Faktor Exacta
Vol 14, No 1 (2021)

ANALISIS KLASIFIKASI POPULASI TERNAK KAMBING DAN DOMBA DENGAN MODEL CONVOLUTIONAL NEURAL NETWORK

Alusyanti Primawati (University of Indraprasta PGRI)
Intan Mutia (University of Indraprasta PGRI)
Dwi Marlina (University of Indraprasta PGRI)



Article Info

Publish Date
30 Mar 2021

Abstract

The number of goat populations is increasing all over the world. Sheep and goats are economically potential for business development because they do not require large areas of land, relatively small investment in business capital, and are easy to market. However, the similarities between goats and sheep can make small breeders who are just starting out in business nervous. Therefore, in goats and sheep, an intensive and efficient Precision Livestock Farming system is required. To answer this problem, goat and sheep objects was studied out using the collaboration software programming R and Python which executed in RStudio editor and Anaconda3 with the Tensor flow package. The sample data of 40 images. The model obtained from the classification results uses 20 pictures of goats and 20 pictures of sheep for training and testing. The accuracy produced shows that the prediction of training data at epoch 70 and 100 has the right accuracy with the actual data. This reinforces that the model used is good (fit) to the training dataset, but when it is applied to the testing dataset, the prediction results are still close to perfect. Epoch 70 identifies there is 1 image of a Goat which is recognized as Lamb.

Copyrights © 2021






Journal Info

Abbrev

Faktor_Exacta

Publisher

Subject

Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Industrial & Manufacturing Engineering

Description

Faktor Exacta is a peer review journal in the field of informatics. This journal was published in March (March, June, September, December) by Institute for Research and Community Service, University of Indraprasta PGRI, Indonesia. All newspapers will be read blind. Accepted papers will be available ...