Improving Microbial Growth Prediction By Product Unit Neural Networks
نویسندگان
چکیده
This paper presents a new approach to the Artificial Neural Networks (ANN) modelling of bacterial growth; using Neural Network models based on Product Units (PUNN) instead of on sigmoidal units (MLP) of kinetic parameters (lag-time, growth rate and maximum population density) of Leuconostoc mesenteroides and those factors affecting their growth such as storage temperature, pH, NaCl and NaNO 2 concentrations under anaerobic conditions. To enable the best degree of interpretability possible, a series of simple rules to simplify the expresión of the model were setted up. The new model PUNN was compared to RS and MLP estimations developed previously. Standard Estimation Error of generalization (SEP G ,) values obtained by PUNN were lower for Lag and GR but higher for yEnd than MLP when validated against a new data set. In all cases B f and A f were close to unity, which indicates a good fit between the observations and predictions for the three models. In our study, PUNN and MLP models were more complex than the RS models, especially in the case of the parameter Gr, but described lower SEP G. With this work we have pretend to propose a new approach to neural nets estimations for its application on predictive microbiology, searching for models with easier interpretation and that has the advantage of having a great ability to fit the boundaries of the range of the input factors. We consider that still there is a lot left to do but PUNN could be very valuable instrument for mathematical modeling.
منابع مشابه
Product Yields Prediction of Tehran Refinery Hydrocracking Unit Using Artificial Neural Networks
متن کامل
Prediction of methanol loss by hydrocarbon gas phase in hydrate inhibition unit by back propagation neural networks
Gas hydrate often occurs in natural gas pipelines and process equipment at high pressure and low temperature. Methanol as a hydrate inhibitor injects to the potential hydrate systems and then recovers from the gas phase and re-injects to the system. Since methanol loss imposes an extra cost on the gas processing plants, designing a process for its reduction is necessary. In this study, an accur...
متن کاملApplication of Artificial Neural Networks (ANN) and Image Processing for Prediction of Gravimetrical Properties of Roasted Pistachio Nuts and Kernels
Roasting is among the most common methods of nut processing causing physical and chemical changes and ultimately increasing overall acceptance of the product. In this research, the effects of temperature (90, 120 ,and 150°C), time (20, 35 ,and 50 min) ,and roasting air velocity (0.5, 1.5 ,and 2.5 m/s) on gravimetrical properties of pistachio nuts and kernels including unit mass, true density, o...
متن کاملAn Adaptive Fuzzy Neural Network Model for Bankruptcy Prediction of Listed Companies on the Tehran Stock Exchange
Nowadays, prediction of corporate bankruptcy is one of the most important issues which have received great attentions among academia and practitioners. Although several studies have been accomplished in the field of bankruptcy prediction, less attention has been devoted for proposing a systematic approach based on fuzzy neural networks. The present study proposes fuzzy neural networks to predi...
متن کاملEvolutionary product unit based neural networks for regression
This paper presents a new method for regression based on the evolution of a type of feed-forward neural networks whose basis function units are products of the inputs raised to real number power. These nodes are usually called product units. The main advantage of product units is their capacity for implementing higher order functions. Nevertheless, the training of product unit based networks po...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2005