AntClust: Ant Clustering and Web Usage Mining

Labroche, Nicolas; Monmarché, Nicolas; Venturini, Gilles

doi:10.1007/3-540-45105-6_3

Cited by 64 publications

(39 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several techniques have been developed to solve clustering problems and those based on the Swarm Intelligence (SI) paradigm seem to be specially attractive because of their robust performance [4,30,31,50]. 2 In those cases where clustering techniques are applied to corpora containing very short documents, further difficulties are introduced due to the low frequencies of the document terms.…”

Section: Introductionmentioning

confidence: 99%

An efficient Particle Swarm Optimization approach to cluster short texts

Cagnina

Errecalde

Ingaramo

et al. 2014

Information Sciences

View full text Add to dashboard Cite

Short texts such as evaluations of commercial products, news, FAQ's and scientific abstracts are important resources on the Web due to the constant requirements of people to use this on line information in real life. In this context, the clustering of short texts is a significant analysis task and a discrete Particle Swarm Optimization (PSO) algorithm named CLUDIPSO has recently shown a promising performance in this type of problems. CLUDIPSO obtained high quality results with small corpora although, with larger corpora, a significant deterioration of performance was observed. This article presents CLUDIPSO ⋆ , an improved version of CLUDIPSO, which includes a different representation of particles, a more efficient evaluation of the function to be optimized and some modifications in the mutation operator. Experimental results with corpora containing scientific abstracts, news and short legal documents obtained from the Web, show that CLUDIPSO ⋆ is an effective clustering method for short-text corpora of small and medium size.

show abstract

Section: Introductionmentioning

confidence: 99%

An efficient Particle Swarm Optimization approach to cluster short texts

Cagnina

Errecalde

Ingaramo

et al. 2014

Information Sciences

View full text Add to dashboard Cite

show abstract

“…ACSC employs the sliding window model when dealing with data streams so at each iteration a fixed size chunk of data is considered. The process for finding ε at each window is based on the algorithm presented in [11]. ε is calculated as the mean value of n Euclidean distance measures, dist(i, j) ∈ [0, 1], between n randomly chosen i and j data points in the current window.…”

Section: Finding the ε-Neighbourhoodmentioning

confidence: 99%

“…The algorithm computes the clusters using K-means, which, again, is limiting in both the number and shape of the clusters that it can potentially find. A variation on the Leader Ant algorithm was proposed in [11] as an accurate and inexpensive agglomerative clustering algorithm. Other ant clustering algorithms are based on the 'pick-and-drop' model proposed in [5].…”

Section: Introductionmentioning

confidence: 99%

Dynamic Stream Clustering Using Ants

Fahy

Yang

2016

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Data stream mining is the process of extracting knowledge from continuous sequences of data. It differs from conventional data mining in that a stream is potentially unbounded, data points arrive online and each data point can be examined only once. Furthermore, in non-stationary environments the statistical properties of the data can change over time. This paper presents a bio-inspired approach to clustering non-stationary data streams. The proposed algorithm, Ant-Colony Stream Clustering (ACSC), is based on the concept of artificial ants which identify clusters as nests of micro-clusters in dense areas of the data. Micro-clusters are N-dimensional spheres with a maximum radius ε. In ACSC the ε-neighbourhood, crucial in density clustering, is adaptive and doesn't require expert, data-dependent tuning. The algorithm uses the sliding window model and summary statistics for each window are stored offline. Experimental results over real and synthetic datasets show that the clustering quality of ACSC is comparable or favourable to leading stream-clustering algorithms while requiring fewer parameters and considerably less computation.

show abstract

“…This method is easily applicable to many fields including web mining and other unsupervised domains. There are many cases of ANTCLUST implementations [Labroche et al, 2003a], [Labroche et al, 2003b], including variants that have been shown to separate noise from data [Zaharie and Zamfirache], credit evaluation of small enterprises [Xue-chun et al, 2007], and web-mining [Inbarani and Thangavel, 2006].…”

Section: Type III -Clustering Inspired By the Chemical Recognition Symentioning

confidence: 99%