Please use this identifier to cite or link to this item:
Title: Modeling energy use in dairy cattle farms by applying multi-layered adaptive neuro-fuzzy inference system (MLANFIS)
Authors: Sefeedpari, P
Rafiee, S
Akram, A
Chau, KW 
Komleh, SHP
Keywords: Adaptive neuro-fuzzy inference system
Dairy farm
Energy use
Milk production
Issue Date: 2015
Publisher: Asian Network for Scientific Information
Source: International journal of dairy science, 2015, v. 10, no. 4, p. 173-185 How to cite?
Journal: International Journal of Dairy Science 
Abstract: This study focused on the capability of two artificial intelligent approaches, including Artificial Neural Networks (ANNs) and Multi-Layered Adaptive Neural Fuzzy Inference System (MLANFIS), as a prediction tool to model and forecast milk yield on the basis of energy consumption in dairy cattle farms of Iran. For this purpose, data was collected from 50 farms in Tehran province, Iran. For the purpose of gaining the best accurate ANFIS model, five energy inputs were clustered into two groups based on their energy share in total energy consumption and an ANFIS network was trained for each cluster. The results of statistical parameter evaluation showed that ANFIS 1 and ANFIS 2 from layer one were not as accurate as ANFIS 3 network (layer two) whereas, coefficient of determination (R2), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) values were 0.75, 1256.72 and 0.129 for ANFIS 1 and 0.65, 1409.43 and 0.144 for ANFIS 2 and 0.93, 681.85 and 0.063 for ANFIS 3 network, respectively. These results were considerably better than ANNs model with R2, RMSE and MAPE calculated as 0.85, 1052.413 and 0.0702, respectively. Eventually, the outcomes revealed that multi-layered ANFIS contrasted to ANNs modeling could successfully predict the milk yield level accurately. Hence, it is recommended that the multi-layered ANFIS can potentially be applied as an alternative approach. ? 2015 Academic Journals Inc.
ISSN: 1811-9743
DOI: 10.3923/ijds.2015.173.185
Appears in Collections:Journal/Magazine Article

View full-text via PolyU eLinks SFX Query
Show full item record


Last Week
Last month
Citations as of Oct 9, 2018

Page view(s)

Last Week
Last month
Citations as of Oct 15, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.