Dealing with noise in ant-based clustering

2003

Abstract. Ant-based clustering and sorting is a nature-inspired heuristic for general clustering tasks. It has been applied variously, from problems arising in commerce, to circuit design, to text-mining, all with some promise. However, although early results were broadly encouraging, there has been very limited analytical evaluation of antbased clustering.

Iberoamerican Journal of Industrial Engineering, 2011

We use the heuristics known as ant colony optimization in the partitioning problem for improving solutions of k-means method. Each ant in the algorithm is associated to a partition, which is modified by the principles of the heuristics; that is, by the random selection of an element, and the assignment of another element which is chosen according to a probability that depends on the pheromone trail (related to the overall criterion: the maximization of the between-classes variance), and a local criterion (the distance between objects). The pheromone trail is reinforced for those objects that belong to the same class. We present some preliminary results, compared to results of other techniques, such as simulated annealing, genetic algorithm, tabu search and k-means. Results are as good as the best of the above methods.

The 2003 Congress on Evolutionary Computation, 2003. CEC '03., 2003

In this paper we will present a new clustering algorithm for unsupervised learning. It is inspired from the self-assembling behavior observed in real ants where ants progressively become attached to an existing support and then successively to other attached ants. The artificial ants that we have defined will similarly build a tree. Each ant represents one data. The way ants move and build this tree depends on the similarity between the data. We have compared our results to those obtained by the k-means algorithm and by AntClass on numerical databases (either artificial, real, or from the CE.R.I.E.S.). We show that AntTree significantly improves the clustering process.

Informatica, 2005

Among the many bio-inspired techniques, ant-based clustering algorithms have received special attention from the community over the past few years for two main reasons. First, they are particularly suitable to perform exploratory data analysis and, second, they still require much investigation to improve performance, stability, convergence, and other key features that would make such algorithms mature tools for diverse applications. Under this perspective, this paper proposes both a progressive vision scheme and pheromone heuristics for the standard ant-clustering algorithm, together with a cooling schedule that improves its convergence properties. The proposed algorithm is evaluated in a number of well-known benchmark data sets, as well as in a real-world bioinformatics dataset. The achieved results are compared to those obtained by the standard ant clustering algorithm, showing that significant improvements are obtained by means of the proposed modifications. As an additional contribution, this work also provides a brief review of ant-based clustering algorithms.

European Journal of Operational Research, 2007

In this paper is presented a new model for data clustering, which is inspired from the selfassembly behavior of real ants. Real ants can build complex structures by connecting themselves to each others. It is shown is this paper that this behavior can be used to build a hierarchical tree-structured partitioning of the data according to the similarities between those data. Several algorithms have been detailed using this model (called AntTree): deterministic or stochastic algorithms that may use or not global or local thresholds. Those algorithms have been evaluated using artificial and real databases. Our algorithms obtain competitive results when compared to the Kmeans, to ANTCLASS, and to Ascending Hierarchical Clustering. AntTree has been applied to three real world applications: the analysis of human healthy skin, the on-line mining of web sites usage, and the automatic construction of portal sites.

Journal of Computer Science and Technology, 2005

Clustering task aims at the unsupervised classi- fication of patterns (e.g., observations, data, vec- tors, etc.) in different groups. Clustering problem has been approached from different disciplines during the last years. Although have been pro- posed different alternatives to cope with cluster- ing, there also exists an interesting and novel field of research from which different bio-inspired al- gorithms have

2007

In this paper, we provide the reasons why the dissimilarity-scaling parameter (α) in the neighbourhood function of ant-based clustering is critical for detecting the correct number of clusters in data sources. We then examine a recently proposed method named ATTA; we show that there is no need to use a population of α-adaptive ants to reproduce ATTA’s results. We devise a method to estimate a fixed (i.e, non-adaptive) single value of α for each dataset. We also introduce a simplified version of ATTA, called SATTA. The reason for introducing SATTA is two-fold: first, to test our proposed α-estimation method; and, second, to simulate ant-based clustering from a purely stochastic perspective. SATTA omits the ant colony but reuses important ant heuristics. Experimental results show that SATTA generally performs better than ATTA on clusters with different densities and clusters that are elongated. Finally, we show that the results can be further improved using a majority voting scheme.

2004

Processes that simulate natural phenomena have successfully been applied to a number of problems for which no simple mathematical solution is known or is practicable. Such meta-heuristic algorithms include genetic algorithms, particle swarm optimization and ant colony systems and have received increasing attention in recent years. This paper extends ant colony systems and discusses a novel data clustering process using Constrained Ant Colony Optimization (CACO). The CACO algorithm extends the Ant Colony Optimization algorithm by accommodating a quadratic distance metric, the Sum of K Nearest Neighbor Distances (SKNND) metric, constrained addition of pheromone and a shrinking range strategy to improve data clustering. We show that the CACO algorithm can resolve the problems of clusters with arbitrary shapes, clusters with outliers and bridges between clusters.

2010

Among the many bio–inspired techniques, ant clustering algorithms have received special attention, especially because they still require much investigation to improve performance, stability and other key features that would make such algorithms mature tools for data mining. Clustering with swarm–based algorithms is emerging as an alternative to more conventional clustering methods, such as k–means algorithm. This proposed approach mimics the clustering behavior observed in real ant colonies. As a case study, this paper focuses on the behavior of clustering procedures in this new approach. The proposed algorithm is evaluated on a number of well–known benchmark data sets. Empirical results clearly show that the ant clustering algorithm (ACA) performs well when compared to other techniques.

2005

Among the many bio-inspired techniques, ant-based clustering algorithms have received special attention from the community over the past few years for two main reasons. First, they are particularly suitable to perform exploratory data analysis and, second, they still require much investigation to improve performance, stability, convergence, and other key features that would make such algorithms mature tools for diverse applications. Under this perspective, this paper proposes both a progressive vision scheme and pheromone heuristics for the standard ant-clustering algorithm, together with a cooling schedule that improves its convergence properties. The proposed algorithm is evaluated in a number of well-known benchmark data sets, as well as in a real-world bioinformatics dataset. The achieved results are compared to those obtained by the standard ant clustering algorithm, showing that significant improvements are obtained by means of the proposed modifications. As an additional cont...

2008 International Conference on Computer Science and Software Engineering, 2008

A wireless ad hoc network (WANET) or MANET is a decentralized type of wireless network and it does not rely on a pre-existing infrastructure. Instead, each node participates in routing by forwarding data for other nodes, so the determination of which nodes forward data is made dynamically on the basis of network connectivity and the routing algorithm in use. The Temporally-Ordered Routing Algorithm (TORA) is an adaptive, distributed, loop-free routing protocol for multi-hop networks which has minimum overhead against topological changes. Quality of Service (QoS) support for MANET in TORA has become a challenging task due to its dynamic topology. This paper proposes QoS enabled Temporally Ordered Routing Algorithm using Ant Colony Optimization called AntTORA. ACO algorithms have shown to be a good technique for developing routing algorithms for ad hoc networks. ACO based routing is an efficient routing scheme based on the behaviour of foraging ants. The collective behaviour of ants helps to find the shortest path from the nest to a food source, by deposition of a chemical substance called pheromone on the visited nodes. ACO technique is used in TORA protocol to optimize multiple QoS metrics like end-to-end delay, throughput, jitter and so on. The performance of TORA and AntTORA are analysed using network simulator-2. The results presented in the end also help the researchers to understand the differences between TORA and AntTORA, therefore to choose appropriate protocol for their research work. Our simulation study shows how this approach has significantly improved the performance of the ad hoc networks.

By classifying the enormous quantity of data, the structure and the relativity that lurks among data can be found. As a data classifying technique, the cluster analysis techniques are well known. However, because those techniques include some defects, the development of a new technique is necessary. Recently, Ant Colony Clustering (ACC) technique using ant swarm intelligence was proposed by Erik D. Lumer. The swarm intelligence is a property that each of individuals acts a simple behavior and exchange information each other, and the entire group makes the best behavior. ACC algorithm tries to overcome the defects of existing techniques by using this swarm intelligence idea. In this research, we propose a new algorithm that improves the efficiency of clustering in Lumer’s ACC algorithms. Numerical experiments show the improvement is effective.

International Journal of Data Mining & Knowledge Management Process, 2012

Clustering analysis is an important function of data mining. There are various clustering methods in Data Mining. Based on these methods various clustering algorithms are developed. Ant-clustering algorithm is one of such approaches that perform cluster analysis based on "Swarm Intelligence'. Existing antclustering algorithm uses two user defined parameters to calculate the picking-up probability and dropping probability those are used to form the cluster. But, use of user defined parameters may lead to form an inaccurate cluster. It is difficult to anticipate about the value of the user defined parameters in advance to form the cluster because of the diversified characteristics of the dataset. In this paper, we have analyzed the existing ant-clustering algorithm and then numerical analysis method of linear equation is proposed based on the characteristics of the dataset that does not need any user defined parameters to form the clusters. Results of numerical experiments on synthetic datasets demonstrate the effectiveness of the proposed method.