Document clustering based on diffusion maps and a comparison of the k-means performances in various spaces

Allah, Fadoua Ataa; Grosky, William I.; Aboutajdine, Driss

doi:10.1109/iscc.2008.4625693

Cited by 6 publications

(7 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The angular component is based on the cosine similarity and expressed as: (3) One can notice that, if x or y are equal to 0 , then   ,0…”

Section: Distance/dissimilarity Components In Sodamentioning

confidence: 99%

“…Data partitioning and clustering techniques have been widely used in different areas of the economy and society [3], [16], [35] However, despite being considered to be an unsupervised form of machine learning, traditional clustering techniques require prior knowledge and handcrafting to operate. Users need to define a number of parameters and make assumptions in advance, i.e.…”

Section: Introductionmentioning

confidence: 99%

“…However, the well-known Euclidean and the Mahalanobis [27], [33] distance metrics are the most frequently used ones. In some fields of study such as natural language processing (NLP), for example, the derivatives of the cosine (dis)similarity, which is a pseudo metric, are also used in the machine learning algorithms for clustering purpose [3], [38], [39]. Nevertheless, once a decision is made, only one type of distance/dissimilarity can be employed by the clustering algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Self-Organised direction aware data partitioning algorithm

Angelov

Kangin

et al. 2018

Information Sciences

View full text Add to dashboard Cite

In this paper, a novel fully data-driven algorithm, named Self-Organised Direction Aware (SODA) data partitioning and forming data clouds is proposed. The proposed SODA algorithm employs an extra cosine similarity-based directional component to work together with a traditional distance metric, thus, takes the advantages of both the spatial and angular divergences. Using the nonparametric Empirical Data Analytics (EDA) operators, the proposed algorithm automatically identifies the main modes of the data pattern from the empirically observed data samples and uses them as focal points to form data clouds. A streaming data processing extension of the SODA algorithm is also proposed. This extension of the SODA algorithm is able to self-adjust the data clouds structure and parameters to follow the possibly changing data patterns and processes.Numerical examples provided as a proof of the concept illustrate the proposed algorithm as an autonomous algorithm and demonstrate its high clustering performance and computational efficiency.

show abstract

“…The angular component is based on the cosine similarity and expressed as: (3) One can notice that, if x or y are equal to 0 , then   ,0…”

Section: Distance/dissimilarity Components In Sodamentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Self-Organised direction aware data partitioning algorithm

Angelov

Kangin

et al. 2018

Information Sciences

View full text Add to dashboard Cite

show abstract

“…For example, the k-means [7], [10], mean-shift clustering [14], k nearest neighbour classification [15] algorithms may use the newly introduced direction-aware distance to enhance the ability in dealing with high dimensional data.…”

Section: The Application Of the Proposed Distance To Traditional Clusmentioning

confidence: 99%

“…Therefore, it is more often used in the natural language processing (NLP) problems [7]- [11]. In NLP problems, machine learning algorithms, for example, k-means [7], [10], mean shift [11], etc., are used to cluster very high dimensional vectors representing the documents together based on the cosine similarity. Nonetheless, the cosine similarity is a pseudo metric because it does not obey the triangle inequality (it obeys the Cauchy-Schwarz inequality [12]).…”

Section: Introductionmentioning

confidence: 99%

A new type of distance metric and its use for clustering

Angelov

Kangin

et al. 2017

Evolving Systems

View full text Add to dashboard Cite

Abstract-In order to address high dimensional problems, a new 'direction-aware' metric is introduced in this paper. This new distance is a combination of two components: i) the traditional Euclidean distance and ii) an angular/directional divergence, derived from the cosine similarity. The newly introduced metric combines the advantages of the Euclidean metric and cosine similarity, and is defined over the Euclidean space domain. Thus, it is able to take the advantage from both spaces, while preserving the Euclidean space domain. The directionaware distance has wide range of applicability and can be used as an alternative distance measure for various traditional clustering approaches to enhance their ability of handling high dimensional problems. A new evolving clustering algorithm using the proposed distance is also proposed in this paper. Numerical examples with benchmark datasets reveal that the direction-aware distance can effectively improve the clustering quality of the k-means algorithm for high dimensional problems and demonstrate the proposed evolving clustering algorithm to be an effective tool for high dimensional data streams processing.

show abstract

Brief Introduction to Statistical Machine Learning

Angelov

2018

Empirical Approach to Machine Learning

View full text Add to dashboard Cite

Document clustering based on diffusion maps and a comparison of the k-means performances in various spaces

Cited by 6 publications

References 10 publications

Self-Organised direction aware data partitioning algorithm

Self-Organised direction aware data partitioning algorithm

A new type of distance metric and its use for clustering

Brief Introduction to Statistical Machine Learning

Contact Info

Product

Resources

About