Analisis Klasifikasi Populasi Ternak Kambing Dan Domba Dengan Model Convolutional Neural Network

Primawati, Alusyanti; Mutia, Intan; Marlina, Dwi

doi:10.30998/faktorexacta.v14i1.8734

“…Kambing adalah ruminansia berukuran sedang. Hewan yang banyak dipelihara oleh masyarakat Indonesia karena memiliki banyak manfaat dan dapat meningkatkan perekonomian salah satunya adalah kambing [5]. Kambing merupakan salah satu hewan ternak yang dapat menghasilkan daging yang sehat dan bergizi.…”

Section: Pendahuluanunclassified

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia

Rika Setiana,

Siregar,

Fahry Husaini

et al. 2023

comforch

0

View full text Add to dashboard Cite

A science that has always developed rapidly until now is artificial neural networks. A computational science that works like the human nervous system is an artificial neural network. Artificial neural networks with the backpropagation method can make a prediction on data. In this article, a prediction will be made on the amount of goat production in Indonesia. Goats are one of the livestock that can produce nutritious meat. The lack of goat meat will cause the price of goat meat to rise. Producing enough goat meat helps stabilize the price of meat, but if goat meat production is less than demand, it will lead to price increases. Therefore, looking at the problems above, this study aims to predict goat meat so that in the future it can know how much goat meat must be predicted by processing data first and then being used as input in predicting the amount of goat meat production. Prediction is one way to estimate future demand. Avoiding the lack of meat availability, by predicting the amount of goat meat produced in such a way that there is no scarcity of goat meat and fluctuations in the price of goat meat in the market. Basic methods and data are required to make predictions. In this study, data was obtained from BPS Indonesia in the livestock section using data from 2001-2021 as training data and 2002-2022 as test data. The method applied in this article is the backpropagation algorithm. This article applies 5 network architectures implemented in the mathlab application. The architecture used in this article is 20-25-1 with a Mean Squred Error testing 0.00447765, in 20-30-1 architecture produces Mean Squred Error 0.00300466, in 20-35-1 architecture produces 0.00426823, in 20-37-1 architecture produces 0.00357757. Based on the best architecture produced in this study, the 20-15-1 architecture with 90% accuracy with a Mean Squared Error testing 0.00262384 at epoch 27915 Iterations. Thus it can be concluded that the backpropagation algorithm can provide good accuracy in the prediction process. With this research, the livestock industry can utilize it as one of the materials to predict goat meat in the future

show abstract

“…Kambing adalah ruminansia berukuran sedang. Hewan yang banyak dipelihara oleh masyarakat Indonesia karena memiliki banyak manfaat dan dapat meningkatkan perekonomian salah satunya adalah kambing [5].…”

Section: Pendahuluanunclassified

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing di Indonesia

Rika Setiana,

Razalfa Aindi Siregar,

Fahry Husaini

et al. 2023

jieee

0

View full text Add to dashboard Cite

A science that has always developed rapidly until now is artificial neural networks. A computational science that works like the human nervous system is an artificial neural network. Artificial neural networks with the backpropagation method can make a prediction on data. In this article, a prediction will be made on the amount of goat production in Indonesia. Goats are one of the livestock that can produce nutritious meat. The lack of goat meat will cause the price of goat meat to rise. Producing enough goat meat helps stabilize the price of meat, but if goat meat production is less than demand, it will lead to price increases. Therefore, looking at the problems above, this study aims to predict goat meat so that in the future it can know how much goat meat must be predicted by processing data first and then being used as input in predicting the amount of goat meat production. Prediction is one way to estimate future demand. Avoiding the lack of meat availability, by predicting the amount of goat meat produced in such a way that there is no scarcity of goat meat and fluctuations in the price of goat meat in the market. Basic methods and data are required to make predictions. In this study, data was obtained from BPS Indonesia in the livestock section using data from 2001-2021 as training data and 2002-2022 as test data. The method applied in this article is the backpropagation algorithm. This article applies 5 network architectures implemented in the mathlab application. The architecture used in this article is 20-25-1 with a Mean Squred Error testing 0.00447765, in 20-30-1 architecture produces Mean Squred Error 0.00300466, in 20-35-1 architecture produces 0.00426823, in 20-37-1 architecture produces 0.00357757. Based on the best architecture produced in this study, the 20-15-1 architecture with 90% accuracy with a Mean Squared Error testing 0.00262384 at epoch 27915 Iterations. Thus it can be concluded that the backpropagation algorithm can provide good accuracy in the prediction process. With this research, the livestock industry can utilize it as one of the materials to predict goat meat in the future

show abstract

“…Pada citra digital sudah banyak dilakukan penerapan CNN, yaitu metode CNN-LSTM sudah banyak dilakukan, seperti [12] melakukan deskripsi gambar dengan memperhatikan fitur semantic, penelitian [13] menggunakan CNN-LSTM dimana deskripsi gambar yang dihasilkan cukup baik, penelitian [14] klasifikasi Populasi Ternak menggunakan CNN. Begitu pula dengan penelitian [15] menyimpulkan bahwa akurasi hasil prediksi kata menggunakan metode CNN lebih baik daripada LSTM.…”

unclassified

Perbandingan Arsitektur ResNet50 dan ResNet101 dalam Klasifikasi Kanker Serviks pada Citra Pap Smear

Niswati

¹

,

Hardatin²,

Muslimah³

et al. 2021

View full text Add to dashboard Cite

Cervical cancer is one of the most deadly types of cancer in women. Cervical cancer ranks second for the type of cancer that attacks women the most. Data from the Indonesian Ministry of Health, there are at least 15000 cases of cervical cancer every year in Indonesia. This cancer is a type of tumor that develops in the epithelial tissue of the cervix. In addition to HPV vaccination, cervical cancer detection can also be carried out with a Pap smear test and VIA examination supported by medical image tests such as CT scan, microscopic, and MRI. Pap smear test is a type of test to detect cervical cancer which is quite widely used because the cost of the test is cheaper than the HPV vaccination. This test is carried out by taking samples of uterine cells which are then analyzed for early detection of cervical cancer. Through a pap smear can be found the presence of HPV infection and abnormal cells that can turn into cancer cells. The purpose of this research is to apply the ResNet50 and ResNet101 architectures on pap smear images to identify cervical cancer and evaluate the performance of the ResNet50 and ResNet101 architectures in the classification of cervical cancer on pap smear images. In this study, CNN ResNet50 and ResNet101 were used to classify cervical cancer on pap smear images. This study has created two models to predict the grade of cervical cancer on pap smear images. The ResNet50 architecture gets 91% accuracy while the Res-Net101 architecture gets 89%. Although the architecture of ResNet101 is more complex than ResNet50, if viewed from the results of the model evaluation, ResNet101 has worse performance. This is due to the relatively small training data when trained with a large architecture such as ResNet101, not necessarily resulting in better accuracy.

show abstract

Analisis Klasifikasi Populasi Ternak Kambing Dan Domba Dengan Model Convolutional Neural Network

Cited by 3 publications

References 12 publications

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing Di Indonesia

Analisis Metode Backpropagation Dalam Memprediksi Jumlah Produksi Daging Kambing di Indonesia

Perbandingan Arsitektur ResNet50 dan ResNet101 dalam Klasifikasi Kanker Serviks pada Citra Pap Smear

Contact Info

Product

Resources

About