OPTIMALISASI PENDISTRIBUSIAN MINYAK KELAPA SAWIT (CPO) MENGGUNAKAN JARINGAN SYARAF TIRUAN DENGAN METODE BACKPROPAGATION
DOI:
https://doi.org/10.24114/jmk.v8i1.33893Keywords:
Kata kunci, Backpropagation, Minyak Kelapa Sawit/Crude Palm Oil (CPO), Jaringan Syaraf Tiruan, Mean Square Error, Pendistribusian Optimal.Abstract
PT. Rimba Mujur Mahkota adalah sebuah perusahaan korporasi modern yang memiliki standar internasional berkecimpung dibidang industri kelapa sawit. PT. Rimba Mujur Mahkta memiliki masalah biaya pendistribusian dikarenakan sulitnya dalam menentukan jumlah kendaraan yang digunakan untuk pengiriman yang dapat menguras biaya distribusi. Penelitian ini bertujuan untuk mengoptimalkan biaya distribusi yang dikeluarkan PT. Rimba Mujur Mahkota menggunakan Jaringan Syaraf Tiruan dengan Metode Backpropagation. Untuk mengoptimalkan biaya distribusi, data yang telah didapatkan kemudian diolah dengan menentukan variabel keputusan, fungsi kendala, dan fungsi tujuan, diperoleh biaya distribusi optimal ialah Rp. 44.093.216 dari biaya distribusi sebelumnya Rp. 56.130.000 sehingga dapat menghemat biaya sebesar Rp. 12.235.572 untuk akurasi tertinggi sebesar 97.80% pada data 75%:25%, neuron hidden 6, learning rate (α) sebesar 0.5 dan jumlah epoch 5000 serta pengujian Mean Square Error (MSE) yaitu 0.0002. ABSTRACTPT. Rimba Mujur Mahkota is a modern corporate company that has international standards working in the palm oil industry. PT. Rimba Mujur Mahkta has a distribution cost problem due to the difficulty in determining the number of vehicles used for delivery which can drain distribution costs. This study aims to optimize distribution costs incurred by PT. Rimba Mujur Mahkota uses an Artificial Neural Network with Backpropagation Method. To optimize distribution costs, the data that has been obtained are then processed by determining the decision variables, constraint functions, and objective functions, the optimal distribution costs are Rp. 44,093,216 from the previous distribution cost of Rp. 56,130,000 so that it can save costs of Rp. 12,235,572 for the highest accuracy of 97.80% on data 75%:25%, 6 hidden neurons, learning rate (α) of 0.5 and the number of epochs of 5000 and the Mean Square Error (MSE) test of 0.0002.References
Imam, H., (2015): Analisis Pengaruh Produk, Harga, Distribusi, danPromosi Terhadap Keputusan Pembelian Serta Implikasinya pada Keputusan Pelanggan, Jurnal Ekonomi, Bisnis dan Entrepreneurship, 9(2), 80“101.
Hermawan, A., (2006): Jaringan Syaraf Tiruan, Teori, dan Aplikasi, Penerbit Andi, Yogyakarta.
Haykin, S., (2009): Nueral Networks and Learning Machines, Pearson, United State of America.
Lesnussa, Y.A dan Latuconsina, S., (2015): Sistem Jaringan Syaraf Tiruan Backpropagation untuk Prediksi Prestasi Siswa SMA, Jurusan Matematika, Fukultas MIPA., Univeritas Pattimura.
Sudarsono, A., (2016): JST Untuk Memprediksi Laju Pertumbuhan Penduduk Menggunakan Metode Backpropagation, Program Studi Teknik Informatika Fakultas Ilmu Komputer, Universitas Dehasen Bengkulu.
Puspitaningrum, D., (2006): Pengantar Jaringan Syaraf Tiruan, Andi, Yogyakarta.
Downloads
Published
Issue
Section
License
Copyright (c) 2022 KARISMATIKA: Kumpulan Artikel Ilmiah, Informatika, Statistik, Matematika dan Aplikasi
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.Penulis.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
