5 Hits in 6.8 sec

Decentralized direct and indirect I-term adaptive fuzzy-neural control of a bioprocess plant

Ieroham S. Baruch, Sergio M. Hernandez, S. Eloy Echeverria, Oscar Castillo
2012 2012 Annual Meeting of the North American Fuzzy Information Processing Society (NAFIPS)  
The paper proposed to use a recurrent neural network model, and a real-time Levenberg-Marquardt algorithm of its learning for decentralized fuzzy-neural data-based modeling, identification and control  ...  of an anaerobic digestion bioprocess, carried out in a fixed bed and a recirculation tank of a wastewater treatment system.  ...  The Levenberg -Marquardt (L-M) recursive algorithm of learning, [21] , could be considered as a continuation of the BP algorithm and it will be used here.  ... 
doi:10.1109/nafips.2012.6291050 fatcat:azbcaumpxjbbxlnfnv7wbchvqi

Distributed Parameter Bioprocess Plant Identification and I-Term Control Using Decentralized Fuzzy-Neural Multi-Models [chapter]

Ieroham Baruch, Rosalba Galvan-Guerra, Sergio-Miguel Hernandez
2011 Advances in Reinforcement Learning  
Conclusion The chapter proposed decentralized recurrent fuzzy-neural identification, direct and indirect I-term control of an anaerobic digestion wastewater treatment bioprocess, composed by a fixed bed  ...  MSE of the indirect decentralized HFNMM I-term control of the bioprocess plant Distributed Parameter Bioprocess Plant Identification and I-Term Control Using Decentralized Fuzzy-Neural Multi-Models  ... 
doi:10.5772/13491 fatcat:unpzkui3pzdjbhi4yzuz77mp5e

Artificial neural networks

J.J. Hopfield
1988 IEEE Circuits & Devices  
optimal k-means adaptive clustering [117] to update the centres and spreads on-line, and to use a version of a recursive least-squares algorithm [69] to compute the linear weights.  ...  A different implementation of the Levenberg-Marquardt algorithm, employing a linesearch algorithm (using the lsqnonlin.m of the Optimization Toolbox).  ...  The problem is that there is not a particular method for doing that, and it is matter of ingenuity. fig. A3.4 ) , and in this case we speak of a limit cycle, or can have other forms.  ... 
doi:10.1109/101.8118 fatcat:c6royelcdzfethnmmur2tj524i

A review on computer vision systems in monitoring of poultry: A welfare perspective

Cedric Okinda, Innocent Nyalala, Tchalla Korohou, Celestine Okinda, Jintao Wang, Tracy Achieng, Patrick Wamalwa, Tai Mang, Mingxia Shen
2020 Artificial Intelligence in Agriculture  
properties, and its ability to present a wide range of information.  ...  With the current development in information technologies, computer vision has become a promising tool in the real-time automation of poultry monitoring systems due to its non-intrusive and non-invasive  ...  Acknowledgments The project was funded by China National Key Research and Development project (Grant No. 2017YFD0701602-2)  ... 
doi:10.1016/j.aiia.2020.09.002 fatcat:yhi7axzj7nasvk6jj5jwi6wy7m

Neural networks for variational problems in engineering

R. Lopez, E. Balsa-Canto, E. Oñate
2008 International Journal for Numerical Methods in Engineering  
The objective of this PhD Thesis is to develop a conceptual theory of neural networks from the perspective of functional analysis and variational calculus.  ...  Only some of these, regarded as variational problems, can be solved analytically, and the only general technique is to approximate the solution using direct methods.  ...  Also, Franco-Lara and Weuster-Botz [35] estimated optimal feeding strategies for bed-batch bioprocesses using neural networks.  ... 
doi:10.1002/nme.2304 fatcat:22lvukm4vncf5hhj5mr5yqrtuq