Investigation of Validity Metrics for Modified K-Means Clustering Algorithm

Rao, S. Govinda; Govardhan, A.

doi:10.26634/jcom.3.2.3548

Cited by 4 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Davies-Bouldin index (DB), an internal validity metric, is used to identify cluster overlap by measuring the ratio of the sum of the "within-cluster scatters" to the "between-cluster separations" [90,91]. The Davies-Bouldin index is defined as follows:…”

Section: Davies Bouldin Indexmentioning

confidence: 99%

K-Hyperparameter Tuning in High-Dimensional Space Clustering: Solving Smooth Elbow Challenges Using an Ensemble Based Technique of a Self-Adapting Autoencoder and Internal Validation Indexes

Gikera,

Mwaura,

Muuro

et al. 2023

Journal on Artificial Intelligence

View full text Add to dashboard Cite

k-means is a popular clustering algorithm because of its simplicity and scalability to handle large datasets. However, one of its setbacks is the challenge of identifying the correct k-hyperparameter value. Tuning this value correctly is critical for building effective k-means models. The use of the traditional elbow method to help identify this value has a long-standing literature. However, when using this method with certain datasets, smooth curves may appear, making it challenging to identify the k-value due to its unclear nature. On the other hand, various internal validation indexes, which are proposed as a solution to this issue, may be inconsistent. Although various techniques for solving smooth elbow challenges exist, k-hyperparameter tuning in high-dimensional spaces still remains intractable and an open research issue. In this paper, we have first reviewed the existing techniques for solving smooth elbow challenges. The identified research gaps are then utilized in the development of the new technique. The new technique, referred to as the ensemble-based technique of a self-adapting autoencoder and internal validation indexes, is then validated in high-dimensional space clustering. The optimal k-value, tuned by this technique using a voting scheme, is a trade-off between the number of clusters visualized in the autoencoder's latent space, k-value from the ensemble internal validation index score and one that generates a value of 0 or close to 0 on the derivativeat the elbow. Experimental results based on the Cochran's Q test, ANOVA, and McNemar's score indicate a relatively good performance of the newly developed technique in k-hyperparameter tuning. KEYWORDS k-hyperparameter tuning; high-dimensional; smooth elbow K-Means ArchitectureK-means is an iterative algorithm that aims to partition a dataset into a set of k non-overlapping groups of data points [9]. The k-hyperparameter is one of the most important hyperparameters to tune in k-means [10,11]. Tuning a machine learning model's hyperparameters has a significant effect on its performance [12]. In this subsection, we explore k-clusters, k-hyperparameters, and the traditional elbow method used to identify the optimal value for the k-hyperparameter. K-Means ClustersThe k-means clusters are the resulting data sub-groups generated by the popular unsupervised partitioning algorithm, known as the k-means clustering algorithm [13]. Cluster analysis using the k-means algorithm is an example of a k-means-based model that has been successfully applied in cluster analysis [14,15]. The k-clusters generated by these algorithms are usually composed of distinct non-overlapping groups of data points, aggregated together because they share specific similarities [16]. The data points within a particular cluster are similar, while the data points across different clusters are different [17]. Both the intra-cluster and inter-cluster data points are measured using a sum of squared distance-based metric [18,19]. For this reason, the original un-partitioned dataset is stan...

show abstract

Section: Davies Bouldin Indexmentioning

confidence: 99%

K-Hyperparameter Tuning in High-Dimensional Space Clustering: Solving Smooth Elbow Challenges Using an Ensemble Based Technique of a Self-Adapting Autoencoder and Internal Validation Indexes

Gikera,

Mwaura,

Muuro

et al. 2023

Journal on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

“…Hierarchical clustering algorithms can be further divided into agglomerative and divisive [5] [6] [7] [8] [9].…”

Section: Introductionmentioning

confidence: 99%

A Group Average Cluster Analysis of Few IGF1R Sequences using Modified Group Average Link Clustering Algorithm

Rambabu¹,

Rao²

2016

IJCA

View full text Add to dashboard Cite

Clustering techniques have been widely used in the fields of information technology, biomedical sciences. Cluster analysis deals with the identification of a set of objects into subsets with some sort of similarities. Such groups are assigned to have similar function. In this paper, a modified group average clustering program was written in python language and applied on a dataset of IGF1R protein sequences to generate orthologous clusters of sequences and the phylogenetic trees were presented.

show abstract

Modified Hierarchical Clustering algorithms to Evaluate the Similarities of Growth Factor IR Inhibitors by Using Regression Analysis

Rao¹,

Rambabu²,

Rao³

2018

2018 4th International Conference on Computing Communication and Automation (ICCCA)

View full text Add to dashboard Cite

Investigation of Validity Metrics for Modified K-Means Clustering Algorithm

Cited by 4 publications

References 8 publications

K-Hyperparameter Tuning in High-Dimensional Space Clustering: Solving Smooth Elbow Challenges Using an Ensemble Based Technique of a Self-Adapting Autoencoder and Internal Validation Indexes

K-Hyperparameter Tuning in High-Dimensional Space Clustering: Solving Smooth Elbow Challenges Using an Ensemble Based Technique of a Self-Adapting Autoencoder and Internal Validation Indexes

A Group Average Cluster Analysis of Few IGF1R Sequences using Modified Group Average Link Clustering Algorithm

Modified Hierarchical Clustering algorithms to Evaluate the Similarities of Growth Factor IR Inhibitors by Using Regression Analysis

Contact Info

Product

Resources

About