Pengembangan Model RNN untuk Prediksi Produksi Daging Sapi dalam Perencanaan Pembangunan Nasional

Yulianingsih Yulianingsih; Tri Yani Akhirina; Za’imatun Niswati

doi:10.30998/faktorexacta.v15i3.12820

Pengembangan Model RNN untuk Prediksi Produksi Daging Sapi dalam Perencanaan Pembangunan Nasional

Yulianingsih Yulianingsih^(1*), Tri Yani Akhirina⁽²⁾, Za’imatun Niswati⁽³⁾

(1) Universitas Indraprasta PGRI
(2) Universitas Indraprasta PGRI
(3) Universitas Indraprasta PGRI
(*) Corresponding Author

Abstract

Data is an important component because it will support in policies / decisions making, serve as control tools to prevent error from occuring and support transparent, accountable and participative governance. This study examines the prediction of beef production and product consumption with the Long Short Term Memory (RNN LSTM) Recurrent Neural Network approach. Using statistical data on beef production and consumption of products per capita per week from BPS. The data used were 12 records for each data source. LSTM contains information outside the normal flow of recurrent network in the gate cell. Cell makes decisions about what should be stored and when to permit reading, writing and deletion, through open and closed gates. The gate conveys information based on the strength that enters into it and will be filtered to be the weight of the gate itself. These weights are the same as the input and hidden unit weights that are adjusted through learning process on the recurrent network. The results of research carried out by building prediction models of beef production and product consumption get the best results using data for 3 years with RMSE 32121.297 for beef production and 0.001 for product consumption.

Full Text:

PDF

References

Direktorat Jenderal Peternakan dan Kesehatan Hewan, Statistik Peternakan dan Kesehatan Hewan 2018/ Livestock and Animal Health Statistics 2018. 2018.

S. Rusdiana, “Fenomena Kebutuhan Pangan Asal Daging Dapat Dipenuhi Melalui Peningkatan Usaha Sapi Potong Di Petani,” SOCA J. Sos. Ekon. Pertan., vol. 13, no. 1, p. 61, 2019.

N. Ilham, “Kebijakan Pengendalian Harga Daging Sapi Nasional,” Kebijak. Pengendali. Harga Daging Sapi Nas., vol. 7, no. 3, pp. 211–221, 2016.

A. A. Rizal and S. Hartati, “PREDIKSI KUNJUNGAN WISATAWAN DENGAN RECURRENT NEURAL NETWORK EXTENDED KALMAN FILTER Program Studi Informatika , STMIK Bumigora Mataram Jurusan Ilmu Komputer dan Elektronika , FMIPA UGM , Yogyakarta,” vol. X, no. 1, pp. 7–18, 2017.

A. Mali, A. Ororbia, D. Kifer, and C. L. Giles, “Recognizing Long Grammatical Sequences Using Recurrent Networks Augmented With An External Differentiable Stack,” 2020.

D. Lee et al., “Long short-term memory recurrent neural network-based acoustic model using connectionist temporal classification on a large-scale training corpus,” China Commun., vol. 14, no. 9, pp. 23–31, 2017.

T. Mikolov, M. Karafiát, L. Burget, C. Jan, and S. Khudanpur, “Recurrent neural network based language model,” Proc. 11th Annu. Conf. Int. Speech Commun. Assoc. INTERSPEECH 2010, no. September, pp. 1045–1048, 2010.

F. A. Gers and J. Schmidhuber, “LSTM recurrent networks learn simple context-free and context-sensitive languages,” IEEE Trans. Neural Networks, vol. 12, no. 6, pp. 1333–1340, 2001.

A. A. Rizal and S. Soraya, “Multi Time Steps Prediction Dengan Recurrent Neural,” vol. 18, no. 1, pp. 115–124, 2018.

Machinelearningmastery.com, “No Title.” [Online]. Available: https://machinelearningmastery.com/time-series-forecasting-long-short-term-memory-network-python/.

E. C. Djamal, “Prediksi Harga Saham menggunakan Metode Recurrent Neural Network,” Semin. Nas. Apl. Teknol. Inf. 2019, p. A-33-A-38, 2019.

R. C. Staudemeyer and E. R. Morris, “Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks,” no. September, 2019.

DOI: http://dx.doi.org/10.30998/faktorexacta.v15i3.12820