Ant-based clustering
Nature-inspired heuristics are computational algorithms
that are inspired by processes observed in nature. Ant-based
clustering is an example of such a heuristic.
Ant-based clustering was originally introduced as a computational model of the
clustering and sorting behaviours observed in some types of
ants. Its first applications were in the area of distributed
robotics, but the model was then extended for the use in
data clustering.
I first worked with ant-based clustering during my research project at Monash, where I used the algorithm as the classification component in a tool for the visualization of web queries in the form of "topic maps". My subsequent Masters project in Brussels focused primarily on the improvement and evaluation of the algorithm's performance for the tasks of clustering and topographic mapping.
Some of the code used in these projects can be downloaded below.
Downloads:
Java source code of the algorithm described by Handl and Meyer (2002). Includes a visualization of the clustering process.
C++ source code of the algorithm described by Handl, Knowles and Dorigo (2005). Includes retrieval of clusters off the grid and measures for the computation of clustering quality.
Publications:
Handl, J. and Meyer, B. (2007). Ant-based and swarm-based clustering. Swarm Intelligence 1(1): 95-113
Handl, J., Knowles, J., and Dorigo, M. (2005). Ant-based clustering and topographic mapping. Artificial Life 12(1)
Handl, J., Knowles, J., and Dorigo, M. (2004). Strategies for the increased robustness of ant-based clustering. In Engineering Self-Organising Systems, Vol. 2977 of Lecture Notes in Computer Science (pp. 90-104). Heidelberg, Germany: Springer-Verlag.
Handl, J., Knowles, J., and Dorigo, M. (2003).
On the performance of ant-based clustering. In Design and Application of Hybrid Intelligent Systems, Vol. 104 of Frontiers in Artificial Intelligence and Applications (pp. 204-213). Amsterdam, The Netherlands: IOS Press. Handl, J. and Meyer, B. (2002). Improved ant-based clustering and sorting in a document retrieval interface. In Proceedings of the Seventh International Conference on Parallel Problem Solving from Nature, Vol. 2439 of Lecture Notes in Computer Science (pp. 913-923). Berlin, Germany: Springer-Verlag.
