On determining efficient finite mixture models with compact and essential components for clustering data

Abas, Ahmed R.

doi:10.1016/j.eij.2013.02.002

Cited by 3 publications

(3 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ACLNN algorithm was proposed for determining the optimal number of clusters and clustering of input small datasets. The ACLNN algorithm uses the ACL criterion for determining the optimal number of output neurons [16], [17]. The ACL criterion is based on the theory stating that the best cluster structure is composed of balanced, dense, and well-separated clusters that have the least number of parameters to be calculated.…”

Section: Related Workmentioning

confidence: 99%

“…The ACL criterion is based on the theory stating that the best cluster structure is composed of balanced, dense, and well-separated clusters that have the least number of parameters to be calculated. The ACLNN algorithm has been proven to be efficient in identifying the optimal number of clusters and clustering small datasets [16], [17]. Because of its sequential running nature, the ACLNN algorithm has high time complexity and thus consumes a large running time, especially when used with big datasets.…”

Section: Related Workmentioning

confidence: 99%

“…The adaptive competitive learning neural network (ACLNN) algorithm was proposed to decide the optimum number of clusters and clustering of a small input dataset. The ACLNN algorithm determines the optimal number of output neurons using the adaptive competitive learning (ACL) criteria [16], [17]. The ACL criteria assume that the best cluster configuration comprises balanced, dense, and well-separated clusters with the fewest parameters to calculate.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Adaptive Landmark-Based Spectral Clustering for Big Datasets

2021

Self Cite

View full text Add to dashboard Cite

Clustering has emerged as an effective tool for the processing and assessment of the vast data generated by modern applications; its primary aim is to classify data into clusters in which the items are grouped into a given category. However, various challenges, such as volume, velocity, and variety, occur during the clustering of big data. Different algorithms have been proposed to enhance the performance of clustering. The landmark-based spectral clustering (LSC) technique has been proven to be efficient in clustering big datasets. In this study, an algorithm called adaptive landmark-based spectral clustering (ALSC) is proposed for clustering big datasets. The proposed algorithm comprises the adaptive competitive learning neural network (ACLNN) algorithm, which can be efficiently used to determine the number of clusters and the LSC technique. The ACLNN algorithm can also be used with small datasets. Thus, in our implementation, the original big dataset is split into N small subdatasets, which run in parallel by N copies of the ACLNN algorithm. To evaluate the performance of the proposed algorithm, two distinctive datasets, namely, Fashion-MNIST and United States Postal Service are used. The experiments show that the proposed ALSC algorithm produces high clustering accuracy with the identification of the number of clusters. Results reveal that the normalized mutual information and adjusted Rand index of the proposed algorithm outperform state-of-the-art models.INDEX TERMS Adaptive competitive learning neural network, big datasets, clustering; landmark-based spectral clustering, parallel processing.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%