مقایسه عملکرد شبکه‌های عصبی پرسپترون چندلایه و توابع با پایه شعاعی در برآورد ستانده انرژی مرغ گوشتی

عمید, سما; مصری گندشمین, ترحم; شاهقلی, غلامحسین

doi:10.22059/ijbse.2016.58781

مقایسه عملکرد شبکه‌های عصبی پرسپترون چندلایه و توابع با پایه شعاعی در برآورد ستانده انرژی مرغ گوشتی

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشگاه محقق اردبیلی

10.22059/ijbse.2016.58781

چکیده

مدیریت انرژی یکی از اصلی‌ترین راه‌های بهینه‌سازی مصرف منابع انرژی است. پیش‌بینی عملکرد محصولات بر اساس ورودی‌های انرژی می‌تواند به کشاورزان و سیاست‌گذاران به منظور برآورد سطح تولید کمک کند. داده‌های مورد نیاز برای مطالعه به طور تصادفی از 70 مزرعه مرغ‌گوشتی در شمال‌غرب ایران جمع‌آوری گردید. انرژی‌های ورودی شامل نیروی انسانی، ماشین‌آلات، سوخت، خوراک و الکتریسیته و انرژی‌های خروجی تولید شده به عنوان متغیرهای خروجی در نظر گرفته شد. شبکه‌های عصبی پرسپترون چندلایه (MLP) و تابع با پایه شعاعی (RBF) به منظور پیش‌بینی انرژی‌های خروجی تولید مرغ‌گوشتی مورد استفاده قرار گرفت. با توجه به نتایج مقایسه به‌دست آمده از شاخص‌های ضریب تبیین (R²)، جذر میانگین مربعات خطا (RMSE) و میانگین قدرمطلق خطا (MAE) عملکرد مدل شبکه عصبی RBF بهتر از شبکه عصبی MLP برآورد گردید. در ارزیابی تأثیرپذیری خروجی از نهاده‌های ورودی، در هر دو مدل سوخت فسیلی بالاترین حساسیت را در بین نهاده‌های تولیدی از خود نشان داد.

کلیدواژه‌ها

20.1001.1.20084803.1395.47.2.13.6

موضوعات

انرژی

عنوان مقاله [English]

Comparison of MLP and RBF neural networks performance for estimation of broiler output energy

نویسندگان [English]

Sama Amid
Tarahom Mesri Gundoshmian
Gholamhossein Shahgoli

چکیده [English]

Energy management is one of the main ways of the efficient use of energy resources. The prediction of crop yields based on energy inputs can help farmers and policymakers to estimate the level of production. Required data for study were randomly collected from 70 broiler farms in North West of Iran. The input energies were included human labour, machinery, fuel, feed and electricity and the output produced energies were considered as output variables. The multi-layer perceptron (MLP) and the radial basis function (RBF) neural networks were applied for prediction of output energies of broiler production. According to the comparison results obtained from the indices of the coefficient of determination (R2), root mean square error (RMSE) and the mean absolute error (MAE) performance of the ANN-RBF model better than ANN-MLP model was estimated. In evaluating the effects of inputs on outputs of production, the production of fossil fuel showed the highest sensitivity among the production inputs in both models.

کلیدواژه‌ها [English]

Energy management
Energy resources
prediction
Sensitivity

مراجع

Alrwis, K.N. & Francis, E. (2003). Technical efficiency of broiler farms in the central region of Saudi Arabia. Research Bulletin, 116, 5-34.

Amid, A. (2014). Assessment of energy efficiency in poultry production units using fuzzy techniques, case study: Ardabil province. M.Sc. dissertation thesis, University of Mohaghegh Ardabili, Iran, (In Farsi).

Amid, S., Mesri-Gundoshmian, T., Rafiee, S. & Shahgoli, G. (2015). Energy and economic analysis of broiler production under different farm sizes. Elixir Agriculture, 78, 29688-29693.

Anonymous. (2013). Statistics and information of Agricultural Jihad of Ardebil province. Department of Animal Production.

Atilgan, A. & Hayati, K. (2006). Cultural energy analysis on broilers reared in different capacity poultry houses. Italian Journal of Animal Science, 5, 393-400.

Berg, M.J., Tymoczkyo, L.J. & Stryer. L. (2002). Biochemistry (5th ed). New York: W.H. Freeman.

Celik, L.O. & Ozturkcan, O. (2003). Effects of dietary supplemental L-carnitine and ascorbic acid on performance, carcass composition and plasma L-carnitine concentration of broiler chicks reared under different temperature. Archives of Animal Nutrition, 57(1), 27-38.

Chauhan, N.S., Mohapatra, P.K.J. & Pandey, K.P. (2006). Improving energy productivity in paddy production through benchmarking: an application of data envelopment analysis. Energy Conversion and Management, 47, 1063–1085.

Cochran, W.G. (1977). Sampling Techniques. Third Edition.

Dawson, C.W. & Wilby, R. (1998). An artificial neural network approach to rainfall-runoff modelling. Mathematical and Computer Modelling, 43(1), 47-66.

Deh Kiani, M.K., Ghobadian, B., Tavakoli, T., Nikbakht, A.M. & Najaﬁ, G. (2010). Application of artiﬁcial neural networks for the prediction of performance and exhaust emissions in SI engine using ethanol- gasoline blends. Energy, 35, 65-69.

Foody, G.M. (2004). Supervised image classiﬁcation by MLP and RBF neural networks with and without an exhaustively deﬁned set of classes. International Journal of Remote Sensing, 25(15), 3091–3104.

Heidari, M.D., Omid M. & Akram, A. (2011a). Energy efficiency and econometric analysis of broiler production farms. Energy, 36, 6536-6541.

Heidari, M.D., Omid, M. & Akram, A. (2011b). Application of Artificial Neural Network for Modeling Benefit to Cost Ratio of Broiler Farms in Tropical Regions of Iran. Research Journal of Applied Science, Engineering and Technology, 3(6), 546–552.

Heidari, M.D., Omid, M. & Akram, A. (2013). An investigation on energy consumption and the effects of number of chicks and ventilation system type on energy efficiency of broiler farms of Yazd province. Journal of Researches in Mechanics of Agricultural Machinery, 1(1), 33–39, (In Farsi).

Khoshnevisan, B., Rafiee, S., Omid, M., Mousazadeh, H. (2014). Application of multi-layer adaptive neure-fuzzy inference system for estimation of greenhouse strawberry yield. Measurement, 47, 903-910.

Khoshnevisan, B., Bolandnazar, E., Barak, S., Shamshirband, S., Maghsoudlou, H., Altameem, T.A. & et al. (2014). A clustering model based on an evolutionary algorithm for better energy use in crop production. Stochastic Environmental Research and Risk Assessment.

Kitani, O. (1999). CIGR handbook of agricultural, volume 5: Energy and biomass engineering. ASAE publications, St Joseph, MI.

Mohammadi, A., Tabatabaeefar, S., Shahin, S., Raﬁee, S. & Keyhani, A. (2008). Energy use and economical analysis of potato production in Iran a case study: Ardabil province. Energy Conversion and Management, 49, 3566–3570.

Mohammadshirazi, A., Akram, A., Raﬁee, S. & Bagheri Kalhor, E. (2015). On the study of energy and cost analyses of orange production in Mazandaran province. Sustainable Energy Technologies and Assessments, 10, 22-28.

Nabavi-Pelesaraei, A., Fallah, A. & Hematian, A. (2013). Relation between energy inputs and yield of broiler production in Guilan province of Iran. In: The Second International Conference on Agriculture and Natural Resources, 25-26 Dec, Razi University, Kermanshah, Iran, pp. 109-117.

Naderloo, L., Alimardani, R., Omid, M., Sarmadian, F., Jvadikia, P., Torabi, M. Y & Alimardani, F. (2012). Application of ANFIS to predict crop yield based on different energy inputs. Measurement, 45, 1406–1413.

Pahlavan, R., Omid, M. & Akramm, A. (2012). Energy input-output analysis and application of artificial neural networks for predicting greenhouse basil production. Energy. 37, 171–176.

Rahman, M.M. & Bala, B.K. (2010). Modeling of jute production using artificial neural networks. Biosystems Engineering, 105, 350-356.

Safa, M. & Samarasinghe, S. (2011). Determination and modelling of energy consumption in wheat production using neural networks: A case study in canterbury province, Newzealand. Energy, 36, 5140–5147.

Sajikumar, N. & Thandaveswara, B.S. (1999). A nonlinear rainfall-runoff model using artificial neural networks. Journal of Hydrology, 216, 32-55.

Salehi, M., Ebrahimi, R., Maleki, A. & Ghasemi Mobtaker, H. (2014). An assessment of energy modeling and input costs for greenhouse button mushroom production in Iran. Journal of Cleaner Production, 64, 377-383.

Sefeedpari, P., Rafiee, S. & Akram, A. (2012). Modeling of energy output in poultry for egg production farms using Artificial Neural networks. Journal of Animal Production Advances, 2(5), 247–253.

Shamshirband, S., Khoshnevisan, B., Youseﬁ, M., Bolandnazar, E., Badrul Anuar, N., Abdul Wahab, A.W. & Rehman Khan, S.U. (2015). A multi-objective evolutionary algorithm for energy management of agricultural systems—A case study in Iran. Renewable and Sustainable Energy Reviews, 44, 457-465.

Sung, A. H. (1998). Ranking importance of input parameters of neural networks. Expert Systems with Applications, 15, 405-411.

Venkatesan, P. & Anitha, S. (2006). Application of a radial basis function neural network for diagnosis of diabetes mellitus. Current Science, 91(9), 1195–1199.

Xianhai, G. (2011). Study of emotion recognition based on electrocardiogram and RBF neural network. Procedia Engineering, 15, 2408–2412.

Youseﬁ, M., Khoramivafa, M. & Mondani, F. (2014). Integrated evaluation of energy use, greenhouse gas emissions and global warming potential for sugar beet (Beta vulgaris) agroecosystems in Iran. Atmospheric Environment, 92, 501-505.

Zhao, Z., Chow, T.L., Rees, H.W., Yang, Q., Xing, Z. & Meng, F.R. (2009). Predict soil texture distributions using an artiﬁcial neural network model. Computers and Electronics in Agriculture, 65(1), 36–48.