Lamb meat quality assessment by support vector machines

• Author(s): Cortez, Paulo ; Portelinha, Manuel ; Rodrigues, Sandra ; Cadavez, Vasco ; Teixeira, A.
• Date: 2006
• Persistent ID: http://hdl.handle.net/10198/858
• Origin: Biblioteca Digital do IPB
• Subject(s): Regression; Multilayer perceptrons; Support vector machines; Meat quality; Data mining; Feature selection
• Document Type: Article
• Language: English

Description

The correct assessment of meat quality (i.e., to fulfill the consumer's needs) is crucial element within the meat industry. Although there are several factors that affect the perception of taste, tenderness is considered the most important characteristic. In this paper, a Feature Selection procedure, based on a Sensitivity Analysis, is combined with a Support Vector Machine, in order to predict lamb meat tenderness. This real-world problem is defined in terms of two difficult regression tasks, by modeling objective (e.g. Warner-Bratzler Shear force) and subjective (e.g. human taste panel) measurements. In both cases, the proposed solution is competitive when compared with other neural (e.g. Multilayer Perceptron) and Multiple Regression approaches.