Performance Evaluation of Threshold-Based and k-means Clustering Algorithms Using Iris Dataset

Abstract

Background: Clustering is one of the data mining tools which classify the raw data reasonably into disjoint clusters. Researchers have developed many algorithms to cluster large data sets based on specific parameters. Objective: This study is centered around the popular partitioning-based technique, i.e., k-means. It requires the number of clusters to be generated as an input parameter; it does not provide a global solution of the problem; and it is sensitive to outliers and initial seed selection. Methods: In this paper, authors have discussed threshold-based clustering method, single pass method, which overcomes the above limitations but it requires a threshold value as an input parameter. Other researchers’ work related to k-means published in patent form is noteworthy and paving path for the researchers. Results: To assess the quality of clustering, numerous validity measures and indices have been assessed on the Iris dataset for both k-means and threshold-based clustering algorithms. It has been observed from the experiments that threshold-based method generates more separated and compact clusters, in addition, there is significant improvement in the validity indices. Conclusion: Threshold-based clustering generates the clusters automatically which are not sensitive to initial seeds selection and outlier; it is more scalable. It will inevitably be an efficient approach of partitioning based clustering whenever one will select the threshold value carefully or will propose new functions for deciding the value of threshold.

Algorithmic analysis for dental caries detection using an adaptive neural network architecture

“…Once the features are extracted, they are multiplied with a weighting factor ranges between [0,1], and the distance between the resultant feature outputs is maximized by employing Nonlinear Programming Optimization. If the distance between the selected features is high, it will obviously improve the classification performance as each feature provides unique information [29]. Eq.…”

“…The resized image is represented as ABand the enhancement of AB takes place in this stage. In order to enhance the visibility of image, adjustments are made in the intensity of the image [29]. In this method, the visibility of image is improved with consideration in the values of the relative darkness, and on the values of the brightness ofAB.…”

Ambient Air Quality Estimation using Supervised Learning Techniques

“…The supervised learning techniques comprises of classification, regression and ensemble techniques where the target variable is categorical in classification and continuous in regression. Clustering is part of unsupervised learning [35,36]. Ensemble techniques combine various models to increase the prediction accuracy.…”

Bug Severity Prediction using Class Imbalance Problem

“…In our work, they are broadly categorized as Severe (blocker, critical and major) and Non-severe (trivial and minor). The number of severe and non-severe bugs of various projects such as Apache cordova, Hadoop-hdfs, Groovy, Hadoop-common, Hive, Ambari, Hbase, Mesos, Lucene, Spark, Qpid Maven and Sling [36] are illustrate through bar graphs in Fig 1.…”