Neural Network Application For The Analysis Of The Nutrition And Environment Effect To Microbial Growth Rate On Fermented Soybean Patty (Tempe) Fermentation

Nur Yanti, Fathur Zaini Rachman


The problems that still often faced by the industry in the processing of soybeans into tempe today is the lengthy process of fermentation is about 72 hours. The Long of fermentation will certainly slow down the productivity tempe. The long fermentation process is influenced by several factors such as the growth of microbial as microorganisms that do fermentation activity. The growth rate of microbes in the fermentation process is influenced by the content of the nutrient or nutrients that support the microbes can multiply rapidly perform cell division. In addition to nutrients, environmental factors such as acidity and temperature also affects to the growth rate of microbes. By applying Neural Network (Artificial Neural Networks), can produce a proper analysis to take into account the adequacy of nutrients, temperature stability and pH which accelerates the growth of tempe mold, so the fermentation process will go faster and the quality of tempe like the flavor and the aroma produced is better. The method that used is the combination method of qualitative and quantitative. The results of this study are the output data analysis results using a neural network to identify the composition of the nutrient content, temperature and pH is good and right for the fermentation process. The learning process of the neural network generates output data with high accuracy, namely with 2-4-1 architecture, learning rate 0:02, MSE 0.000999 <target error at epoch 315 0001 for nutrient content analysis. As for the temperature and pH stability analysis, learning outcomes network architecture yields 2-3-1, with learning rate 0:02, MSE 0.000986 <target error at epoch 295. 0001 performance results for the performance of the neural network is better than other architectures.


Tempe (Fermented Soybean Patty) Fermentation, Environment, Nutrients, Neural Network

Full Text:



Drs. Siang Jek Jong, M.Sc. 2009.

Jaringan Syaraf Tiruan & Pemrogramannya Menggunakan

Matlab. Andi Yogyakarta.

Fausett, L. 1994. Fundamentals of Neurals Network, Architecture, Algorithms, and Applications, Prentice Hall.

Haykin, S. 1994. Neural Networks, a Comprehensive Foundation, Prentice Hall.

Kosko, B. 1992. Neural Networks and Fuzzy Systems : A Dynamic Systems Approach to Machine Intelligence, Prentice Hall.

LiMin Fu. 1994. Neural Networks in Computer Intelligence. McGraw-Hill, Inc.

Kusumadewi, D. 2003. Artificial Intelligence, Teknik dan Aplikasi. Graha Ilmu. Yogyakarta.

Kusumadewi, D. 2004. Membangun Jaringan Syaraf Tiruan. Graha Ilmu. Yogyakarta

Nur Yanti, Maria Ulfa. 2015. Aplikasi Jaringan Syaraf Tiruan Untuk Clustering Polutan Kimia Penyebab Pencemaran Udara. Jurnal Teknologi Terpadu Politeknik Negeri Balikpapan ISSN 2338-6649.



  • There are currently no refbacks.

JTT (Jurnal Teknologi Terpadu) has been indexed by:




JTT Visitor Stats