Book ChapterDOI
Investigation of Geometrical Properties of Kernels Belonging to Seeds
M. Aishwarya,Vaidya Srivani,A. Aishwarya,P. Natarajan +3 more
- pp 151-157
Reads0
Chats0
TLDR
The geometrical properties of kernels belonging to seeds using Naive Bayesian classification and Hierarchical clustering techniques are analyzed and a comparison between the accuracies obtained is made to conclude a better data mining technique.Abstract:
The estimation of the kernel density has been successfully tried on several data mining tasks. In this paper, the geometrical properties of kernels belonging to seeds using Naive Bayesian classification and Hierarchical clustering techniques are analyzed. A method, which has been applied to real data set of grains and analysis of the kernels belonging to three types of seeds namely Canadian, Rosa, and Kama are classified based on the geometrical properties like perimeter, compactness, length of kernel, width of kernel, asymmetric coefficient, and length of kernel groove has been proposed. Also, a comparison between the accuracies obtained after performing Naive Bayes Classification and Hierarchical Clustering has been made to conclude a better data mining technique.read more
References
More filters
An empirical study of the naive Bayes classifier
TL;DR: This work analyzes the impact of the distribution entropy on the classification error, showing that low-entropy feature distributions yield good performance of naive Bayes and demonstrates that naive Baye works well for certain nearlyfunctional feature dependencies.
Proceedings ArticleDOI
Naive Bayes models for probability estimation
Daniel Lowd,Pedro Domingos +1 more
TL;DR: It is shown that, for a wide range of benchmark datasets, naive Bayes models learned using EM have accuracy and learning time comparable to Bayesian networks with context-specific independence.
Confusion Matrix-Based Feature Selection
TL;DR: A new technique for feature selection that uses information from a confusion matrix and evaluates one attribute at a time, creating subsets of attributes that are complementary that is, they misclassify different classes.
Journal ArticleDOI
On dendrogram-based measures of functional diversity
János Podani,Dénes Schmera +1 more
TL;DR: Gower's formula and UPGMA clustering are suggested in this paper as a standard combination of techniques for calculating functional diversity (FD), and the effect of individual species on FD is best evaluated by species removals and subsequent comparisons of tree length values.