Abstract
Being a world-renowned heritage site, the Ming Great Wall, located in Qinghai Province, China, mainly has existed as the form of earthen sites with high historical, artistic, and scientific values. However, exposed under environmental impacts for about 500 years, these sites have been seriously threatened. The study on their damage assessment using reasonable methods is the key premise for further protection work. As there are few studies focused on the damage assessment of earthen sites, especially by using machine learning methods, this study explored to apply the current effective machine learning approaches, namely Support Vector Machine (SVM) and back-propagation (BP) Neural Network, into solving this problem. The authors used two such algorithms by training and testing the existing data of damage assessment results of 18 earthen sites located in Qinghai Province. By comparing experimental results, the prediction effects of SVM are much better than those of BP Neural Network. To test its practicability, Liutun Great Wall was chosen as an engineering case, showing better prediction and reasonable performance of SVM. This research has proved that SVM can be selected as a suitable model to assess the damage levels of earthen sites located in Qinghai Province for their future conservation works.
- David Alexander. 1991. Natural disasters: A framework for research and teaching. Disasters 15, 3 (1991), 209--226. DOI:https://doi.org/10.1111/j.1467-7717.1991.tb00455.xGoogle ScholarCross Ref
- ristiano Ballabio and Simone Sterlacchini. 2012. Support vector machines for landslide susceptibility mapping: The Staffora River Basin case study, Italy. Math. Geosci. 44, 1 (2012), 47--70. DOI:https://doi.org/10.1007/s11004-011-9379-9Google ScholarCross Ref
- Adnan A. Basma and Nabil Kallas. 2004. Modeling soil collapse by artificial neural networks. Geotech. Geol. Eng. 22, 3 (2004), 427--438. DOI:https://doi.org/10.1023/B:GEGE.0000025044.72718.dbGoogle ScholarCross Ref
- A. Brenning. 2005. Spatial prediction models for landslide hazards: Review, comparison and evaluation. Nat. Hazards Earth Syst. Sci. 5, 6 (2005), 853--862.Google ScholarCross Ref
- Dieu Tien Bui, Biswajeet Pradhan, Owe Lofman, Inge Revhaug, and Oystein B. Dick. 2012. Application of support vector machines in landslide susceptibility assessment for the Hoa Binh province (Vietnam) with kernel functions analysis. In Proceedings of the 6th International Congress on Environmental Modelling and Software (iEMSs), Leipzig, Germany 382--389.Google Scholar
- Jun Chen, Shuping Jin, Anping Liao, Yousong Zhao, Hongwei Zhang, Dawei Rong, and Zhaojun Yang. 2010. Stereo mapping of Ming Great Wall with remote sensing. Chin. Sci. Bull. 55, 21 (2010), 2290--2294. DOI:https://doi.org/10.1007/s11434-010-4295-9Google ScholarCross Ref
- Wenwu Chen, Yingmin Zhang, Jingke Zhang, and Pengfei Dai. 2018. Consolidation effect of composite materials on earthen sites. Constr. Build. Mater. 187, (2018), 730--737. DOI:https://doi.org/10.1016/j.conbuildmat.2018.07.239Google Scholar
- Corinna Cortes and Vladimir Vapnik. 1995. Support-vector networks. Mach. Learn. 20, 3 (1995), 273--297. DOI:https://doi.org/10.1007/BF00994018Google ScholarCross Ref
- J. J. González Costa, M. J. Reigosa, J. M. Matías, and E. F. Covelo. 2017. Soil Cd, Cr, Cu, Ni, Pb, and Zn sorption and retention models using SVM: Variable selection and competitive model. Sci. Total Environ. 593--594, (2017), 508--522. DOI:https://doi.org/10.1016/j.scitotenv.2017.03.195Google Scholar
- Nello Cristianini and John Shawe-Taylor. 2000. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, Cambridge, UK.Google ScholarCross Ref
- Kai Cui, Guopeng Wu, Yumin Du, Xinyue An, and Zelin Wang. 2019. The coupling effects of freeze-thaw cycles and salinization due to snowfall on the rammed earth used in historical freeze-thaw cycles relics in northwest China. Cold Reg. Sci. Technol. 160, (2019). DOI:https://doi.org/10.1016/j.coldregions.2019.01.016Google Scholar
- Yumin Du, Wenwu Chen, Kai Cui, Shuya Gong, Tianbiao Pu, and Xianglong Fu. 2017. A model characterizing deterioration at earthen sites of the Ming Great Wall in Qinghai Province, China. Soil Mech. Found. Eng. 53, 6 (2017), 426--434. DOI:https://doi.org/10.1007/s11204-017-9423-yGoogle ScholarCross Ref
- Yumin Du, Wenwu Chen, Kai Cui, and Kewen Zhang. 2019. Study on damage assessment of earthen sites of the Ming Great Wall in Qinghai Province based on fuzzy-AHP and AHP-TOPSIS. Int. J. Archit. Herit. (2019), 1--14. DOI:https://doi.org/10.1080/15583058.2019.1576241Google Scholar
- Jerome Friedman, Trevor Hastie, and Robert Tibshirani. 2003. The Elements of Statistical Learning. Springer-Verlag, New York, NY.Google Scholar
- Eren Gultepe, Thomas Edward Conturo, and Masoud Makrehchi. 2018. Predicting and grouping digitized paintings by style using unsupervised feature learning. J. Cult. Herit. 31, (2018), 13--23. DOI:doi.org/10.1016/j.culher.2017.11.008Google Scholar
- Esmaeil Hadavandi, Hassan Shavandi, and Arash Ghanbari. 2010. Integration of genetic fuzzy systems and artificial neural networks for stock price forecasting. Knowl.-Based Syst. 23, 8 (2010), 800--808. DOI:https://doi.org/10.1016/j.knosys.2010.05.004Google ScholarDigital Library
- T. Kavzoglu and I. Colkesen. 2009. A kernel functions analysis for support vector machines for land cover classification. Int. J. Appl. Earth Obs. Geoinformation 11, 5 (2009), 352--359. DOI:https://doi.org/10.1016/j.jag.2009.06.002Google ScholarCross Ref
- Taskin Kavzoglu, Emrehan Kutlug Sahin, and Ismail Colkesen. 2014. Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression. Landslides 11, 3 (2014), 425--439. DOI:https://doi.org/10.1007/s10346-013-0391-7Google ScholarCross Ref
- Abbas Khosravi, Saeid Nahavandi, and Doug Creighton. 2013. Quantifying uncertainties of neural network-based electricity price forecasts. Appl. Energy 112, (2013), 120--129. DOI:https://doi.org/10.1016/j.apenergy.2013.05.075Google Scholar
- A. Khotanzad, H. Elragal, and T.-L. Lu. 2000. Combination of artificial neural-network forecasters for prediction of natural gas consumption. IEEE Trans. Neural Netw. 11, 2 (2000), 464--473. DOI:https://doi.org/10.1109/72.839015Google ScholarDigital Library
- Jing Li, Ji-hang Cheng, Jing-yuan Shi, and Fei Huang. 2012a. Brief introduction of back propagation (BP) neural network algorithm and its improvement. In Advances in Computer Science and Information Engineering, D. Jin and S. Lin (Eds.). Advances in CSIE. 2. Springer, Berlin, Germany. 553--558.Google Scholar
- Li Li, Mingshen Shao, Sijing Wang, and Zuixiong Li. 2011a. Preservation of earthen heritage sites on the Silk Road, northwest China from the impact of the environment. Environ. Earth Sci. 64, 6 (2011), 1625--1639. DOI:https://doi.org/10.1007/s12665-010-0829-3Google ScholarCross Ref
- Zuixiong Li, Xudong Wang, Wenwu Chen, Manli Sun, Qinglin Guo, Jingke Zhang, Faguo He, and Shanlong Yang. 2012b. Specifications of Investigation for Preservation Engineering of Earthen Sites. Cultural Relics Press, Beijing, China.Google Scholar
- Zuixiong Li, Xudong Wang, Manli Sun, Wenwu Chen, Qinglin Guo, and Huyuan Zhang. 2011b. Conservation of Jiaohe ancient earthen site in China. J. Rock Mech. Geotech. Eng. 3, 3 (2011), 270--281. DOI:https://doi.org/10.3724/SP.J.1235.2011.00270Google ScholarCross Ref
- Xilin Liu and Junzhong Lei. 2003. A method for assessing regional debris flow risk: An application in Zhaotong of Yunnan Province (SW China). Geomorphology 52, 3 (2003), 181--191. DOI:https://doi.org/10.1016/S0169-555X(02)00242-8Google ScholarCross Ref
- Miloš Marjanović, Miloš Kovačević, Branislav Bajat, and Vít Voženílek. 2011. Landslide susceptibility assessment using SVM machine learning algorithm. Eng. Geol. 123, 3 (2011), 225--234. DOI:https://doi.org/10.1016/j.enggeo.2011.09.006Google ScholarCross Ref
- Seyed Amir Naghibi, Davood Davoodi Moghaddam, Bahareh Kalantar, Biswajeet Pradhan, and Ozgur Kisi. 2017. A comparative assessment of GIS-based data mining models and a novel ensemble model in groundwater well potential mapping. J. Hydrol. 548, (2017), 471--483. DOI:https://doi.org/10.1016/j.jhydrol.2017.03.020Google Scholar
- Tianbiao Pu, Wenwu Chen, Yumin Du, Wenjuan Li, and Na Su. 2016. Snowfall-related deterioration behavior of the Ming Great Wall in the eastern Qinghai-Tibet Plateau. Nat. Hazards 84, 3 (2016), 1539--1550. DOI:https://doi.org/10.1007/s11069-016-2497-4Google ScholarCross Ref
- Xiaoyan Ren. 2012. Resources’ Investigation Report of Ming Great Wall in Qinghai Province. Cultural Relics Press, Beijing, China.Google Scholar
- David E. Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams. 1986. Learning representations by back-propagating errors. Nature 323, 6088 (1986), 533--536. DOI:https://doi.org/10.1038/323533a0Google ScholarCross Ref
- B. H. M. Sadeghi. 2000. A BP-neural network predictor model for plastic injection molding process. J. Mater. Process. Technol. 103, 3 (2000), 411--416. DOI:https://doi.org/10.1016/S0924-0136(00)00498-2Google ScholarCross Ref
- Mingshen Shao, Li Li, Sijing Wang, Enzhi Wang, and Zuixiong Li. 2013. Deterioration mechanisms of building materials of Jiaohe Ruins in China. J. Cult. Herit. 14, 1 (2013), 38--44. DOI:https://doi.org/10.1016/j.culher.2012.03.006Google ScholarCross Ref
- Yunxia Shen, Wenwu Chen, Jing Kuang, and Weifei Du. 2017. Effect of salts on earthen materials deterioration after humidity cycling. J. Cent. South Univ. 24, 4 (2017), 796--806. DOI:https://doi.org/10.1007/s11771-017-3482-0Google ScholarCross Ref
- Ingo Steinwart and Andreas Christmann. 2008. Support Vector Machines. Springer, New York, NY.Google Scholar
- H. Su, L.-J. Qu, K. He, Z. Zhang, J. Wang, Z. Chen, and H. Gu. 2003. The Great Wall of China: A physical barrier to gene flow? Heredity 90, 3 (2003), 212--219. DOI:https://doi.org/10.1038/sj.hdy.6800237Google ScholarCross Ref
- Ming Ming Su and Geoffrey Wall. 2012. Global--local relationships and governance issues at the Great Wall World Heritage Site, China. J. Sustain. Tour. 20, 8 (2012), 1067--1086. DOI:https://doi.org/10.1080/09669582.2012.671330Google ScholarCross Ref
- Guohua Tan, Jianzhuo Yan, Chen Gao, and Suhua Yang. 2012. Prediction of water quality time series data based on least squares support vector machine. Procedia Eng. 31, (2012), 1194--1199. DOI:https://doi.org/10.1016/j.proeng.2012.01.1162Google ScholarCross Ref
- Ilker Bekir Topcu and Mustafa Sarıdemir. 2008. Prediction of compressive strength of concrete containing fly ash using artificial neural networks and fuzzy logic. Comput. Mater. Sci. 41, 3 (2008), 305--311. DOI:https://doi.org/10.1016/j.commatsci.2007.04.009Google ScholarCross Ref
- Vladimir N. Vapnik. 1995. The Nature of Statistical Learning Theory. Springer, New York, NY.Google ScholarDigital Library
- Xudong Wang, Huyuan Zhang, Zuixiong Li, Qinglin Guo, Ping Liu, and Gengsheng Yan. 2012. Testing Techniques Specification for Preservation of Earthen Sites (WW/T 0039-2012). Cultural Relics Press, Beijing, China.Google Scholar
- Yong Zhang, Qian Cong, Yunfei Xie, Jingxiu Yang, and Bing Zhao. 2008. Quantitative analysis of routine chemical constituents in tobacco by near-infrared spectroscopy and support vector machine. Spectrochim. Acta. A. Mol. Biomol. Spectrosc. 71, 4 (2008), 1408--1413. DOI:https://doi.org/10.1016/j.saa.2008.04.020Google ScholarCross Ref
- Yudong Zhang and Lenan Wu. 2009. Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network. Expert Syst. Appl. 36, 5 (2009), 8849--8854. DOI:https://doi.org/10.1016/j.eswa.2008.11.028Google ScholarDigital Library
- Haiying Zhao, Zuixiong Li, Wenfeng Han, Manli Sun, and Xudong Wang. 2007. Study on the main disease of the Great Wall and its conservation in Gansu Province. Sci. Conserv. Archaeol. 19, 1 (2007), 28--32. (in Chinese)Google Scholar
Index Terms
- Damage Assessment of Earthen Sites of the Ming Great Wall in Qinghai Province: A Comparison between Support Vector Machine (SVM) and BP Neural Network
Recommendations
Reinforced concrete structural damage diagnosis by using artificial neural network
IIS '97: Proceedings of the 1997 IASTED International Conference on Intelligent Information Systems (IIS '97)Typical defects exist in reinforced concrete structures include honeycomb, crack, and scaling and strength deduction for concrete, and corrosion and decreased section area for steel members. These defects are a result of many factors such as unproper ...
A Damage Assessment System for Aero-engine Borscopic Inspection Based on Support Vector Machines
HIS '09: Proceedings of the 2009 Ninth International Conference on Hybrid Intelligent Systems - Volume 02Defects are often arise on the inner surface of an aeroengine, but most of the aeroengine borescopes can only detect the damages and cannot determine the degree of damages. We propose a novel borescope assessment expert system (ES) to evaluate the ...
Damage assessment of structures using hybrid neuro-genetic algorithm
AbstractTechniques for detecting elemental level damage using the traditional methods receive the setback because of the difficulties in formulating the problems mathematically, specially in case of inverse problems. Artificial neural networks ...
Comments