I-Gaia: an information processing layer for the DIET platform

In this paper we introduce one application layer for information processing in the DIET platform, a MAS development platform. This application layer is basically formed of three types of agents, here called "infocytes", designed to cater for the information needs of information providers, requesters and brokers. We have also defined and implemented under I-Gaia two separate tasks using the well-known Reuters text-classification corpus: an information-pull and an information-push task, mainly to validate the ability of such layer to effectively retrieve information on demand or spontaneously route it to users. We have also analysed the performance achieved using measurements based on precision/recall. The results show that the I-Gaia environment is completely operative and that can achieve this type of tasks without loosing performance with respect to other centralised, non-agent-based technologies with full information about the task.

[1]  Katia P. Sycara,et al.  Designing behaviors for information agents , 1997, AGENTS '97.

[2]  John C. Platt,et al.  Fast training of support vector machines using sequential minimal optimization, advances in kernel methods , 1999 .

[3]  Harry L. Van Trees,et al.  Detection, Estimation, and Modulation Theory: Radar-Sonar Signal Processing and Gaussian Signals in Noise , 1992 .

[4]  Stephen E. Robertson,et al.  The TREC-8 Filtering Track Final Report , 1999, TREC.

[5]  Daphne Koller,et al.  Support Vector Machine Active Learning with Application sto Text Classification , 2000, ICML.

[6]  Vipul Kashyap,et al.  InfoSleuth: agent-based semantic integration of information in open and dynamic environments , 1997, SIGMOD '97.

[7]  Thorsten Joachims,et al.  Text Categorization with Support Vector Machines: Learning with Many Relevant Features , 1998, ECML.

[8]  Thomas L. Marzetta,et al.  Detection, Estimation, and Modulation Theory , 1976 .

[9]  M. Ángeles Zarco Tejada.  Reseña de Varile. G. B. y A. Zampolli (eds) (1997): Survey of the State of the Art in Human Language Technology. Linguistica Computazionale. vol. XII-XIII. Giardini Editori e Stampatori in Pisa., Pisa, Italy. , 1997 .

[10]  Thorsten Joachims,et al.  Transductive Inference for Text Classification using Support Vector Machines , 1999, ICML.

[11]  George Karypis,et al.  Centroid-Based Document Classification: Analysis and Experimental Results , 2000, PKDD.

[12]  Manolis Koubarakis,et al.  Agents in decentralised information ecosystems:the diet approach , 2001 .

[13]  Patrick van Bommel,et al.  Cumulative Duality in Designing Information Brokers , 1998, DEXA.

[14]  Nicolas Lhuillier,et al.  FOUNDATION FOR INTELLIGENT PHYSICAL AGENTS , 2003 .

[15]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[16]  Nicholas J. Belkin,et al.  Information filtering and information retrieval: two sides of the same coin? , 1992, CACM.