مقایسه بین شبکه عصبی مصنوعی و تحلیل رگرسیون در برآورد مدت زمان قطع درخت

نوع مقاله: علمی- پژوهشی

نویسندگان

1 دانشجوی کارشناسی ارشد، گروه جنگلداری، دانشکده منابع طبیعی و عوم دریایی دانشگاه تربیت مدرس

2 گروه جنگلداری، دانشکده منابع طبیعی و علوم دریایی دانشگاه تربیت مدرس

3 دانشیار، دانشکده علوم زیستی دانشگاه تربیت مدرس

چکیده

قطع درخت در بین مؤلفه‌های بهره‌برداری، اهمیت زیادی دارد. برآورد تولید تجهیزات جنگلی، بخش مهمی از مدیریت هزینه‌ها در یک واحد جنگلداری است که با کاهش هزینه‌های عملیات همراه است. به عبارت دیگر، هزینه‌های بالای سرمایه‌گذاری در بهره‌برداری جنگل، دلیل خوبی برای تحقیقات مهندسی جنگل و همچنین مدل‌سازی زمان می‌باشد. روشهای زیادی مانند انواع رگرسیون‌ها، منطق فازی، شبکه‌های عصبی و غیره برای پیش‌بینی زمان قطع وجود دارد که به کمک آنها می‌توان به ارتباط منطقی بین زمان قطع درخت و متغیرهای مستقل موجود دست یافت و برای عملیات آینده میزان زمان قطع درخت را پیش‌بینی نمود. در این تحقیق از تحلیل رگرسیون و شبکه‌‌های عصبی پرسپترون چند لایه و تابع شعاع مدار برای پیش‌بینی زمان قطع درخت در جنگلهای شرکت نکاچوب استفاده شد. به‌منظور جمع‌آوری داده‌های زمان قطع، از روش مطالعه زمانی پیوسته استفاده شد. بدین منظور تعداد 84 درخت از درختان نشانه‌گذاری شده انتخاب شد و زمان خالص قطع درخت با استفاده از شبکه پرسپترون چندلایه و تابع شعاع مدار، و همچنین روش رایج تحلیل رگرسیون پیش‌بینی گردید. نتایج نشان داد که شبکه عصبی تابع پایه شعاعی نسبت به شبکه عصبی پرسپترون چندلایه دارای دقت بیشتری در برآورد زمان قطع درخت می‌باشد. همچنین مقایسه معیارهای ارزیابی شبکه عصبی مصنوعی با رگرسیون گام‌به‌گام نشان داد که شبکه عصبی MLP و RBF به‌ترتیب دارای مقدار RMSE 0/94 و 81/0 بوده، در حالی که مقدار RMSE مدل رگرسیون 15/1 می‌باشد.

کلیدواژه‌ها


عنوان مقاله [English]

Comparison between artificial neural network (ANN) and regression analysis in tree felling time estimation

نویسندگان [English]

  • Hadi Bayati 1
  • Akbar Najafi 2
  • Parviz Abdolmaleki 3
1 M.Sc. student of forestry, Faculty of Natural Resources and Marine Sciences, University of Tarbiat Modares
2 Assistant prof., Faculty of Natural Resources and Marine Sciences, University of Tarbiat Modares
3 Associated prof, Faculty of Biological Sciences, University of Tarbiat Modares
چکیده [English]

Tree felling is a most important one among the tree harvesting components. Production estimation of forest equipments is an important part of cost management in forestry operational units which is associated with reduction of the operating expenses. In other words, the high cost of investment in forest utilization, is a good reason for forest engineering research and modeling time. Many techniques such as regression, fuzzy logic, neural networks, etc. are utilized to estimate trees felling time. They make a logical connection between the tree felling time and the independent variables and could be used to predict the tree felling time for the future operations. In this study the regression analysis, two neural network models, multi-layer perceptron (MLP) and radial basis function (RBF) were used to predict the trees felling time in the cutting operations of the Neka Choob Co. In order to collect the felling time data, the time continuous study method was applied. For this purpose, 84 trees were selected from the marked stands and the net felling time was estimated, using the Multi Layer Perceptron and Radial Basis Function and also by the common method of linear regression analysis. The results showed that the Radial Basis Function network provided more accurate results in estimating the net tree felling time than the MLP neural network. Comparing the evaluation criteria of ANN with the stepwise regression methods,  showed that MLP and RBF neural networks had RMSE value of 0.94 and 0.81, respectively whereas the RMSE value of the regression model was 1.15.

کلیدواژه‌ها [English]

  • Forest engineering
  • time study
  • Radial basis function
  • Multi Layer Perceptron
  • Forest harvesting
- Bayati, H. and Najafi, A., 2013. Performance comparison artificial neural networks with regression analysis in trees trunk volume estimation. Forest and Wood Products (Iranian Journal of Natural Resources), 66(1) (In Publish).

- Behjou, F.K., Majnounian, B., Dvořák, J., Namiranian, M., Saeed, A., Feghhi, J., 2009. Productivity and cost of manual felling with a chainsaw in Caspian forests. Journal of Forest Science, 55(2): 96–100.

- Dagli, C.H., 1994. Artificial neural networks for intelligent manufacturing. Operating Research Journal, 6(1): 25 p.

- Davis, C. and Kellogg, L., 2005. Measuring machine productivity with the MultiDat logger: A demonstration on three forest machines, IN: 2005 Annual COFE proceedings, Fortuna, CA, 10 pp.

- Dekker, S.C., Bouten, W. and Schaap, M.G., 2001. Analyzing forest transpiration model errors with artificial neural networks. Journal of Hydrology, 246(2): 197-208.

- Diamantopoulou, M.J., 2005. Artificial neural networks as an alternative tool in pine bark volume estimation. Computers and Electronics in Agriculture, 48(3): 235-244.

- Fathi, J., Azarnoosh, M.R., Rafatnia, N. and Mirarab, J., 2011. Prediction model of tree felling by chainsaw in selection system (Case study: Namkhaneh District, Kheiroud forest). Iranian Journal of Forest and Poplar Research, 19(2): 340-351.

- Gardner, R., 1963. New tools for harvesting. Pulp and Paper, 75 p.

- Ghanbari, F., Shataee, Sh., Dehghani, A.A. and Ayoubi, Sh., 2009. Tree density estimation of forests by terrain analysis and artificial neural network. Journal of Wood & Forest Science and Technology, 16(4): 25-42.

- Gimblett, R.H. and Ball, G.L., 1995. Neural network architectures for monitoring and simulating changes in forest resources management. AI Applications, 9(2): 103-123.

- Hasenauer, H., Merkl, D. and Weingartner, M., 2001. Estimating tree mortality of Norway spruce stands with neural networks. Advances in Environmental Research, 5(4): 405-414.

- Heinemann, H.R., 2004. Forest Operation under Mountainous Conditions. In: J. Burley, J. Evans and J. Youngquist, (Eds.). Encyclopedia of Forest Sciences, Elsevier Academic Press, Amsterdam, 279-285.

- Hilbert, D.W. and Ostendorf, B., 2001. The utility of artificial neural networks for modeling the distribution of vegetation in past, present and future climates. Ecological Modeling, 146(1): 311–327.

- Ingram, J.C., Dawson, T.P. and Whittaker, R.J., 2005. Mapping tropical forest structure in southeastern Madagascar using remote sensing and artificial neural networks. Remote Sensing of Environment, 94(4): 491–507.

- Jutras, P., Prasherb, S.O. and Mehuys, G.R., 2009. Prediction of street tree morphological parameters using artificial neural networks. Computers and Electronics in Agriculture, 67(1): 9–17.

- Karaman, A. and Caliskan, E., 2009. Affective factors weight estimation in tree felling time by artificial neural networks. Expert Systems with Applications, 36(3): 4491-4496.

- Kia, M., 2010. Neural network in MATLAB. Kian Rayaneh Sabz Publisher, 229 p.

- Laar, A., 1991. Forest Biometry. University of Stellenbosch, Publ. Sponsored by Sappi Forests, 590 p.

- Li, Y., Wang, J., Miller, G. and McNeel, J., 2006. Production economics of harvesting small-diameter hardwood stands in central Appalachia. Forest Products Journal, 56(3): 81-86.

- Lortz, D., Kluender, R., McCoy, W., Stokes, B. and Klepac, J., 1997. Manual felling time and productivity in southern forests. Forest Products Journal, 47(10): 59-63.

- Majnounian, B., Jourgholami, M., Zobeiri, M., Feghhi, J. and Fathi, J., 2009. Production and costs of tree limbing operation using chainsaw (case study: Namkhaneh district in Kheyrud forest). J. of Wood & Forest Science and Technology, 16(4): 43-57

- McDonald, T., 1999. Time study of harvesting equipment using GPS-derived positional data. In proceedings of the forestry engineering for tomorrow, Edinburgh University, Edinburgh, Scotland: 28-30.

- Melesse, A.M. and Hanley, R.S., 2005. Artificial neural network application for multi-ecosystem carbon flux simulation. Ecological Modeling, 189(3): 305–314.

- Menhaj, M.B., 2002. Neural Network Basis. Amir Kabir Industrial University Publication, Tehran, 715 p.

- Naghdi, R., Nikooy, M., Mohammadi Limaie, S. and Shormage, Y., 2010. Evaluation of felling productivity in Shafarood forest (Guilan province). Iranian Journal of Forest and Poplar Research, 18(3): 417-425.

- Nikooy, M., 2007. Optimizing production cost and damage reduction to wood, trees and forest by harvest planning (case study: Asalem forest district area). PhD Thesis, Dept. of Forest Management and Forest Economics, Faculty of Natural Resources, Tehran University, 215p.

- Norusis, M.J., 2000. SPSS for Windows, SPSS Inc Press, Chicago, USA.

Ozcelik, R., Diamantopoulou, M.J., Brooks, J.R. and Wiant, H.V.Jr., 2010. Estimating tree bole volume using artificial neural network models for four species in Turkey. Journal of Environmental Management, 91(3): 742-753.

- Pulido-Calvo, I., Montesinos, P., Roldan, J., Ruiz-Navarro, F., 2007. Linear regressions and neural approaches to water demand forecasting in irrigation districts with telemetry systems. Biosystems Engineering, 97(2): 283–293.

- Rummer, R. and Klepac, J., 2002. Mechanized or hand operations: which is less expensive for small timber? In: Baumgartner, D.M., Johnson, L.R. and DePuit, E.J., (Eds.). Small Diameter Timber: Resource Management, Manufacturing, and Markets proceedings from conference held February 25-27, 2002 in Spokane, Washington, 268 p.

- Safi Samghabadi, A., 2005. Interactive multiple criteria forest planning using artificial neural networks. PhD thesis, Dept. of Forestry, Faculty of Natural Resources and Marine Sciences, Tarbiat Modares University, Noor, Mazandaran Province, I.R. Iran, 156 p.

- Sarikhani, N., 2001. Forest utilization. University of Tehran Press, No. 2099, Second Edition, 776p.

- Sessions, J., Boston, K., Murphy, G., Wing, M.G., Kellogg, L., Pilkerton, S., Zweede, J.C., and Heinrich, R., 2007. Harvesting operation in the Tropics. Springer-Verlag, Berlin, Heidelberg, 170p.

- Sobhani, H., Ghaffarian, M.R. and Khakzade Rostami, M.J., 2007. Study of the production and cost of tree felling in Patom district at Kheyroudkenar Forest Education and Research Station. Journal of the Iranian Natural Res, 60(2): 485-491.

- Strobl, R.O. and Forte, F., 2007. Artificial neural network exploration of the influential factors in drainage network derivation. Hydrological processes, 21(22): 2965-2978.

- Wang, J., Long, C., McNeel, J. and Baumgras, J., 2004. Productivity and cost of manual felling and cable skidding in central Appalachian hardwood forests. Forest Products Journal, 54(12): 45-51.

- Wu, J.K. 1994. Neural networks and simulation methods. Marcel Dekker Inc, New York, 456 p.