Klasifikasi Tingkat Kematangan dan Kemasakan Buah Durian dengan Model Neural Network


Amin Rejo(1*), Hadi K. Purwadaria(2), I Wayan Budiastra(3), Suroso Suroso(4), Slamet Susanto(5), Yul Y Nazaruddin(6)

(1) Program Studi Keteknikan Pertanian FAPERTA UNSRI, Palembang
(2) Jurusan Keteknikan Pertanian, Fakultas Teknologi Pertanian, IPB, Bogor
(3) Jurusan Keteknikan Pertanian, Fakultas Teknologi Pertanian, IPB, Bogor
(4) Jurusan Keteknikan Pertanian, Fakultas Teknologi Pertanian, IPB, Bogor
(5) Jurusan Budidaya Pertanian, IPB, Bogor
(6) Jurusan Teknik Fisika Fakultas Teknik Industri, ITB, Bandung
(*) Corresponding Author


This study was aimed to develop the model to predict the maturity and ripeness of durian based on its physical and chemical characteristics using neural network. The physicochemical and acoustic characteristics measurement was fed into the model as the inputs, which provided the levels of maturity and ripeness as the output of the model. The results suggested that the physico-chemical properties and the acoustic charcteristic decreased with the increase of both maturity and ripeness level of durian. The total solid soluble, the water content and the total sugar increased according to the fruits maturity. The total acids increased in the beginning of durian maturing process and then decreased when the maturity and ripeness level reached the mature-over ripened stage. Data training were done by model of neural network: model 4 output, with various node in the hidden layer 4, 6, 8 and 10 nodes. The results recommended that the best model to be applied was model 4 output with 4 nodes in the hidden layer and iteration 1000 and 5000 with the model accuration 87.5 % - 100%.


Neural network; durian; maturity and ripeness

Full Text:


DOI: https://doi.org/10.22146/agritech.13583

Article Metrics

Abstract views : 1807 | views : 2804


  • There are currently no refbacks.

Copyright (c) 2016 Amin Rejo, Hadi K. Purwadaria, I Wayan Budiastra, Suroso Suroso, Slamet Susanto, Yul Y Nazaruddin

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

agriTECH has been Indexed by:

agriTECH (print ISSN 0216-0455; online ISSN 2527-3825) is published by Faculty of Agricultural Technology, Universitas Gadjah Mada in colaboration with Indonesian Association of Food Technologies.

website statisticsView My Stats