Intelligent Decision Technologies

In this paper we describe the information-gathering problem which can be characterized as transforming large amounts of data obtained from sensors into accurate, concise, timely and meaningful information that can be used by decision makers faced with a specific task and a number of options for performing that task. The approach to this information-gathering problem as described here consists of three phases: data validation, data aggregation and abstraction, and information interpretation. Each of these phases will be described in general, and for each of these phases we describe techniques that are reasonably generic to be applicable in many domains, but domain specific knowledge will of course always be needed too.

Modern information systems are required to operate in distributed and dynamic environments. In such open settings, coordination technologies play a crucial role in the design of flexible software systems. Research efforts in different areas are converging to devise suitable mechanisms for process and peer coordination: in particular, current results on service-oriented computing and multi-agent systems are being integrated to support dynamic decision-making processes among autonomous components in large, open systems. This paper addresses how agent technologies can be designed, applied, and eventually integrated with standard technologies, in order to build more robust and intelligent systems. The focus of our research is on the engineering, exploitation and evaluation of an agent protocol language in realistic contexts. In particular, a specific executable protocol language is adopted to specify simulated interactions among distributed processes which will be tested in emergency response domain activities (that we will refer to hereafter as e-Response activities), chosen as an example of knowledge-intensive and dynamic application domain where intelligent decision making is crucial. We present a novel approach based on shared protocols models distributed through a peer-to-peer infrastructure and we show how it can be applied in the context of crisis management to support coalition formation and process coordination in open environments. Specifically, a prototype e-Response simulation system – built on a Peer-to-Peer (P2P) infrastructure – has been developed to execute interaction models describing common coordination tasks in the emergency response domain. Preliminary evaluation of the proposed framework demonstrates its capability to support such e-Response tasks.

The paper presents an approach and the supporting software tools for integration of intelligent multi-agent systems and the peer-to-peer (P2P) technologies to support the development of heterogeneous distributed decision making applications operating in dynamic ubiquitous environment. Particularly, the proposed technology integrates two software tools, MASDK 4.0 software tool and a P2P agent platform. MASDK 4.0 is provided with a graphical application specification language that supports the thorough and consistent conceptual analysis, detailed design, code generation and deployment of multi-agent systems applications including those operating in dynamic environments. P2P agent platform is a FIPA compliant middleware enabling transparent P2P interaction of agents operating in heterogeneous and ubiquitous environment. The platform is fully compatible with the multi-agent applications developed by MASDK 4.0. The combined application of MASDK 4.0 and P2P agent platform is demonstrated by a case study of the air traffic control and emergency management. In this case study a model of autonomous air traffic control is implemented by a set of distributed intelligent agents. This application is a typical example of a modern agent-based distributed decision making system operating in a dynamic P2P environment.

Neurobiologically inspired algorithms for exploiting track data to learn normal patterns of motion behavior, detect deviations from normalcy, and predict future behavior are presented. These capabilities contribute to higher-level fusion situational awareness and assessment objectives. They also provide essential elements for automated scene understanding to shift operator focus from sensor monitoring and activity detection to behavior assessment and response decision-making. Our learning algorithms construct models of normal activity patterns at a variety of conceptual, spatial, and temporal levels to reduce a massive amount of track data to a rich set of information regarding the current status of active entities within an operator's field of regard. Continuous incremental learning enables the models of normal behavior to adapt well to evolving situations while maintaining high levels of performance. Deviations from normalcy result in notification reports that can be published directly to operator displays. Deviation tolerance levels are user settable during system operation to tune alerting sensitivity. Operator responses to anomaly alerts can be fed back into the algorithms to further enhance and refine learned models. These algorithms have been successfully demonstrated to learn vessel behaviors across the maritime domain and to learn vehicle and dismount behavior in land-based settings.

It is well-known that human roles within and across organizations have to cooperate during a disaster. During Tsunami in Asia in 2004, more than one hundred organizations were working at a point of time in Banda Aceh area of Indonesia. Although many of the state agencies, e.g., Federal Emergency Management Agency (FEMA) in USA have well-developed processes for managing such events, people within these organizations have to coordinate with many Non Government Organizations (NGOs) from various countries. Hence full automation of these situation management processes is not possible. Therefore, such processes have to use Computer Supported Cooperative Work (CSCW) where information technology artifacts support cooperation. But it is important to measure cooperation to implement any cooperative management (situation management using CSCW) system for disaster situations. This paper presents a novel attempt to address this issue with a generic concept model, called fuzzy awareness model.