Publicações 

  Aprender a Aprender: Sistema Tutor Inteligente

1999

[1] Hugo Gamboa. Aprender a aprender, Sistema tutor inteligente implementado na Internet usando redes bayesianas, Em Fourth Workshop on Biomedical Engineering, Ana Fred (Editor), IST, DEEC, Agosto de 1999

SUMÁRIO :: Este documento apresenta o sistema tutor inteligente Aprender a aprender, implementado na internet sobre o domínio da aprendizagem usando redes bayesianas para a adaptação ao utilizador. A implementação do sistema é dividida em dois blocos, a plataforma de desenvolvimento e o domínio específico. A plataforma de desenvolvimento é a união dos componentes: modelo do utilizador, base de conhecimento, módulo de adaptação, módulo pedagógico e módulo de apresentação. As redes bayesianas são usadas para fazer adaptação ao utilizador, sequenciamento curricular e escolha do conhecimento a apresentar
.doc

 

 An evolutionary multi-agent system for simulating  e-commerce markets

2001

[2] Nuno Valero Ribeiro, Hugo Gamboa. An evolutionary multi-agent system for simulating e-commerce markets. 1st Enterprise Networking Applications and Services Conference,  EntNet2001, Atlanta USA.

Sumário: This paper describes a multi-agent system used for simulating a generic e-trading market. The simulated market is imagined to be on the Internet. Four different types of agents are used in our system: clients, producers, distributors and mediators --- for clients and  producers. The simulation starts with an initially given market which evolves under various assumptions about mediators. Mediation services support the following aspects: brokerage, billing, delivery and connectivity. Each mediator has a profile based on its degree of greediness, effort and speed. The evolution of the system is controlled by the individual fitness of the mediator agents. Those that profit from their negotiations stay alive, while others die. The most successful mediators are cloned and populate the system. Thus, the system evolution helps with identifying the appropriate mediator profiles. Internal implementation choices are discussed and analyzed. Results from an experiment using a typical market scenario are presented to illustrate the system in use.
 
.ps

 

  An e-learning Platform Concept

2001

[3] Hugo Gamboa, Nuno Valero Ribeiro, Anatol Holt, Ana Fred. An e-learning Platform Concept,  2a Conferência Internacional em Tecnologias de Informação e Comunicação na Educação: Chalanges 2001.

Abstract: In this paper we describe an e-learning platform concept-a new approach for the learning/teaching activity in an academic environment. Our perspective of e-learning is based on the organizational reality which involves the learning/teaching activity, therefore, adapted to the physical environment and human relations present in real schools. We envision three type of users-students, teachers and maintainers-their roles and levels of interaction with the platform being outlined. Three main functional requirements are identified, underling the platform concept, namely: (a) coordination-of a group of users under the baton of one user; (b) communication-between different users; knowledge transfer-from the teacher to his students. The platform implementation is undergoing and it will be tested in three courses. Future directions for e?learning and the proposed platform are discussed focusing on the integration of tutoring facilities and on the e-school concept.
.ps

 

  Designing Intelligent Tutoring Systems: a Bayesian Approach

2001

[4] Hugo Gamboa, Ana Fred. Designing Intelligent Tutoring Systems: a Bayesian Approach. 3rd International Conference on Enterprise Information Systems, ICEIS'2001.

Abstract: This paper proposes a model and an architecture for designing intelligent tutoring system using Bayesian Networks. The design model of an intelligent tutoring system is directed towards the separation between the domain knowledge and the tutor shell. The architecture is composed by the user model, the knowledge base, the adaptation module, the pedagogical module and the presentation module. Bayesian Networks are used to assess user's state of knowledge and preferences, in order to suggest pedagogical options and recommend future steps in the tutor. The proposed architecture is implemented in the Internet, enabling its use as an e-learning tool. An example of an intelligent tutoring system is shown for illustration purposes.
.pdf

 

  WIDAM - Web Interaction Display and Monitoring

2003

[5] Hugo Gamboa, Vasco Ferreira. WIDAM - Web Interaction Display and Monitoring. 5th International Conference on Enterprise Information Systems, ICEIS'2003.

Abstract: In this paper we describe the design and implementation of a system called Web Interaction Display and Monitoring (WIDAM). We have developed a web based client-server application that offers several services: (i) real time monitoring of the user interaction to be used in synchronous playback (Synchronous Monitoring Service) (ii) real time observation by other users (Synchronous Playback Service); (iii) storage of the user interaction information in the server database (Recording Service); (iv) retrieval and playback of a stored monitored interaction (Asynchronous Playback Service).WIDAM allows the usage of an interaction monitoring system directly over a web page, without the need of any installation, using low bandwidth comparatively to image based remote display systems. We discuss several applications of the presented system like intelligent tutoring systems, usability analysis, system performance monitoring, synchronous or asynchronous e-learning tools.
.pdf

 

 

  An Identity Authentication System Based on Human Computer Interaction Behaviour

2003

[6] Hugo Gamboa, Ana Fred. An Identity Authentication System Based on Human Computer Interaction Behaviour. Aceite para publicação na 3rd Workshop on Pattern Recognition in Information Systems PRIS 2003.

Abstract: Human behaviour has been used in biometrics. In this paper we describe a new behavioural biometric technic based on human computer interaction. We developed a system that captures the user interaction via a pointing device, and uses this behavioural information to verify the identity of an individual. Using statistical pattern recognition technics, we developed a sequential classifier that processes user interaction, according to which the user identity is considered genuine if a predefined accuracy level is achieved, and the user is classified as an impostor otherwise. We found that the normal user interaction with the computer entails discriminant information, useful for creating a behavioural biometric identity authentication system. The paper presents experimental results revealing that our system can achieve good performance in the collected interaction information.
.ps

 

 

  A User-Centred Feature Selection Approach to Personal  Authentication Exploring Computer Interaction Behaviour

2003

[7] Hugo Gamboa, Ana Fred. A User-Centred Feature Selection Approach to Personal Authentication Exploring Computer Interaction Behaviour. Aceite para publicação na 4th International Conference on Audio and Video-based Biometric Person Authentication 2003

Abstract. Human behaviour has been used in biometrics. In this paperwe propose a new behavioural biometric technic based on human computer interaction. We developed a system that captures the user interaction via a pointing device, and uses this behavioural information to verify the identity of an individual. Using statistical pattern recognition technics, we designed a sequential classifier that processes user interaction, and according to which the user identity is considered genuine, if a predefined accuracy level is achieved, or the user is classified as an impostor otherwise. Experimental results show that the normal user interaction with the computer has discriminating power, as measured by the global equal error rate, used to assess the performance of the behavioural biometric identity authentication system. Exploration of feature selection techniques reveals that better performances are achieved by the introduction of user specific features. Preliminary results show that the proposed technique is a promising tool for user authentication. Furthermore, it is an inexpensive authentication technique, that uses standard human-computer interaction devices, and remotely accesses user behavioural information through the world wide web.
.ps