Title :
TROJAN: a scalable distributed semantic network system
Author :
Lee, Chain-Wu ; Huang, Chun-Hsi ; Rajasekaran, Sanguthevar
Author_Institution :
Dept. of Comput. Sci. & Eng., State Univ. of New York, New York, USA
Abstract :
This paper describes a new parallel semantic network system, the TROJAN. Unlike the synchronous and static marker passing algorithm previously used for parallel semantic network design, the TROJAN operates asynchronously, supporting knowledge sharing, dynamic load balancing and duplicate checking. Current implementation of the TROJAN focuses on path-based knowledge inferences, using ANSI C and the MPICH-G2 with flex lexical analyzer and the yacc parser generator. The performance tests have been carried out on a local Grid, consisting of three heterogeneous systems: a SUN Cluster, an SGI Origin 3800, and a Dell Pentium cluster. The experiments demonstrate promising speedups.
Keywords :
computational complexity; inference mechanisms; resource allocation; semantic networks; ANSI C; Dell Pentium cluster; MPICH-G2; NP-hardness; SGI Origin 3800; SUN cluster; TROJAN; duplicate checking; dynamic load balancing; flex lexical analyzer; knowledge inference; knowledge sharing; local grid; parallel networks; performance test; scalable distributed semantic network; semantic network design; static marker passing algorithm; synchronous marker passing algorithm; yacc parser generator; Algorithm design and analysis; Computer science; Inference algorithms; Inference mechanisms; Knowledge representation; Load management; Natural languages; Spine; Sun; System testing;
Conference_Titel :
Tools with Artificial Intelligence, 2003. Proceedings. 15th IEEE International Conference on
Print_ISBN :
0-7695-2038-3
DOI :
10.1109/TAI.2003.1250194