Mathematical Model of Drying Edamame (Glycine max (L.) Merill) Using Food Dehydrator Technology Based on Multiple Linear Regression (MLR) and Artificial Neural Network (ANN)

Rizza Wijaya (Politeknik Negeri Jember)
Silvia Oktavianur Yudiastuti (Politeknik Negeri Jember)
Anna Mardhiana Handayani (Politeknik Negeri Jember)
Elok Kurnia Novita Sari (Politeknik Negeri Jember)
Tri Wahyu Saputra (Universitas Jember)
Febryan Kusuma Wisnu (Universitas Lampung)
Aulia Brilliantina (Politeknik Negeri Jember)

Jurnal Teknik Pertanian Lampung (Journal of Agricultural Engineering)
Vol 11, No 4 (2022): Desember 2022

Edamame is included in perishable products or products that have a fairly short shelf life if post-harvest processing is not carried out. One of the post-harvest processing methods commonly used by the community is drying. The purpose of this study was to analyze the drying process of edamame related to the MLRL and ANN models. This study used a completely randomized design (CRD) with three variations of air velocity, namely 1 m/s, 3 m/s, and 5 m/s. Data collection was repeated three times every 30 minutes until 330 minutes.  Multiple linear regression (MLR) model training and validation produce accuracy values of 88.03 and 82.23, and the value of R2 of 0.93 and 0.90. While the training and validation of the artificial neural network (ANN) model resulted in accuracy values of 88.34 and 82.15, and R2 values of 0.93 and 0.90. Keywords:    ANN, Drying, Edamame, Food  dehydrator