1995
DOI: 10.13031/2013.27977
|View full text |Cite
|
Sign up to set email alerts
|

Techniques for Development of Swine Performance Response Surfaces

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
7
0

Year Published

1998
1998
2024
2024

Publication Types

Select...
7
1

Relationship

0
8

Authors

Journals

citations
Cited by 12 publications
(7 citation statements)
references
References 1 publication
0
7
0
Order By: Relevance
“…Real-time or prospective: These procedures generate models that continuously modify their responses to inputs and outputs by estimating system parameters in real time. In PLF or precision livestock feeding applications, examples of these models are included in some research [33][34][35][36].…”
Section: Data Processingmentioning
confidence: 99%
“…Real-time or prospective: These procedures generate models that continuously modify their responses to inputs and outputs by estimating system parameters in real time. In PLF or precision livestock feeding applications, examples of these models are included in some research [33][34][35][36].…”
Section: Data Processingmentioning
confidence: 99%
“…Model parameters are estimated on-line during the process, resulting in a model that continuously adapts its response to on-line process inputs and outputs. There are few examples in which these models have been used in PLF or precision livestock feeding applications (Korthals et al, 1994;Bridges et al, 1995;Aerts et al, 2000;Thomson and Smith, 2000). The limitation of using the recursive approach in precision livestock feeding is related to the fact that model parameters and model structure do not provide biological insight in the causal mechanisms implicated in animal responses, that animal response and input parameters may have unsymmetrical variation, and that the animal responses to input variation does not evolve in the same timeframe.…”
Section: Data Processingmentioning
confidence: 99%
“…The disadvantages associated with black-box models can be overcome by using an intermediate approach of grey-box models in which recursive technologies and mechanistic models are combined. This approach was suggested by Bridges et al (1995) who used a mechanistic swine growth model to generate physiological response data and this response data were then used to train and validate three backward propagation neural network models describing the effect of the environment on average daily gain, feed intake, heat production, and physiological status of the animal. The authors concluded that neural network models can be used to simplify data extraction from complex models and be used in instances where the use of the full model is difficult or impossible.…”
Section: Data Processingmentioning
confidence: 99%
“…An important advantage of such mechanistic models is that they represent the state-of-the-art knowledge of the considered system [7, 90–93], and are particularly useful in the general scientific process of connecting biophysical findings to psychophysical phenomena, generating new hypotheses and developing new assertions [94], and improving reliability of drug development and drug dosing [13]. However, in terms of direct translational utility in terms of clinical decision-making (monitoring and/or controlling of systems), these models are either too unwieldy [95, 96] or contain too much uncertainty [94]. …”
Section: Applications Of Mechanistic Models To Acute Critical Illnessmentioning
confidence: 99%