Max stable set problem to found the initial centroids in clustering problem

In this paper, we propose a new approach to solve the document-clustering using the K-Means algorithm. The latter is sensitive to the random selection of the k cluster centroids in the initialization phase. To evaluate the quality of K-Means clustering we propose to model the text document clustering problem as the max stable set problem (MSSP) and use continuous Hopfield network to solve the MSSP problem to have initial centroids. The idea is inspired by the fact that MSSP and clustering share the same principle, MSSP consists to find the largest set of nodes completely disconnected in a graph, and in clustering, all objects are divided into disjoint clusters. Simulation results demonstrate that the proposed K-Means improved by MSSP (KM_MSSP) is efficient of large data sets, is much optimized in terms of time, and provides better quality of clustering than other methods.

Grey wolf optimization algorithm for hierarchical document clustering

In data mining, the application of grey wolf optimization (GWO) algorithm has been used in several learning approaches because of its simplicity in adapting to different application domains. Most recent works that concern unsupervised learning have focused on text clustering, where the GWO algorithm shows promising results. Although GWO has great potential in performing text clustering, it has limitations in dealing with outlier documents and noise data. This research introduces medoid GWO (M-GWO) algorithm, which incorporates a medoid recalculation process to share the information of medoids among the three best wolves and the rest of the population. This improvement aims to find the best set of medoids during the algorithm run and increases the exploitation search to find more local regions in the search space. Experimental results obtained from using well-known algorithms, such as genetic, firefly, GWO, and k-means algorithms, in four benchmarks. The results of external evaluation metrics, such as rand, purity, F-measure, and entropy, indicates that the proposed M-GWO algorithm achieves better document clustering than all other algorithms (i.e., 75% better when using Rand metric, 50% better than all algorithm based on purity metric, 75% better than all algorithms using F-measure metric, and 100% based on entropy metric).

Biomedical Document Clustering Based on Accelerated Symbiotic Organisms Search Algorithm

Clustering is an important unsupervised analysis technique for big data mining. It finds its application in several domains including biomedical documents of the MEDLINE database. Document clustering algorithms based on metaheuristics is an active research area. However, these algorithms suffer from the problems of getting trapped in local optima, need many parameters to adjust, and the documents should be indexed by a high dimensionality matrix using the traditional vector space model. In order to overcome these limitations, in this paper a new documents clustering algorithm (ASOS-LSI) with no parameters is proposed. It is based on the recent symbiotic organisms search metaheuristic (SOS) and enhanced by an acceleration technique. Furthermore, the documents are represented by semantic indexing based on the famous latent semantic indexing (LSI). Conducted experiments on well-known biomedical documents datasets show the significant superiority of ASOS-LSI over five famous algorithms in terms of compactness, f-measure, purity, misclassified documents, entropy, and runtime.

Similarity Measure Algorithm for Text Document Clustering, Using Singular Value Decomposition

We examined a similarity measure between text documents clustering. Data mining is a challenging field with more research and application areas. Text document clustering, which is a subset of data mining helps groups and organizes a large quantity of unstructured text documents into a small number of meaningful clusters. An algorithm which works better by calculating the degree of closeness of documents using their document matrix was used to query the terms/words in each document. We also determined whether a given set of text documents are similar/different to the other when these terms are queried. We found that, the ability to rank and approximate documents using matrix allows the use of Singular Value Decomposition (SVD) as an enhanced text data mining algorithm. Also, applying SVD to a matrix of a high dimension results in matrix of a lower dimension, to expose the relationships in the original matrix by ordering it from the most variant to the lowest.