Neural Network System to Forecast the Soybean Exportation on Brazilian Port of Santos

Abraham, Emerson Rodolfo; Reis, João Gilberto Mendes dos; Colossetti, Adriane Paulieli; Souza, Aguinaldo Eduardo de; Toloi, Rodrigo Carlo

doi:10.1007/978-3-319-66926-7_10

Cited by 3 publications

(2 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Oleh karena itu dibutuhkan sebuah analisis, perhitungan matematis serta implementasi proses penentuan rute jalan. Pendekatan baru dalam menyelesaikan perbedaan persepsi pemilihan rute digunakan metode fuzzy (Abraham, Toloi, Dos Reis, & Colossetti, 2016). Teori himpunan fuzzy memungkinkan untuk menerapkan deskripsi linguistik dalam pengambilan keputusan (Olenych et al, 2018).…”

Section: Pendahuluanunclassified

Analisis Pemilihan Rute dengan Logika Fuzzy

Kartika

Nahdalina

2023

jts

View full text Add to dashboard Cite

Pelaku perjalanan memiliki persepsi yang berbeda dalam menentukan arah rute perjalanan. Tujuan dari penelitian ini memprediksi pemilihan rute berdasarkan rute tercepat dengan mempertimbangkan variabel waktu tempuh, kecepatan rata-rata, dan derajat kejenuhan jalan. Metode yang digunakan terdiri dari kombinasi pemilihan rute dan pembobotan rute. Pembobotan rute tersebut dihitung menggunakan logika fuzzy metode Mamdani dengan menghasilkan bobot yang paling rendah. Penelitian dilakukan di Kabupaten Bogor dengan 1 asal dan 3 tujuan yang dihubungkan oleh 25 ruas jalan dan 19 titik simpul. Analisis yang dilakukan terdiri dari 2 skenario. Hasil analisis menunjukan bahwa rute yang dihasilkan berdasarkan skenario 1 dan skenario 2 berbeda. Hasil skenario 1 menggunakan waktu tempuh dan DS untuk asal 1 ke tujuan 2 melalui simpul 1-10-11-7-5-6-9-2 dengan nilai pembobotan sebesar 0,186, asal 1 ke tujuan 3 melalui simpul 1-10-12-13-14-3 dengan hasil pembobotan sebesar 0,224, dan asal 1 ke tujuan 4 melalui simpul 1-10-12-15-16-18-19-4 dengan hasil pembobotan sebesar 0,291. Sedangkan hasil skenario 2 kecepatan rata-rata dan DS untuk asal 1 tujuan 2 melalui simpul 1-10-11-7-8-9-2 dengan hasil pembobotan sebesar 0,198, asal 1 tujuan 3 melalui simpul 1-5-6-9-8-13-14-3 dengan hasil pembobotan sebesar 0,222, dan asal 1 tujuan 4 melaui simpul 1-5-6-9-8-13-12-15-16-17-19-4 dengan hasil pembobotan sebesar 0,208. Tingkat validasi program mencapai 99,91%.

show abstract

Section: Pendahuluanunclassified

Analisis Pemilihan Rute dengan Logika Fuzzy

Kartika

Nahdalina

2023

jts

View full text Add to dashboard Cite

show abstract

“…Abraham et al [40] propose to design, train, and simulate an ANN on to forecast the demand of soybean production in Mato Grosso state, Brazil that is exported by the port of Santos. A nonlinear autoregressive solution was adopted considering 80% of data for training, 5% to validation, and 15% for testing the network-a value of 9.0 million tons for 2017 as an increase of about 26.5% compared with the 2016.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Time Series Prediction with Artificial Neural Networks: An Analysis Using Brazilian Soybean Production

et al. 2020

Self Cite

View full text Add to dashboard Cite

Food production to meet human demand has been a challenge to society. Nowadays, one of the main sources of feeding is soybean. Considering agriculture food crops, soybean is sixth by production volume and the fourth by both production area and economic value. The grain can be used directly to human consumption, but it is highly used as a source of protein for animal production that corresponds 75% of the total, or as oil and derived food products. Brazil and the US are the most important players responsible for more than 70% of world production. Therefore, a reliable forecasting is essential for decision-makers to plan adequate policies to this important commodity and to establish the necessary logistical resources. In this sense, this study aims to predict soybean harvest area, yield, and production using Artificial Neural Networks (ANN) and compare with classical methods of Time Series Analysis. To this end, we collected data from a time series (1961–2016) regarding soybean production in Brazil. The results reveal that ANN is the best approach to predict soybean harvest area and production while classical linear function remains more effective to predict soybean yield. Moreover, ANN presents as a reliable model to predict time series and can help the stakeholders to anticipate the world soybean offer.

show abstract