پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 158 |
| تعداد شماره‌ها | 6,226 |
| تعداد مقالات | 67,708 |
| تعداد مشاهده مقاله | 115,011,789 |
| تعداد دریافت فایل اصل مقاله | 89,695,084 |
مقایسۀ عملکرد شبکه‌‌های عصبیِ مصنوعی با تحلیل رگرسیون در برآورد حجم تنۀ درختان | ||
| نشریه جنگل و فرآورده های چوب | ||
| مقاله 5، دوره 66، شماره 2، تیر 1392، صفحه 177-191 اصل مقاله (750.63 K) | ||
| نوع مقاله: مقاله پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22059/jfwp.2013.35451 | ||
| نویسندگان | ||
| هادی بیاتی1؛ اکبر نجفی* 2 | ||
| 1کارشناس ارشد مهندسی جنگل، دانشکدۀ منابع طبیعی، دانشگاه تربیت مدرس | ||
| 2استادیار گروه جنگلداری دانشکدۀ منابع طبیعی، دانشگاه تربیت مدرس (نویسندۀ مسئول) | ||
| چکیده | ||
| آنالیز رگرسیون روش رایجی است که امروزه برای برآورد حجم تنۀ درختان استفاده می‌‌‌شود. این روش با تعیین رابطه‌‌ای، حجم را با دقت خاصی برآورد می‌‌کند، اما محدودیت‌‌هایی مانند نرمال‌بودن متغیر وابسته و همگن‌بودن واریانس خطاها نیز دارد. در این پژوهش سعی شده از شبکه‌‌های عصبی مصنوعی (ANN)، به‌عنوان یکی از زیر‌مجموعه‌‌های فنّاوری جدید هوش مصنوعی (AI)، به‌‌منظور برآورد حجم تنه، استفاده شود. بدین‌منظور، تعداد 101 درخت از درختان نشانه‌‌گذاری‌شدۀ جنگل آموزشی‌ـ‌پژوهشی دانشگاه تربیت مدرس انتخاب، و قطر برابر سینه، قطر در ارتفاع کنده، قطر انتهای تنه، ارتفاع تنه، و ارتفاع کل درخت، با دقت بسیار اندازه‌گیری شدند. از دو مدل شبکۀ عصبی، پرسپترون چند‌لایه (MLP) و تابع پایۀ شعاعی (RBF)، به‌‌منظور پیش‌‌بینی حجم تنه استفاده شد. نتایج نشان داد با افزایش متغیرهایی که همبستگی بیشتری با حجم تنه دارند، ضریب تشخیص شبکۀ عصبی از 80/0 به 95/0 افزایش می‌‌‌یابد. شبکۀ عصبی تابع پایۀ شعاعی در مقایسه با شبکۀ عصبی پرسپترون چند‌لایه دقت بیشتری در برآورد حجم تنه دارد. مقایسۀ معیارهای ارزیابی شبکۀ عصبی مصنوعی با رگرسیون گام‌به‌گام نشان داد که شبکۀ عصبی MLP و RBF به‌ترتیب دارای مقدار RMSE 18/1 و 05/1 است، درحالی‌که مقدار RMSE مدل رگرسیون 57/2 می‌‌‌باشد. ضریب تشخیص رگرسیون در مقایسه با هر دو مدل شبکۀ عصبی نیز مقدار کمتری است. | ||
| کلیدواژه‌ها | ||
| برآورد حجم تنۀ درخت؛ بهره‌‌برداری جنگل؛ پرسپترون چند‌لایه؛ مدیریت جنگل؛ تابع پایۀ شعاعی؛ رگرسیون؛ هوش مصنوعی | ||
| عنوان مقاله [English] | ||
| Performance Comparison Artificial Neural Networks with Regression Analysis in Trees Trunk Volume Estimation | ||
| نویسندگان [English] | ||
| Hadi Bayati1؛ Akbar Najafi2 | ||
| 1M.Sc Student, Faculty of Natural Resources, University of Tarbiat Modares, I. R. Iran | ||
| 2Corresponding author, Assistant Prof, Faculty of Natural Resources, University of Tarbiat Modares, I. R. Iran | ||
| چکیده [English] | ||
| Nowadays, regression analysis is a common method to estimate trees stem volume. Althought trees trunk volume can be estimated with a certain accuracy, however there are many constraints such as normality of variables and homogeneity of errors variance, when foresters use this method. In this study, Artificial Neural Networks (ANN) as a subset of the technology of Artificial Intelligence (AI), was used as a new method to estimate the volume trunk. For this purpose, 101 trees were selected. Marked trees were located in Research and Educational Forest of Tarbiat Modarres University (REFTMU). DBH, diameter at stump height, end diameter trunk, trunk height and total tree height were mesuared with high accuracy during tree marking. Two neural network models, multi-layer perceptron (MLP) and radial basis function (RBF), were developed to estimate trunk volume. The results showed that with increasing the number of variables, that have more correlation with trunk volume,correlation coefficient of neural networks increased from 0.80 to .95. Also the RBF neural network was more accuracte in trunk volume estimation than to MLP neural network. Comparing evaluation criteria for ANN with stepwise regression showed that MLP and RBF neural networks had RMSE value 1.18 and 1.05, respectively while the RMSE value of regression was 2.57. Also the regression correlation coefficient is less in compared with two models neural network. | ||
| کلیدواژه‌ها [English] | ||
| Artificial Intelligence, Forest harvesting, Forest management, Multi-Layer Perceptron, Radial Basis Function, Regression, trees trunk volume | ||
| مراجع | ||
|
[1]. Masumian, A. (1997). Study of shape of tree in order to estimation of the volume for beec species in veisar stand. MSc. Thesis. Faculty of Natural Resources, University of Tarbiat Modares. [2]. 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. [3]. Bihamta, M.R., and Chahouki, M.A.Z. (2008). Principles of Statistics for the Natural Resource Science. University of Tehran Press. [4]. Peng, C., and Wen. X, (1999). Recent applications of artificial neural networks in forest resource management: an overview. Environmental Decision Support Systems and Artificial Intelligence, 15-22. [5]. 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. [6]. Coulson, R.N., Folse, L.J., and Loh, D. K. (1987). Artificial intelligence and natural resource management. Science, (237): 262-267. [7]. McRoberts, R.E., Schmoldt, D.L., and Rauscher. H.M. (1991). Enhancing the Scientific process with artificial intelligence. Forest Science Applications, (5): 5-26. [8]. Lek, S., Delacoste, M., Baran, P., Dimopoulos, I., Lauques, J., Aulagnier, S. (1996). Application of neural networks to modelling nonlinear relation-ships in ecology. Ecol . Modell, 90(1): 39-52. [9]. Atkinson, P.M., and Tatnall, A.R. (1997). Introduction neural networks in remote sensing. International Journal of Remote Sensin, 18(4): 699-709. [10]. Strobl, R.O., and Forte, F. (2007). Artificial neural network exploration of the influential factors in drainage network derivation. Hydrological Processes, 21: 2965-2978. [11]. Dagli, C.H. (1994). Artificial neural networks for intelligent manufacturing. Operating Research Journal, Chapman & Hall, Ltd. London, UK. [12]. Wu, J.K. (1994). Neural networks and simulation methods, Marcel Dekker Inc, New York. [13]. Kavzoglu, T. (2009). Increasing the accuracy of neural network classification using refined training data. Environmental Modelling & Software, 24(7): 850–858. [14]. Civco, D.L., and Wanug, Y. (1994). Classification of multispectral, multitemporal, multisource Spatial data using artificial neural networks, Congress on Surveying and Mapping. USA. [15]. Benediktsson, J.A., Swain, P.H., and Erosy, O.K. (1990). Neural network approaches versus statistical methods in classification of multisource remote Sensing data. IEEE Transaction on Geosciences and Remote Sensing, 28(4): 540-551. [16]. Kia, M. (2010). Neural network in MATLAB, Kian Rayaneh Sabz Publisher. [17]. Rumelhart, D.E., Hinton, G.E., and Williams, R.J. (1986). Learning representations by backpropagating errors. Nature, 323 (9): 533-536. [18]. Norusis, M.J. (2007). SPSS Neural Networks 17.0. SPSS Inc. Chicago IL. [19]. Blackard, J.A., and Dean, D.J. (1999). Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables. Computers and Electronics in Agriculture, 24 (3): 231-251. [20]. Jensen, J.R., Qiu, F., and Ji, M. (1999). Predictive modelling of coniferous forest age using statistical and artificial neural network approaches applied to remote sensor data. International Journal of Remote Sensing 20(14): 2805-2822. [21]. Hasenauer, H., Merkl, D., and Weingartner, M. (2001). Estimating tree mortality of norway spruce stands with neural networks. Advances in Environmental Research, 5: 405-414. [22]. Leduc, D.J., Matney, T.G., Belli, K.L., and V.C.Jr, Baldwin. (2001). Predicting diameter distributions of longleaf pine plantations: A comparison between artificial neural networks and other accepted methodologies. Southern Research Station RS, 25: 1-18. [23]. Diamantopoulou, M.J. (2005). Artificial neural networks as an alternative tool in pine bark volume estimation. Computers and Electronics in Agriculture, 48: 235-244. [24]. Hanewinkela, M., Zhou, W., and Schill, Ch. (2004). A neural network approach to identify forest stands susceptible to wind damage. Forest Ecology and Management, 196(2): 227-243. [25]. Karaman, A., and Caliskan, E.. (2009). Affective factors weight estimation in tree felling time by artificial neural networks, Expert Systems with Applications, 36: 4491-4496. [26]. 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. [27]. Bayati, H. (2012). Application of Artificial Neural Networks in Assessment of Damages to Standing Trees in Forest Harvesting Operation. M.Sc Thesis. Tarbiat Modares University. [28]. Bayati, H., Najafi, A., and Abdolmaleki, P. (2013). Comparison between Artificial Neural Network (ANN) and Regression Analysis in Tree Felling Time Estimation ). Iranian Journal of Forest and Poplar Research, 20(4): 595-607. [29]. Zobeiry, M. 2000. Forest Inventory: (Measurement of Tree and Stand). Tehran University Publication. | ||
|
آمار تعداد مشاهده مقاله: 8,510 تعداد دریافت فایل اصل مقاله: 9,513 |
||