| 光谱学与光谱分析 |
|
|
|
|
|
| Research on Living Tree Volume Forecast Based on PSO Embedding SVM |
| JIAO You-quan1, 2, FENG Zhong-ke1*, ZHAO Li-xi3, XU Wei-heng1, 4, CAO Zhong1 |
1. Institute of GIS, RS & GPS, Beijing Forestry University, Beijing 100083, China
2. Beijing Vocational College of Agriculture，Beijing 102442, China
3. Water Conservancy and Civil Engineering, China Agricultural University, Beijing 100083, China
4. College of Computer and Information Engineering, Southwest Forestry University, Kunming 650224, China |
|
|
|
|
Abstract In order to establish volume model，living trees have to be fallen and be divided into many sections, which is a kind of destructive experiment. So hundreds of thousands of trees have been fallen down each year in China. To solve this problem, a new method called living tree volume accurate measurement without falling tree was proposed in the present paper. In the method, new measuring methods and calculation ways are used by using photoelectric theodolite and auxiliary artificial measurement. The diameter at breast height and diameter at ground was measured manually, and diameters at other heights were obtained by photoelectric theodolite. Tree volume and height of each tree was calculated by a special software that was programmed by the authors. Zhonglin aspens No.107 were selected as experiment object, and 400 data records were obtained. Based on these data, a nonlinear intelligent living tree volume prediction model with Particle Swarm Optimization algorithm based on support vector machines (PSO-SVM) was established. Three hundred data records including tree height and diameter at breast height were randomly selected form a total of 400 data records as input data, tree volume as output data, using PSO-SVM tool box of Matlab7.11, thus a tree volume model was obtained. One hundred data records were used to test the volume model. The results show that the complex correlation coefficient (R2) between predicted and measured values is 0.91, which is 2% higher than the value calculated by classic Spurr binary volume model, and the mean absolute error rates were reduced by 0.44%. Compared with Spurr binary volume model, PSO-SVM model has self-learning and self-adaption ability，moreover，with the characteristics of high prediction accuracy，fast learning speed，and a small sample size requirement，PSO-SVM model with well prospect is worth popularization and application.
|
|
Received: 2013-06-17
Accepted: 2013-09-12
|
|
|
|
Corresponding Authors:
FENG Zhong-ke
E-mail: fengzhongke@126.com
|
|
[1] ZHENG Zhi-gang, ZHOU Mei-ke(郑治刚，周美珂). Systems Engineering—Theory & Practice(系统工程理论与实践), 1992, 12(3): 55.
[2] Von Gadow K. Forstwissenschaftliches Centralblatt Vereinigt Mit Tharandter forstliches Jahrbuch, 2003, 122(4): 258.
[3] Kubler H. Trees, 1991, 5(3): 125.
[4] zelik R, Brooks J R. Annals of Forest Science, 2012, 69(1): 105.
[5] Zeide B. Trees, 2005, 19(1): 1.
[6] XU Hui, MENG Xian-yu(胥 辉，孟宪宇). Journal of Beijing Forestry University(北京林业大学学报), 1996, 18(3): 21.
[7] Manzoni L, Castelli M, Vanneschi L. Genetic Programming and Evolvable Machines, 2013, 14(4): 457.
[8] Lu Y, Roychowdhury V. Knowledge and Information Systems, 2008, 14(2): 233.
[9] Fourie P C, Groenwold A A. Structural and Multidisciplinary Optimization, 2002, 23(4): 259.
[10] Dong Xiaojian, Wu Zhijian, Dong Chao, et al. Wuhan University Journal of Natural Sciences, 2011, 16(3): 237.
[11] Qu R, Xu Y, Castro J P, et al. Journal of Heuristics, 2013, 19(2): 317.
[12] Nattachote，Rugthaicharoenchep，Somkieat, et al. Journal of Enerhy and Power Engineering, 2012, 6(10): 1718.
[13] NI Qing-jian，XING Han-cheng，ZHANG Zhi-zheng, et al(倪庆剑，邢汉承，张志政, 等). Pattern Recognition and Artificial Intelligence(模式识别与人工智能), 2007, 20(3): 349.
[14] WANG Xing-yuan，ZHANG Peng(王兴元，张 鹏). Systems Engineering and Electronics(系统工程与电子技术), 2012, 34(7): 1484.
[15] CHEN Gang, LU Jia-jun, LIU Cheng, et al(陈 刚，陆嘉骏，刘 澄, 等). China Management Informationization(中国管理信息化), 2012，(16): 32.
|
| [1] |
ZHENG Guang-hui1,2, JIAO Cai-xia2, SHANGGUAN Chen-xi2, WU Wen-qian2, LIU Yi3, HONG Chang-qiao2,4. Horizon Classification in Soil Profile Using Imaging Spectroscopy[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2019, 39(03): 882-885. |
| [2] |
ZHANG Ying, LI Ying*, GU Yan-hong, GUO Hao, LI Na. LIBS Quantitative Analysis of Cr and Ni in Iron Alloys with Support Vector Machine (SVM)[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2016, 36(07): 2244-2248. |
| [3] |
WANG Xiao-yan, WANG Xi-chang*, LIU Yuan*, DONG Ruo-yan. Application of Near Infrared Spectroscopy Technique Based on Support Vector Machine in the Measurement of Moisture and Protein Contents in Surimi [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2012, 32(09): 2418-2421. |
| [4] |
DENG Wei1, ZHANG Lu-da1, HE Xiong-kui1*, Mueller J2, ZENG Ai-jun1, SONG Jian-li1, LIU Ya-jia1, ZHOU Ji-zhong1, CHEN Ji1, WANG Xu1. SVM-Based Spectral Recognition of Corn and Weeds at Seedling Stage in Fields [J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2009, 29(07): 1906-1910. |
|
|
|
|
