Fabio Abbattista

An agent that learns to support users of a Web site

The terms agent, intelligent agent and 3D agent are becoming more and more frequently used in literature. A key issue in the web community is that a web site must be equipped with a virtual agent able to support users in a natural way. Following this trend, we decided to implement scenographic agents mimic intelligent reasoning (SAMIR), a prototype of a tool for animating 3D intelligent agents, mainly founded on a genetic algorithms-based learning system, namely an XCS, and on an FFD-based technique for the facial deformation of the character. SAMIR is based on an object-oriented architecture, and it adopts the MPEG-4 facial animation parameters (FAPs) as a description format for facial expressions and animations.

Analyzing the application of a reverse engineering process to a real situation

A reverse engineering process model was applied and, on the basis of the data collected, some modifications were made aiming to improve its efficacy. The experience gave rise to various considerations of interest, first among them being the clear interaction between the quality of the product and the quality of the process. A method of synergetic application of static and dynamic analysis to improve understanding of the program was consolidated. The experience enabled modifications to be introduced connecting the reverse engineering process more closely with the understanding of the programs and information deriving from the application domain. Finally, the problem of the efficacy of the tools used to obtain the reverse engineering products was made evident during the experimentation on the field.<<ETX>>

Incorporating social software into distributed agile development environments

The use of social software applications, such as wikis and blogs, has emerged as a practical and economical option to consider as global teams may use them to organize, track, publish their work, and then, share knowledge. We intend to push further the application of social software principles and technologies into collaborative development environments for agile and distributed projects. As a first step, in this paper we first present a survey of social software, as well as tools and environments for collaborative development. Then, we present some opportunities and challenges of incorporating social software aspects in agile distributed development.

Evaluation and validation of a conversational agent embodied in a bookstore

This work presents an agent-based interface that is not merely reactive to some user request, but is proactive since it is capable of engaging in a goal-directed conversation with the user, e.g., by taking the initiative to recommend new products. The naturalness of interaction, especially for casual users, is enhanced by appropriate 2D facial models. The proactiveness of the agent is based on a recommendation engine that combines content-based retrieval, which exploits user profiles based on content features extracted from the dialogue and descriptions of items that users find relevant, with collaborative filtering, which clusters users according to their expressed taste to generate recommendations within these virtual communities. The proposed system has been evaluated and validated by using a top-down approach, focusing on the system/user interaction.

Learning Interaction Models in a Digital Library Service

We present the exploitation of an improved version of the Learning Server for modeling the user interaction in a digital library service architecture. This module is the basic component for providing the service with an added value such as an essential extensible form of interface adaptivity. Indeed, the system is equipped with a web-based visual environment, primarily intended to improve the user interaction by automating the assignment of a suitable interface depending on data relative to the previous experience with the system, coded in log files. The experiments performed show that accurate interaction models can be inferred automatically by using up-to-date learning algorithms.

An evolutionary approach to training relaxation labeling processes

In a recent work, a learning procedure for relaxation labeling algorithms has been introduced which involves minimizing a certain cost function with classical gradient methods. Although the results obtained so far are extremely promising, the gradient-based learning algorithm suffers from some inherent drawbacks that could prevent its application to real-world problems of practical interest. Essentially, these include the inability to escape from local minima and its computational complexity. In this paper, we propose using genetic algorithms to solve the relaxation labeling learning problem in an attempt to overcome the difficulties with the gradient algorithm. Experiments are presented which demonstrate the superiority of the proposed approach both in terms of quality of solutions and robustness.

Evolutionary Learning for Relaxation Labeling Processes

Relaxation labeling processes are a class of parallel iterative procedures widely used in artificial intelligence and computer vision. Recently, a learning algorithm for relaxation labeling has been developed which involves minimizing a certain cost function with a gradient method. Despite the encouraging results obtained so far, the gradient algorithm suffers from some drawbacks that could prevent its application to practical problems. Essentially, these include the inability to escape from local minima and its computational complexity. In this paper we attempt to overcome the difficulties with the gradient procedure and propose the use of genetic algorithms for solving the learning problem of relaxation. Some results are reported which prove the effectiveness of the proposed approach.

Intelligent E-Commerce with Guiding Agents Based on Personalized Interaction Tools

This chapter presents an agent-based interface for business-to-customer (B2C) applications that is not merely reactive to some user request, but proactive and capable of engaging in a goal-directed conversation with the user, e.g. by taking the initiative to recommend new products. The approach combines content-based filtering, where user profiles are generated based on content features extracted from documents that users find relevant, with collaborative filtering which clusters users according to their expressed taste to generate recommendations within these virtual communities. In addition, the naturalness of interaction, especially for casual users, is enhanced by appropriate 2D and 3D animations that express the agent’s emotional reactions.

User brain-driven evaluation of an educational 3D virtual environment

In evaluating interactive systems, several attempts have been made to broaden the traditional focus on the efficient achievement of goals and incorporate an understanding of additional aspects linked to the User eXperience (UX). In this direction, usability tests also based on the users emotional level should be performed. This requires the introduction of suitable methods which can capture and convert subjective feelings into concrete design parameters. In this paper we propose a user-centered approach to the evaluation of the UX in a 3D Educational Virtual Environment, in which the user is required to explore reconstructions of cultural places and to solve games for educational purposes by using innovative controllers. We employ a commercial Brain Computer Interface to collect information on the users feelings. The preliminary results of this research show that our method allows the identification of elements that do not result in high subject agreement in terms of elicited emotions. Moreover, it provides the opportunity to redesign the environment. The domain-independent nature of the presented approach allows designers to apply it in a wide range of 3D interactive environments, such as games and serious games, training simulators, etc.

Shaping personal information spaces from collaborative tagging systems

The appearance of powerful tools for lightweight metadata creation, such as collaborative tagging systems, is harnessing the power of online communities, although such metadata are limited to human consumption only. In this paper we first propose an abstract model for representing a generic collaborative tagging system which uses RDF as the underlying technology to store metadata created by different online communities. Then, we present a scenario with the purpose of illustrating how a service able to retrieve tags from different folksonomies can support users in the organization of their personal information spaces within the context of a digital library.