Classification of Animal Species Using Neural Network

Download Edit this record How to cite View on PhilPapers
Abstract
Abstract: Over 1.5 million living animal species have been described—of which around 1 million are insects—but it has been estimated there are over 7 million animal species in total. Animals range in length from 8.5 micrometres to 33.6 metres. In this paper an Artificial Neural Network (ANN) model, was developed and tested to predict animal species. There are a number of features that influence the classification of animal species. Such as the existence of hair/ feather, if the animal gives birth or spawns, it is airborne, aquatic, predator, toothed, backboned, venomous, has –fins, has-tail, cat-sized, and domestic. A model based on the Multilayer Perceptron Topology was proposed and trained, using data set what was collected from UCI Machine Learning Repository. Evaluation of the proposed model shows that the ANN model is able to correctly predict the animal category with 100% accuracy.
Categories
No categories specified
(categorize this paper)
PhilPapers/Archive ID
ALACOA-2
Upload history
Archival date: 2020-10-29
View other versions
Added to PP index
2020-10-29

Total views
92 ( #43,869 of 2,438,899 )

Recent downloads (6 months)
60 ( #11,140 of 2,438,899 )

How can I increase my downloads?

Downloads since first upload
This graph includes both downloads from PhilArchive and clicks on external links on PhilPapers.