Prediction of Feed Utilization Performance in Clarias gariepinus Using Multiple Linear Regression in Machine Learning
Journal: Journal of Bioresource Management (JBM) (Vol.7, No. 2)Publication Date: 2020-06-01
Authors : Adekunle Oluwatosin Familusi;
Page : 79-87
Keywords : Machine learning; protein efficiency ratio; weight gain; specific growth rate; feed conversion ratio;
Abstract
Machine learning models can be used to make predictions about nutrient utilization performance index using available proximate analysis data on feed composition. Data from similar experiments on nutrient utilization performance was used to fit a multiple linear regression model for the prediction of four performance indexes. The Specific Growth Rate and percentage inclusion with strength of 0.57 was noted along with a negative relationship between protein efficiency and protein content. A negative relationship between Nitrogen Free Extract (NFE) and Protein Efficiency Ratio (PER) at NFE content ≥25 % was observed. PER was predicted with 85 % accuracy, while Weight Gain (WG), Feed Conversion Ratio (FCR) and Specific Growth Rate (SGR) were predicted at 48 %, 7.6 % and 4.2 % respectively. WG model showed highest coefficient value to ash content (1.23) which is less likely to contribute to fish weight compared to values of fat content (-0.34) and crude protein (-1.02). FCR and SGR models appeared to be dependent on variables outside those included in the proximate analysis data for this study.
Other Latest Articles
- Trends in Cancer Prevalence in Punjab, Pakistan: A Systematic Study from 2010 to 2016
- Physical and Chemical Properties of Soils in Gambari Forest Reserve Near Ibadan, South Western Nigeria
- Feeding Ecology, Behaviour and Habitat Utilization of Black Drongo (Dicrurus Macrocercus) in Pothwar Plateau, Pakistan
- Survey of human-leopard (Panthera Pardus) conflict in Ayubia National Park, Pakistan
- Use of Different Agro-wastes in the Cultivation of Pleurotus ostreatus (Jacq.) Kummer
Last modified: 2020-11-19 19:06:34