Yanira de Paz

Social-based planning model for multiagent systems

An idea that seems to be gaining considerable ground is that modeling the interactions of a multi-agent system cannot be related exclusively to the actual agent and its communication capabilities, but must involve the use of concepts found in organizational engineering as well. It is possible to establish different types of agent organizations according to the type of communication, the coordination among agents, and the type of agents that comprise the group. Each organization needs to be supported by a coordinated effort that explicitly determines how the agents should be organized and carry out the actions and tasks assigned to them. This research presents a new global coordination model for an agent organization. The primary novelty of the model consists of the dynamic and adaptive planning capability to distribute tasks among the agent members of the organization as effectively as possible. This model is unique in its conception, allowing an organization in a highly dynamic environment to employ self-adaptive capabilities in execution time. This allows for the behavior of an agent to be determined by the goals it wishes to reach, while still giving consideration to the goals of other agents and any changes in the environment. The model is evaluated in a multi-agent system developed within an architecture oriented toward THOMAS organizations and simulated in a virtual environment.

SHOMAS: Intelligent guidance and suggestions in shopping centres

This paper introduces the SHOMAS Multiagent System that provides guidance on leisure facilities and suggestions for shopping in malls. The multiagent architecture incorporates reactive and deliberative agents that take decisions automatically. The developed deliberative agent provides suggestions in execution time, with the help of case-based planners. This agent is described together with its guidance and suggestion mechanism. SHOMAS has been tested successfully, and the results obtained are presented in this paper.

An execution time planner for the ARTIS agent architecture

The purpose of this paper is to present an approach for integrating new complex deliberative behaviours in a real-time agent architecture, specifically in the ARTIS agent architecture, which is specially designed for hard real-time environments. The new deliberative agent proposed remakes its plans at runtime conserving the system integrity and its real-time feature. The proposed system has been successfully tested in a robotic test environment. This environment consisted of the automated management of the internal and external mail in a department plant, where the main goal was to ease the workload of a mail-robot. The results obtained increased the flexibility and adaptability of the real-time agent while retaining the temporal restrictions.

Context-aware multiagent system: Planning home care tasks

Context-aware systems are able to capture information from the context in which they are executed, assign a meaning to the gathered information, and change their behavior accordingly. As a result, the systems can offer services to users according to their individual situation within the context. This article analyzes the important aspects of context-aware computing such as capturing information for context attributes and determining the manner of interacting with users in the environment. Used in conjunction with mobile devices, context-aware systems are specifically used to improve the usability of applications and services. This article proposes the home care context-aware computing (HoCCAC) multiagent system that identifies and maintains a permanent fix on the location of patients in their home, and manages the infrastructure of services within their environment securely and reliably by processing and reasoning the data received. Based on the multiagent system, a prototype was developed to monitor patients in their home. The HoCCAC multiagent system uses a critical path method-based planning model that, in the present study, prepares the most optimal task-planning schedule for the patients in their home, is capable of reacting automatically when faced with dangerous or emergency situations, replanning any plans in progress and sending alert messages to the system. The results obtained with this prototype are presented in this article.

SMas: a shopping mall multiagent systems

This paper presents a multiagent model that facilitates aspects of shopping mall management, as well as increasing the quality of leisure facilities and shopping on offer. The work presented focuses on the use of a multi agent architecture, based on the use of deliberative agents that incorporates case-based planning. The architecture considers a dynamic framework, and the need to use autonomous models that are able to evolve over time. The architecture incorporates agents whose aim is to acquire knowledge and adapt themselves to the environmental changes. The system has been tested successfully, and the results obtained are presented in this paper.

A CBR System: The Core of an Ambient Intelligence Health Care Application

This paper presents a case-based reasoning system developed to generate an efficient and proactive ambient intelligent application. Ambient Intelligence (AmI) proposes a new way to interact between people and technology, where this last one is adapted to individuals and their context (Friedewald and Da Costa 2003). The objective of Ambient Intelligence is to develop intelligent and intuitive systems and interfaces capable to recognize and respond to the user’s necessities in a ubiquitous way, providing capabilities for ubiquitous computation and communication, considering people in the centre of the development, and creating technologically complex environments in medical, domestic, academic, etc. fields (Susperregui et al. 2004). Ambient Intelligence requires new ways for developing intelligent and intuitive systems and interfaces, capable to recognize and respond to the user’s necessities in a ubiquitous way, providing capabilities for ubiquitous computation and communication. The multi-agent systems (Wooldridge and Jennings 1995) have become increasingly relevant for developing distributed and dynamic intelligent environments. A case-based reasoning system (Aamodt and Plaza 1994) has been embedded within a deliberative agent and allows it to respond to events, to take the initiative according to its goals, to communicate with other agents, to interact with users, and to make use of past experiences to find the best plans to achieve goals. The deliberative agent works with the concepts of Belief, Desire, Intention (BDI) (Bratman 1987), and has learning and adaptation capabilities, which facilitates its work in dynamic environment.

A Multiagent Based Strategy for Detecting Attacks in Databases in a Distributed Mode

This paper presents a distributed hierarchical multiagent architecture for detecting SQL injection attacks against databases. It uses a novel strategy, which is supported by a Case-Based Reasoning mechanism, which provides to the classifier agents with a great capacity of learning and adaptation to face this type of attack. The architecture combines strategies of intrusion detection systems such as misuse detection and anomaly detection. It has been tested and the results are presented in this paper.

Classification Agent-Based Techniques for Detecting Intrusions in Databases

This paper presents an agent specially designed for the prevention and detection of SQL injection at the database layer of an application. The agent incorporates a Case-based reasoning mechanism whose main characteristic involves a mixture of neural networks that carry out the task of filtering attacks. The agent had been tested and the results obtained are presented in this study.

TaskCBP: an intelligent agent for task planning in elderly care

This paper presents an autonomous intelligent agent developed for healthcare in geriatric residences. The paper focuses on the role of ambient intelligence in the automation of healthcare services. The work here presented shows the development of an autonomous agent, TaskCBP, which incorporates a model of human thinking, such as reasoning based on past experiences. The planning mechanism integrated within the agent has been implemented by means of a novel QSOR neural network. The system has been tested and this paper presents the results obtained.

An Attack Detection Mechanism Based on a Distributed Hierarchical Multi-agent Architecture for Protecting Databases

This paper presents an innovative approach to detect and classify SQL injection attacks. The existing approaches are centralized while this proposal is based on a distributed hierarchical architecture to provide a robust and dynamic strategy. The strategy for the classification and detection of SQL injection attacks uses a combination based on detection by anomalies and misuses. The detection by anomaly uses a case-based reasoning mechanism incorporating a mixture of neural networks. The approach has been tested and the results are presented in this paper.