Suggestion and Generation (IBSAG) is designed in order to satisfy these requirements. Market Basket Analysis supports the system in user requirement elicitation task. Experimental results prove the ability of system in finding the optimal tradeoff between different and conflicting constraints.

Computer Crime Investigation by Means of Fuzzy Semantic Maps

This work introduces an architecture for data mining and knowledge discovery, applied in a effective real world domain, i.e. computer forensics and digital evidence. The approach integrates Computational Intelligence techniques and Semantic Web methodologies in a distributed agent-based environment. The system elicits conceptual representation of textual resources and generates an automatic catalogue, whose categories evolve in a continuous learning process.

A multi-layered agent ontology system for resource inventory

Nowadays, worldwide public utility services providers feel the necessity of new flexible and scalable solutions aimed at managing their distribution networks and services. This is fundamentally due to the continuously technological evolution of distribution network infrastructures that impacts deeply on the software in charge of handling the services supply chain management. The purpose of this paper is to present an innovative system aimed at defining a new approach to resource inventory. This approach is designed both to reduce the influence of infrastructure evolution and to enable value-added services performed by autonomous intelligent agents. Based on the integration of semantic web technologies and agents paradigm, the systempsilas mission is to define a new ontology-based model for resource inventory. Moreover, the system defines a new behavioral model enabling software agents to effectively react to the network environment in which they are embedded.

Semantic based events signaling for AAL systems

The synergistic cooperation of a set of different devices is still one of the major open issues in designing the new generation of collaborative AAL system. To contribute to fill this gap, this paper introduces Semantic Events Notifier (SEN), a lightweight prototype of semantic-based and agent-oriented middleware that aims to provide near real-time events notification among all the enabled devices of an AAL system. The idea behind this research work goes in the direction to find scalable technological solution to answer the continued growth of objects connected to the IoT network, in particular, within the domestic environment. SEN enables the involved Smart Objects to cooperate synergistically based on a shared semantic model, thus contributing to support various tailored services that assist elderly users or users with disabilities for a better and healthier life in their preferred living environment. Moreover, a prototype of the platform has been implemented and validated to prove the correctness of the approach. Finally, the evaluation of its quality of service requirements in terms of latency, efficiency, and scalability has been conducted in a real case study by means of a defined benchmark.

Semantic Knowledge Management and Integration Services for AAL

The integration of a set of heterogeneous data streams coming from different source into a coherent scheme is still one of the key challenges in designing the new generation of AAL system enabling the Smart Home. This paper introduces a service-oriented platform that aims to enhance data integration and synchronization between physical and virtual components of an AAL system. The idea behind this research work goes in the direction to find scalable technological solution in order to answer the continued growth of objects (Things) connected to the network within the domestic environment. Thus, the Smart Objects can operate synergistically on the basis of a shared semantic model, supporting various tailored services that assist elderly users or users with disabilities for a better and healthier life in their preferred living environment. Moreover, a prototype of the platform has been implemented and validated in order to prove the correctness of the approach and conduct a preliminary performance evaluation.

Customized Advertising in E-Commerce Services Provision

While traditional marketing is product-focused, e-commerce market is specifically oriented to the customers. The challenge in e-commerce is to actually get the Internet users interest and customize answers according to his requirements. Recommendations and hints in a form of banner ads or advertising messages not only provide the opportunity of selling products, but also help enterprises to target the right customers with the proper products or services. Starting from this key point, this paper introduces a web-centric system for e-commerce services, which offers ad-hoc advertisements to users during their navigation. In order to address these issues, the system analyzes the asset marketing of the web enterprises for connect advertising to the targeted customer groups. Through an agent-based architecture and fuzzy techniques, the system provides a simple support to an e-commerce market mediation.

Fuzzy pro-active agents as key issue to increase traffic safety for next generation tunnels

Nowadays, in Europe tunnel safety is a problem of great interest. Recent tragic events have led community and national politicians to start a process of legislation harmonization planning investments toward new technologies designed to improve tunnel safety. The purpose of this paper is to present an innovative system aiming at monitoring and steering vehicular flows nearby tunnels with high accidents risk rate. Based on the integration of IC, video, agent and soft computing technologies, the systems mission is to reduce the risk of accidents which occur inside tunnel through the adaptive generation of speed limits and information to the users approximating tunnels. Strict real-time requirements of the applicative context impose our goal being achieved through a parallel hierarchical fuzzy controller (HFC) implemented by means of a fuzzy control agents network (FCAN) allowing the system to gain higher performances. The fuzzy controller is divided into several sub controllers conceived separately. Some of these, adopt in turn a hierarchical prioritized structure.